release 2014.07.23.2

Fixes #3326
Apparently, on some platforms, even outputting this fails already.

.gitignore

@@ -23,6 +23,8 @@ updates_key.pem
 *.vtt
 *.flv
 *.mp4
+*.m4a
+*.m4v
 *.part
 test/testdata
 .tox

.travis.yml

@@ -3,6 +3,7 @@ python:
   - "2.6"
   - "2.7"
   - "3.3"
+  - "3.4"
 script: nosetests test --verbose
 notifications:
   email:

CHANGELOG

@@ -1,14 +0,0 @@
-2013.01.02  Codename: GIULIA
-
-    * Add support for ComedyCentral clips <nto>
-    * Corrected Vimeo description fetching <Nick Daniels>
-    * Added the --no-post-overwrites argument <Barbu Paul - Gheorghe>
-    * --verbose offers more environment info
-    * New info_dict field: uploader_id
-    * New updates system, with signature checking
-    * New IEs: NBA, JustinTV, FunnyOrDie, TweetReel, Steam, Ustream
-    * Fixed IEs: BlipTv
-    * Fixed for Python 3 IEs: Xvideo, Youku, XNXX, Dailymotion, Vimeo, InfoQ
-    * Simplified IEs and test code
-    * Various (Python 3 and other) fixes
-    * Revamped and expanded tests

MANIFEST.in

@@ -3,3 +3,4 @@ include test/*.py
 include test/*.json
 include youtube-dl.bash-completion
 include youtube-dl.1
+recursive-include docs Makefile conf.py *.rst

Makefile

@@ -1,7 +1,7 @@
 all: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion
 
 clean:
-	rm -rf youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz
+	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz
 
 cleanall: clean
 	rm -f youtube-dl youtube-dl.exe
@@ -55,7 +55,9 @@ README.txt: README.md
 	pandoc -f markdown -t plain README.md -o README.txt
 
 youtube-dl.1: README.md
-	pandoc -s -f markdown -t man README.md -o youtube-dl.1
+	python devscripts/prepare_manpage.py >youtube-dl.1.temp.md
+	pandoc -s -f markdown -t man youtube-dl.1.temp.md -o youtube-dl.1
+	rm -f youtube-dl.1.temp.md
 
 youtube-dl.bash-completion: youtube_dl/*.py youtube_dl/*/*.py devscripts/bash-completion.in
 	python devscripts/bash-completion.py
@@ -72,8 +74,9 @@ youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-
 		--exclude '__pycache' \
 		--exclude '.git' \
 		--exclude 'testdata' \
+		--exclude 'docs/_build' \
 		-- \
-		bin devscripts test youtube_dl \
-		CHANGELOG LICENSE README.md README.txt \
+		bin devscripts test youtube_dl docs \
+		LICENSE README.md README.txt \
 		Makefile MANIFEST.in youtube-dl.1 youtube-dl.bash-completion setup.py \
 		youtube-dl

README.md

@@ -1,11 +1,24 @@
-% YOUTUBE-DL(1)
-
-# NAME
 youtube-dl - download videos from youtube.com or other video platforms
 
 # SYNOPSIS
 **youtube-dl** [OPTIONS] URL [URL...]
 
+# INSTALLATION
+
+To install it right away for all UNIX users (Linux, OS X, etc.), type:
+
+    sudo curl https://yt-dl.org/latest/youtube-dl -o /usr/local/bin/youtube-dl
+    sudo chmod a+x /usr/local/bin/youtube-dl
+
+If you do not have curl, you can alternatively use a recent wget:
+
+    sudo wget https://yt-dl.org/downloads/latest/youtube-dl -O /usr/local/bin/youtube-dl
+    sudo chmod a+x /usr/local/bin/youtube-dl
+
+Windows users can [download a .exe file](https://yt-dl.org/latest/youtube-dl.exe) and place it in their home directory or any other location on their [PATH](http://en.wikipedia.org/wiki/PATH_%28variable%29).
+
+Alternatively, refer to the developer instructions below for how to check out and work with the git repository. For further options, including PGP signatures, see https://rg3.github.io/youtube-dl/download.html .
+
 # DESCRIPTION
 **youtube-dl** is a small command-line program to download videos from
 YouTube.com and a few more sites. It requires the Python interpreter, version
@@ -14,175 +27,255 @@ your Unix box, on Windows or on Mac OS X. It is released to the public domain,
 which means you can modify it, redistribute it or use it however you like.
 
 # OPTIONS
-    -h, --help                 print this help text and exit
-    --version                  print program version and exit
-    -U, --update               update this program to latest version. Make sure
-                               that you have sufficient permissions (run with
-                               sudo if needed)
-    -i, --ignore-errors        continue on download errors, for example to to
-                               skip unavailable videos in a playlist
-    --abort-on-error           Abort downloading of further videos (in the
-                               playlist or the command line) if an error occurs
-    --dump-user-agent          display the current browser identification
-    --user-agent UA            specify a custom user agent
-    --referer REF              specify a custom referer, use if the video access
-                               is restricted to one domain
-    --list-extractors          List all supported extractors and the URLs they
-                               would handle
-    --extractor-descriptions   Output descriptions of all supported extractors
-    --proxy URL                Use the specified HTTP/HTTPS proxy
-    --no-check-certificate     Suppress HTTPS certificate validation.
-    --cache-dir DIR            Location in the filesystem where youtube-dl can
-                               store downloaded information permanently. By
-                               default $XDG_CACHE_HOME/youtube-dl or ~/.cache
-                               /youtube-dl .
-    --no-cache-dir             Disable filesystem caching
+    -h, --help                       print this help text and exit
+    --version                        print program version and exit
+    -U, --update                     update this program to latest version. Make
+                                     sure that you have sufficient permissions
+                                     (run with sudo if needed)
+    -i, --ignore-errors              continue on download errors, for example to
+                                     skip unavailable videos in a playlist
+    --abort-on-error                 Abort downloading of further videos (in the
+                                     playlist or the command line) if an error
+                                     occurs
+    --dump-user-agent                display the current browser identification
+    --user-agent UA                  specify a custom user agent
+    --referer REF                    specify a custom referer, use if the video
+                                     access is restricted to one domain
+    --add-header FIELD:VALUE         specify a custom HTTP header and its value,
+                                     separated by a colon ':'. You can use this
+                                     option multiple times
+    --list-extractors                List all supported extractors and the URLs
+                                     they would handle
+    --extractor-descriptions         Output descriptions of all supported
+                                     extractors
+    --proxy URL                      Use the specified HTTP/HTTPS proxy. Pass in
+                                     an empty string (--proxy "") for direct
+                                     connection
+    --no-check-certificate           Suppress HTTPS certificate validation.
+    --prefer-insecure                Use an unencrypted connection to retrieve
+                                     information about the video. (Currently
+                                     supported only for YouTube)
+    --cache-dir DIR                  Location in the filesystem where youtube-dl
+                                     can store some downloaded information
+                                     permanently. By default $XDG_CACHE_HOME
+                                     /youtube-dl or ~/.cache/youtube-dl . At the
+                                     moment, only YouTube player files (for
+                                     videos with obfuscated signatures) are
+                                     cached, but that may change.
+    --no-cache-dir                   Disable filesystem caching
+    --socket-timeout None            Time to wait before giving up, in seconds
+    --bidi-workaround                Work around terminals that lack
+                                     bidirectional text support. Requires bidiv
+                                     or fribidi executable in PATH
+    --default-search PREFIX          Use this prefix for unqualified URLs. For
+                                     example "gvsearch2:" downloads two videos
+                                     from google videos for  youtube-dl "large
+                                     apple". Use the value "auto" to let
+                                     youtube-dl guess. The default value "error"
+                                     just throws an error.
+    --ignore-config                  Do not read configuration files. When given
+                                     in the global configuration file /etc
+                                     /youtube-dl.conf: do not read the user
+                                     configuration in ~/.config/youtube-dl.conf
+                                     (%APPDATA%/youtube-dl/config.txt on
+                                     Windows)
+    --encoding ENCODING              Force the specified encoding (experimental)
 
 ## Video Selection:
-    --playlist-start NUMBER    playlist video to start at (default is 1)
-    --playlist-end NUMBER      playlist video to end at (default is last)
-    --match-title REGEX        download only matching titles (regex or caseless
-                               sub-string)
-    --reject-title REGEX       skip download for matching titles (regex or
-                               caseless sub-string)
-    --max-downloads NUMBER     Abort after downloading NUMBER files
-    --min-filesize SIZE        Do not download any videos smaller than SIZE
-                               (e.g. 50k or 44.6m)
-    --max-filesize SIZE        Do not download any videos larger than SIZE (e.g.
-                               50k or 44.6m)
-    --date DATE                download only videos uploaded in this date
-    --datebefore DATE          download only videos uploaded before this date
-    --dateafter DATE           download only videos uploaded after this date
-    --no-playlist              download only the currently playing video
-    --age-limit YEARS          download only videos suitable for the given age
-    --download-archive FILE    Download only videos not present in the archive
-                               file. Record all downloaded videos in it.
+    --playlist-start NUMBER          playlist video to start at (default is 1)
+    --playlist-end NUMBER            playlist video to end at (default is last)
+    --match-title REGEX              download only matching titles (regex or
+                                     caseless sub-string)
+    --reject-title REGEX             skip download for matching titles (regex or
+                                     caseless sub-string)
+    --max-downloads NUMBER           Abort after downloading NUMBER files
+    --min-filesize SIZE              Do not download any videos smaller than
+                                     SIZE (e.g. 50k or 44.6m)
+    --max-filesize SIZE              Do not download any videos larger than SIZE
+                                     (e.g. 50k or 44.6m)
+    --date DATE                      download only videos uploaded in this date
+    --datebefore DATE                download only videos uploaded on or before
+                                     this date (i.e. inclusive)
+    --dateafter DATE                 download only videos uploaded on or after
+                                     this date (i.e. inclusive)
+    --min-views COUNT                Do not download any videos with less than
+                                     COUNT views
+    --max-views COUNT                Do not download any videos with more than
+                                     COUNT views
+    --no-playlist                    download only the currently playing video
+    --age-limit YEARS                download only videos suitable for the given
+                                     age
+    --download-archive FILE          Download only videos not listed in the
+                                     archive file. Record the IDs of all
+                                     downloaded videos in it.
+    --include-ads                    Download advertisements as well
+                                     (experimental)
+    --youtube-include-dash-manifest  Try to download the DASH manifest on
+                                     YouTube videos (experimental)
 
 ## Download Options:
-    -r, --rate-limit LIMIT     maximum download rate in bytes per second (e.g.
-                               50K or 4.2M)
-    -R, --retries RETRIES      number of retries (default is 10)
-    --buffer-size SIZE         size of download buffer (e.g. 1024 or 16K)
-                               (default is 1024)
-    --no-resize-buffer         do not automatically adjust the buffer size. By
-                               default, the buffer size is automatically resized
-                               from an initial value of SIZE.
+    -r, --rate-limit LIMIT           maximum download rate in bytes per second
+                                     (e.g. 50K or 4.2M)
+    -R, --retries RETRIES            number of retries (default is 10)
+    --buffer-size SIZE               size of download buffer (e.g. 1024 or 16K)
+                                     (default is 1024)
+    --no-resize-buffer               do not automatically adjust the buffer
+                                     size. By default, the buffer size is
+                                     automatically resized from an initial value
+                                     of SIZE.
 
 ## Filesystem Options:
-    -t, --title                use title in file name (default)
-    --id                       use only video ID in file name
-    -l, --literal              [deprecated] alias of --title
-    -A, --auto-number          number downloaded files starting from 00000
-    -o, --output TEMPLATE      output filename template. Use %(title)s to get
-                               the title, %(uploader)s for the uploader name,
-                               %(uploader_id)s for the uploader nickname if
-                               different, %(autonumber)s to get an automatically
-                               incremented number, %(ext)s for the filename
-                               extension, %(format)s for the format description
-                               (like "22 - 1280x720" or "HD"),%(format_id)s for
-                               the unique id of the format (like Youtube's
-                               itags: "137"),%(upload_date)s for the upload date
-                               (YYYYMMDD), %(extractor)s for the provider
-                               (youtube, metacafe, etc), %(id)s for the video id
-                               , %(playlist)s for the playlist the video is in,
-                               %(playlist_index)s for the position in the
-                               playlist and %% for a literal percent. Use - to
-                               output to stdout. Can also be used to download to
-                               a different directory, for example with -o '/my/d
-                               ownloads/%(uploader)s/%(title)s-%(id)s.%(ext)s' .
-    --autonumber-size NUMBER   Specifies the number of digits in %(autonumber)s
-                               when it is present in output filename template or
-                               --auto-number option is given
-    --restrict-filenames       Restrict filenames to only ASCII characters, and
-                               avoid "&" and spaces in filenames
-    -a, --batch-file FILE      file containing URLs to download ('-' for stdin)
-    -w, --no-overwrites        do not overwrite files
-    -c, --continue             force resume of partially downloaded files. By
-                               default, youtube-dl will resume downloads if
-                               possible.
-    --no-continue              do not resume partially downloaded files (restart
-                               from beginning)
-    --cookies FILE             file to read cookies from and dump cookie jar in
-    --no-part                  do not use .part files
-    --no-mtime                 do not use the Last-modified header to set the
-                               file modification time
-    --write-description        write video description to a .description file
-    --write-info-json          write video metadata to a .info.json file
-    --write-annotations        write video annotations to a .annotation file
-    --write-thumbnail          write thumbnail image to disk
+    -t, --title                      use title in file name (default)
+    --id                             use only video ID in file name
+    -l, --literal                    [deprecated] alias of --title
+    -A, --auto-number                number downloaded files starting from 00000
+    -o, --output TEMPLATE            output filename template. Use %(title)s to
+                                     get the title, %(uploader)s for the
+                                     uploader name, %(uploader_id)s for the
+                                     uploader nickname if different,
+                                     %(autonumber)s to get an automatically
+                                     incremented number, %(ext)s for the
+                                     filename extension, %(format)s for the
+                                     format description (like "22 - 1280x720" or
+                                     "HD"), %(format_id)s for the unique id of
+                                     the format (like Youtube's itags: "137"),
+                                     %(upload_date)s for the upload date
+                                     (YYYYMMDD), %(extractor)s for the provider
+                                     (youtube, metacafe, etc), %(id)s for the
+                                     video id, %(playlist)s for the playlist the
+                                     video is in, %(playlist_index)s for the
+                                     position in the playlist and %% for a
+                                     literal percent. %(height)s and %(width)s
+                                     for the width and height of the video
+                                     format. %(resolution)s for a textual
+                                     description of the resolution of the video
+                                     format. Use - to output to stdout. Can also
+                                     be used to download to a different
+                                     directory, for example with -o '/my/downloa
+                                     ds/%(uploader)s/%(title)s-%(id)s.%(ext)s' .
+    --autonumber-size NUMBER         Specifies the number of digits in
+                                     %(autonumber)s when it is present in output
+                                     filename template or --auto-number option
+                                     is given
+    --restrict-filenames             Restrict filenames to only ASCII
+                                     characters, and avoid "&" and spaces in
+                                     filenames
+    -a, --batch-file FILE            file containing URLs to download ('-' for
+                                     stdin)
+    --load-info FILE                 json file containing the video information
+                                     (created with the "--write-json" option)
+    -w, --no-overwrites              do not overwrite files
+    -c, --continue                   force resume of partially downloaded files.
+                                     By default, youtube-dl will resume
+                                     downloads if possible.
+    --no-continue                    do not resume partially downloaded files
+                                     (restart from beginning)
+    --cookies FILE                   file to read cookies from and dump cookie
+                                     jar in
+    --no-part                        do not use .part files
+    --no-mtime                       do not use the Last-modified header to set
+                                     the file modification time
+    --write-description              write video description to a .description
+                                     file
+    --write-info-json                write video metadata to a .info.json file
+    --write-annotations              write video annotations to a .annotation
+                                     file
+    --write-thumbnail                write thumbnail image to disk
 
 ## Verbosity / Simulation Options:
-    -q, --quiet                activates quiet mode
-    -s, --simulate             do not download the video and do not write
-                               anything to disk
-    --skip-download            do not download the video
-    -g, --get-url              simulate, quiet but print URL
-    -e, --get-title            simulate, quiet but print title
-    --get-id                   simulate, quiet but print id
-    --get-thumbnail            simulate, quiet but print thumbnail URL
-    --get-description          simulate, quiet but print video description
-    --get-filename             simulate, quiet but print output filename
-    --get-format               simulate, quiet but print output format
-    -j, --dump-json            simulate, quiet but print JSON information
-    --newline                  output progress bar as new lines
-    --no-progress              do not print progress bar
-    --console-title            display progress in console titlebar
-    -v, --verbose              print various debugging information
-    --dump-intermediate-pages  print downloaded pages to debug problems(very
-                               verbose)
-    --write-pages              Write downloaded pages to files in the current
-                               directory
+    -q, --quiet                      activates quiet mode
+    --no-warnings                    Ignore warnings
+    -s, --simulate                   do not download the video and do not write
+                                     anything to disk
+    --skip-download                  do not download the video
+    -g, --get-url                    simulate, quiet but print URL
+    -e, --get-title                  simulate, quiet but print title
+    --get-id                         simulate, quiet but print id
+    --get-thumbnail                  simulate, quiet but print thumbnail URL
+    --get-description                simulate, quiet but print video description
+    --get-duration                   simulate, quiet but print video length
+    --get-filename                   simulate, quiet but print output filename
+    --get-format                     simulate, quiet but print output format
+    -j, --dump-json                  simulate, quiet but print JSON information.
+                                     See --output for a description of available
+                                     keys.
+    --newline                        output progress bar as new lines
+    --no-progress                    do not print progress bar
+    --console-title                  display progress in console titlebar
+    -v, --verbose                    print various debugging information
+    --dump-intermediate-pages        print downloaded pages to debug problems
+                                     (very verbose)
+    --write-pages                    Write downloaded intermediary pages to
+                                     files in the current directory to debug
+                                     problems
+    --print-traffic                  Display sent and read HTTP traffic
 
 ## Video Format Options:
-    -f, --format FORMAT        video format code, specifiy the order of
-                               preference using slashes: "-f 22/17/18". "-f mp4"
-                               and "-f flv" are also supported
-    --all-formats              download all available video formats
-    --prefer-free-formats      prefer free video formats unless a specific one
-                               is requested
-    --max-quality FORMAT       highest quality format to download
-    -F, --list-formats         list all available formats (currently youtube
-                               only)
+    -f, --format FORMAT              video format code, specify the order of
+                                     preference using slashes: "-f 22/17/18".
+                                     "-f mp4" and "-f flv" are also supported.
+                                     You can also use the special names "best",
+                                     "bestvideo", "bestaudio", "worst",
+                                     "worstvideo" and "worstaudio". By default,
+                                     youtube-dl will pick the best quality.
+    --all-formats                    download all available video formats
+    --prefer-free-formats            prefer free video formats unless a specific
+                                     one is requested
+    --max-quality FORMAT             highest quality format to download
+    -F, --list-formats               list all available formats
 
 ## Subtitle Options:
-    --write-sub                write subtitle file
-    --write-auto-sub           write automatic subtitle file (youtube only)
-    --all-subs                 downloads all the available subtitles of the
-                               video
-    --list-subs                lists all available subtitles for the video
-    --sub-format FORMAT        subtitle format (default=srt) ([sbv/vtt] youtube
-                               only)
-    --sub-lang LANGS           languages of the subtitles to download (optional)
-                               separated by commas, use IETF language tags like
-                               'en,pt'
+    --write-sub                      write subtitle file
+    --write-auto-sub                 write automatic subtitle file (youtube
+                                     only)
+    --all-subs                       downloads all the available subtitles of
+                                     the video
+    --list-subs                      lists all available subtitles for the video
+    --sub-format FORMAT              subtitle format (default=srt) ([sbv/vtt]
+                                     youtube only)
+    --sub-lang LANGS                 languages of the subtitles to download
+                                     (optional) separated by commas, use IETF
+                                     language tags like 'en,pt'
 
 ## Authentication Options:
-    -u, --username USERNAME    account username
-    -p, --password PASSWORD    account password
-    -n, --netrc                use .netrc authentication data
-    --video-password PASSWORD  video password (vimeo only)
+    -u, --username USERNAME          account username
+    -p, --password PASSWORD          account password
+    -n, --netrc                      use .netrc authentication data
+    --video-password PASSWORD        video password (vimeo, smotri)
 
 ## Post-processing Options:
-    -x, --extract-audio        convert video files to audio-only files (requires
-                               ffmpeg or avconv and ffprobe or avprobe)
-    --audio-format FORMAT      "best", "aac", "vorbis", "mp3", "m4a", "opus", or
-                               "wav"; best by default
-    --audio-quality QUALITY    ffmpeg/avconv audio quality specification, insert
-                               a value between 0 (better) and 9 (worse) for VBR
-                               or a specific bitrate like 128K (default 5)
-    --recode-video FORMAT      Encode the video to another format if necessary
-                               (currently supported: mp4|flv|ogg|webm)
-    -k, --keep-video           keeps the video file on disk after the post-
-                               processing; the video is erased by default
-    --no-post-overwrites       do not overwrite post-processed files; the post-
-                               processed files are overwritten by default
-    --embed-subs               embed subtitles in the video (only for mp4
-                               videos)
-    --add-metadata             add metadata to the files
+    -x, --extract-audio              convert video files to audio-only files
+                                     (requires ffmpeg or avconv and ffprobe or
+                                     avprobe)
+    --audio-format FORMAT            "best", "aac", "vorbis", "mp3", "m4a",
+                                     "opus", or "wav"; best by default
+    --audio-quality QUALITY          ffmpeg/avconv audio quality specification,
+                                     insert a value between 0 (better) and 9
+                                     (worse) for VBR or a specific bitrate like
+                                     128K (default 5)
+    --recode-video FORMAT            Encode the video to another format if
+                                     necessary (currently supported:
+                                     mp4|flv|ogg|webm|mkv)
+    -k, --keep-video                 keeps the video file on disk after the
+                                     post-processing; the video is erased by
+                                     default
+    --no-post-overwrites             do not overwrite post-processed files; the
+                                     post-processed files are overwritten by
+                                     default
+    --embed-subs                     embed subtitles in the video (only for mp4
+                                     videos)
+    --embed-thumbnail                embed thumbnail in the audio as cover art
+    --add-metadata                   write metadata to the video file
+    --xattrs                         write metadata to the video file's xattrs
+                                     (using dublin core and xdg standards)
+    --prefer-avconv                  Prefer avconv over ffmpeg for running the
+                                     postprocessors (default)
+    --prefer-ffmpeg                  Prefer ffmpeg over avconv for running the
+                                     postprocessors
 
 # CONFIGURATION
 
-You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl.conf`.
+You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl/config`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<Yourname>\youtube-dl.conf`.
 
 # OUTPUT TEMPLATE
 
@@ -217,9 +310,14 @@ Videos can be filtered by their upload date using the options `--date`, `--dateb
  
 Examples:
 
-	$ youtube-dl --dateafter now-6months #will only download the videos uploaded in the last 6 months
-	$ youtube-dl --date 19700101 #will only download the videos uploaded in January 1, 1970
-	$ youtube-dl --dateafter 20000101 --datebefore 20100101 #will only download the videos uploaded between 2000 and 2010
+    # Download only the videos uploaded in the last 6 months
+    $ youtube-dl --dateafter now-6months
+
+    # Download only the videos uploaded on January 1, 1970
+    $ youtube-dl --date 19700101
+
+    $ # will only download the videos uploaded in the 200x decade
+    $ youtube-dl --dateafter 20000101 --datebefore 20091231
 
 # FAQ
 
@@ -264,22 +362,152 @@ Since June 2012 (#342) youtube-dl is packed as an executable zipfile, simply unz
 
 To run the exe you need to install first the [Microsoft Visual C++ 2008 Redistributable Package](http://www.microsoft.com/en-us/download/details.aspx?id=29).
 
+# DEVELOPER INSTRUCTIONS
+
+Most users do not need to build youtube-dl and can [download the builds](http://rg3.github.io/youtube-dl/download.html) or get them from their distribution.
+
+To run youtube-dl as a developer, you don't need to build anything either. Simply execute
+
+    python -m youtube_dl
+
+To run the test, simply invoke your favorite test runner, or execute a test file directly; any of the following work:
+
+    python -m unittest discover
+    python test/test_download.py
+    nosetests
+
+If you want to create a build of youtube-dl yourself, you'll need
+
+* python
+* make
+* pandoc
+* zip
+* nosetests
+
+### Adding support for a new site
+
+If you want to add support for a new site, you can follow this quick list (assuming your service is called `yourextractor`):
+
+1. [Fork this repository](https://github.com/rg3/youtube-dl/fork)
+2. Check out the source code with `git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git`
+3. Start a new git branch with `cd youtube-dl; git checkout -b yourextractor`
+4. Start with this simple template and save it to `youtube_dl/extractor/yourextractor.py`:
+
+        # coding: utf-8
+        from __future__ import unicode_literals
+
+        import re
+
+        from .common import InfoExtractor
+        
+        
+        class YourExtractorIE(InfoExtractor):
+            _VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P<id>[0-9]+)'
+            _TEST = {
+                'url': 'http://yourextractor.com/watch/42',
+                'md5': 'TODO: md5 sum of the first 10KiB of the video file',
+                'info_dict': {
+                    'id': '42',
+                    'ext': 'mp4',
+                    'title': 'Video title goes here',
+                    # TODO more properties, either as:
+                    # * A value
+                    # * MD5 checksum; start the string with md5:
+                    # * A regular expression; start the string with re:
+                    # * Any Python type (for example int or float)
+                }
+            }
+
+            def _real_extract(self, url):
+                mobj = re.match(self._VALID_URL, url)
+                video_id = mobj.group('id')
+
+                # TODO more code goes here, for example ...
+                webpage = self._download_webpage(url, video_id)
+                title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
+
+                return {
+                    'id': video_id,
+                    'title': title,
+                    # TODO more properties (see youtube_dl/extractor/common.py)
+                }
+
+
+5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
+6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done.
+7. Have a look at [`youtube_dl/common/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L38). Add tests and code for as many as you want.
+8. If you can, check the code with [pyflakes](https://pypi.python.org/pypi/pyflakes) (a good idea) and [pep8](https://pypi.python.org/pypi/pep8) (optional, ignore E501).
+9. When the tests pass, [add](https://www.kernel.org/pub/software/scm/git/docs/git-add.html) the new files and [commit](https://www.kernel.org/pub/software/scm/git/docs/git-commit.html) them and [push](https://www.kernel.org/pub/software/scm/git/docs/git-push.html) the result, like this:
+
+        $ git add youtube_dl/extractor/__init__.py
+        $ git add youtube_dl/extractor/yourextractor.py
+        $ git commit -m '[yourextractor] Add new extractor'
+        $ git push origin yourextractor
+
+10. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it.
+
+In any case, thank you very much for your contributions!
+
+# BUGS
+
+Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues> . Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email.
+
+Please include the full output of the command when run with `--verbose`. The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
+
+For discussions, join us in the irc channel #youtube-dl on freenode.
+
+When you submit a request, please re-read it once to avoid a couple of mistakes (you can and should use this as a checklist):
+
+### Is the description of the issue itself sufficient?
+
+We often get issue reports that we cannot really decipher. While in most cases we eventually get the required information after asking back multiple times, this poses an unnecessary drain on our resources. Many contributors, including myself, are also not native speakers, so we may misread some parts.
+
+So please elaborate on what feature you are requesting, or what bug you want to be fixed. Make sure that it's obvious
+
+- What the problem is
+- How it could be fixed
+- How your proposed solution would look like
+
+If your report is shorter than two lines, it is almost certainly missing some of these, which makes it hard for us to respond to it. We're often too polite to close the issue outright, but the missing info makes misinterpretation likely. As a commiter myself, I often get frustrated by these issues, since the only possible way for me to move forward on them is to ask for clarification over and over.
+
+For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the -v flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information.
+
+Site support requests **must contain an example URL**. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL.
+
+###  Are you using the latest version?
+
+Before reporting any issue, type youtube-dl -U. This should report that you're up-to-date. About 20% of the reports we receive are already fixed, but people are using outdated versions. This goes for feature requests as well.
+
+###  Is the issue already documented?
+
+Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or at https://github.com/rg3/youtube-dl/search?type=Issues . If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity.
+
+###  Why are existing options not enough?
+
+Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#synopsis). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem.
+
+###  Is there enough context in your bug report?
+
+People want to solve problems, and often think they do us a favor by breaking down their larger problems (e.g. wanting to skip already downloaded files) to a specific request (e.g. requesting us to look whether the file exists before downloading the info page). However, what often happens is that they break down the problem into two steps: One simple, and one impossible (or extremely complicated one).
+
+We are then presented with a very complicated request when the original problem could be solved far easier, e.g. by recording the downloaded video IDs in a separate file. To avoid this, you must include the greater context where it is non-obvious. In particular, every feature request that does not consist of adding support for a new site should contain a use case scenario that explains in what situation the missing feature would be useful.
+
+###  Does the issue involve one problem, and one problem only?
+
+Some of our users seem to think there is a limit of issues they can or should open. There is no limit of issues they can or should open. While it may seem appealing to be able to dump all your issues into one ticket, that means that someone who solves one of your issues cannot mark the issue as closed. Typically, reporting a bunch of issues leads to the ticket lingering since nobody wants to attack that behemoth, until someone mercifully splits the issue into multiple ones.
+
+In particular, every site support request issue should only pertain to services at one site (generally under a common domain, but always using the same backend technology). Do not request support for vimeo user videos, Whitehouse podcasts, and Google Plus pages in the same issue. Also, make sure that you don't post bug reports alongside feature requests. As a rule of thumb, a feature request does not include outputs of youtube-dl that are not immediately related to the feature at hand. Do not post reports of a network error alongside the request for a new video service.
+
+###  Is anyone going to need the feature?
+
+Only post features that you (or an incapicated friend you can personally talk to) require. Do not post features because they seem like a good idea. If they are really useful, they will be requested by someone who requires them.
+
+###  Is your question about youtube-dl?
+
+It may sound strange, but some bug reports we receive are completely unrelated to youtube-dl and relate to a different or even the reporter's own application. Please make sure that you are actually using youtube-dl. If you are using a UI for youtube-dl, report the bug to the maintainer of the actual application providing the UI. On the other hand, if your UI for youtube-dl fails in some way you believe is related to youtube-dl, by all means, go ahead and report the bug.
+
 # COPYRIGHT
 
 youtube-dl is released into the public domain by the copyright holders.
 
 This README file was originally written by Daniel Bolton (<https://github.com/dbbolton>) and is likewise released into the public domain.
-
-# BUGS
-
-Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues>
-
-Please include:
-
-* Your exact command line, like `youtube-dl -t "http://www.youtube.com/watch?v=uHlDtZ6Oc3s&feature=channel_video_title"`. A common mistake is not to escape the `&`. Putting URLs in quotes should solve this problem.
-* If possible re-run the command with `--verbose`, and include the full output, it is really helpful to us.
-* The output of `youtube-dl --version`
-* The output of `python --version`
-* The name and version of your Operating System ("Ubuntu 11.04 x64" or "Windows 7 x64" is usually enough).
-
-For discussions, join us in the irc channel #youtube-dl on freenode.

devscripts/bash-completion.in

@@ -1,10 +1,21 @@
 __youtube_dl()
 {
-    local cur prev opts
+    local cur prev opts fileopts diropts keywords
     COMPREPLY=()
     cur="${COMP_WORDS[COMP_CWORD]}"
+    prev="${COMP_WORDS[COMP_CWORD-1]}"
     opts="{{flags}}"
-    keywords=":ytfavorites :ytrecommended :ytsubscriptions :ytwatchlater"
+    keywords=":ytfavorites :ytrecommended :ytsubscriptions :ytwatchlater :ythistory"
+    fileopts="-a|--batch-file|--download-archive|--cookies|--load-info"
+    diropts="--cache-dir"
+
+    if [[ ${prev} =~ ${fileopts} ]]; then
+        COMPREPLY=( $(compgen -f -- ${cur}) )
+        return 0
+    elif [[ ${prev} =~ ${diropts} ]]; then
+        COMPREPLY=( $(compgen -d -- ${cur}) )
+        return 0
+    fi
 
     if [[ ${cur} =~ : ]]; then
         COMPREPLY=( $(compgen -W "${keywords}" -- ${cur}) )

devscripts/check-porn.py

@@ -3,6 +3,9 @@
 """
 This script employs a VERY basic heuristic ('porn' in webpage.lower()) to check
 if we are not 'age_limit' tagging some porn site
+
+A second approach implemented relies on a list of porn domains, to activate it
+pass the list filename as the only argument
 """
 
 # Allow direct execution
@@ -11,25 +14,42 @@ import sys
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from test.helper import get_testcases
+from youtube_dl.utils import compat_urllib_parse_urlparse
 from youtube_dl.utils import compat_urllib_request
 
+if len(sys.argv) > 1:
+    METHOD = 'LIST'
+    LIST = open(sys.argv[1]).read().decode('utf8').strip()
+else:
+    METHOD = 'EURISTIC'
+
 for test in get_testcases():
-    try:
-        webpage = compat_urllib_request.urlopen(test['url'], timeout=10).read()
-    except:
-        print('\nFail: {0}'.format(test['name']))
-        continue
+    if METHOD == 'EURISTIC':
+        try:
+            webpage = compat_urllib_request.urlopen(test['url'], timeout=10).read()
+        except:
+            print('\nFail: {0}'.format(test['name']))
+            continue
 
-    webpage = webpage.decode('utf8', 'replace')
+        webpage = webpage.decode('utf8', 'replace')
 
-    if 'porn' in webpage.lower() and ('info_dict' not in test
-                                      or 'age_limit' not in test['info_dict']
-                                      or test['info_dict']['age_limit'] != 18):
+        RESULT = 'porn' in webpage.lower()
+
+    elif METHOD == 'LIST':
+        domain = compat_urllib_parse_urlparse(test['url']).netloc
+        if not domain:
+            print('\nFail: {0}'.format(test['name']))
+            continue
+        domain = '.'.join(domain.split('.')[-2:])
+
+        RESULT = ('.' + domain + '\n' in LIST or '\n' + domain + '\n' in LIST)
+
+    if RESULT and ('info_dict' not in test or 'age_limit' not in test['info_dict']
+                   or test['info_dict']['age_limit'] != 18):
         print('\nPotential missing age_limit check: {0}'.format(test['name']))
 
-    elif 'porn' not in webpage.lower() and ('info_dict' in test and
-                                            'age_limit' in test['info_dict'] and
-                                            test['info_dict']['age_limit'] == 18):
+    elif not RESULT and ('info_dict' in test and 'age_limit' in test['info_dict']
+                         and test['info_dict']['age_limit'] == 18):
         print('\nPotential false negative: {0}'.format(test['name']))
 
     else:

devscripts/gh-pages/update-feed.py

@@ -1,56 +1,76 @@
 #!/usr/bin/env python3
 
 import datetime
-
+import io
+import json
 import textwrap
 
-import json
 
-atom_template=textwrap.dedent("""\
-								<?xml version='1.0' encoding='utf-8'?>
-								<atom:feed xmlns:atom="http://www.w3.org/2005/Atom">
-									<atom:title>youtube-dl releases</atom:title>
-									<atom:id>youtube-dl-updates-feed</atom:id>
-									<atom:updated>@TIMESTAMP@</atom:updated>
-									@ENTRIES@
-								</atom:feed>""")
+atom_template = textwrap.dedent("""\
+    <?xml version="1.0" encoding="utf-8"?>
+    <feed xmlns="http://www.w3.org/2005/Atom">
+        <link rel="self" href="http://rg3.github.io/youtube-dl/update/releases.atom" />
+        <title>youtube-dl releases</title>
+        <id>https://yt-dl.org/feed/youtube-dl-updates-feed</id>
+        <updated>@TIMESTAMP@</updated>
+        @ENTRIES@
+    </feed>""")
 
-entry_template=textwrap.dedent("""
-								<atom:entry>
-									<atom:id>youtube-dl-@VERSION@</atom:id>
-									<atom:title>New version @VERSION@</atom:title>
-									<atom:link href="http://rg3.github.io/youtube-dl" />
-									<atom:content type="xhtml">
-										<div xmlns="http://www.w3.org/1999/xhtml">
-											Downloads available at <a href="https://yt-dl.org/downloads/@VERSION@/">https://yt-dl.org/downloads/@VERSION@/</a>
-										</div>
-									</atom:content>
-									<atom:author>
-										<atom:name>The youtube-dl maintainers</atom:name>
-									</atom:author>
-									<atom:updated>@TIMESTAMP@</atom:updated>
-								</atom:entry>
-								""")
+entry_template = textwrap.dedent("""
+    <entry>
+        <id>https://yt-dl.org/feed/youtube-dl-updates-feed/youtube-dl-@VERSION@</id>
+        <title>New version @VERSION@</title>
+        <link href="http://rg3.github.io/youtube-dl" />
+        <content type="xhtml">
+            <div xmlns="http://www.w3.org/1999/xhtml">
+                Downloads available at <a href="https://yt-dl.org/downloads/@VERSION@/">https://yt-dl.org/downloads/@VERSION@/</a>
+            </div>
+        </content>
+        <author>
+            <name>The youtube-dl maintainers</name>
+        </author>
+        <updated>@TIMESTAMP@</updated>
+    </entry>
+    """)
 
 now = datetime.datetime.now()
-now_iso = now.isoformat()
+now_iso = now.isoformat() + 'Z'
 
-atom_template = atom_template.replace('@TIMESTAMP@',now_iso)
-
-entries=[]
+atom_template = atom_template.replace('@TIMESTAMP@', now_iso)
 
 versions_info = json.load(open('update/versions.json'))
 versions = list(versions_info['versions'].keys())
 versions.sort()
 
+entries = []
 for v in versions:
-	entry = entry_template.replace('@TIMESTAMP@',v.replace('.','-'))
-	entry = entry.replace('@VERSION@',v)
-	entries.append(entry)
+    fields = v.split('.')
+    year, month, day = map(int, fields[:3])
+    faked = 0
+    patchlevel = 0
+    while True:
+        try:
+            datetime.date(year, month, day)
+        except ValueError:
+            day -= 1
+            faked += 1
+            assert day > 0
+            continue
+        break
+    if len(fields) >= 4:
+        try:
+            patchlevel = int(fields[3])
+        except ValueError:
+            patchlevel = 1
+    timestamp = '%04d-%02d-%02dT00:%02d:%02dZ' % (year, month, day, faked, patchlevel)
+
+    entry = entry_template.replace('@TIMESTAMP@', timestamp)
+    entry = entry.replace('@VERSION@', v)
+    entries.append(entry)
 
 entries_str = textwrap.indent(''.join(entries), '\t')
 atom_template = atom_template.replace('@ENTRIES@', entries_str)
 
-with open('update/releases.atom','w',encoding='utf-8') as atom_file:
-	atom_file.write(atom_template)
+with io.open('update/releases.atom', 'w', encoding='utf-8') as atom_file:
+    atom_file.write(atom_template)
 

devscripts/make_readme.py

@@ -1,20 +1,24 @@
+import io
 import sys
 import re
 
 README_FILE = 'README.md'
 helptext = sys.stdin.read()
 
-with open(README_FILE) as f:
+if isinstance(helptext, bytes):
+    helptext = helptext.decode('utf-8')
+
+with io.open(README_FILE, encoding='utf-8') as f:
     oldreadme = f.read()
 
 header = oldreadme[:oldreadme.index('# OPTIONS')]
 footer = oldreadme[oldreadme.index('# CONFIGURATION'):]
 
-options = helptext[helptext.index('  General Options:')+19:]
-options = re.sub(r'^  (\w.+)$', r'## \1', options, flags=re.M)
+options = helptext[helptext.index('  General Options:') + 19:]
+options = re.sub(r'(?m)^  (\w.+)$', r'## \1', options)
 options = '# OPTIONS\n' + options + '\n'
 
-with open(README_FILE, 'w') as f:
+with io.open(README_FILE, 'w', encoding='utf-8') as f:
     f.write(header)
     f.write(options)
     f.write(footer)

devscripts/prepare_manpage.py

@@ -0,0 +1,20 @@
+
+import io
+import os.path
+import sys
+import re
+
+ROOT_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+README_FILE = os.path.join(ROOT_DIR, 'README.md')
+
+with io.open(README_FILE, encoding='utf-8') as f:
+    readme = f.read()
+
+PREFIX = '%YOUTUBE-DL(1)\n\n# NAME\n'
+readme = re.sub(r'(?s)# INSTALLATION.*?(?=# DESCRIPTION)', '', readme)
+readme = PREFIX + readme
+
+if sys.version_info < (3, 0):
+    print(readme.encode('utf-8'))
+else:
+    print(readme)

devscripts/release.sh

@@ -14,16 +14,24 @@
 
 set -e
 
-skip_tests=false
-if [ "$1" = '--skip-test' ]; then
-    skip_tests=true
+skip_tests=true
+if [ "$1" = '--run-tests' ]; then
+    skip_tests=false
     shift
 fi
 
 if [ -z "$1" ]; then echo "ERROR: specify version number like this: $0 1994.09.06"; exit 1; fi
 version="$1"
+major_version=$(echo "$version" | sed -n 's#^\([0-9]*\.[0-9]*\.[0-9]*\).*#\1#p')
+if test "$major_version" '!=' "$(date '+%Y.%m.%d')"; then
+    echo "$version does not start with today's date!"
+    exit 1
+fi
+
 if [ ! -z "`git tag | grep "$version"`" ]; then echo 'ERROR: version already present'; exit 1; fi
 if [ ! -z "`git status --porcelain | grep -v CHANGELOG`" ]; then echo 'ERROR: the working directory is not clean; commit or stash changes'; exit 1; fi
+useless_files=$(find youtube_dl -type f -not -name '*.py')
+if [ ! -z "$useless_files" ]; then echo "ERROR: Non-.py files in youtube_dl: $useless_files"; exit 1; fi
 if [ ! -f "updates_key.pem" ]; then echo 'ERROR: updates_key.pem missing'; exit 1; fi
 
 /bin/echo -e "\n### First of all, testing..."
@@ -37,9 +45,9 @@ fi
 /bin/echo -e "\n### Changing version in version.py..."
 sed -i "s/__version__ = '.*'/__version__ = '$version'/" youtube_dl/version.py
 
-/bin/echo -e "\n### Committing CHANGELOG README.md and youtube_dl/version.py..."
+/bin/echo -e "\n### Committing README.md and youtube_dl/version.py..."
 make README.md
-git add CHANGELOG README.md youtube_dl/version.py
+git add README.md youtube_dl/version.py
 git commit -m "release $version"
 
 /bin/echo -e "\n### Now tagging, signing and pushing..."
@@ -68,7 +76,7 @@ RELEASE_FILES="youtube-dl youtube-dl.exe youtube-dl-$version.tar.gz"
 git checkout HEAD -- youtube-dl youtube-dl.exe
 
 /bin/echo -e "\n### Signing and uploading the new binaries to yt-dl.org ..."
-for f in $RELEASE_FILES; do gpg --detach-sig "build/$version/$f"; done
+for f in $RELEASE_FILES; do gpg --passphrase-repeat 5 --detach-sig "build/$version/$f"; done
 scp -r "build/$version" ytdl@yt-dl.org:html/tmp/
 ssh ytdl@yt-dl.org "mv html/tmp/$version html/downloads/"
 ssh ytdl@yt-dl.org "sh html/update_latest.sh $version"
@@ -95,7 +103,7 @@ rm -rf build
 
 make pypi-files
 echo "Uploading to PyPi ..."
-python setup.py sdist upload
+python setup.py sdist bdist_wheel upload
 make clean
 
 /bin/echo -e "\n### DONE!"

docs/.gitignore

@@ -0,0 +1 @@
+_build/

docs/Makefile

@@ -0,0 +1,177 @@
+# Makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line.
+SPHINXOPTS    =
+SPHINXBUILD   = sphinx-build
+PAPER         =
+BUILDDIR      = _build
+
+# User-friendly check for sphinx-build
+ifeq ($(shell which $(SPHINXBUILD) >/dev/null 2>&1; echo $$?), 1)
+$(error The '$(SPHINXBUILD)' command was not found. Make sure you have Sphinx installed, then set the SPHINXBUILD environment variable to point to the full path of the '$(SPHINXBUILD)' executable. Alternatively you can add the directory with the executable to your PATH. If you don't have Sphinx installed, grab it from http://sphinx-doc.org/)
+endif
+
+# Internal variables.
+PAPEROPT_a4     = -D latex_paper_size=a4
+PAPEROPT_letter = -D latex_paper_size=letter
+ALLSPHINXOPTS   = -d $(BUILDDIR)/doctrees $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) .
+# the i18n builder cannot share the environment and doctrees with the others
+I18NSPHINXOPTS  = $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) .
+
+.PHONY: help clean html dirhtml singlehtml pickle json htmlhelp qthelp devhelp epub latex latexpdf text man changes linkcheck doctest gettext
+
+help:
+	@echo "Please use \`make <target>' where <target> is one of"
+	@echo "  html       to make standalone HTML files"
+	@echo "  dirhtml    to make HTML files named index.html in directories"
+	@echo "  singlehtml to make a single large HTML file"
+	@echo "  pickle     to make pickle files"
+	@echo "  json       to make JSON files"
+	@echo "  htmlhelp   to make HTML files and a HTML help project"
+	@echo "  qthelp     to make HTML files and a qthelp project"
+	@echo "  devhelp    to make HTML files and a Devhelp project"
+	@echo "  epub       to make an epub"
+	@echo "  latex      to make LaTeX files, you can set PAPER=a4 or PAPER=letter"
+	@echo "  latexpdf   to make LaTeX files and run them through pdflatex"
+	@echo "  latexpdfja to make LaTeX files and run them through platex/dvipdfmx"
+	@echo "  text       to make text files"
+	@echo "  man        to make manual pages"
+	@echo "  texinfo    to make Texinfo files"
+	@echo "  info       to make Texinfo files and run them through makeinfo"
+	@echo "  gettext    to make PO message catalogs"
+	@echo "  changes    to make an overview of all changed/added/deprecated items"
+	@echo "  xml        to make Docutils-native XML files"
+	@echo "  pseudoxml  to make pseudoxml-XML files for display purposes"
+	@echo "  linkcheck  to check all external links for integrity"
+	@echo "  doctest    to run all doctests embedded in the documentation (if enabled)"
+
+clean:
+	rm -rf $(BUILDDIR)/*
+
+html:
+	$(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html
+	@echo
+	@echo "Build finished. The HTML pages are in $(BUILDDIR)/html."
+
+dirhtml:
+	$(SPHINXBUILD) -b dirhtml $(ALLSPHINXOPTS) $(BUILDDIR)/dirhtml
+	@echo
+	@echo "Build finished. The HTML pages are in $(BUILDDIR)/dirhtml."
+
+singlehtml:
+	$(SPHINXBUILD) -b singlehtml $(ALLSPHINXOPTS) $(BUILDDIR)/singlehtml
+	@echo
+	@echo "Build finished. The HTML page is in $(BUILDDIR)/singlehtml."
+
+pickle:
+	$(SPHINXBUILD) -b pickle $(ALLSPHINXOPTS) $(BUILDDIR)/pickle
+	@echo
+	@echo "Build finished; now you can process the pickle files."
+
+json:
+	$(SPHINXBUILD) -b json $(ALLSPHINXOPTS) $(BUILDDIR)/json
+	@echo
+	@echo "Build finished; now you can process the JSON files."
+
+htmlhelp:
+	$(SPHINXBUILD) -b htmlhelp $(ALLSPHINXOPTS) $(BUILDDIR)/htmlhelp
+	@echo
+	@echo "Build finished; now you can run HTML Help Workshop with the" \
+	      ".hhp project file in $(BUILDDIR)/htmlhelp."
+
+qthelp:
+	$(SPHINXBUILD) -b qthelp $(ALLSPHINXOPTS) $(BUILDDIR)/qthelp
+	@echo
+	@echo "Build finished; now you can run "qcollectiongenerator" with the" \
+	      ".qhcp project file in $(BUILDDIR)/qthelp, like this:"
+	@echo "# qcollectiongenerator $(BUILDDIR)/qthelp/youtube-dl.qhcp"
+	@echo "To view the help file:"
+	@echo "# assistant -collectionFile $(BUILDDIR)/qthelp/youtube-dl.qhc"
+
+devhelp:
+	$(SPHINXBUILD) -b devhelp $(ALLSPHINXOPTS) $(BUILDDIR)/devhelp
+	@echo
+	@echo "Build finished."
+	@echo "To view the help file:"
+	@echo "# mkdir -p $$HOME/.local/share/devhelp/youtube-dl"
+	@echo "# ln -s $(BUILDDIR)/devhelp $$HOME/.local/share/devhelp/youtube-dl"
+	@echo "# devhelp"
+
+epub:
+	$(SPHINXBUILD) -b epub $(ALLSPHINXOPTS) $(BUILDDIR)/epub
+	@echo
+	@echo "Build finished. The epub file is in $(BUILDDIR)/epub."
+
+latex:
+	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
+	@echo
+	@echo "Build finished; the LaTeX files are in $(BUILDDIR)/latex."
+	@echo "Run \`make' in that directory to run these through (pdf)latex" \
+	      "(use \`make latexpdf' here to do that automatically)."
+
+latexpdf:
+	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
+	@echo "Running LaTeX files through pdflatex..."
+	$(MAKE) -C $(BUILDDIR)/latex all-pdf
+	@echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex."
+
+latexpdfja:
+	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
+	@echo "Running LaTeX files through platex and dvipdfmx..."
+	$(MAKE) -C $(BUILDDIR)/latex all-pdf-ja
+	@echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex."
+
+text:
+	$(SPHINXBUILD) -b text $(ALLSPHINXOPTS) $(BUILDDIR)/text
+	@echo
+	@echo "Build finished. The text files are in $(BUILDDIR)/text."
+
+man:
+	$(SPHINXBUILD) -b man $(ALLSPHINXOPTS) $(BUILDDIR)/man
+	@echo
+	@echo "Build finished. The manual pages are in $(BUILDDIR)/man."
+
+texinfo:
+	$(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo
+	@echo
+	@echo "Build finished. The Texinfo files are in $(BUILDDIR)/texinfo."
+	@echo "Run \`make' in that directory to run these through makeinfo" \
+	      "(use \`make info' here to do that automatically)."
+
+info:
+	$(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo
+	@echo "Running Texinfo files through makeinfo..."
+	make -C $(BUILDDIR)/texinfo info
+	@echo "makeinfo finished; the Info files are in $(BUILDDIR)/texinfo."
+
+gettext:
+	$(SPHINXBUILD) -b gettext $(I18NSPHINXOPTS) $(BUILDDIR)/locale
+	@echo
+	@echo "Build finished. The message catalogs are in $(BUILDDIR)/locale."
+
+changes:
+	$(SPHINXBUILD) -b changes $(ALLSPHINXOPTS) $(BUILDDIR)/changes
+	@echo
+	@echo "The overview file is in $(BUILDDIR)/changes."
+
+linkcheck:
+	$(SPHINXBUILD) -b linkcheck $(ALLSPHINXOPTS) $(BUILDDIR)/linkcheck
+	@echo
+	@echo "Link check complete; look for any errors in the above output " \
+	      "or in $(BUILDDIR)/linkcheck/output.txt."
+
+doctest:
+	$(SPHINXBUILD) -b doctest $(ALLSPHINXOPTS) $(BUILDDIR)/doctest
+	@echo "Testing of doctests in the sources finished, look at the " \
+	      "results in $(BUILDDIR)/doctest/output.txt."
+
+xml:
+	$(SPHINXBUILD) -b xml $(ALLSPHINXOPTS) $(BUILDDIR)/xml
+	@echo
+	@echo "Build finished. The XML files are in $(BUILDDIR)/xml."
+
+pseudoxml:
+	$(SPHINXBUILD) -b pseudoxml $(ALLSPHINXOPTS) $(BUILDDIR)/pseudoxml
+	@echo
+	@echo "Build finished. The pseudo-XML files are in $(BUILDDIR)/pseudoxml."

docs/conf.py

@@ -0,0 +1,71 @@
+# -*- coding: utf-8 -*-
+#
+# youtube-dl documentation build configuration file, created by
+# sphinx-quickstart on Fri Mar 14 21:05:43 2014.
+#
+# This file is execfile()d with the current directory set to its
+# containing dir.
+#
+# Note that not all possible configuration values are present in this
+# autogenerated file.
+#
+# All configuration values have a default; values that are commented out
+# serve to show the default.
+
+import sys
+import os
+# Allows to import youtube_dl
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+# -- General configuration ------------------------------------------------
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = [
+    'sphinx.ext.autodoc',
+]
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ['_templates']
+
+# The suffix of source filenames.
+source_suffix = '.rst'
+
+# The master toctree document.
+master_doc = 'index'
+
+# General information about the project.
+project = u'youtube-dl'
+copyright = u'2014, Ricardo Garcia Gonzalez'
+
+# The version info for the project you're documenting, acts as replacement for
+# |version| and |release|, also used in various other places throughout the
+# built documents.
+#
+# The short X.Y version.
+import youtube_dl
+version = youtube_dl.__version__
+# The full version, including alpha/beta/rc tags.
+release = version
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+exclude_patterns = ['_build']
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = 'sphinx'
+
+# -- Options for HTML output ----------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+html_theme = 'default'
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ['_static']
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = 'youtube-dldoc'

docs/index.rst

@@ -0,0 +1,23 @@
+Welcome to youtube-dl's documentation!
+======================================
+
+*youtube-dl* is a command-line program to download videos from YouTube.com and more sites.
+It can also be used in Python code.
+
+Developer guide
+---------------
+
+This section contains information for using *youtube-dl* from Python programs.
+
+.. toctree::
+    :maxdepth: 2
+
+    module_guide
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`
+

docs/module_guide.rst

@@ -0,0 +1,67 @@
+Using the ``youtube_dl`` module
+===============================
+
+When using the ``youtube_dl`` module, you start by creating an instance of :class:`YoutubeDL` and adding all the available extractors:
+
+.. code-block:: python
+
+    >>> from youtube_dl import YoutubeDL
+    >>> ydl = YoutubeDL()
+    >>> ydl.add_default_info_extractors()
+
+Extracting video information
+----------------------------
+
+You use the :meth:`YoutubeDL.extract_info` method for getting the video information, which returns a dictionary:
+
+.. code-block:: python
+
+    >>> info = ydl.extract_info('http://www.youtube.com/watch?v=BaW_jenozKc', download=False)
+    [youtube] Setting language
+    [youtube] BaW_jenozKc: Downloading webpage
+    [youtube] BaW_jenozKc: Downloading video info webpage
+    [youtube] BaW_jenozKc: Extracting video information
+    >>> info['title']
+    'youtube-dl test video "\'/\\ä↭𝕐'
+    >>> info['height'], info['width']
+    (720, 1280)
+
+If you want to download or play the video you can get its url:
+
+.. code-block:: python
+
+    >>> info['url']
+    'https://...'
+
+Extracting playlist information
+-------------------------------
+
+The playlist information is extracted in a similar way, but the dictionary is a bit different:
+
+.. code-block:: python
+
+    >>> playlist = ydl.extract_info('http://www.ted.com/playlists/13/open_source_open_world', download=False)
+    [TED] open_source_open_world: Downloading playlist webpage
+    ...
+    >>> playlist['title']
+    'Open-source, open world'
+
+
+
+You can access the videos in the playlist with the ``entries`` field:
+
+.. code-block:: python
+
+    >>> for video in playlist['entries']:
+    ...     print('Video #%d: %s' % (video['playlist_index'], video['title']))
+
+    Video #1: How Arduino is open-sourcing imagination
+    Video #2: The year open data went worldwide
+    Video #3: Massive-scale online collaboration
+    Video #4: The art of asking
+    Video #5: How cognitive surplus will change the world
+    Video #6: The birth of Wikipedia
+    Video #7: Coding a better government
+    Video #8: The era of open innovation
+    Video #9: The currency of the new economy is trust
+

setup.cfg

@@ -0,0 +1,2 @@
+[wheel]
+universal = True

setup.py

@@ -3,7 +3,9 @@
 
 from __future__ import print_function
 
+import os.path
 import pkg_resources
+import warnings
 import sys
 
 try:
@@ -44,12 +46,24 @@ py2exe_params = {
 if len(sys.argv) >= 2 and sys.argv[1] == 'py2exe':
     params = py2exe_params
 else:
+    files_spec = [
+        ('etc/bash_completion.d', ['youtube-dl.bash-completion']),
+        ('share/doc/youtube_dl', ['README.txt']),
+        ('share/man/man1', ['youtube-dl.1'])
+    ]
+    root = os.path.dirname(os.path.abspath(__file__))
+    data_files = []
+    for dirname, files in files_spec:
+        resfiles = []
+        for fn in files:
+            if not os.path.exists(fn):
+                warnings.warn('Skipping file %s since it is not present. Type  make  to build all automatically generated files.' % fn)
+            else:
+                resfiles.append(fn)
+        data_files.append((dirname, resfiles))
+
     params = {
-        'data_files': [  # Installing system-wide would require sudo...
-            ('etc/bash_completion.d', ['youtube-dl.bash-completion']),
-            ('share/doc/youtube_dl', ['README.txt']),
-            ('share/man/man1', ['youtube-dl.1'])
-        ]
+        'data_files': data_files,
     }
     if setuptools_available:
         params['entry_points'] = {'console_scripts': ['youtube-dl = youtube_dl:main']}
@@ -71,7 +85,10 @@ setup(
     author_email='ytdl@yt-dl.org',
     maintainer='Philipp Hagemeister',
     maintainer_email='phihag@phihag.de',
-    packages=['youtube_dl', 'youtube_dl.extractor'],
+    packages=[
+        'youtube_dl',
+        'youtube_dl.extractor', 'youtube_dl.downloader',
+        'youtube_dl.postprocessor'],
 
     # Provokes warning on most systems (why?!)
     # test_suite = 'nose.collector',

test/helper.py

@@ -9,7 +9,10 @@ import sys
 
 import youtube_dl.extractor
 from youtube_dl import YoutubeDL
-from youtube_dl.utils import preferredencoding
+from youtube_dl.utils import (
+    compat_str,
+    preferredencoding,
+)
 
 
 def get_params(override=None):
@@ -71,15 +74,84 @@ class FakeYDL(YoutubeDL):
             old_report_warning(message)
         self.report_warning = types.MethodType(report_warning, self)
 
-def get_testcases():
+
+def gettestcases(include_onlymatching=False):
     for ie in youtube_dl.extractor.gen_extractors():
         t = getattr(ie, '_TEST', None)
         if t:
-            t['name'] = type(ie).__name__[:-len('IE')]
-            yield t
-        for t in getattr(ie, '_TESTS', []):
+            assert not hasattr(ie, '_TESTS'), \
+                '%s has _TEST and _TESTS' % type(ie).__name__
+            tests = [t]
+        else:
+            tests = getattr(ie, '_TESTS', [])
+        for t in tests:
+            if not include_onlymatching and t.get('only_matching', False):
+                continue
             t['name'] = type(ie).__name__[:-len('IE')]
             yield t
 
 
 md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
+
+
+def expect_info_dict(self, expected_dict, got_dict):
+    for info_field, expected in expected_dict.items():
+        if isinstance(expected, compat_str) and expected.startswith('re:'):
+            got = got_dict.get(info_field)
+            match_str = expected[len('re:'):]
+            match_rex = re.compile(match_str)
+
+            self.assertTrue(
+                isinstance(got, compat_str) and match_rex.match(got),
+                u'field %s (value: %r) should match %r' % (info_field, got, match_str))
+        elif isinstance(expected, type):
+            got = got_dict.get(info_field)
+            self.assertTrue(isinstance(got, expected),
+                u'Expected type %r for field %s, but got value %r of type %r' % (expected, info_field, got, type(got)))
+        else:
+            if isinstance(expected, compat_str) and expected.startswith('md5:'):
+                got = 'md5:' + md5(got_dict.get(info_field))
+            else:
+                got = got_dict.get(info_field)
+            self.assertEqual(expected, got,
+                u'invalid value for field %s, expected %r, got %r' % (info_field, expected, got))
+
+    # Check for the presence of mandatory fields
+    for key in ('id', 'url', 'title', 'ext'):
+        self.assertTrue(got_dict.get(key), 'Missing mandatory field %s' % key)
+    # Check for mandatory fields that are automatically set by YoutubeDL
+    for key in ['webpage_url', 'extractor', 'extractor_key']:
+        self.assertTrue(got_dict.get(key), u'Missing field: %s' % key)
+
+    # Are checkable fields missing from the test case definition?
+    test_info_dict = dict((key, value if not isinstance(value, compat_str) or len(value) < 250 else 'md5:' + md5(value))
+        for key, value in got_dict.items()
+        if value and key in ('title', 'description', 'uploader', 'upload_date', 'timestamp', 'uploader_id', 'location'))
+    missing_keys = set(test_info_dict.keys()) - set(expected_dict.keys())
+    if missing_keys:
+        sys.stderr.write(u'\n"info_dict": ' + json.dumps(test_info_dict, ensure_ascii=False, indent=4) + u'\n')
+        self.assertFalse(
+            missing_keys,
+            'Missing keys in test definition: %s' % (
+                ', '.join(sorted(missing_keys))))
+
+
+def assertRegexpMatches(self, text, regexp, msg=None):
+    if hasattr(self, 'assertRegexp'):
+        return self.assertRegexp(text, regexp, msg)
+    else:
+        m = re.match(regexp, text)
+        if not m:
+            note = 'Regexp didn\'t match: %r not found in %r' % (regexp, text)
+            if msg is None:
+                msg = note
+            else:
+                msg = note + ', ' + msg
+            self.assertTrue(m, msg)
+
+
+def assertGreaterEqual(self, got, expected, msg=None):
+    if not (got >= expected):
+        if msg is None:
+            msg = '%r not greater than or equal to %r' % (got, expected)
+        self.assertTrue(got >= expected, msg)

test/parameters.json

@@ -39,5 +39,6 @@
     "writeinfojson": true, 
     "writesubtitles": false,
     "allsubtitles": false,
-    "listssubtitles": false
+    "listssubtitles": false,
+    "socket_timeout": 20
 }

test/swftests/.gitignore

@@ -0,0 +1 @@
+*.swf

test/swftests/ArrayAccess.as

@@ -0,0 +1,19 @@
+// input: [["a", "b", "c", "d"]]
+// output: ["c", "b", "a", "d"]
+
+package {
+public class ArrayAccess {
+    public static function main(ar:Array):Array {
+    	var aa:ArrayAccess = new ArrayAccess();
+    	return aa.f(ar, 2);
+    }
+
+    private function f(ar:Array, num:Number):Array{
+        var x:String = ar[0];
+        var y:String = ar[num % ar.length];
+        ar[0] = y;
+        ar[num] = x;
+        return ar;
+    }
+}
+}

test/swftests/ClassCall.as

@@ -0,0 +1,17 @@
+// input: []
+// output: 121
+
+package {
+public class ClassCall {
+    public static function main():int{
+    	var f:OtherClass = new OtherClass();
+        return f.func(100,20);
+    }
+}
+}
+
+class OtherClass {
+	public function func(x: int, y: int):int {
+		return x+y+1;
+	}
+}

test/swftests/ClassConstruction.as

@@ -0,0 +1,15 @@
+// input: []
+// output: 0
+
+package {
+public class ClassConstruction {
+    public static function main():int{
+    	var f:Foo = new Foo();
+        return 0;
+    }
+}
+}
+
+class Foo {
+
+}

test/swftests/LocalVars.as

@@ -0,0 +1,13 @@
+// input: [1, 2]
+// output: 3
+
+package {
+public class LocalVars {
+    public static function main(a:int, b:int):int{
+        var c:int = a + b + b;
+        var d:int = c - b;
+        var e:int = d;
+        return e;
+    }
+}
+}

test/swftests/PrivateCall.as

@@ -0,0 +1,21 @@
+// input: []
+// output: 9
+
+package {
+public class PrivateCall {
+    public static function main():int{
+    	var f:OtherClass = new OtherClass();
+        return f.func();
+    }
+}
+}
+
+class OtherClass {
+	private function pf():int {
+		return 9;
+	}
+
+	public function func():int {
+		return this.pf();
+	}
+}

test/swftests/StaticAssignment.as

@@ -0,0 +1,13 @@
+// input: [1]
+// output: 1
+
+package {
+public class StaticAssignment {
+	public static var v:int;
+
+    public static function main(a:int):int{
+        v = a;
+        return v;
+    }
+}
+}

test/swftests/StaticRetrieval.as

@@ -0,0 +1,16 @@
+// input: []
+// output: 1
+
+package {
+public class StaticRetrieval {
+	public static var v:int;
+
+    public static function main():int{
+        if (v) {
+        	return 0;
+        } else {
+        	return 1;
+        }
+    }
+}
+}

test/test_InfoExtractor.py

@@ -0,0 +1,44 @@
+#!/usr/bin/env python
+
+from __future__ import unicode_literals
+
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from test.helper import FakeYDL
+from youtube_dl.extractor.common import InfoExtractor
+from youtube_dl.extractor import YoutubeIE, get_info_extractor
+
+
+class TestIE(InfoExtractor):
+    pass
+
+
+class TestInfoExtractor(unittest.TestCase):
+    def setUp(self):
+        self.ie = TestIE(FakeYDL())
+
+    def test_ie_key(self):
+        self.assertEqual(get_info_extractor(YoutubeIE.ie_key()), YoutubeIE)
+
+    def test_html_search_regex(self):
+        html = '<p id="foo">Watch this <a href="http://www.youtube.com/watch?v=BaW_jenozKc">video</a></p>'
+        search = lambda re, *args: self.ie._html_search_regex(re, html, *args)
+        self.assertEqual(search(r'<p id="foo">(.+?)</p>', 'foo'), 'Watch this video')
+
+    def test_opengraph(self):
+        ie = self.ie
+        html = '''
+            <meta name="og:title" content='Foo'/>
+            <meta content="Some video's description " name="og:description"/>
+            <meta property='og:image' content='http://domain.com/pic.jpg?key1=val1&amp;key2=val2'/>
+            '''
+        self.assertEqual(ie._og_search_title(html), 'Foo')
+        self.assertEqual(ie._og_search_description(html), 'Some video\'s description ')
+        self.assertEqual(ie._og_search_thumbnail(html), 'http://domain.com/pic.jpg?key1=val1&key2=val2')
+
+if __name__ == '__main__':
+    unittest.main()

test/test_YoutubeDL.py

@@ -1,12 +1,16 @@
 #!/usr/bin/env python
 
+from __future__ import unicode_literals
+
 # Allow direct execution
 import os
 import sys
 import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
-from test.helper import FakeYDL
+from test.helper import FakeYDL, assertRegexpMatches
+from youtube_dl import YoutubeDL
+from youtube_dl.extractor import YoutubeIE
 
 
 class YDL(FakeYDL):
@@ -22,111 +26,227 @@ class YDL(FakeYDL):
         self.msgs.append(msg)
 
 
+def _make_result(formats, **kwargs):
+    res = {
+        'formats': formats,
+        'id': 'testid',
+        'title': 'testttitle',
+        'extractor': 'testex',
+    }
+    res.update(**kwargs)
+    return res
+
+
 class TestFormatSelection(unittest.TestCase):
     def test_prefer_free_formats(self):
         # Same resolution => download webm
         ydl = YDL()
         ydl.params['prefer_free_formats'] = True
         formats = [
-            {u'ext': u'webm', u'height': 460},
-            {u'ext': u'mp4',  u'height': 460},
+            {'ext': 'webm', 'height': 460, 'url': 'x'},
+            {'ext': 'mp4', 'height': 460, 'url': 'y'},
         ]
-        info_dict = {u'formats': formats, u'extractor': u'test'}
+        info_dict = _make_result(formats)
+        yie = YoutubeIE(ydl)
+        yie._sort_formats(info_dict['formats'])
         ydl.process_ie_result(info_dict)
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded[u'ext'], u'webm')
+        self.assertEqual(downloaded['ext'], 'webm')
 
         # Different resolution => download best quality (mp4)
         ydl = YDL()
         ydl.params['prefer_free_formats'] = True
         formats = [
-            {u'ext': u'webm', u'height': 720},
-            {u'ext': u'mp4', u'height': 1080},
+            {'ext': 'webm', 'height': 720, 'url': 'a'},
+            {'ext': 'mp4', 'height': 1080, 'url': 'b'},
         ]
-        info_dict[u'formats'] = formats
+        info_dict['formats'] = formats
+        yie = YoutubeIE(ydl)
+        yie._sort_formats(info_dict['formats'])
         ydl.process_ie_result(info_dict)
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded[u'ext'], u'mp4')
+        self.assertEqual(downloaded['ext'], 'mp4')
 
-        # No prefer_free_formats => keep original formats order
+        # No prefer_free_formats => prefer mp4 and flv for greater compatibility
         ydl = YDL()
         ydl.params['prefer_free_formats'] = False
         formats = [
-            {u'ext': u'webm', u'height': 720},
-            {u'ext': u'flv', u'height': 720},
+            {'ext': 'webm', 'height': 720, 'url': '_'},
+            {'ext': 'mp4', 'height': 720, 'url': '_'},
+            {'ext': 'flv', 'height': 720, 'url': '_'},
         ]
-        info_dict[u'formats'] = formats
+        info_dict['formats'] = formats
+        yie = YoutubeIE(ydl)
+        yie._sort_formats(info_dict['formats'])
         ydl.process_ie_result(info_dict)
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded[u'ext'], u'flv')
+        self.assertEqual(downloaded['ext'], 'mp4')
+
+        ydl = YDL()
+        ydl.params['prefer_free_formats'] = False
+        formats = [
+            {'ext': 'flv', 'height': 720, 'url': '_'},
+            {'ext': 'webm', 'height': 720, 'url': '_'},
+        ]
+        info_dict['formats'] = formats
+        yie = YoutubeIE(ydl)
+        yie._sort_formats(info_dict['formats'])
+        ydl.process_ie_result(info_dict)
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['ext'], 'flv')
 
     def test_format_limit(self):
         formats = [
-            {u'format_id': u'meh', u'url': u'http://example.com/meh'},
-            {u'format_id': u'good', u'url': u'http://example.com/good'},
-            {u'format_id': u'great', u'url': u'http://example.com/great'},
-            {u'format_id': u'excellent', u'url': u'http://example.com/exc'},
+            {'format_id': 'meh', 'url': 'http://example.com/meh', 'preference': 1},
+            {'format_id': 'good', 'url': 'http://example.com/good', 'preference': 2},
+            {'format_id': 'great', 'url': 'http://example.com/great', 'preference': 3},
+            {'format_id': 'excellent', 'url': 'http://example.com/exc', 'preference': 4},
         ]
-        info_dict = {
-            u'formats': formats, u'extractor': u'test', 'id': 'testvid'}
+        info_dict = _make_result(formats)
 
         ydl = YDL()
         ydl.process_ie_result(info_dict)
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded[u'format_id'], u'excellent')
+        self.assertEqual(downloaded['format_id'], 'excellent')
 
         ydl = YDL({'format_limit': 'good'})
         assert ydl.params['format_limit'] == 'good'
-        ydl.process_ie_result(info_dict)
+        ydl.process_ie_result(info_dict.copy())
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded[u'format_id'], u'good')
+        self.assertEqual(downloaded['format_id'], 'good')
 
         ydl = YDL({'format_limit': 'great', 'format': 'all'})
-        ydl.process_ie_result(info_dict)
-        self.assertEqual(ydl.downloaded_info_dicts[0][u'format_id'], u'meh')
-        self.assertEqual(ydl.downloaded_info_dicts[1][u'format_id'], u'good')
-        self.assertEqual(ydl.downloaded_info_dicts[2][u'format_id'], u'great')
+        ydl.process_ie_result(info_dict.copy())
+        self.assertEqual(ydl.downloaded_info_dicts[0]['format_id'], 'meh')
+        self.assertEqual(ydl.downloaded_info_dicts[1]['format_id'], 'good')
+        self.assertEqual(ydl.downloaded_info_dicts[2]['format_id'], 'great')
         self.assertTrue('3' in ydl.msgs[0])
 
         ydl = YDL()
         ydl.params['format_limit'] = 'excellent'
-        ydl.process_ie_result(info_dict)
+        ydl.process_ie_result(info_dict.copy())
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded[u'format_id'], u'excellent')
+        self.assertEqual(downloaded['format_id'], 'excellent')
 
     def test_format_selection(self):
         formats = [
-            {u'format_id': u'35', u'ext': u'mp4'},
-            {u'format_id': u'45', u'ext': u'webm'},
-            {u'format_id': u'47', u'ext': u'webm'},
-            {u'format_id': u'2', u'ext': u'flv'},
+            {'format_id': '35', 'ext': 'mp4', 'preference': 1, 'url': '_'},
+            {'format_id': '45', 'ext': 'webm', 'preference': 2, 'url': '_'},
+            {'format_id': '47', 'ext': 'webm', 'preference': 3, 'url': '_'},
+            {'format_id': '2', 'ext': 'flv', 'preference': 4, 'url': '_'},
         ]
-        info_dict = {u'formats': formats, u'extractor': u'test'}
+        info_dict = _make_result(formats)
 
-        ydl = YDL({'format': u'20/47'})
-        ydl.process_ie_result(info_dict)
+        ydl = YDL({'format': '20/47'})
+        ydl.process_ie_result(info_dict.copy())
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], u'47')
+        self.assertEqual(downloaded['format_id'], '47')
 
-        ydl = YDL({'format': u'20/71/worst'})
-        ydl.process_ie_result(info_dict)
+        ydl = YDL({'format': '20/71/worst'})
+        ydl.process_ie_result(info_dict.copy())
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], u'35')
+        self.assertEqual(downloaded['format_id'], '35')
 
         ydl = YDL()
-        ydl.process_ie_result(info_dict)
+        ydl.process_ie_result(info_dict.copy())
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], u'2')
+        self.assertEqual(downloaded['format_id'], '2')
 
-        ydl = YDL({'format': u'webm/mp4'})
-        ydl.process_ie_result(info_dict)
+        ydl = YDL({'format': 'webm/mp4'})
+        ydl.process_ie_result(info_dict.copy())
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], u'47')
+        self.assertEqual(downloaded['format_id'], '47')
 
-        ydl = YDL({'format': u'3gp/40/mp4'})
-        ydl.process_ie_result(info_dict)
+        ydl = YDL({'format': '3gp/40/mp4'})
+        ydl.process_ie_result(info_dict.copy())
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], u'35')
+        self.assertEqual(downloaded['format_id'], '35')
+
+    def test_format_selection_audio(self):
+        formats = [
+            {'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none', 'url': '_'},
+            {'format_id': 'audio-mid', 'ext': 'webm', 'preference': 2, 'vcodec': 'none', 'url': '_'},
+            {'format_id': 'audio-high', 'ext': 'flv', 'preference': 3, 'vcodec': 'none', 'url': '_'},
+            {'format_id': 'vid', 'ext': 'mp4', 'preference': 4, 'url': '_'},
+        ]
+        info_dict = _make_result(formats)
+
+        ydl = YDL({'format': 'bestaudio'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'audio-high')
+
+        ydl = YDL({'format': 'worstaudio'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'audio-low')
+
+        formats = [
+            {'format_id': 'vid-low', 'ext': 'mp4', 'preference': 1, 'url': '_'},
+            {'format_id': 'vid-high', 'ext': 'mp4', 'preference': 2, 'url': '_'},
+        ]
+        info_dict = _make_result(formats)
+
+        ydl = YDL({'format': 'bestaudio/worstaudio/best'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'vid-high')
+
+    def test_format_selection_video(self):
+        formats = [
+            {'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': '_'},
+            {'format_id': 'dash-video-high', 'ext': 'mp4', 'preference': 2, 'acodec': 'none', 'url': '_'},
+            {'format_id': 'vid', 'ext': 'mp4', 'preference': 3, 'url': '_'},
+        ]
+        info_dict = _make_result(formats)
+
+        ydl = YDL({'format': 'bestvideo'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'dash-video-high')
+
+        ydl = YDL({'format': 'worstvideo'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'dash-video-low')
+
+    def test_youtube_format_selection(self):
+        order = [
+            '38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '36', '17', '13',
+            # Apple HTTP Live Streaming
+            '96', '95', '94', '93', '92', '132', '151',
+            # 3D
+            '85', '84', '102', '83', '101', '82', '100',
+            # Dash video
+            '138', '137', '248', '136', '247', '135', '246',
+            '245', '244', '134', '243', '133', '242', '160',
+            # Dash audio
+            '141', '172', '140', '139', '171',
+        ]
+
+        for f1id, f2id in zip(order, order[1:]):
+            f1 = YoutubeIE._formats[f1id].copy()
+            f1['format_id'] = f1id
+            f1['url'] = 'url:' + f1id
+            f2 = YoutubeIE._formats[f2id].copy()
+            f2['format_id'] = f2id
+            f2['url'] = 'url:' + f2id
+
+            info_dict = _make_result([f1, f2], extractor='youtube')
+            ydl = YDL()
+            yie = YoutubeIE(ydl)
+            yie._sort_formats(info_dict['formats'])
+            ydl.process_ie_result(info_dict)
+            downloaded = ydl.downloaded_info_dicts[0]
+            self.assertEqual(downloaded['format_id'], f1id)
+
+            info_dict = _make_result([f2, f1], extractor='youtube')
+            ydl = YDL()
+            yie = YoutubeIE(ydl)
+            yie._sort_formats(info_dict['formats'])
+            ydl.process_ie_result(info_dict)
+            downloaded = ydl.downloaded_info_dicts[0]
+            self.assertEqual(downloaded['format_id'], f1id)
 
     def test_add_extra_info(self):
         test_dict = {
@@ -140,6 +260,26 @@ class TestFormatSelection(unittest.TestCase):
         self.assertEqual(test_dict['extractor'], 'Foo')
         self.assertEqual(test_dict['playlist'], 'funny videos')
 
+    def test_prepare_filename(self):
+        info = {
+            'id': '1234',
+            'ext': 'mp4',
+            'width': None,
+        }
+        def fname(templ):
+            ydl = YoutubeDL({'outtmpl': templ})
+            return ydl.prepare_filename(info)
+        self.assertEqual(fname('%(id)s.%(ext)s'), '1234.mp4')
+        self.assertEqual(fname('%(id)s-%(width)s.%(ext)s'), '1234-NA.mp4')
+        # Replace missing fields with 'NA'
+        self.assertEqual(fname('%(uploader_date)s-%(id)s.%(ext)s'), 'NA-1234.mp4')
+
+    def test_format_note(self):
+        ydl = YoutubeDL()
+        self.assertEqual(ydl._format_note({}), '')
+        assertRegexpMatches(self, ydl._format_note({
+            'vbr': 10,
+        }), '^\s*10k$')
 
 if __name__ == '__main__':
     unittest.main()

test/test_age_restriction.py

@@ -13,7 +13,7 @@ from youtube_dl import YoutubeDL
 
 
 def _download_restricted(url, filename, age):
-    """ Returns true iff the file has been downloaded """
+    """ Returns true if the file has been downloaded """
 
     params = {
         'age_limit': age,

test/test_all_urls.py

@@ -1,5 +1,7 @@
 #!/usr/bin/env python
 
+from __future__ import unicode_literals
+
 # Allow direct execution
 import os
 import sys
@@ -7,11 +9,13 @@ import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 
-from test.helper import get_testcases
+from test.helper import gettestcases
 
 from youtube_dl.extractor import (
+    FacebookIE,
     gen_extractors,
     JustinTVIE,
+    PBSIE,
     YoutubeIE,
 )
 
@@ -28,21 +32,24 @@ class TestAllURLsMatching(unittest.TestCase):
 
     def test_youtube_playlist_matching(self):
         assertPlaylist = lambda url: self.assertMatch(url, ['youtube:playlist'])
-        assertPlaylist(u'ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
-        assertPlaylist(u'UUBABnxM4Ar9ten8Mdjj1j0Q') #585
-        assertPlaylist(u'PL63F0C78739B09958')
-        assertPlaylist(u'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
-        assertPlaylist(u'https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
-        assertPlaylist(u'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
-        assertPlaylist(u'https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') #668
-        self.assertFalse('youtube:playlist' in self.matching_ies(u'PLtS2H6bU1M'))
+        assertPlaylist('ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
+        assertPlaylist('UUBABnxM4Ar9ten8Mdjj1j0Q') #585
+        assertPlaylist('PL63F0C78739B09958')
+        assertPlaylist('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
+        assertPlaylist('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
+        assertPlaylist('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
+        assertPlaylist('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') #668
+        self.assertFalse('youtube:playlist' in self.matching_ies('PLtS2H6bU1M'))
+        # Top tracks
+        assertPlaylist('https://www.youtube.com/playlist?list=MCUS.20142101')
 
     def test_youtube_matching(self):
-        self.assertTrue(YoutubeIE.suitable(u'PLtS2H6bU1M'))
-        self.assertFalse(YoutubeIE.suitable(u'https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')) #668
+        self.assertTrue(YoutubeIE.suitable('PLtS2H6bU1M'))
+        self.assertFalse(YoutubeIE.suitable('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')) #668
         self.assertMatch('http://youtu.be/BaW_jenozKc', ['youtube'])
         self.assertMatch('http://www.youtube.com/v/BaW_jenozKc', ['youtube'])
         self.assertMatch('https://youtube.googleapis.com/v/BaW_jenozKc', ['youtube'])
+        self.assertMatch('http://www.cleanvideosearch.com/media/action/yt/watch?videoId=8v_4O44sfjM', ['youtube'])
 
     def test_youtube_channel_matching(self):
         assertChannel = lambda url: self.assertMatch(url, ['youtube:channel'])
@@ -62,24 +69,28 @@ class TestAllURLsMatching(unittest.TestCase):
     def test_youtube_show_matching(self):
         self.assertMatch('http://www.youtube.com/show/airdisasters', ['youtube:show'])
 
+    def test_youtube_search_matching(self):
+        self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url'])
+        self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url'])
+
     def test_justin_tv_channelid_matching(self):
-        self.assertTrue(JustinTVIE.suitable(u"justin.tv/vanillatv"))
-        self.assertTrue(JustinTVIE.suitable(u"twitch.tv/vanillatv"))
-        self.assertTrue(JustinTVIE.suitable(u"www.justin.tv/vanillatv"))
-        self.assertTrue(JustinTVIE.suitable(u"www.twitch.tv/vanillatv"))
-        self.assertTrue(JustinTVIE.suitable(u"http://www.justin.tv/vanillatv"))
-        self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/vanillatv"))
-        self.assertTrue(JustinTVIE.suitable(u"http://www.justin.tv/vanillatv/"))
-        self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/vanillatv/"))
+        self.assertTrue(JustinTVIE.suitable('justin.tv/vanillatv'))
+        self.assertTrue(JustinTVIE.suitable('twitch.tv/vanillatv'))
+        self.assertTrue(JustinTVIE.suitable('www.justin.tv/vanillatv'))
+        self.assertTrue(JustinTVIE.suitable('www.twitch.tv/vanillatv'))
+        self.assertTrue(JustinTVIE.suitable('http://www.justin.tv/vanillatv'))
+        self.assertTrue(JustinTVIE.suitable('http://www.twitch.tv/vanillatv'))
+        self.assertTrue(JustinTVIE.suitable('http://www.justin.tv/vanillatv/'))
+        self.assertTrue(JustinTVIE.suitable('http://www.twitch.tv/vanillatv/'))
 
     def test_justintv_videoid_matching(self):
-        self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/vanillatv/b/328087483"))
+        self.assertTrue(JustinTVIE.suitable('http://www.twitch.tv/vanillatv/b/328087483'))
 
     def test_justin_tv_chapterid_matching(self):
-        self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/tsm_theoddone/c/2349361"))
+        self.assertTrue(JustinTVIE.suitable('http://www.twitch.tv/tsm_theoddone/c/2349361'))
 
     def test_youtube_extract(self):
-        assertExtractId = lambda url, id: self.assertEqual(YoutubeIE()._extract_id(url), id)
+        assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
         assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
         assertExtractId('https://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
         assertExtractId('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc', 'BaW_jenozKc')
@@ -87,12 +98,15 @@ class TestAllURLsMatching(unittest.TestCase):
         assertExtractId('http://www.youtube.com/watch?v=BaW_jenozKcsharePLED17F32AD9753930', 'BaW_jenozKc')
         assertExtractId('BaW_jenozKc', 'BaW_jenozKc')
 
+    def test_facebook_matching(self):
+        self.assertTrue(FacebookIE.suitable('https://www.facebook.com/Shiniknoh#!/photo.php?v=10153317450565268'))
+
     def test_no_duplicates(self):
         ies = gen_extractors()
-        for tc in get_testcases():
+        for tc in gettestcases(include_onlymatching=True):
             url = tc['url']
             for ie in ies:
-                if type(ie).__name__ in ['GenericIE', tc['name'] + 'IE']:
+                if type(ie).__name__ in ('GenericIE', tc['name'] + 'IE'):
                     self.assertTrue(ie.suitable(url), '%s should match URL %r' % (type(ie).__name__, url))
                 else:
                     self.assertFalse(ie.suitable(url), '%s should not match URL %r' % (type(ie).__name__, url))
@@ -106,6 +120,59 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertMatch(':colbertreport', ['ComedyCentralShows'])
         self.assertMatch(':cr', ['ComedyCentralShows'])
 
+    def test_vimeo_matching(self):
+        self.assertMatch('http://vimeo.com/channels/tributes', ['vimeo:channel'])
+        self.assertMatch('http://vimeo.com/channels/31259', ['vimeo:channel'])
+        self.assertMatch('http://vimeo.com/channels/31259/53576664', ['vimeo'])
+        self.assertMatch('http://vimeo.com/user7108434', ['vimeo:user'])
+        self.assertMatch('http://vimeo.com/user7108434/videos', ['vimeo:user'])
+        self.assertMatch('https://vimeo.com/user21297594/review/75524534/3c257a1b5d', ['vimeo:review'])
+
+    # https://github.com/rg3/youtube-dl/issues/1930
+    def test_soundcloud_not_matching_sets(self):
+        self.assertMatch('http://soundcloud.com/floex/sets/gone-ep', ['soundcloud:set'])
+
+    def test_tumblr(self):
+        self.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes', ['Tumblr'])
+        self.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430', ['Tumblr'])
+
+    def test_pbs(self):
+        # https://github.com/rg3/youtube-dl/issues/2350
+        self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['PBS'])
+        self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['PBS'])
+
+    def test_ComedyCentralShows(self):
+        self.assertMatch(
+            'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview',
+            ['ComedyCentralShows'])
+        self.assertMatch(
+            'http://thecolbertreport.cc.com/videos/29w6fx/-realhumanpraise-for-fox-news',
+            ['ComedyCentralShows'])
+        self.assertMatch(
+            'http://thecolbertreport.cc.com/videos/gh6urb/neil-degrasse-tyson-pt--1?xrs=eml_col_031114',
+            ['ComedyCentralShows'])
+        self.assertMatch(
+            'http://thedailyshow.cc.com/guests/michael-lewis/3efna8/exclusive---michael-lewis-extended-interview-pt--3',
+            ['ComedyCentralShows'])
+        self.assertMatch(
+            'http://thedailyshow.cc.com/episodes/sy7yv0/april-8--2014---denis-leary',
+            ['ComedyCentralShows'])
+        self.assertMatch(
+            'http://thecolbertreport.cc.com/episodes/8ase07/april-8--2014---jane-goodall',
+            ['ComedyCentralShows'])
+        self.assertMatch(
+            'http://thedailyshow.cc.com/video-playlists/npde3s/the-daily-show-19088-highlights',
+            ['ComedyCentralShows'])
+        self.assertMatch(
+            'http://thedailyshow.cc.com/special-editions/2l8fdb/special-edition---a-look-back-at-food',
+            ['ComedyCentralShows'])
+
+    def test_yahoo_https(self):
+        # https://github.com/rg3/youtube-dl/issues/2701
+        self.assertMatch(
+            'https://screen.yahoo.com/smartwatches-latest-wearable-gadgets-163745379-cbs.html',
+            ['Yahoo'])
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_download.py

@@ -8,10 +8,11 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from test.helper import (
     get_params,
-    get_testcases,
-    try_rm,
+    gettestcases,
+    expect_info_dict,
     md5,
-    report_warning
+    try_rm,
+    report_warning,
 )
 
 
@@ -22,6 +23,7 @@ import socket
 
 import youtube_dl.YoutubeDL
 from youtube_dl.utils import (
+    compat_http_client,
     compat_str,
     compat_urllib_error,
     compat_HTTPError,
@@ -49,7 +51,7 @@ def _file_md5(fn):
     with open(fn, 'rb') as f:
         return hashlib.md5(f.read()).hexdigest()
 
-defs = get_testcases()
+defs = gettestcases()
 
 
 class TestDownload(unittest.TestCase):
@@ -71,9 +73,7 @@ def generator(test_case):
         if 'playlist' not in test_case:
             info_dict = test_case.get('info_dict', {})
             if not test_case.get('file') and not (info_dict.get('id') and info_dict.get('ext')):
-                print_skipping('The output file cannot be know, the "file" '
-                    'key is missing or the info_dict is incomplete')
-                return
+                raise Exception('Test definition incorrect. The output file cannot be known. Are both \'id\' and \'ext\' keys present?')
         if 'skip' in test_case:
             print_skipping(test_case['skip'])
             return
@@ -90,7 +90,7 @@ def generator(test_case):
         def _hook(status):
             if status['status'] == 'finished':
                 finished_hook_called.add(status['filename'])
-        ydl.fd.add_progress_hook(_hook)
+        ydl.add_progress_hook(_hook)
 
         def get_tc_filename(tc):
             return tc.get('file') or ydl.prepare_filename(tc.get('info_dict', {}))
@@ -110,7 +110,7 @@ def generator(test_case):
                     ydl.download([test_case['url']])
                 except (DownloadError, ExtractorError) as err:
                     # Check if the exception is not a network related one
-                    if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError) or (err.exc_info[0] == compat_HTTPError and err.exc_info[1].code == 503):
+                    if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError, compat_http_client.BadStatusLine) or (err.exc_info[0] == compat_HTTPError and err.exc_info[1].code == 503):
                         raise
 
                     if try_num == RETRIES:
@@ -135,27 +135,8 @@ def generator(test_case):
                     self.assertEqual(md5_for_file, tc['md5'])
                 with io.open(info_json_fn, encoding='utf-8') as infof:
                     info_dict = json.load(infof)
-                for (info_field, expected) in tc.get('info_dict', {}).items():
-                    if isinstance(expected, compat_str) and expected.startswith('md5:'):
-                        got = 'md5:' + md5(info_dict.get(info_field))
-                    else:
-                        got = info_dict.get(info_field)
-                    self.assertEqual(expected, got,
-                        u'invalid value for field %s, expected %r, got %r' % (info_field, expected, got))
 
-                # If checkable fields are missing from the test case, print the info_dict
-                test_info_dict = dict((key, value if not isinstance(value, compat_str) or len(value) < 250 else 'md5:' + md5(value))
-                    for key, value in info_dict.items()
-                    if value and key in ('title', 'description', 'uploader', 'upload_date', 'uploader_id', 'location'))
-                if not all(key in tc.get('info_dict', {}).keys() for key in test_info_dict.keys()):
-                    sys.stderr.write(u'\n"info_dict": ' + json.dumps(test_info_dict, ensure_ascii=False, indent=2) + u'\n')
-
-                # Check for the presence of mandatory fields
-                for key in ('id', 'url', 'title', 'ext'):
-                    self.assertTrue(key in info_dict.keys() and info_dict[key])
-                # Check for mandatory fields that are automatically set by YoutubeDL
-                for key in ['webpage_url', 'extractor', 'extractor_key']:
-                    self.assertTrue(info_dict.get(key), u'Missing field: %s' % key)
+                expect_info_dict(self, tc.get('info_dict', {}), info_dict)
         finally:
             try_rm_tcs_files()
 

test/test_playlists.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python
 # encoding: utf-8
 
+from __future__ import unicode_literals
 
 # Allow direct execution
 import os
@@ -8,20 +9,48 @@ import sys
 import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
-from test.helper import FakeYDL
-
+from test.helper import (
+    assertRegexpMatches,
+    assertGreaterEqual,
+    expect_info_dict,
+    FakeYDL,
+)
 
 from youtube_dl.extractor import (
+    AcademicEarthCourseIE,
     DailymotionPlaylistIE,
     DailymotionUserIE,
     VimeoChannelIE,
+    VimeoUserIE,
+    VimeoAlbumIE,
+    VimeoGroupsIE,
+    VineUserIE,
     UstreamChannelIE,
     SoundcloudSetIE,
     SoundcloudUserIE,
+    SoundcloudPlaylistIE,
+    TeacherTubeUserIE,
     LivestreamIE,
+    LivestreamOriginalIE,
     NHLVideocenterIE,
     BambuserChannelIE,
-    BandcampAlbumIE
+    BandcampAlbumIE,
+    SmotriCommunityIE,
+    SmotriUserIE,
+    IviCompilationIE,
+    ImdbListIE,
+    KhanAcademyIE,
+    EveryonesMixtapeIE,
+    RutubeChannelIE,
+    RutubePersonIE,
+    GoogleSearchIE,
+    GenericIE,
+    TEDIE,
+    ToypicsUserIE,
+    XTubeUserIE,
+    InstagramUserIE,
+    CSpanIE,
+    AolIE,
 )
 
 
@@ -35,64 +64,122 @@ class TestPlaylists(unittest.TestCase):
         ie = DailymotionPlaylistIE(dl)
         result = ie.extract('http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q')
         self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], u'SPORT')
+        self.assertEqual(result['title'], 'SPORT')
         self.assertTrue(len(result['entries']) > 20)
 
     def test_dailymotion_user(self):
         dl = FakeYDL()
         ie = DailymotionUserIE(dl)
-        result = ie.extract('http://www.dailymotion.com/user/generation-quoi/')
+        result = ie.extract('https://www.dailymotion.com/user/nqtv')
         self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], u'Génération Quoi')
-        self.assertTrue(len(result['entries']) >= 26)
+        assertGreaterEqual(self, len(result['entries']), 100)
+        self.assertEqual(result['title'], 'Rémi Gaillard')
 
     def test_vimeo_channel(self):
         dl = FakeYDL()
         ie = VimeoChannelIE(dl)
         result = ie.extract('http://vimeo.com/channels/tributes')
         self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], u'Vimeo Tributes')
+        self.assertEqual(result['title'], 'Vimeo Tributes')
         self.assertTrue(len(result['entries']) > 24)
 
+    def test_vimeo_user(self):
+        dl = FakeYDL()
+        ie = VimeoUserIE(dl)
+        result = ie.extract('http://vimeo.com/nkistudio/videos')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['title'], 'Nki')
+        self.assertTrue(len(result['entries']) > 65)
+
+    def test_vimeo_album(self):
+        dl = FakeYDL()
+        ie = VimeoAlbumIE(dl)
+        result = ie.extract('http://vimeo.com/album/2632481')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['title'], 'Staff Favorites: November 2013')
+        self.assertTrue(len(result['entries']) > 12)
+
+    def test_vimeo_groups(self):
+        dl = FakeYDL()
+        ie = VimeoGroupsIE(dl)
+        result = ie.extract('http://vimeo.com/groups/rolexawards')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['title'], 'Rolex Awards for Enterprise')
+        self.assertTrue(len(result['entries']) > 72)
+
+    def test_vine_user(self):
+        dl = FakeYDL()
+        ie = VineUserIE(dl)
+        result = ie.extract('https://vine.co/Visa')
+        self.assertIsPlaylist(result)
+        assertGreaterEqual(self, len(result['entries']), 47)
+
     def test_ustream_channel(self):
         dl = FakeYDL()
         ie = UstreamChannelIE(dl)
-        result = ie.extract('http://www.ustream.tv/channel/young-americans-for-liberty')
+        result = ie.extract('http://www.ustream.tv/channel/channeljapan')
         self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], u'5124905')
-        self.assertTrue(len(result['entries']) >= 11)
+        self.assertEqual(result['id'], '10874166')
+        assertGreaterEqual(self, len(result['entries']), 54)
 
     def test_soundcloud_set(self):
         dl = FakeYDL()
         ie = SoundcloudSetIE(dl)
         result = ie.extract('https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep')
         self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], u'The Royal Concept EP')
-        self.assertTrue(len(result['entries']) >= 6)
+        self.assertEqual(result['title'], 'The Royal Concept EP')
+        assertGreaterEqual(self, len(result['entries']), 6)
 
     def test_soundcloud_user(self):
         dl = FakeYDL()
         ie = SoundcloudUserIE(dl)
         result = ie.extract('https://soundcloud.com/the-concept-band')
         self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], u'9615865')
-        self.assertTrue(len(result['entries']) >= 12)
+        self.assertEqual(result['id'], '9615865')
+        assertGreaterEqual(self, len(result['entries']), 12)
+
+    def test_soundcloud_likes(self):
+        dl = FakeYDL()
+        ie = SoundcloudUserIE(dl)
+        result = ie.extract('https://soundcloud.com/the-concept-band/likes')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], '9615865')
+        assertGreaterEqual(self, len(result['entries']), 1)
+
+    def test_soundcloud_playlist(self):
+        dl = FakeYDL()
+        ie = SoundcloudPlaylistIE(dl)
+        result = ie.extract('http://api.soundcloud.com/playlists/4110309')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], '4110309')
+        self.assertEqual(result['title'], 'TILT Brass - Bowery Poetry Club, August \'03 [Non-Site SCR 02]')
+        assertRegexpMatches(
+            self, result['description'], r'.*?TILT Brass - Bowery Poetry Club')
+        self.assertEqual(len(result['entries']), 6)
 
     def test_livestream_event(self):
         dl = FakeYDL()
         ie = LivestreamIE(dl)
         result = ie.extract('http://new.livestream.com/tedx/cityenglish')
         self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], u'TEDCity2.0 (English)')
-        self.assertTrue(len(result['entries']) >= 4)
+        self.assertEqual(result['title'], 'TEDCity2.0 (English)')
+        assertGreaterEqual(self, len(result['entries']), 4)
+
+    def test_livestreamoriginal_folder(self):
+        dl = FakeYDL()
+        ie = LivestreamOriginalIE(dl)
+        result = ie.extract('https://www.livestream.com/newplay/folder?dirId=a07bf706-d0e4-4e75-a747-b021d84f2fd3')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'a07bf706-d0e4-4e75-a747-b021d84f2fd3')
+        assertGreaterEqual(self, len(result['entries']), 28)
 
     def test_nhl_videocenter(self):
         dl = FakeYDL()
         ie = NHLVideocenterIE(dl)
         result = ie.extract('http://video.canucks.nhl.com/videocenter/console?catid=999')
         self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], u'999')
-        self.assertEqual(result['title'], u'Highlights')
+        self.assertEqual(result['id'], '999')
+        self.assertEqual(result['title'], 'Highlights')
         self.assertEqual(len(result['entries']), 12)
 
     def test_bambuser_channel(self):
@@ -100,16 +187,214 @@ class TestPlaylists(unittest.TestCase):
         ie = BambuserChannelIE(dl)
         result = ie.extract('http://bambuser.com/channel/pixelversity')
         self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], u'pixelversity')
-        self.assertTrue(len(result['entries']) >= 60)
+        self.assertEqual(result['title'], 'pixelversity')
+        assertGreaterEqual(self, len(result['entries']), 60)
 
     def test_bandcamp_album(self):
         dl = FakeYDL()
         ie = BandcampAlbumIE(dl)
         result = ie.extract('http://mpallante.bandcamp.com/album/nightmare-night-ep')
         self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], u'Nightmare Night EP')
-        self.assertTrue(len(result['entries']) >= 4)
+        self.assertEqual(result['title'], 'Nightmare Night EP')
+        assertGreaterEqual(self, len(result['entries']), 4)
+        
+    def test_smotri_community(self):
+        dl = FakeYDL()
+        ie = SmotriCommunityIE(dl)
+        result = ie.extract('http://smotri.com/community/video/kommuna')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'kommuna')
+        self.assertEqual(result['title'], 'КПРФ')
+        assertGreaterEqual(self, len(result['entries']), 4)
+        
+    def test_smotri_user(self):
+        dl = FakeYDL()
+        ie = SmotriUserIE(dl)
+        result = ie.extract('http://smotri.com/user/inspector')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'inspector')
+        self.assertEqual(result['title'], 'Inspector')
+        assertGreaterEqual(self, len(result['entries']), 9)
+
+    def test_AcademicEarthCourse(self):
+        dl = FakeYDL()
+        ie = AcademicEarthCourseIE(dl)
+        result = ie.extract('http://academicearth.org/playlists/laws-of-nature/')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'laws-of-nature')
+        self.assertEqual(result['title'], 'Laws of Nature')
+        self.assertEqual(result['description'],u'Introduce yourself to the laws of nature with these free online college lectures from Yale, Harvard, and MIT.')# u"Today's websites are increasingly dynamic. Pages are no longer static HTML files but instead generated by scripts and database calls. User interfaces are more seamless, with technologies like Ajax replacing traditional page reloads. This course teaches students how to build dynamic websites with Ajax and with Linux, Apache, MySQL, and PHP (LAMP), one of today's most popular frameworks. Students learn how to set up domain names with DNS, how to structure pages with XHTML and CSS, how to program in JavaScript and PHP, how to configure Apache and MySQL, how to design and query databases with SQL, how to use Ajax with both XML and JSON, and how to build mashups. The course explores issues of security, scalability, and cross-browser support and also discusses enterprise-level deployments of websites, including third-party hosting, virtualization, colocation in data centers, firewalling, and load-balancing.")
+        self.assertEqual(len(result['entries']), 4)
+        
+    def test_ivi_compilation(self):
+        dl = FakeYDL()
+        ie = IviCompilationIE(dl)
+        result = ie.extract('http://www.ivi.ru/watch/dvoe_iz_lartsa')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'dvoe_iz_lartsa')
+        self.assertEqual(result['title'], 'Двое из ларца (2006 - 2008)')
+        assertGreaterEqual(self, len(result['entries']), 24)
+
+    def test_ivi_compilation_season(self):
+        dl = FakeYDL()
+        ie = IviCompilationIE(dl)
+        result = ie.extract('http://www.ivi.ru/watch/dvoe_iz_lartsa/season1')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'dvoe_iz_lartsa/season1')
+        self.assertEqual(result['title'], 'Двое из ларца (2006 - 2008) 1 сезон')
+        assertGreaterEqual(self, len(result['entries']), 12)
+        
+    def test_imdb_list(self):
+        dl = FakeYDL()
+        ie = ImdbListIE(dl)
+        result = ie.extract('http://www.imdb.com/list/JFs9NWw6XI0')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'JFs9NWw6XI0')
+        self.assertEqual(result['title'], 'March 23, 2012 Releases')
+        self.assertEqual(len(result['entries']), 7)
+
+    def test_khanacademy_topic(self):
+        dl = FakeYDL()
+        ie = KhanAcademyIE(dl)
+        result = ie.extract('https://www.khanacademy.org/math/applied-math/cryptography')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'cryptography')
+        self.assertEqual(result['title'], 'Journey into cryptography')
+        self.assertEqual(result['description'], 'How have humans protected their secret messages through history? What has changed today?')
+        assertGreaterEqual(self, len(result['entries']), 3)
+
+    def test_EveryonesMixtape(self):
+        dl = FakeYDL()
+        ie = EveryonesMixtapeIE(dl)
+        result = ie.extract('http://everyonesmixtape.com/#/mix/m7m0jJAbMQi')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'm7m0jJAbMQi')
+        self.assertEqual(result['title'], 'Driving')
+        self.assertEqual(len(result['entries']), 24)
+        
+    def test_rutube_channel(self):
+        dl = FakeYDL()
+        ie = RutubeChannelIE(dl)
+        result = ie.extract('http://rutube.ru/tags/video/1800/')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], '1800')
+        assertGreaterEqual(self, len(result['entries']), 68)
+
+    def test_rutube_person(self):
+        dl = FakeYDL()
+        ie = RutubePersonIE(dl)
+        result = ie.extract('http://rutube.ru/video/person/313878/')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], '313878')
+        assertGreaterEqual(self, len(result['entries']), 37)
+
+    def test_multiple_brightcove_videos(self):
+        # https://github.com/rg3/youtube-dl/issues/2283
+        dl = FakeYDL()
+        ie = GenericIE(dl)
+        result = ie.extract('http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'always-never-nuclear-command-and-control')
+        self.assertEqual(result['title'], 'Always/Never: A Little-Seen Movie About Nuclear Command and Control : The New Yorker')
+        self.assertEqual(len(result['entries']), 3)
+
+    def test_GoogleSearch(self):
+        dl = FakeYDL()
+        ie = GoogleSearchIE(dl)
+        result = ie.extract('gvsearch15:python language')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'python language')
+        self.assertEqual(result['title'], 'python language')
+        self.assertEqual(len(result['entries']), 15)
+
+    def test_generic_rss_feed(self):
+        dl = FakeYDL()
+        ie = GenericIE(dl)
+        result = ie.extract('http://phihag.de/2014/youtube-dl/rss.xml')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'http://phihag.de/2014/youtube-dl/rss.xml')
+        self.assertEqual(result['title'], 'Zero Punctuation')
+        self.assertTrue(len(result['entries']) > 10)
+
+    def test_ted_playlist(self):
+        dl = FakeYDL()
+        ie = TEDIE(dl)
+        result = ie.extract('http://www.ted.com/playlists/who_are_the_hackers')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], '10')
+        self.assertEqual(result['title'], 'Who are the hackers?')
+        assertGreaterEqual(self, len(result['entries']), 6)
+
+    def test_toypics_user(self):
+        dl = FakeYDL()
+        ie = ToypicsUserIE(dl)
+        result = ie.extract('http://videos.toypics.net/Mikey')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'Mikey')
+        assertGreaterEqual(self, len(result['entries']), 17)
+
+    def test_xtube_user(self):
+        dl = FakeYDL()
+        ie = XTubeUserIE(dl)
+        result = ie.extract('http://www.xtube.com/community/profile.php?user=greenshowers')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'greenshowers')
+        assertGreaterEqual(self, len(result['entries']), 155)
+
+    def test_InstagramUser(self):
+        dl = FakeYDL()
+        ie = InstagramUserIE(dl)
+        result = ie.extract('http://instagram.com/porsche')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'porsche')
+        assertGreaterEqual(self, len(result['entries']), 2)
+        test_video = next(
+            e for e in result['entries']
+            if e['id'] == '614605558512799803_462752227')
+        dl.add_default_extra_info(test_video, ie, '(irrelevant URL)')
+        dl.process_video_result(test_video, download=False)
+        EXPECTED = {
+            'id': '614605558512799803_462752227',
+            'ext': 'mp4',
+            'title': '#Porsche Intelligent Performance.',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'uploader': 'Porsche',
+            'uploader_id': 'porsche',
+            'timestamp': 1387486713,
+            'upload_date': '20131219',
+        }
+        expect_info_dict(self, EXPECTED, test_video)
+
+    def test_CSpan_playlist(self):
+        dl = FakeYDL()
+        ie = CSpanIE(dl)
+        result = ie.extract(
+            'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], '342759')
+        self.assertEqual(
+            result['title'], 'General Motors Ignition Switch Recall')
+        whole_duration = sum(e['duration'] for e in result['entries'])
+        self.assertEqual(whole_duration, 14855)
+
+    def test_aol_playlist(self):
+        dl = FakeYDL()
+        ie = AolIE(dl)
+        result = ie.extract(
+            'http://on.aol.com/playlist/brace-yourself---todays-weirdest-news-152147?icid=OnHomepageC4_Omg_Img#_videoid=518184316')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], '152147')
+        self.assertEqual(
+            result['title'], 'Brace Yourself - Today\'s Weirdest News')
+        assertGreaterEqual(self, len(result['entries']), 10)
+
+    def test_TeacherTubeUser(self):
+        dl = FakeYDL()
+        ie = TeacherTubeUserIE(dl)
+        result = ie.extract('http://www.teachertube.com/user/profile/rbhagwati2')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'rbhagwati2')
+        assertGreaterEqual(self, len(result['entries']), 179)
 
 if __name__ == '__main__':
     unittest.main()

test/test_subtitles.py

@@ -10,9 +10,11 @@ from test.helper import FakeYDL, md5
 
 
 from youtube_dl.extractor import (
+    BlipTVIE,
     YoutubeIE,
     DailymotionIE,
     TEDIE,
+    VimeoIE,
 )
 
 
@@ -36,10 +38,6 @@ class TestYoutubeSubtitles(BaseTestSubtitles):
     url = 'QRS8MkLhQmM'
     IE = YoutubeIE
 
-    def getSubtitles(self):
-        info_dict = self.getInfoDict()
-        return info_dict[0]['subtitles']
-
     def test_youtube_no_writesubtitles(self):
         self.DL.params['writesubtitles'] = False
         subtitles = self.getSubtitles()
@@ -72,7 +70,7 @@ class TestYoutubeSubtitles(BaseTestSubtitles):
         self.DL.params['writesubtitles'] = True
         self.DL.params['subtitlesformat'] = 'vtt'
         subtitles = self.getSubtitles()
-        self.assertEqual(md5(subtitles['en']), '356cdc577fde0c6783b9b822e7206ff7')
+        self.assertEqual(md5(subtitles['en']), '3cb210999d3e021bd6c7f0ea751eab06')
 
     def test_youtube_list_subtitles(self):
         self.DL.expect_warning(u'Video doesn\'t have automatic captions')
@@ -89,7 +87,7 @@ class TestYoutubeSubtitles(BaseTestSubtitles):
 
     def test_youtube_nosubtitles(self):
         self.DL.expect_warning(u'video doesn\'t have subtitles')
-        self.url = 'sAjKT8FhjI8'
+        self.url = 'n5BB19UTcdA'
         self.DL.params['writesubtitles'] = True
         self.DL.params['allsubtitles'] = True
         subtitles = self.getSubtitles()
@@ -171,19 +169,19 @@ class TestTedSubtitles(BaseTestSubtitles):
     def test_subtitles(self):
         self.DL.params['writesubtitles'] = True
         subtitles = self.getSubtitles()
-        self.assertEqual(md5(subtitles['en']), '2154f31ff9b9f89a0aa671537559c21d')
+        self.assertEqual(md5(subtitles['en']), '4262c1665ff928a2dada178f62cb8d14')
 
     def test_subtitles_lang(self):
         self.DL.params['writesubtitles'] = True
         self.DL.params['subtitleslangs'] = ['fr']
         subtitles = self.getSubtitles()
-        self.assertEqual(md5(subtitles['fr']), '7616cbc6df20ec2c1204083c83871cf6')
+        self.assertEqual(md5(subtitles['fr']), '66a63f7f42c97a50f8c0e90bc7797bb5')
 
     def test_allsubtitles(self):
         self.DL.params['writesubtitles'] = True
         self.DL.params['allsubtitles'] = True
         subtitles = self.getSubtitles()
-        self.assertEqual(len(subtitles.keys()), 28)
+        self.assertTrue(len(subtitles.keys()) >= 28)
 
     def test_list_subtitles(self):
         self.DL.expect_warning(u'Automatic Captions not supported by this server')
@@ -206,5 +204,80 @@ class TestTedSubtitles(BaseTestSubtitles):
         for lang in langs:
             self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
 
+
+class TestBlipTVSubtitles(BaseTestSubtitles):
+    url = 'http://blip.tv/a/a-6603250'
+    IE = BlipTVIE
+
+    def test_list_subtitles(self):
+        self.DL.expect_warning(u'Automatic Captions not supported by this server')
+        self.DL.params['listsubtitles'] = True
+        info_dict = self.getInfoDict()
+        self.assertEqual(info_dict, None)
+
+    def test_allsubtitles(self):
+        self.DL.expect_warning(u'Automatic Captions not supported by this server')
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(set(subtitles.keys()), set(['en']))
+        self.assertEqual(md5(subtitles['en']), '5b75c300af65fe4476dff79478bb93e4')
+
+
+class TestVimeoSubtitles(BaseTestSubtitles):
+    url = 'http://vimeo.com/76979871'
+    IE = VimeoIE
+
+    def test_no_writesubtitles(self):
+        subtitles = self.getSubtitles()
+        self.assertEqual(subtitles, None)
+
+    def test_subtitles(self):
+        self.DL.params['writesubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(md5(subtitles['en']), '8062383cf4dec168fc40a088aa6d5888')
+
+    def test_subtitles_lang(self):
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['subtitleslangs'] = ['fr']
+        subtitles = self.getSubtitles()
+        self.assertEqual(md5(subtitles['fr']), 'b6191146a6c5d3a452244d853fde6dc8')
+
+    def test_allsubtitles(self):
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(set(subtitles.keys()), set(['de', 'en', 'es', 'fr']))
+
+    def test_list_subtitles(self):
+        self.DL.expect_warning(u'Automatic Captions not supported by this server')
+        self.DL.params['listsubtitles'] = True
+        info_dict = self.getInfoDict()
+        self.assertEqual(info_dict, None)
+
+    def test_automatic_captions(self):
+        self.DL.expect_warning(u'Automatic Captions not supported by this server')
+        self.DL.params['writeautomaticsub'] = True
+        self.DL.params['subtitleslang'] = ['en']
+        subtitles = self.getSubtitles()
+        self.assertTrue(len(subtitles.keys()) == 0)
+
+    def test_nosubtitles(self):
+        self.DL.expect_warning(u'video doesn\'t have subtitles')
+        self.url = 'http://vimeo.com/56015672'
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(len(subtitles), 0)
+
+    def test_multiple_langs(self):
+        self.DL.params['writesubtitles'] = True
+        langs = ['es', 'fr', 'de']
+        self.DL.params['subtitleslangs'] = langs
+        subtitles = self.getSubtitles()
+        for lang in langs:
+            self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
+
+
 if __name__ == '__main__':
     unittest.main()

test/test_swfinterp.py

@@ -0,0 +1,77 @@
+#!/usr/bin/env python
+
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+
+import errno
+import io
+import json
+import re
+import subprocess
+
+from youtube_dl.swfinterp import SWFInterpreter
+
+
+TEST_DIR = os.path.join(
+    os.path.dirname(os.path.abspath(__file__)), 'swftests')
+
+
+class TestSWFInterpreter(unittest.TestCase):
+    pass
+
+
+def _make_testfunc(testfile):
+    m = re.match(r'^(.*)\.(as)$', testfile)
+    if not m:
+        return
+    test_id = m.group(1)
+
+    def test_func(self):
+        as_file = os.path.join(TEST_DIR, testfile)
+        swf_file = os.path.join(TEST_DIR, test_id + '.swf')
+        if ((not os.path.exists(swf_file))
+                or os.path.getmtime(swf_file) < os.path.getmtime(as_file)):
+            # Recompile
+            try:
+                subprocess.check_call(['mxmlc', '-output', swf_file, as_file])
+            except OSError as ose:
+                if ose.errno == errno.ENOENT:
+                    print('mxmlc not found! Skipping test.')
+                    return
+                raise
+
+        with open(swf_file, 'rb') as swf_f:
+            swf_content = swf_f.read()
+        swfi = SWFInterpreter(swf_content)
+
+        with io.open(as_file, 'r', encoding='utf-8') as as_f:
+            as_content = as_f.read()
+
+        def _find_spec(key):
+            m = re.search(
+                r'(?m)^//\s*%s:\s*(.*?)\n' % re.escape(key), as_content)
+            if not m:
+                raise ValueError('Cannot find %s in %s' % (key, testfile))
+            return json.loads(m.group(1))
+
+        input_args = _find_spec('input')
+        output = _find_spec('output')
+
+        swf_class = swfi.extract_class(test_id)
+        func = swfi.extract_function(swf_class, 'main')
+        res = func(input_args)
+        self.assertEqual(res, output)
+
+    test_func.__name__ = str('test_swf_' + test_id)
+    setattr(TestSWFInterpreter, test_func.__name__, test_func)
+
+
+for testfile in os.listdir(TEST_DIR):
+    _make_testfunc(testfile)
+
+if __name__ == '__main__':
+    unittest.main()

test/test_unicode_literals.py

@@ -0,0 +1,47 @@
+from __future__ import unicode_literals
+
+import io
+import os
+import re
+import unittest
+
+rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+
+IGNORED_FILES = [
+    'setup.py',  # http://bugs.python.org/issue13943
+]
+
+
+class TestUnicodeLiterals(unittest.TestCase):
+    def test_all_files(self):
+        print('Skipping this test (not yet fully implemented)')
+        return
+
+        for dirpath, _, filenames in os.walk(rootDir):
+            for basename in filenames:
+                if not basename.endswith('.py'):
+                    continue
+                if basename in IGNORED_FILES:
+                    continue
+
+                fn = os.path.join(dirpath, basename)
+                with io.open(fn, encoding='utf-8') as inf:
+                    code = inf.read()
+
+                if "'" not in code and '"' not in code:
+                    continue
+                imps = 'from __future__ import unicode_literals'
+                self.assertTrue(
+                    imps in code,
+                    ' %s  missing in %s' % (imps, fn))
+
+                m = re.search(r'(?<=\s)u[\'"](?!\)|,|$)', code)
+                if m is not None:
+                    self.assertTrue(
+                        m is None,
+                        'u present in %s, around %s' % (
+                            fn, code[m.start() - 10:m.end() + 10]))
+
+
+if __name__ == '__main__':
+    unittest.main()

test/test_utils.py

@@ -9,23 +9,36 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 
 # Various small unit tests
+import io
+import json
 import xml.etree.ElementTree
 
 #from youtube_dl.utils import htmlentity_transform
 from youtube_dl.utils import (
-    timeconvert,
-    sanitize_filename,
-    unescapeHTML,
-    orderedSet,
     DateRange,
-    unified_strdate,
-    find_xpath_attr,
-    get_meta_content,
-    xpath_with_ns,
-    smuggle_url,
-    unsmuggle_url,
-    shell_quote,
     encodeFilename,
+    find_xpath_attr,
+    fix_xml_ampersands,
+    get_meta_content,
+    orderedSet,
+    PagedList,
+    parse_duration,
+    read_batch_urls,
+    sanitize_filename,
+    shell_quote,
+    smuggle_url,
+    str_to_int,
+    struct_unpack,
+    timeconvert,
+    unescapeHTML,
+    unified_strdate,
+    unsmuggle_url,
+    url_basename,
+    urlencode_postdata,
+    xpath_with_ns,
+    parse_iso8601,
+    strip_jsonp,
+    uppercase_escape,
 )
 
 if sys.version_info < (3, 0):
@@ -122,6 +135,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unified_strdate('8/7/2009'), '20090708')
         self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
         self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
+        self.assertEqual(unified_strdate('1968-12-10'), '19681210')
 
     def test_find_xpath_attr(self):
         testxml = u'''<root>
@@ -176,6 +190,99 @@ class TestUtil(unittest.TestCase):
         args = ['ffmpeg', '-i', encodeFilename(u'ñ€ß\'.mp4')]
         self.assertEqual(shell_quote(args), u"""ffmpeg -i 'ñ€ß'"'"'.mp4'""")
 
+    def test_str_to_int(self):
+        self.assertEqual(str_to_int('123,456'), 123456)
+        self.assertEqual(str_to_int('123.456'), 123456)
+
+    def test_url_basename(self):
+        self.assertEqual(url_basename(u'http://foo.de/'), u'')
+        self.assertEqual(url_basename(u'http://foo.de/bar/baz'), u'baz')
+        self.assertEqual(url_basename(u'http://foo.de/bar/baz?x=y'), u'baz')
+        self.assertEqual(url_basename(u'http://foo.de/bar/baz#x=y'), u'baz')
+        self.assertEqual(url_basename(u'http://foo.de/bar/baz/'), u'baz')
+        self.assertEqual(
+            url_basename(u'http://media.w3.org/2010/05/sintel/trailer.mp4'),
+            u'trailer.mp4')
+
+    def test_parse_duration(self):
+        self.assertEqual(parse_duration(None), None)
+        self.assertEqual(parse_duration('1'), 1)
+        self.assertEqual(parse_duration('1337:12'), 80232)
+        self.assertEqual(parse_duration('9:12:43'), 33163)
+        self.assertEqual(parse_duration('12:00'), 720)
+        self.assertEqual(parse_duration('00:01:01'), 61)
+        self.assertEqual(parse_duration('x:y'), None)
+        self.assertEqual(parse_duration('3h11m53s'), 11513)
+        self.assertEqual(parse_duration('62m45s'), 3765)
+        self.assertEqual(parse_duration('6m59s'), 419)
+        self.assertEqual(parse_duration('49s'), 49)
+        self.assertEqual(parse_duration('0h0m0s'), 0)
+        self.assertEqual(parse_duration('0m0s'), 0)
+        self.assertEqual(parse_duration('0s'), 0)
+
+    def test_fix_xml_ampersands(self):
+        self.assertEqual(
+            fix_xml_ampersands('"&x=y&z=a'), '"&amp;x=y&amp;z=a')
+        self.assertEqual(
+            fix_xml_ampersands('"&amp;x=y&wrong;&z=a'),
+            '"&amp;x=y&amp;wrong;&amp;z=a')
+        self.assertEqual(
+            fix_xml_ampersands('&amp;&apos;&gt;&lt;&quot;'),
+            '&amp;&apos;&gt;&lt;&quot;')
+        self.assertEqual(
+            fix_xml_ampersands('&#1234;&#x1abC;'), '&#1234;&#x1abC;')
+        self.assertEqual(fix_xml_ampersands('&#&#'), '&amp;#&amp;#')
+
+    def test_paged_list(self):
+        def testPL(size, pagesize, sliceargs, expected):
+            def get_page(pagenum):
+                firstid = pagenum * pagesize
+                upto = min(size, pagenum * pagesize + pagesize)
+                for i in range(firstid, upto):
+                    yield i
+
+            pl = PagedList(get_page, pagesize)
+            got = pl.getslice(*sliceargs)
+            self.assertEqual(got, expected)
+
+        testPL(5, 2, (), [0, 1, 2, 3, 4])
+        testPL(5, 2, (1,), [1, 2, 3, 4])
+        testPL(5, 2, (2,), [2, 3, 4])
+        testPL(5, 2, (4,), [4])
+        testPL(5, 2, (0, 3), [0, 1, 2])
+        testPL(5, 2, (1, 4), [1, 2, 3])
+        testPL(5, 2, (2, 99), [2, 3, 4])
+        testPL(5, 2, (20, 99), [])
+
+    def test_struct_unpack(self):
+        self.assertEqual(struct_unpack(u'!B', b'\x00'), (0,))
+
+    def test_read_batch_urls(self):
+        f = io.StringIO(u'''\xef\xbb\xbf foo
+            bar\r
+            baz
+            # More after this line\r
+            ; or after this
+            bam''')
+        self.assertEqual(read_batch_urls(f), [u'foo', u'bar', u'baz', u'bam'])
+
+    def test_urlencode_postdata(self):
+        data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
+        self.assertTrue(isinstance(data, bytes))
+
+    def test_parse_iso8601(self):
+        self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
+        self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
+        self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
+
+    def test_strip_jsonp(self):
+        stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
+        d = json.loads(stripped)
+        self.assertEqual(d, [{"id": "532cb", "x": 3}])
+
+    def test_uppercase_escpae(self):
+        self.assertEqual(uppercase_escape(u'aä'), u'aä')
+        self.assertEqual(uppercase_escape(u'\\U0001d550'), u'𝕐')
 
 if __name__ == '__main__':
     unittest.main()

test/test_write_info_json.py

@@ -33,6 +33,7 @@ TEST_ID = 'BaW_jenozKc'
 INFO_JSON_FILE = TEST_ID + '.info.json'
 DESCRIPTION_FILE = TEST_ID + '.mp4.description'
 EXPECTED_DESCRIPTION = u'''test chars:  "'/\ä↭𝕐
+test URL: https://github.com/rg3/youtube-dl/issues/1892
 
 This is a test video for youtube-dl.
 

test/test_youtube_lists.py

@@ -15,6 +15,8 @@ from youtube_dl.extractor import (
     YoutubeIE,
     YoutubeChannelIE,
     YoutubeShowIE,
+    YoutubeTopListIE,
+    YoutubeSearchURLIE,
 )
 
 
@@ -29,7 +31,7 @@ class TestYoutubeLists(unittest.TestCase):
         result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
         self.assertIsPlaylist(result)
         self.assertEqual(result['title'], 'ytdl test PL')
-        ytie_results = [YoutubeIE()._extract_id(url['url']) for url in result['entries']]
+        ytie_results = [YoutubeIE().extract_id(url['url']) for url in result['entries']]
         self.assertEqual(ytie_results, [ 'bV9L5Ht9LgY', 'FXxLjLQi3Fg', 'tU3Bgo5qJZE'])
 
     def test_youtube_playlist_noplaylist(self):
@@ -38,7 +40,7 @@ class TestYoutubeLists(unittest.TestCase):
         ie = YoutubePlaylistIE(dl)
         result = ie.extract('https://www.youtube.com/watch?v=FXxLjLQi3Fg&list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
         self.assertEqual(result['_type'], 'url')
-        self.assertEqual(YoutubeIE()._extract_id(result['url']), 'FXxLjLQi3Fg')
+        self.assertEqual(YoutubeIE().extract_id(result['url']), 'FXxLjLQi3Fg')
 
     def test_issue_673(self):
         dl = FakeYDL()
@@ -58,7 +60,7 @@ class TestYoutubeLists(unittest.TestCase):
         dl = FakeYDL()
         ie = YoutubePlaylistIE(dl)
         result = ie.extract('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
-        ytie_results = [YoutubeIE()._extract_id(url['url']) for url in result['entries']]
+        ytie_results = [YoutubeIE().extract_id(url['url']) for url in result['entries']]
         self.assertFalse('pElCt5oNDuI' in ytie_results)
         self.assertFalse('KdPEApIVdWM' in ytie_results)
         
@@ -75,9 +77,9 @@ class TestYoutubeLists(unittest.TestCase):
         # TODO find a > 100 (paginating?) videos course
         result = ie.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
         entries = result['entries']
-        self.assertEqual(YoutubeIE()._extract_id(entries[0]['url']), 'j9WZyLZCBzs')
+        self.assertEqual(YoutubeIE().extract_id(entries[0]['url']), 'j9WZyLZCBzs')
         self.assertEqual(len(entries), 25)
-        self.assertEqual(YoutubeIE()._extract_id(entries[-1]['url']), 'rYefUsYuEp0')
+        self.assertEqual(YoutubeIE().extract_id(entries[-1]['url']), 'rYefUsYuEp0')
 
     def test_youtube_channel(self):
         dl = FakeYDL()
@@ -107,5 +109,39 @@ class TestYoutubeLists(unittest.TestCase):
         result = ie.extract('http://www.youtube.com/show/airdisasters')
         self.assertTrue(len(result) >= 3)
 
+    def test_youtube_mix(self):
+        dl = FakeYDL()
+        ie = YoutubePlaylistIE(dl)
+        result = ie.extract('https://www.youtube.com/watch?v=W01L70IGBgE&index=2&list=RDOQpdSVF_k_w')
+        entries = result['entries']
+        self.assertTrue(len(entries) >= 20)
+        original_video = entries[0]
+        self.assertEqual(original_video['id'], 'OQpdSVF_k_w')
+
+    def test_youtube_toptracks(self):
+        print('Skipping: The playlist page gives error 500')
+        return
+        dl = FakeYDL()
+        ie = YoutubePlaylistIE(dl)
+        result = ie.extract('https://www.youtube.com/playlist?list=MCUS')
+        entries = result['entries']
+        self.assertEqual(len(entries), 100)
+
+    def test_youtube_toplist(self):
+        dl = FakeYDL()
+        ie = YoutubeTopListIE(dl)
+        result = ie.extract('yttoplist:music:Trending')
+        entries = result['entries']
+        self.assertTrue(len(entries) >= 5)
+
+    def test_youtube_search_url(self):
+        dl = FakeYDL()
+        ie = YoutubeSearchURLIE(dl)
+        result = ie.extract('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video')
+        entries = result['entries']
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['title'], 'youtube-dl test video')
+        self.assertTrue(len(entries) >= 5)
+
 if __name__ == '__main__':
     unittest.main()

test/test_youtube_signature.py

@@ -28,11 +28,41 @@ _TESTS = [
         u'3456789a0cdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRS[UVWXYZ!"#$%&\'()*+,-./:;<=>?@',
     ),
     (
-        u'https://s.ytimg.com/yts/swfbin/watch_as3-vflg5GhxU.swf',
-        u'swf',
-        82,
-        u':/.-,+*)=\'&%$#"!ZYX0VUTSRQPONMLKJIHGFEDCBAzyxw>utsrqponmlkjihgfedcba987654321'
+        u'https://s.ytimg.com/yts/jsbin/html5player-vfle-mVwz.js',
+        u'js',
+        90,
+        u']\\[@?>=<;:/.-,+*)(\'&%$#"hZYXWVUTSRQPONMLKJIHGFEDCBAzyxwvutsrqponmlkjiagfedcb39876',
     ),
+    (
+        u'https://s.ytimg.com/yts/jsbin/html5player-en_US-vfl0Cbn9e.js',
+        u'js',
+        84,
+        u'O1I3456789abcde0ghijklmnopqrstuvwxyzABCDEFGHfJKLMN2PQRSTUVW@YZ!"#$%&\'()*+,-./:;<=',
+    ),
+    (
+        u'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflXGBaUN.js',
+        u'js',
+        u'2ACFC7A61CA478CD21425E5A57EBD73DDC78E22A.2094302436B2D377D14A3BBA23022D023B8BC25AA',
+        u'A52CB8B320D22032ABB3A41D773D2B6342034902.A22E87CDD37DBE75A5E52412DC874AC16A7CFCA2',
+    ),
+    (
+        u'http://s.ytimg.com/yts/swfbin/player-vfl5vIhK2/watch_as3.swf',
+        u'swf',
+        86,
+        u'O1I3456789abcde0ghijklmnopqrstuvwxyzABCDEFGHfJKLMN2PQRSTUVWXY\\!"#$%&\'()*+,-./:;<=>?'
+    ),
+    (
+        u'http://s.ytimg.com/yts/swfbin/player-vflmDyk47/watch_as3.swf',
+        u'swf',
+        u'F375F75BF2AFDAAF2666E43868D46816F83F13E81C46.3725A8218E446A0DECD33F79DC282994D6AA92C92C9',
+        u'9C29AA6D499282CD97F33DCED0A644E8128A5273.64C18E31F38361864D86834E6662FAADFA2FB57F'
+    ),
+    (
+        u'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflBb0OQx.js',
+        u'js',
+        84,
+        u'123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQ0STUVWXYZ!"#$%&\'()*+,@./:;<=>'
+    )
 ]
 
 
@@ -44,13 +74,13 @@ class TestSignature(unittest.TestCase):
             os.mkdir(self.TESTDATA_DIR)
 
 
-def make_tfunc(url, stype, sig_length, expected_sig):
-    basename = url.rpartition('/')[2]
-    m = re.match(r'.*-([a-zA-Z0-9_-]+)\.[a-z]+$', basename)
-    assert m, '%r should follow URL format' % basename
+def make_tfunc(url, stype, sig_input, expected_sig):
+    m = re.match(r'.*-([a-zA-Z0-9_-]+)(?:/watch_as3)?\.[a-z]+$', url)
+    assert m, '%r should follow URL format' % url
     test_id = m.group(1)
 
     def test_func(self):
+        basename = 'player-%s.%s' % (test_id, stype)
         fn = os.path.join(self.TESTDATA_DIR, basename)
 
         if not os.path.exists(fn):
@@ -66,7 +96,9 @@ def make_tfunc(url, stype, sig_length, expected_sig):
             with open(fn, 'rb') as testf:
                 swfcode = testf.read()
             func = ie._parse_sig_swf(swfcode)
-        src_sig = compat_str(string.printable[:sig_length])
+        src_sig = (
+            compat_str(string.printable[:sig_input])
+            if isinstance(sig_input, int) else sig_input)
         got_sig = func(src_sig)
         self.assertEqual(got_sig, expected_sig)
 

youtube-dl.plugin.zsh

@@ -0,0 +1,24 @@
+# This allows the youtube-dl command to be installed in ZSH using antigen.
+# Antigen is a bundle manager. It allows you to enhance the functionality of
+# your zsh session by installing bundles and themes easily.
+
+# Antigen documentation:
+# http://antigen.sharats.me/
+# https://github.com/zsh-users/antigen
+
+# Install youtube-dl:
+# antigen bundle rg3/youtube-dl
+# Bundles installed by antigen are available for use immediately.
+
+# Update youtube-dl (and all other antigen bundles):
+# antigen update
+
+# The antigen command will download the git repository to a folder and then
+# execute an enabling script (this file). The complete process for loading the
+# code is documented here:
+# https://github.com/zsh-users/antigen#notes-on-writing-plugins
+
+# This specific script just aliases youtube-dl to the python script that this
+# library provides. This requires updating the PYTHONPATH to ensure that the
+# full set of code can be located.
+alias youtube-dl="PYTHONPATH=$(dirname $0) $(dirname $0)/bin/youtube-dl"

youtube_dl/FileDownloader.py

@@ -1,683 +1,12 @@
-import os
-import re
-import subprocess
-import sys
-import time
-
-from .utils import (
-    compat_urllib_error,
-    compat_urllib_request,
-    ContentTooShortError,
-    determine_ext,
-    encodeFilename,
-    format_bytes,
-    sanitize_open,
-    timeconvert,
-)
-
-
-class FileDownloader(object):
-    """File Downloader class.
-
-    File downloader objects are the ones responsible of downloading the
-    actual video file and writing it to disk.
-
-    File downloaders accept a lot of parameters. In order not to saturate
-    the object constructor with arguments, it receives a dictionary of
-    options instead.
-
-    Available options:
-
-    verbose:           Print additional info to stdout.
-    quiet:             Do not print messages to stdout.
-    ratelimit:         Download speed limit, in bytes/sec.
-    retries:           Number of times to retry for HTTP error 5xx
-    buffersize:        Size of download buffer in bytes.
-    noresizebuffer:    Do not automatically resize the download buffer.
-    continuedl:        Try to continue downloads if possible.
-    noprogress:        Do not print the progress bar.
-    logtostderr:       Log messages to stderr instead of stdout.
-    consoletitle:      Display progress in console window's titlebar.
-    nopart:            Do not use temporary .part files.
-    updatetime:        Use the Last-modified header to set output file timestamps.
-    test:              Download only first bytes to test the downloader.
-    min_filesize:      Skip files smaller than this size
-    max_filesize:      Skip files larger than this size
-    """
-
-    params = None
-
-    def __init__(self, ydl, params):
-        """Create a FileDownloader object with the given options."""
-        self.ydl = ydl
-        self._progress_hooks = []
-        self.params = params
-
-    @staticmethod
-    def format_seconds(seconds):
-        (mins, secs) = divmod(seconds, 60)
-        (hours, mins) = divmod(mins, 60)
-        if hours > 99:
-            return '--:--:--'
-        if hours == 0:
-            return '%02d:%02d' % (mins, secs)
-        else:
-            return '%02d:%02d:%02d' % (hours, mins, secs)
-
-    @staticmethod
-    def calc_percent(byte_counter, data_len):
-        if data_len is None:
-            return None
-        return float(byte_counter) / float(data_len) * 100.0
-
-    @staticmethod
-    def format_percent(percent):
-        if percent is None:
-            return '---.-%'
-        return '%6s' % ('%3.1f%%' % percent)
-
-    @staticmethod
-    def calc_eta(start, now, total, current):
-        if total is None:
-            return None
-        dif = now - start
-        if current == 0 or dif < 0.001: # One millisecond
-            return None
-        rate = float(current) / dif
-        return int((float(total) - float(current)) / rate)
-
-    @staticmethod
-    def format_eta(eta):
-        if eta is None:
-            return '--:--'
-        return FileDownloader.format_seconds(eta)
-
-    @staticmethod
-    def calc_speed(start, now, bytes):
-        dif = now - start
-        if bytes == 0 or dif < 0.001: # One millisecond
-            return None
-        return float(bytes) / dif
-
-    @staticmethod
-    def format_speed(speed):
-        if speed is None:
-            return '%10s' % '---b/s'
-        return '%10s' % ('%s/s' % format_bytes(speed))
-
-    @staticmethod
-    def best_block_size(elapsed_time, bytes):
-        new_min = max(bytes / 2.0, 1.0)
-        new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB
-        if elapsed_time < 0.001:
-            return int(new_max)
-        rate = bytes / elapsed_time
-        if rate > new_max:
-            return int(new_max)
-        if rate < new_min:
-            return int(new_min)
-        return int(rate)
-
-    @staticmethod
-    def parse_bytes(bytestr):
-        """Parse a string indicating a byte quantity into an integer."""
-        matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr)
-        if matchobj is None:
-            return None
-        number = float(matchobj.group(1))
-        multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
-        return int(round(number * multiplier))
-
-    def to_screen(self, *args, **kargs):
-        self.ydl.to_screen(*args, **kargs)
-
-    def to_stderr(self, message):
-        self.ydl.to_screen(message)
-
-    def to_console_title(self, message):
-        self.ydl.to_console_title(message)
-
-    def trouble(self, *args, **kargs):
-        self.ydl.trouble(*args, **kargs)
-
-    def report_warning(self, *args, **kargs):
-        self.ydl.report_warning(*args, **kargs)
-
-    def report_error(self, *args, **kargs):
-        self.ydl.report_error(*args, **kargs)
-
-    def slow_down(self, start_time, byte_counter):
-        """Sleep if the download speed is over the rate limit."""
-        rate_limit = self.params.get('ratelimit', None)
-        if rate_limit is None or byte_counter == 0:
-            return
-        now = time.time()
-        elapsed = now - start_time
-        if elapsed <= 0.0:
-            return
-        speed = float(byte_counter) / elapsed
-        if speed > rate_limit:
-            time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit)
-
-    def temp_name(self, filename):
-        """Returns a temporary filename for the given filename."""
-        if self.params.get('nopart', False) or filename == u'-' or \
-                (os.path.exists(encodeFilename(filename)) and not os.path.isfile(encodeFilename(filename))):
-            return filename
-        return filename + u'.part'
-
-    def undo_temp_name(self, filename):
-        if filename.endswith(u'.part'):
-            return filename[:-len(u'.part')]
-        return filename
-
-    def try_rename(self, old_filename, new_filename):
-        try:
-            if old_filename == new_filename:
-                return
-            os.rename(encodeFilename(old_filename), encodeFilename(new_filename))
-        except (IOError, OSError):
-            self.report_error(u'unable to rename file')
-
-    def try_utime(self, filename, last_modified_hdr):
-        """Try to set the last-modified time of the given file."""
-        if last_modified_hdr is None:
-            return
-        if not os.path.isfile(encodeFilename(filename)):
-            return
-        timestr = last_modified_hdr
-        if timestr is None:
-            return
-        filetime = timeconvert(timestr)
-        if filetime is None:
-            return filetime
-        # Ignore obviously invalid dates
-        if filetime == 0:
-            return
-        try:
-            os.utime(filename, (time.time(), filetime))
-        except:
-            pass
-        return filetime
-
-    def report_destination(self, filename):
-        """Report destination filename."""
-        self.to_screen(u'[download] Destination: ' + filename)
-
-    def report_progress(self, percent, data_len_str, speed, eta):
-        """Report download progress."""
-        if self.params.get('noprogress', False):
-            return
-        clear_line = (u'\x1b[K' if sys.stderr.isatty() and os.name != 'nt' else u'')
-        if eta is not None:
-            eta_str = self.format_eta(eta)
-        else:
-            eta_str = 'Unknown ETA'
-        if percent is not None:
-            percent_str = self.format_percent(percent)
-        else:
-            percent_str = 'Unknown %'
-        speed_str = self.format_speed(speed)
-        if self.params.get('progress_with_newline', False):
-            self.to_screen(u'[download] %s of %s at %s ETA %s' %
-                (percent_str, data_len_str, speed_str, eta_str))
-        else:
-            self.to_screen(u'\r%s[download] %s of %s at %s ETA %s' %
-                (clear_line, percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
-        self.to_console_title(u'youtube-dl - %s of %s at %s ETA %s' %
-                (percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip()))
-
-    def report_resuming_byte(self, resume_len):
-        """Report attempt to resume at given byte."""
-        self.to_screen(u'[download] Resuming download at byte %s' % resume_len)
-
-    def report_retry(self, count, retries):
-        """Report retry in case of HTTP error 5xx"""
-        self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries))
-
-    def report_file_already_downloaded(self, file_name):
-        """Report file has already been fully downloaded."""
-        try:
-            self.to_screen(u'[download] %s has already been downloaded' % file_name)
-        except UnicodeEncodeError:
-            self.to_screen(u'[download] The file has already been downloaded')
-
-    def report_unable_to_resume(self):
-        """Report it was impossible to resume download."""
-        self.to_screen(u'[download] Unable to resume')
-
-    def report_finish(self, data_len_str, tot_time):
-        """Report download finished."""
-        if self.params.get('noprogress', False):
-            self.to_screen(u'[download] Download completed')
-        else:
-            clear_line = (u'\x1b[K' if sys.stderr.isatty() and os.name != 'nt' else u'')
-            self.to_screen(u'\r%s[download] 100%% of %s in %s' %
-                (clear_line, data_len_str, self.format_seconds(tot_time)))
-
-    def _download_with_rtmpdump(self, filename, url, player_url, page_url, play_path, tc_url, live):
-        def run_rtmpdump(args):
-            start = time.time()
-            resume_percent = None
-            resume_downloaded_data_len = None
-            proc = subprocess.Popen(args, stderr=subprocess.PIPE)
-            cursor_in_new_line = True
-            proc_stderr_closed = False
-            while not proc_stderr_closed:
-                # read line from stderr
-                line = u''
-                while True:
-                    char = proc.stderr.read(1)
-                    if not char:
-                        proc_stderr_closed = True
-                        break
-                    if char in [b'\r', b'\n']:
-                        break
-                    line += char.decode('ascii', 'replace')
-                if not line:
-                    # proc_stderr_closed is True
-                    continue
-                mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec \(([0-9]{1,2}\.[0-9])%\)', line)
-                if mobj:
-                    downloaded_data_len = int(float(mobj.group(1))*1024)
-                    percent = float(mobj.group(2))
-                    if not resume_percent:
-                        resume_percent = percent
-                        resume_downloaded_data_len = downloaded_data_len
-                    eta = self.calc_eta(start, time.time(), 100-resume_percent, percent-resume_percent)
-                    speed = self.calc_speed(start, time.time(), downloaded_data_len-resume_downloaded_data_len)
-                    data_len = None
-                    if percent > 0:
-                        data_len = int(downloaded_data_len * 100 / percent)
-                    data_len_str = u'~' + format_bytes(data_len)
-                    self.report_progress(percent, data_len_str, speed, eta)
-                    cursor_in_new_line = False
-                    self._hook_progress({
-                        'downloaded_bytes': downloaded_data_len,
-                        'total_bytes': data_len,
-                        'tmpfilename': tmpfilename,
-                        'filename': filename,
-                        'status': 'downloading',
-                        'eta': eta,
-                        'speed': speed,
-                    })
-                elif self.params.get('verbose', False):
-                    if not cursor_in_new_line:
-                        self.to_screen(u'')
-                    cursor_in_new_line = True
-                    self.to_screen(u'[rtmpdump] '+line)
-            proc.wait()
-            if not cursor_in_new_line:
-                self.to_screen(u'')
-            return proc.returncode
-
-        self.report_destination(filename)
-        tmpfilename = self.temp_name(filename)
-        test = self.params.get('test', False)
-
-        # Check for rtmpdump first
-        try:
-            subprocess.call(['rtmpdump', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
-        except (OSError, IOError):
-            self.report_error(u'RTMP download detected but "rtmpdump" could not be run')
-            return False
-
-        # Download using rtmpdump. rtmpdump returns exit code 2 when
-        # the connection was interrumpted and resuming appears to be
-        # possible. This is part of rtmpdump's normal usage, AFAIK.
-        basic_args = ['rtmpdump', '--verbose', '-r', url, '-o', tmpfilename]
-        if player_url is not None:
-            basic_args += ['--swfVfy', player_url]
-        if page_url is not None:
-            basic_args += ['--pageUrl', page_url]
-        if play_path is not None:
-            basic_args += ['--playpath', play_path]
-        if tc_url is not None:
-            basic_args += ['--tcUrl', url]
-        if test:
-            basic_args += ['--stop', '1']
-        if live:
-            basic_args += ['--live']
-        args = basic_args + [[], ['--resume', '--skip', '1']][self.params.get('continuedl', False)]
-
-        if sys.platform == 'win32' and sys.version_info < (3, 0):
-            # Windows subprocess module does not actually support Unicode
-            # on Python 2.x
-            # See http://stackoverflow.com/a/9951851/35070
-            subprocess_encoding = sys.getfilesystemencoding()
-            args = [a.encode(subprocess_encoding, 'ignore') for a in args]
-        else:
-            subprocess_encoding = None
-
-        if self.params.get('verbose', False):
-            if subprocess_encoding:
-                str_args = [
-                    a.decode(subprocess_encoding) if isinstance(a, bytes) else a
-                    for a in args]
-            else:
-                str_args = args
-            try:
-                import pipes
-                shell_quote = lambda args: ' '.join(map(pipes.quote, str_args))
-            except ImportError:
-                shell_quote = repr
-            self.to_screen(u'[debug] rtmpdump command line: ' + shell_quote(str_args))
-
-        retval = run_rtmpdump(args)
-
-        while (retval == 2 or retval == 1) and not test:
-            prevsize = os.path.getsize(encodeFilename(tmpfilename))
-            self.to_screen(u'[rtmpdump] %s bytes' % prevsize)
-            time.sleep(5.0) # This seems to be needed
-            retval = run_rtmpdump(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
-            cursize = os.path.getsize(encodeFilename(tmpfilename))
-            if prevsize == cursize and retval == 1:
-                break
-             # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those
-            if prevsize == cursize and retval == 2 and cursize > 1024:
-                self.to_screen(u'[rtmpdump] Could not download the whole video. This can happen for some advertisements.')
-                retval = 0
-                break
-        if retval == 0 or (test and retval == 2):
-            fsize = os.path.getsize(encodeFilename(tmpfilename))
-            self.to_screen(u'[rtmpdump] %s bytes' % fsize)
-            self.try_rename(tmpfilename, filename)
-            self._hook_progress({
-                'downloaded_bytes': fsize,
-                'total_bytes': fsize,
-                'filename': filename,
-                'status': 'finished',
-            })
-            return True
-        else:
-            self.to_stderr(u"\n")
-            self.report_error(u'rtmpdump exited with code %d' % retval)
-            return False
-
-    def _download_with_mplayer(self, filename, url):
-        self.report_destination(filename)
-        tmpfilename = self.temp_name(filename)
-
-        args = ['mplayer', '-really-quiet', '-vo', 'null', '-vc', 'dummy', '-dumpstream', '-dumpfile', tmpfilename, url]
-        # Check for mplayer first
-        try:
-            subprocess.call(['mplayer', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
-        except (OSError, IOError):
-            self.report_error(u'MMS or RTSP download detected but "%s" could not be run' % args[0] )
-            return False
-
-        # Download using mplayer. 
-        retval = subprocess.call(args)
-        if retval == 0:
-            fsize = os.path.getsize(encodeFilename(tmpfilename))
-            self.to_screen(u'\r[%s] %s bytes' % (args[0], fsize))
-            self.try_rename(tmpfilename, filename)
-            self._hook_progress({
-                'downloaded_bytes': fsize,
-                'total_bytes': fsize,
-                'filename': filename,
-                'status': 'finished',
-            })
-            return True
-        else:
-            self.to_stderr(u"\n")
-            self.report_error(u'mplayer exited with code %d' % retval)
-            return False
-
-    def _download_m3u8_with_ffmpeg(self, filename, url):
-        self.report_destination(filename)
-        tmpfilename = self.temp_name(filename)
-
-        args = ['-y', '-i', url, '-f', 'mp4', '-c', 'copy',
-            '-bsf:a', 'aac_adtstoasc', tmpfilename]
-
-        for program in ['avconv', 'ffmpeg']:
-            try:
-                subprocess.call([program, '-version'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
-                break
-            except (OSError, IOError):
-                pass
-        else:
-            self.report_error(u'm3u8 download detected but ffmpeg or avconv could not be found')
-        cmd = [program] + args
-
-        retval = subprocess.call(cmd)
-        if retval == 0:
-            fsize = os.path.getsize(encodeFilename(tmpfilename))
-            self.to_screen(u'\r[%s] %s bytes' % (args[0], fsize))
-            self.try_rename(tmpfilename, filename)
-            self._hook_progress({
-                'downloaded_bytes': fsize,
-                'total_bytes': fsize,
-                'filename': filename,
-                'status': 'finished',
-            })
-            return True
-        else:
-            self.to_stderr(u"\n")
-            self.report_error(u'ffmpeg exited with code %d' % retval)
-            return False
+# Legacy file for backwards compatibility, use youtube_dl.downloader instead!
+from .downloader import FileDownloader as RealFileDownloader
+from .downloader import get_suitable_downloader
 
 
+# This class reproduces the old behaviour of FileDownloader
+class FileDownloader(RealFileDownloader):
     def _do_download(self, filename, info_dict):
-        url = info_dict['url']
-
-        # Check file already present
-        if self.params.get('continuedl', False) and os.path.isfile(encodeFilename(filename)) and not self.params.get('nopart', False):
-            self.report_file_already_downloaded(filename)
-            self._hook_progress({
-                'filename': filename,
-                'status': 'finished',
-                'total_bytes': os.path.getsize(encodeFilename(filename)),
-            })
-            return True
-
-        # Attempt to download using rtmpdump
-        if url.startswith('rtmp'):
-            return self._download_with_rtmpdump(filename, url,
-                                                info_dict.get('player_url', None),
-                                                info_dict.get('page_url', None),
-                                                info_dict.get('play_path', None),
-                                                info_dict.get('tc_url', None),
-                                                info_dict.get('rtmp_live', False))
-
-        # Attempt to download using mplayer
-        if url.startswith('mms') or url.startswith('rtsp'):
-            return self._download_with_mplayer(filename, url)
-
-        # m3u8 manifest are downloaded with ffmpeg
-        if determine_ext(url) == u'm3u8':
-            return self._download_m3u8_with_ffmpeg(filename, url)
-
-        tmpfilename = self.temp_name(filename)
-        stream = None
-
-        # Do not include the Accept-Encoding header
-        headers = {'Youtubedl-no-compression': 'True'}
-        if 'user_agent' in info_dict:
-            headers['Youtubedl-user-agent'] = info_dict['user_agent']
-        basic_request = compat_urllib_request.Request(url, None, headers)
-        request = compat_urllib_request.Request(url, None, headers)
-
-        if self.params.get('test', False):
-            request.add_header('Range','bytes=0-10240')
-
-        # Establish possible resume length
-        if os.path.isfile(encodeFilename(tmpfilename)):
-            resume_len = os.path.getsize(encodeFilename(tmpfilename))
-        else:
-            resume_len = 0
-
-        open_mode = 'wb'
-        if resume_len != 0:
-            if self.params.get('continuedl', False):
-                self.report_resuming_byte(resume_len)
-                request.add_header('Range','bytes=%d-' % resume_len)
-                open_mode = 'ab'
-            else:
-                resume_len = 0
-
-        count = 0
-        retries = self.params.get('retries', 0)
-        while count <= retries:
-            # Establish connection
-            try:
-                if count == 0 and 'urlhandle' in info_dict:
-                    data = info_dict['urlhandle']
-                data = compat_urllib_request.urlopen(request)
-                break
-            except (compat_urllib_error.HTTPError, ) as err:
-                if (err.code < 500 or err.code >= 600) and err.code != 416:
-                    # Unexpected HTTP error
-                    raise
-                elif err.code == 416:
-                    # Unable to resume (requested range not satisfiable)
-                    try:
-                        # Open the connection again without the range header
-                        data = compat_urllib_request.urlopen(basic_request)
-                        content_length = data.info()['Content-Length']
-                    except (compat_urllib_error.HTTPError, ) as err:
-                        if err.code < 500 or err.code >= 600:
-                            raise
-                    else:
-                        # Examine the reported length
-                        if (content_length is not None and
-                                (resume_len - 100 < int(content_length) < resume_len + 100)):
-                            # The file had already been fully downloaded.
-                            # Explanation to the above condition: in issue #175 it was revealed that
-                            # YouTube sometimes adds or removes a few bytes from the end of the file,
-                            # changing the file size slightly and causing problems for some users. So
-                            # I decided to implement a suggested change and consider the file
-                            # completely downloaded if the file size differs less than 100 bytes from
-                            # the one in the hard drive.
-                            self.report_file_already_downloaded(filename)
-                            self.try_rename(tmpfilename, filename)
-                            self._hook_progress({
-                                'filename': filename,
-                                'status': 'finished',
-                            })
-                            return True
-                        else:
-                            # The length does not match, we start the download over
-                            self.report_unable_to_resume()
-                            open_mode = 'wb'
-                            break
-            # Retry
-            count += 1
-            if count <= retries:
-                self.report_retry(count, retries)
-
-        if count > retries:
-            self.report_error(u'giving up after %s retries' % retries)
-            return False
-
-        data_len = data.info().get('Content-length', None)
-        if data_len is not None:
-            data_len = int(data_len) + resume_len
-            min_data_len = self.params.get("min_filesize", None)
-            max_data_len =  self.params.get("max_filesize", None)
-            if min_data_len is not None and data_len < min_data_len:
-                self.to_screen(u'\r[download] File is smaller than min-filesize (%s bytes < %s bytes). Aborting.' % (data_len, min_data_len))
-                return False
-            if max_data_len is not None and data_len > max_data_len:
-                self.to_screen(u'\r[download] File is larger than max-filesize (%s bytes > %s bytes). Aborting.' % (data_len, max_data_len))
-                return False
-
-        data_len_str = format_bytes(data_len)
-        byte_counter = 0 + resume_len
-        block_size = self.params.get('buffersize', 1024)
-        start = time.time()
-        while True:
-            # Download and write
-            before = time.time()
-            data_block = data.read(block_size)
-            after = time.time()
-            if len(data_block) == 0:
-                break
-            byte_counter += len(data_block)
-
-            # Open file just in time
-            if stream is None:
-                try:
-                    (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode)
-                    assert stream is not None
-                    filename = self.undo_temp_name(tmpfilename)
-                    self.report_destination(filename)
-                except (OSError, IOError) as err:
-                    self.report_error(u'unable to open for writing: %s' % str(err))
-                    return False
-            try:
-                stream.write(data_block)
-            except (IOError, OSError) as err:
-                self.to_stderr(u"\n")
-                self.report_error(u'unable to write data: %s' % str(err))
-                return False
-            if not self.params.get('noresizebuffer', False):
-                block_size = self.best_block_size(after - before, len(data_block))
-
-            # Progress message
-            speed = self.calc_speed(start, time.time(), byte_counter - resume_len)
-            if data_len is None:
-                eta = percent = None
-            else:
-                percent = self.calc_percent(byte_counter, data_len)
-                eta = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
-            self.report_progress(percent, data_len_str, speed, eta)
-
-            self._hook_progress({
-                'downloaded_bytes': byte_counter,
-                'total_bytes': data_len,
-                'tmpfilename': tmpfilename,
-                'filename': filename,
-                'status': 'downloading',
-                'eta': eta,
-                'speed': speed,
-            })
-
-            # Apply rate limit
-            self.slow_down(start, byte_counter - resume_len)
-
-        if stream is None:
-            self.to_stderr(u"\n")
-            self.report_error(u'Did not get any data blocks')
-            return False
-        stream.close()
-        self.report_finish(data_len_str, (time.time() - start))
-        if data_len is not None and byte_counter != data_len:
-            raise ContentTooShortError(byte_counter, int(data_len))
-        self.try_rename(tmpfilename, filename)
-
-        # Update file modification time
-        if self.params.get('updatetime', True):
-            info_dict['filetime'] = self.try_utime(filename, data.info().get('last-modified', None))
-
-        self._hook_progress({
-            'downloaded_bytes': byte_counter,
-            'total_bytes': byte_counter,
-            'filename': filename,
-            'status': 'finished',
-        })
-
-        return True
-
-    def _hook_progress(self, status):
+        real_fd = get_suitable_downloader(info_dict)(self.ydl, self.params)
         for ph in self._progress_hooks:
-            ph(status)
-
-    def add_progress_hook(self, ph):
-        """ ph gets called on download progress, with a dictionary with the entries
-        * filename: The final filename
-        * status: One of "downloading" and "finished"
-
-        It can also have some of the following entries:
-
-        * downloaded_bytes: Bytes on disks
-        * total_bytes: Total bytes, None if unknown
-        * tmpfilename: The filename we're currently writing to
-        * eta: The estimated time in seconds, None if unknown
-        * speed: The download speed in bytes/second, None if unknown
-
-        Hooks are guaranteed to be called at least once (with status "finished")
-        if the download is successful.
-        """
-        self._progress_hooks.append(ph)
+            real_fd.add_progress_hook(ph)
+        return real_fd.download(filename, info_dict)

youtube_dl/InfoExtractors.py

@@ -1,4 +0,0 @@
-# Legacy file for backwards compatibility, use youtube_dl.extractor instead!
-
-from .extractor.common import InfoExtractor, SearchInfoExtractor
-from .extractor import gen_extractors, get_info_extractor

youtube_dl/__init__.py

@@ -36,31 +36,63 @@ __authors__  = (
     'Marcin Cieślak',
     'Anton Larionov',
     'Takuya Tsuchida',
+    'Sergey M.',
+    'Michael Orlitzky',
+    'Chris Gahan',
+    'Saimadhav Heblikar',
+    'Mike Col',
+    'Oleg Prutz',
+    'pulpe',
+    'Andreas Schmitz',
+    'Michael Kaiser',
+    'Niklas Laxström',
+    'David Triendl',
+    'Anthony Weems',
+    'David Wagner',
+    'Juan C. Olivares',
+    'Mattias Harrysson',
+    'phaer',
+    'Sainyam Kapoor',
+    'Nicolas Évrard',
+    'Jason Normore',
+    'Hoje Lee',
+    'Adam Thalhammer',
+    'Georg Jähnig',
+    'Ralf Haring',
+    'Koki Takahashi',
+    'Ariset Llerena',
+    'Adam Malcontenti-Wilson',
+    'Tobias Bell',
+    'Naglis Jonaitis',
+    'Charles Chen',
+    'Hassaan Ali',
 )
 
 __license__ = 'Public Domain'
 
 import codecs
-import getpass
+import io
 import optparse
 import os
 import random
-import re
 import shlex
-import subprocess
 import sys
 
 
 from .utils import (
+    compat_getpass,
     compat_print,
     DateRange,
+    DEFAULT_OUTTMPL,
     decodeOption,
-    determine_ext,
+    get_term_width,
     DownloadError,
     get_cachedir,
     MaxDownloadsReached,
     preferredencoding,
+    read_batch_urls,
     SameFileError,
+    setproctitle,
     std_headers,
     write_string,
 )
@@ -71,20 +103,23 @@ from .FileDownloader import (
 from .extractor import gen_extractors
 from .version import __version__
 from .YoutubeDL import YoutubeDL
-from .PostProcessor import (
+from .postprocessor import (
+    AtomicParsleyPP,
+    FFmpegAudioFixPP,
     FFmpegMetadataPP,
     FFmpegVideoConvertor,
     FFmpegExtractAudioPP,
     FFmpegEmbedSubtitlePP,
+    XAttrMetadataPP,
 )
 
 
 def parseOpts(overrideArguments=None):
-    def _readOptions(filename_bytes):
+    def _readOptions(filename_bytes, default=[]):
         try:
             optionf = open(filename_bytes)
         except IOError:
-            return [] # silently skip if file is not present
+            return default  # silently skip if file is not present
         try:
             res = []
             for l in optionf:
@@ -93,6 +128,43 @@ def parseOpts(overrideArguments=None):
             optionf.close()
         return res
 
+    def _readUserConf():
+        xdg_config_home = os.environ.get('XDG_CONFIG_HOME')
+        if xdg_config_home:
+            userConfFile = os.path.join(xdg_config_home, 'youtube-dl', 'config')
+            if not os.path.isfile(userConfFile):
+                userConfFile = os.path.join(xdg_config_home, 'youtube-dl.conf')
+        else:
+            userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl', 'config')
+            if not os.path.isfile(userConfFile):
+                userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf')
+        userConf = _readOptions(userConfFile, None)
+
+        if userConf is None:
+            appdata_dir = os.environ.get('appdata')
+            if appdata_dir:
+                userConf = _readOptions(
+                    os.path.join(appdata_dir, 'youtube-dl', 'config'),
+                    default=None)
+                if userConf is None:
+                    userConf = _readOptions(
+                        os.path.join(appdata_dir, 'youtube-dl', 'config.txt'),
+                        default=None)
+
+        if userConf is None:
+            userConf = _readOptions(
+                os.path.join(os.path.expanduser('~'), 'youtube-dl.conf'),
+                default=None)
+        if userConf is None:
+            userConf = _readOptions(
+                os.path.join(os.path.expanduser('~'), 'youtube-dl.conf.txt'),
+                default=None)
+
+        if userConf is None:
+            userConf = []
+
+        return userConf
+
     def _format_option_string(option):
         ''' ('-o', '--option') -> -o, --format METAVAR'''
 
@@ -112,19 +184,6 @@ def parseOpts(overrideArguments=None):
     def _comma_separated_values_options_callback(option, opt_str, value, parser):
         setattr(parser.values, option.dest, value.split(','))
 
-    def _find_term_columns():
-        columns = os.environ.get('COLUMNS', None)
-        if columns:
-            return int(columns)
-
-        try:
-            sp = subprocess.Popen(['stty', 'size'], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
-            out,err = sp.communicate()
-            return int(out.split()[1])
-        except:
-            pass
-        return None
-
     def _hide_login_info(opts):
         opts = list(opts)
         for private_opt in ['-p', '--password', '-u', '--username', '--video-password']:
@@ -139,7 +198,7 @@ def parseOpts(overrideArguments=None):
     max_help_position = 80
 
     # No need to wrap help messages if we're on a wide console
-    columns = _find_term_columns()
+    columns = get_term_width()
     if columns: max_width = columns
 
     fmt = optparse.IndentedHelpFormatter(width=max_width, max_help_position=max_help_position)
@@ -172,7 +231,7 @@ def parseOpts(overrideArguments=None):
     general.add_option('-U', '--update',
             action='store_true', dest='update_self', help='update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed)')
     general.add_option('-i', '--ignore-errors',
-            action='store_true', dest='ignoreerrors', help='continue on download errors, for example to to skip unavailable videos in a playlist', default=False)
+            action='store_true', dest='ignoreerrors', help='continue on download errors, for example to skip unavailable videos in a playlist', default=False)
     general.add_option('--abort-on-error',
             action='store_false', dest='ignoreerrors',
             help='Abort downloading of further videos (in the playlist or the command line) if an error occurs')
@@ -184,26 +243,54 @@ def parseOpts(overrideArguments=None):
     general.add_option('--referer',
             dest='referer', help='specify a custom referer, use if the video access is restricted to one domain',
             metavar='REF', default=None)
+    general.add_option('--add-header',
+            dest='headers', help='specify a custom HTTP header and its value, separated by a colon \':\'. You can use this option multiple times', action="append",
+            metavar='FIELD:VALUE')
     general.add_option('--list-extractors',
             action='store_true', dest='list_extractors',
             help='List all supported extractors and the URLs they would handle', default=False)
     general.add_option('--extractor-descriptions',
             action='store_true', dest='list_extractor_descriptions',
             help='Output descriptions of all supported extractors', default=False)
-    general.add_option('--proxy', dest='proxy', default=None, help='Use the specified HTTP/HTTPS proxy', metavar='URL')
+    general.add_option(
+        '--proxy', dest='proxy', default=None, metavar='URL',
+        help='Use the specified HTTP/HTTPS proxy. Pass in an empty string (--proxy "") for direct connection')
     general.add_option('--no-check-certificate', action='store_true', dest='no_check_certificate', default=False, help='Suppress HTTPS certificate validation.')
+    general.add_option(
+        '--prefer-insecure', '--prefer-unsecure', action='store_true', dest='prefer_insecure',
+        help='Use an unencrypted connection to retrieve information about the video. (Currently supported only for YouTube)')
     general.add_option(
         '--cache-dir', dest='cachedir', default=get_cachedir(), metavar='DIR',
-        help='Location in the filesystem where youtube-dl can store downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl or ~/.cache/youtube-dl .')
+        help='Location in the filesystem where youtube-dl can store some downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl or ~/.cache/youtube-dl . At the moment, only YouTube player files (for videos with obfuscated signatures) are cached, but that may change.')
     general.add_option(
         '--no-cache-dir', action='store_const', const=None, dest='cachedir',
         help='Disable filesystem caching')
+    general.add_option(
+        '--socket-timeout', dest='socket_timeout',
+        type=float, default=None, help=u'Time to wait before giving up, in seconds')
+    general.add_option(
+        '--bidi-workaround', dest='bidi_workaround', action='store_true',
+        help=u'Work around terminals that lack bidirectional text support. Requires bidiv or fribidi executable in PATH')
+    general.add_option(
+        '--default-search',
+        dest='default_search', metavar='PREFIX',
+        help='Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for  youtube-dl "large apple". Use the value "auto" to let youtube-dl guess. The default value "error" just throws an error.')
+    general.add_option(
+        '--ignore-config',
+        action='store_true',
+        help='Do not read configuration files. When given in the global configuration file /etc/youtube-dl.conf: do not read the user configuration in ~/.config/youtube-dl.conf (%APPDATA%/youtube-dl/config.txt on Windows)')
+    general.add_option(
+        '--encoding', dest='encoding', metavar='ENCODING',
+        help='Force the specified encoding (experimental)')
 
-
-    selection.add_option('--playlist-start',
-            dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is %default)', default=1)
-    selection.add_option('--playlist-end',
-            dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1)
+    selection.add_option(
+        '--playlist-start',
+        dest='playliststart', metavar='NUMBER', default=1, type=int,
+        help='playlist video to start at (default is %default)')
+    selection.add_option(
+        '--playlist-end',
+        dest='playlistend', metavar='NUMBER', default=None, type=int,
+        help='playlist video to end at (default is last)')
     selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)')
     selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)')
     selection.add_option('--max-downloads', metavar='NUMBER',
@@ -212,16 +299,35 @@ def parseOpts(overrideArguments=None):
     selection.add_option('--min-filesize', metavar='SIZE', dest='min_filesize', help="Do not download any videos smaller than SIZE (e.g. 50k or 44.6m)", default=None)
     selection.add_option('--max-filesize', metavar='SIZE', dest='max_filesize', help="Do not download any videos larger than SIZE (e.g. 50k or 44.6m)", default=None)
     selection.add_option('--date', metavar='DATE', dest='date', help='download only videos uploaded in this date', default=None)
-    selection.add_option('--datebefore', metavar='DATE', dest='datebefore', help='download only videos uploaded before this date', default=None)
-    selection.add_option('--dateafter', metavar='DATE', dest='dateafter', help='download only videos uploaded after this date', default=None)
+    selection.add_option(
+        '--datebefore', metavar='DATE', dest='datebefore', default=None,
+        help='download only videos uploaded on or before this date (i.e. inclusive)')
+    selection.add_option(
+        '--dateafter', metavar='DATE', dest='dateafter', default=None,
+        help='download only videos uploaded on or after this date (i.e. inclusive)')
+    selection.add_option(
+        '--min-views', metavar='COUNT', dest='min_views',
+        default=None, type=int,
+        help="Do not download any videos with less than COUNT views",)
+    selection.add_option(
+        '--max-views', metavar='COUNT', dest='max_views',
+        default=None, type=int,
+        help="Do not download any videos with more than COUNT views",)
     selection.add_option('--no-playlist', action='store_true', dest='noplaylist', help='download only the currently playing video', default=False)
     selection.add_option('--age-limit', metavar='YEARS', dest='age_limit',
                          help='download only videos suitable for the given age',
                          default=None, type=int)
     selection.add_option('--download-archive', metavar='FILE',
                          dest='download_archive',
-                         help='Download only videos not present in the archive file. Record all downloaded videos in it.')
-
+                         help='Download only videos not listed in the archive file. Record the IDs of all downloaded videos in it.')
+    selection.add_option(
+        '--include-ads', dest='include_ads',
+        action='store_true',
+        help='Download advertisements as well (experimental)')
+    selection.add_option(
+        '--youtube-include-dash-manifest', action='store_true',
+        dest='youtube_include_dash_manifest', default=False,
+        help='Try to download the DASH manifest on YouTube videos (experimental)')
 
     authentication.add_option('-u', '--username',
             dest='username', metavar='USERNAME', help='account username')
@@ -230,12 +336,12 @@ def parseOpts(overrideArguments=None):
     authentication.add_option('-n', '--netrc',
             action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
     authentication.add_option('--video-password',
-            dest='videopassword', metavar='PASSWORD', help='video password (vimeo only)')
+            dest='videopassword', metavar='PASSWORD', help='video password (vimeo, smotri)')
 
 
     video_format.add_option('-f', '--format',
-            action='store', dest='format', metavar='FORMAT', default='best',
-            help='video format code, specifiy the order of preference using slashes: "-f 22/17/18". "-f mp4" and "-f flv" are also supported')
+            action='store', dest='format', metavar='FORMAT', default=None,
+            help='video format code, specify the order of preference using slashes: "-f 22/17/18". "-f mp4" and "-f flv" are also supported. You can also use the special names "best", "bestvideo", "bestaudio", "worst", "worstvideo" and "worstaudio". By default, youtube-dl will pick the best quality.')
     video_format.add_option('--all-formats',
             action='store_const', dest='format', help='download all available video formats', const='all')
     video_format.add_option('--prefer-free-formats',
@@ -243,7 +349,7 @@ def parseOpts(overrideArguments=None):
     video_format.add_option('--max-quality',
             action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
     video_format.add_option('-F', '--list-formats',
-            action='store_true', dest='listformats', help='list all available formats (currently youtube only)')
+            action='store_true', dest='listformats', help='list all available formats')
 
     subtitles.add_option('--write-sub', '--write-srt',
             action='store_true', dest='writesubtitles',
@@ -278,6 +384,10 @@ def parseOpts(overrideArguments=None):
 
     verbosity.add_option('-q', '--quiet',
             action='store_true', dest='quiet', help='activates quiet mode', default=False)
+    verbosity.add_option(
+        '--no-warnings',
+        dest='no_warnings', action='store_true', default=False,
+        help='Ignore warnings')
     verbosity.add_option('-s', '--simulate',
             action='store_true', dest='simulate', help='do not download the video and do not write anything to disk', default=False)
     verbosity.add_option('--skip-download',
@@ -294,6 +404,9 @@ def parseOpts(overrideArguments=None):
     verbosity.add_option('--get-description',
             action='store_true', dest='getdescription',
             help='simulate, quiet but print video description', default=False)
+    verbosity.add_option('--get-duration',
+            action='store_true', dest='getduration',
+            help='simulate, quiet but print video length', default=False)
     verbosity.add_option('--get-filename',
             action='store_true', dest='getfilename',
             help='simulate, quiet but print output filename', default=False)
@@ -302,7 +415,7 @@ def parseOpts(overrideArguments=None):
             help='simulate, quiet but print output format', default=False)
     verbosity.add_option('-j', '--dump-json',
             action='store_true', dest='dumpjson',
-            help='simulate, quiet but print JSON information', default=False)
+            help='simulate, quiet but print JSON information. See --output for a description of available keys.', default=False)
     verbosity.add_option('--newline',
             action='store_true', dest='progress_with_newline', help='output progress bar as new lines', default=False)
     verbosity.add_option('--no-progress',
@@ -314,13 +427,16 @@ def parseOpts(overrideArguments=None):
             action='store_true', dest='verbose', help='print various debugging information', default=False)
     verbosity.add_option('--dump-intermediate-pages',
             action='store_true', dest='dump_intermediate_pages', default=False,
-            help='print downloaded pages to debug problems(very verbose)')
+            help='print downloaded pages to debug problems (very verbose)')
     verbosity.add_option('--write-pages',
             action='store_true', dest='write_pages', default=False,
-            help='Write downloaded pages to files in the current directory')
+            help='Write downloaded intermediary pages to files in the current directory to debug problems')
     verbosity.add_option('--youtube-print-sig-code',
             action='store_true', dest='youtube_print_sig_code', default=False,
             help=optparse.SUPPRESS_HELP)
+    verbosity.add_option('--print-traffic',
+            dest='debug_printtraffic', action='store_true', default=False,
+            help='Display sent and read HTTP traffic')
 
 
     filesystem.add_option('-t', '--title',
@@ -338,12 +454,14 @@ def parseOpts(overrideArguments=None):
                   '%(uploader)s for the uploader name, %(uploader_id)s for the uploader nickname if different, '
                   '%(autonumber)s to get an automatically incremented number, '
                   '%(ext)s for the filename extension, '
-                  '%(format)s for the format description (like "22 - 1280x720" or "HD"),'
-                  '%(format_id)s for the unique id of the format (like Youtube\'s itags: "137"),'
+                  '%(format)s for the format description (like "22 - 1280x720" or "HD"), '
+                  '%(format_id)s for the unique id of the format (like Youtube\'s itags: "137"), '
                   '%(upload_date)s for the upload date (YYYYMMDD), '
                   '%(extractor)s for the provider (youtube, metacafe, etc), '
-                  '%(id)s for the video id , %(playlist)s for the playlist the video is in, '
+                  '%(id)s for the video id, %(playlist)s for the playlist the video is in, '
                   '%(playlist_index)s for the position in the playlist and %% for a literal percent. '
+                  '%(height)s and %(width)s for the width and height of the video format. '
+                  '%(resolution)s for a textual description of the resolution of the video format. '
                   'Use - to output to stdout. Can also be used to download to a different directory, '
                   'for example with -o \'/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s\' .'))
     filesystem.add_option('--autonumber-size',
@@ -354,6 +472,9 @@ def parseOpts(overrideArguments=None):
             help='Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames', default=False)
     filesystem.add_option('-a', '--batch-file',
             dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
+    filesystem.add_option('--load-info',
+            dest='load_info_filename', metavar='FILE',
+            help='json file containing the video information (created with the "--write-json" option)')
     filesystem.add_option('-w', '--no-overwrites',
             action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
     filesystem.add_option('-c', '--continue',
@@ -389,15 +510,23 @@ def parseOpts(overrideArguments=None):
     postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='5',
             help='ffmpeg/avconv audio quality specification, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default 5)')
     postproc.add_option('--recode-video', metavar='FORMAT', dest='recodevideo', default=None,
-            help='Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm)')
+            help='Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm|mkv)')
     postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False,
             help='keeps the video file on disk after the post-processing; the video is erased by default')
     postproc.add_option('--no-post-overwrites', action='store_true', dest='nopostoverwrites', default=False,
             help='do not overwrite post-processed files; the post-processed files are overwritten by default')
     postproc.add_option('--embed-subs', action='store_true', dest='embedsubtitles', default=False,
             help='embed subtitles in the video (only for mp4 videos)')
+    postproc.add_option('--embed-thumbnail', action='store_true', dest='embedthumbnail', default=False,
+            help='embed thumbnail in the audio as cover art')
     postproc.add_option('--add-metadata', action='store_true', dest='addmetadata', default=False,
-            help='add metadata to the files')
+            help='write metadata to the video file')
+    postproc.add_option('--xattrs', action='store_true', dest='xattrs', default=False,
+            help='write metadata to the video file\'s xattrs (using dublin core and xdg standards)')
+    postproc.add_option('--prefer-avconv', action='store_false', dest='prefer_ffmpeg',
+        help='Prefer avconv over ffmpeg for running the postprocessors (default)')
+    postproc.add_option('--prefer-ffmpeg', action='store_true', dest='prefer_ffmpeg',
+        help='Prefer ffmpeg over avconv for running the postprocessors')
 
 
     parser.add_option_group(general)
@@ -415,19 +544,18 @@ def parseOpts(overrideArguments=None):
         if opts.verbose:
             write_string(u'[debug] Override config: ' + repr(overrideArguments) + '\n')
     else:
-        xdg_config_home = os.environ.get('XDG_CONFIG_HOME')
-        if xdg_config_home:
-            userConfFile = os.path.join(xdg_config_home, 'youtube-dl', 'config')
-            if not os.path.isfile(userConfFile):
-                userConfFile = os.path.join(xdg_config_home, 'youtube-dl.conf')
-        else:
-            userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl', 'config')
-            if not os.path.isfile(userConfFile):
-                userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf')
-        systemConf = _readOptions('/etc/youtube-dl.conf')
-        userConf = _readOptions(userConfFile)
         commandLineConf = sys.argv[1:]
+        if '--ignore-config' in commandLineConf:
+            systemConf = []
+            userConf = []
+        else:
+            systemConf = _readOptions('/etc/youtube-dl.conf')
+            if '--ignore-config' in systemConf:
+                userConf = []
+            else:
+                userConf = _readUserConf()
         argv = systemConf + userConf + commandLineConf
+
         opts, args = parser.parse_args(argv)
         if opts.verbose:
             write_string(u'[debug] System config: ' + repr(_hide_login_info(systemConf)) + '\n')
@@ -436,12 +564,15 @@ def parseOpts(overrideArguments=None):
 
     return parser, opts, args
 
+
 def _real_main(argv=None):
     # Compatibility fixes for Windows
     if sys.platform == 'win32':
         # https://github.com/rg3/youtube-dl/issues/820
         codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
 
+    setproctitle(u'youtube-dl')
+
     parser, opts, args = parseOpts(argv)
 
     # Set user agent
@@ -452,28 +583,38 @@ def _real_main(argv=None):
     if opts.referer is not None:
         std_headers['Referer'] = opts.referer
 
+    # Custom HTTP headers
+    if opts.headers is not None:
+        for h in opts.headers:
+            if h.find(':', 1) < 0:
+                parser.error(u'wrong header formatting, it should be key:value, not "%s"'%h)
+            key, value = h.split(':', 2)
+            if opts.verbose:
+                write_string(u'[debug] Adding header from command line option %s:%s\n'%(key, value))
+            std_headers[key] = value
+
     # Dump user agent
     if opts.dump_user_agent:
         compat_print(std_headers['User-Agent'])
         sys.exit(0)
 
     # Batch file verification
-    batchurls = []
+    batch_urls = []
     if opts.batchfile is not None:
         try:
             if opts.batchfile == '-':
                 batchfd = sys.stdin
             else:
-                batchfd = open(opts.batchfile, 'r')
-            batchurls = batchfd.readlines()
-            batchurls = [x.strip() for x in batchurls]
-            batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)]
+                batchfd = io.open(opts.batchfile, 'r', encoding='utf-8', errors='ignore')
+            batch_urls = read_batch_urls(batchfd)
             if opts.verbose:
-                write_string(u'[debug] Batch file urls: ' + repr(batchurls) + u'\n')
+                write_string(u'[debug] Batch file urls: ' + repr(batch_urls) + u'\n')
         except IOError:
             sys.exit(u'ERROR: batch file could not be read')
-    all_urls = batchurls + args
+    all_urls = batch_urls + args
     all_urls = [url.strip() for url in all_urls]
+    _enc = preferredencoding()
+    all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
 
     extractors = gen_extractors()
 
@@ -481,7 +622,6 @@ def _real_main(argv=None):
         for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()):
             compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else ''))
             matchedUrls = [url for url in all_urls if ie.suitable(url)]
-            all_urls = [url for url in all_urls if url not in matchedUrls]
             for mu in matchedUrls:
                 compat_print(u'  ' + mu)
         sys.exit(0)
@@ -493,7 +633,7 @@ def _real_main(argv=None):
             if desc is False:
                 continue
             if hasattr(ie, 'SEARCH_KEY'):
-                _SEARCHES = (u'cute kittens', u'slithering pythons', u'falling cat', u'angry poodle', u'purple fish', u'running tortoise')
+                _SEARCHES = (u'cute kittens', u'slithering pythons', u'falling cat', u'angry poodle', u'purple fish', u'running tortoise', u'sleeping bunny')
                 _COUNTS = (u'', u'5', u'10', u'all')
                 desc += u' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
             compat_print(desc)
@@ -504,13 +644,13 @@ def _real_main(argv=None):
     if opts.usenetrc and (opts.username is not None or opts.password is not None):
         parser.error(u'using .netrc conflicts with giving username/password')
     if opts.password is not None and opts.username is None:
-        parser.error(u' account username missing\n')
+        parser.error(u'account username missing\n')
     if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
         parser.error(u'using output template conflicts with using title, video ID or auto number')
     if opts.usetitle and opts.useid:
         parser.error(u'using title conflicts with using video ID')
     if opts.username is not None and opts.password is None:
-        opts.password = getpass.getpass(u'Type account password and press return:')
+        opts.password = compat_getpass(u'Type account password and press [Return]: ')
     if opts.ratelimit is not None:
         numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
         if numeric_limit is None:
@@ -536,18 +676,10 @@ def _real_main(argv=None):
         if numeric_buffersize is None:
             parser.error(u'invalid buffer size specified')
         opts.buffersize = numeric_buffersize
-    try:
-        opts.playliststart = int(opts.playliststart)
-        if opts.playliststart <= 0:
-            raise ValueError(u'Playlist start must be positive')
-    except (TypeError, ValueError):
-        parser.error(u'invalid playlist start number specified')
-    try:
-        opts.playlistend = int(opts.playlistend)
-        if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart):
-            raise ValueError(u'Playlist end must be greater than playlist start')
-    except (TypeError, ValueError):
-        parser.error(u'invalid playlist end number specified')
+    if opts.playliststart <= 0:
+        raise ValueError(u'Playlist start must be positive')
+    if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
+        raise ValueError(u'Playlist end must be greater than playlist start')
     if opts.extractaudio:
         if opts.audioformat not in ['best', 'aac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']:
             parser.error(u'invalid audio format specified')
@@ -556,12 +688,18 @@ def _real_main(argv=None):
         if not opts.audioquality.isdigit():
             parser.error(u'invalid audio quality specified')
     if opts.recodevideo is not None:
-        if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg']:
+        if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']:
             parser.error(u'invalid video recode format specified')
     if opts.date is not None:
         date = DateRange.day(opts.date)
     else:
         date = DateRange(opts.dateafter, opts.datebefore)
+    if opts.default_search not in ('auto', 'auto_warning', None) and ':' not in opts.default_search:
+        parser.error(u'--default-search invalid; did you forget a colon (:) at the end?')
+
+    # Do not download videos when there are audio-only formats
+    if opts.extractaudio and not opts.keepvideo and opts.format is None:
+        opts.format = 'bestaudio/best'
 
     # --all-sub automatically sets --write-sub if --write-auto-sub is not given
     # this was the old behaviour if only --all-sub was given.
@@ -579,28 +717,33 @@ def _real_main(argv=None):
             or (opts.usetitle and u'%(title)s-%(id)s.%(ext)s')
             or (opts.useid and u'%(id)s.%(ext)s')
             or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
-            or u'%(title)s-%(id)s.%(ext)s')
-    if '%(ext)s' not in outtmpl and opts.extractaudio:
+            or DEFAULT_OUTTMPL)
+    if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
         parser.error(u'Cannot download a video and extract audio into the same'
-                     u' file! Use "%%(ext)s" instead of %r' %
-                     determine_ext(outtmpl, u''))
+                     u' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
+                     u' template'.format(outtmpl))
+
+    any_printing = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson
+    download_archive_fn = os.path.expanduser(opts.download_archive) if opts.download_archive is not None else opts.download_archive
 
     ydl_opts = {
         'usenetrc': opts.usenetrc,
         'username': opts.username,
         'password': opts.password,
         'videopassword': opts.videopassword,
-        'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.dumpjson),
+        'quiet': (opts.quiet or any_printing),
+        'no_warnings': opts.no_warnings,
         'forceurl': opts.geturl,
         'forcetitle': opts.gettitle,
         'forceid': opts.getid,
         'forcethumbnail': opts.getthumbnail,
         'forcedescription': opts.getdescription,
+        'forceduration': opts.getduration,
         'forcefilename': opts.getfilename,
         'forceformat': opts.getformat,
         'forcejson': opts.dumpjson,
         'simulate': opts.simulate,
-        'skip_download': (opts.skip_download or opts.simulate or opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.dumpjson),
+        'skip_download': (opts.skip_download or opts.simulate or any_printing),
         'format': opts.format,
         'format_limit': opts.format_limit,
         'listformats': opts.listformats,
@@ -644,13 +787,25 @@ def _real_main(argv=None):
         'keepvideo': opts.keepvideo,
         'min_filesize': opts.min_filesize,
         'max_filesize': opts.max_filesize,
+        'min_views': opts.min_views,
+        'max_views': opts.max_views,
         'daterange': date,
         'cachedir': opts.cachedir,
         'youtube_print_sig_code': opts.youtube_print_sig_code,
         'age_limit': opts.age_limit,
-        'download_archive': opts.download_archive,
+        'download_archive': download_archive_fn,
         'cookiefile': opts.cookiefile,
         'nocheckcertificate': opts.no_check_certificate,
+        'prefer_insecure': opts.prefer_insecure,
+        'proxy': opts.proxy,
+        'socket_timeout': opts.socket_timeout,
+        'bidi_workaround': opts.bidi_workaround,
+        'debug_printtraffic': opts.debug_printtraffic,
+        'prefer_ffmpeg': opts.prefer_ffmpeg,
+        'include_ads': opts.include_ads,
+        'default_search': opts.default_search,
+        'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
+        'encoding': opts.encoding,
     }
 
     with YoutubeDL(ydl_opts) as ydl:
@@ -667,20 +822,29 @@ def _real_main(argv=None):
             ydl.add_post_processor(FFmpegVideoConvertor(preferedformat=opts.recodevideo))
         if opts.embedsubtitles:
             ydl.add_post_processor(FFmpegEmbedSubtitlePP(subtitlesformat=opts.subtitlesformat))
+        if opts.xattrs:
+            ydl.add_post_processor(XAttrMetadataPP())
+        if opts.embedthumbnail:
+            if not opts.addmetadata:
+                ydl.add_post_processor(FFmpegAudioFixPP())
+            ydl.add_post_processor(AtomicParsleyPP())
 
         # Update version
         if opts.update_self:
             update_self(ydl.to_screen, opts.verbose)
 
         # Maybe do nothing
-        if len(all_urls) < 1:
+        if (len(all_urls) < 1) and (opts.load_info_filename is None):
             if not opts.update_self:
                 parser.error(u'you must provide at least one URL')
             else:
                 sys.exit()
 
         try:
-            retcode = ydl.download(all_urls)
+            if opts.load_info_filename is not None:
+                retcode = ydl.download_with_info_file(opts.load_info_filename)
+            else:
+                retcode = ydl.download(all_urls)
         except MaxDownloadsReached:
             ydl.to_screen(u'--max-download limit reached, aborting.')
             retcode = 101

youtube_dl/aes.py

@@ -1,4 +1,4 @@
-__all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_decrypt_text']
+__all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_cbc_decrypt', 'aes_decrypt_text']
 
 import base64
 from math import ceil
@@ -32,6 +32,31 @@ def aes_ctr_decrypt(data, key, counter):
     
     return decrypted_data
 
+def aes_cbc_decrypt(data, key, iv):
+    """
+    Decrypt with aes in CBC mode
+    
+    @param {int[]} data        cipher
+    @param {int[]} key         16/24/32-Byte cipher key
+    @param {int[]} iv          16-Byte IV
+    @returns {int[]}           decrypted data
+    """
+    expanded_key = key_expansion(key)
+    block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES))
+    
+    decrypted_data=[]
+    previous_cipher_block = iv
+    for i in range(block_count):
+        block = data[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES]
+        block += [0]*(BLOCK_SIZE_BYTES - len(block))
+        
+        decrypted_block = aes_decrypt(block, expanded_key)
+        decrypted_data += xor(decrypted_block, previous_cipher_block)
+        previous_cipher_block = block
+    decrypted_data = decrypted_data[:len(data)]
+    
+    return decrypted_data
+
 def key_expansion(data):
     """
     Generate key schedule
@@ -75,7 +100,7 @@ def aes_encrypt(data, expanded_key):
     @returns {int[]}             16-Byte cipher
     """
     rounds = len(expanded_key) // BLOCK_SIZE_BYTES - 1
-    
+
     data = xor(data, expanded_key[:BLOCK_SIZE_BYTES])
     for i in range(1, rounds+1):
         data = sub_bytes(data)
@@ -83,6 +108,26 @@ def aes_encrypt(data, expanded_key):
         if i != rounds:
             data = mix_columns(data)
         data = xor(data, expanded_key[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES])
+
+    return data
+
+def aes_decrypt(data, expanded_key):
+    """
+    Decrypt one block with aes
+    
+    @param {int[]} data          16-Byte cipher
+    @param {int[]} expanded_key  176/208/240-Byte expanded key
+    @returns {int[]}             16-Byte state
+    """
+    rounds = len(expanded_key) // BLOCK_SIZE_BYTES - 1
+    
+    for i in range(rounds, 0, -1):
+        data = xor(data, expanded_key[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES])
+        if i != rounds:
+            data = mix_columns_inv(data)
+        data = shift_rows_inv(data)
+        data = sub_bytes_inv(data)
+    data = xor(data, expanded_key[:BLOCK_SIZE_BYTES])
     
     return data
 
@@ -139,14 +184,69 @@ SBOX = (0x63, 0x7C, 0x77, 0x7B, 0xF2, 0x6B, 0x6F, 0xC5, 0x30, 0x01, 0x67, 0x2B,
         0x70, 0x3E, 0xB5, 0x66, 0x48, 0x03, 0xF6, 0x0E, 0x61, 0x35, 0x57, 0xB9, 0x86, 0xC1, 0x1D, 0x9E,
         0xE1, 0xF8, 0x98, 0x11, 0x69, 0xD9, 0x8E, 0x94, 0x9B, 0x1E, 0x87, 0xE9, 0xCE, 0x55, 0x28, 0xDF,
         0x8C, 0xA1, 0x89, 0x0D, 0xBF, 0xE6, 0x42, 0x68, 0x41, 0x99, 0x2D, 0x0F, 0xB0, 0x54, 0xBB, 0x16)
-MIX_COLUMN_MATRIX = ((2,3,1,1),
-                     (1,2,3,1),
-                     (1,1,2,3),
-                     (3,1,1,2))
+SBOX_INV = (0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38, 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb,
+            0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87, 0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb,
+            0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d, 0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e,
+            0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2, 0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25,
+            0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16, 0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92,
+            0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda, 0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84,
+            0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a, 0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06,
+            0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02, 0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b,
+            0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea, 0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73,
+            0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85, 0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e,
+            0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89, 0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b,
+            0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20, 0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4,
+            0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31, 0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f,
+            0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d, 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef,
+            0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0, 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61,
+            0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26, 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d)
+MIX_COLUMN_MATRIX = ((0x2,0x3,0x1,0x1),
+                     (0x1,0x2,0x3,0x1),
+                     (0x1,0x1,0x2,0x3),
+                     (0x3,0x1,0x1,0x2))
+MIX_COLUMN_MATRIX_INV = ((0xE,0xB,0xD,0x9),
+                         (0x9,0xE,0xB,0xD),
+                         (0xD,0x9,0xE,0xB),
+                         (0xB,0xD,0x9,0xE))
+RIJNDAEL_EXP_TABLE = (0x01, 0x03, 0x05, 0x0F, 0x11, 0x33, 0x55, 0xFF, 0x1A, 0x2E, 0x72, 0x96, 0xA1, 0xF8, 0x13, 0x35,
+                      0x5F, 0xE1, 0x38, 0x48, 0xD8, 0x73, 0x95, 0xA4, 0xF7, 0x02, 0x06, 0x0A, 0x1E, 0x22, 0x66, 0xAA,
+                      0xE5, 0x34, 0x5C, 0xE4, 0x37, 0x59, 0xEB, 0x26, 0x6A, 0xBE, 0xD9, 0x70, 0x90, 0xAB, 0xE6, 0x31,
+                      0x53, 0xF5, 0x04, 0x0C, 0x14, 0x3C, 0x44, 0xCC, 0x4F, 0xD1, 0x68, 0xB8, 0xD3, 0x6E, 0xB2, 0xCD,
+                      0x4C, 0xD4, 0x67, 0xA9, 0xE0, 0x3B, 0x4D, 0xD7, 0x62, 0xA6, 0xF1, 0x08, 0x18, 0x28, 0x78, 0x88,
+                      0x83, 0x9E, 0xB9, 0xD0, 0x6B, 0xBD, 0xDC, 0x7F, 0x81, 0x98, 0xB3, 0xCE, 0x49, 0xDB, 0x76, 0x9A,
+                      0xB5, 0xC4, 0x57, 0xF9, 0x10, 0x30, 0x50, 0xF0, 0x0B, 0x1D, 0x27, 0x69, 0xBB, 0xD6, 0x61, 0xA3,
+                      0xFE, 0x19, 0x2B, 0x7D, 0x87, 0x92, 0xAD, 0xEC, 0x2F, 0x71, 0x93, 0xAE, 0xE9, 0x20, 0x60, 0xA0,
+                      0xFB, 0x16, 0x3A, 0x4E, 0xD2, 0x6D, 0xB7, 0xC2, 0x5D, 0xE7, 0x32, 0x56, 0xFA, 0x15, 0x3F, 0x41,
+                      0xC3, 0x5E, 0xE2, 0x3D, 0x47, 0xC9, 0x40, 0xC0, 0x5B, 0xED, 0x2C, 0x74, 0x9C, 0xBF, 0xDA, 0x75,
+                      0x9F, 0xBA, 0xD5, 0x64, 0xAC, 0xEF, 0x2A, 0x7E, 0x82, 0x9D, 0xBC, 0xDF, 0x7A, 0x8E, 0x89, 0x80,
+                      0x9B, 0xB6, 0xC1, 0x58, 0xE8, 0x23, 0x65, 0xAF, 0xEA, 0x25, 0x6F, 0xB1, 0xC8, 0x43, 0xC5, 0x54,
+                      0xFC, 0x1F, 0x21, 0x63, 0xA5, 0xF4, 0x07, 0x09, 0x1B, 0x2D, 0x77, 0x99, 0xB0, 0xCB, 0x46, 0xCA,
+                      0x45, 0xCF, 0x4A, 0xDE, 0x79, 0x8B, 0x86, 0x91, 0xA8, 0xE3, 0x3E, 0x42, 0xC6, 0x51, 0xF3, 0x0E,
+                      0x12, 0x36, 0x5A, 0xEE, 0x29, 0x7B, 0x8D, 0x8C, 0x8F, 0x8A, 0x85, 0x94, 0xA7, 0xF2, 0x0D, 0x17,
+                      0x39, 0x4B, 0xDD, 0x7C, 0x84, 0x97, 0xA2, 0xFD, 0x1C, 0x24, 0x6C, 0xB4, 0xC7, 0x52, 0xF6, 0x01)
+RIJNDAEL_LOG_TABLE = (0x00, 0x00, 0x19, 0x01, 0x32, 0x02, 0x1a, 0xc6, 0x4b, 0xc7, 0x1b, 0x68, 0x33, 0xee, 0xdf, 0x03,
+                      0x64, 0x04, 0xe0, 0x0e, 0x34, 0x8d, 0x81, 0xef, 0x4c, 0x71, 0x08, 0xc8, 0xf8, 0x69, 0x1c, 0xc1,
+                      0x7d, 0xc2, 0x1d, 0xb5, 0xf9, 0xb9, 0x27, 0x6a, 0x4d, 0xe4, 0xa6, 0x72, 0x9a, 0xc9, 0x09, 0x78,
+                      0x65, 0x2f, 0x8a, 0x05, 0x21, 0x0f, 0xe1, 0x24, 0x12, 0xf0, 0x82, 0x45, 0x35, 0x93, 0xda, 0x8e,
+                      0x96, 0x8f, 0xdb, 0xbd, 0x36, 0xd0, 0xce, 0x94, 0x13, 0x5c, 0xd2, 0xf1, 0x40, 0x46, 0x83, 0x38,
+                      0x66, 0xdd, 0xfd, 0x30, 0xbf, 0x06, 0x8b, 0x62, 0xb3, 0x25, 0xe2, 0x98, 0x22, 0x88, 0x91, 0x10,
+                      0x7e, 0x6e, 0x48, 0xc3, 0xa3, 0xb6, 0x1e, 0x42, 0x3a, 0x6b, 0x28, 0x54, 0xfa, 0x85, 0x3d, 0xba,
+                      0x2b, 0x79, 0x0a, 0x15, 0x9b, 0x9f, 0x5e, 0xca, 0x4e, 0xd4, 0xac, 0xe5, 0xf3, 0x73, 0xa7, 0x57,
+                      0xaf, 0x58, 0xa8, 0x50, 0xf4, 0xea, 0xd6, 0x74, 0x4f, 0xae, 0xe9, 0xd5, 0xe7, 0xe6, 0xad, 0xe8,
+                      0x2c, 0xd7, 0x75, 0x7a, 0xeb, 0x16, 0x0b, 0xf5, 0x59, 0xcb, 0x5f, 0xb0, 0x9c, 0xa9, 0x51, 0xa0,
+                      0x7f, 0x0c, 0xf6, 0x6f, 0x17, 0xc4, 0x49, 0xec, 0xd8, 0x43, 0x1f, 0x2d, 0xa4, 0x76, 0x7b, 0xb7,
+                      0xcc, 0xbb, 0x3e, 0x5a, 0xfb, 0x60, 0xb1, 0x86, 0x3b, 0x52, 0xa1, 0x6c, 0xaa, 0x55, 0x29, 0x9d,
+                      0x97, 0xb2, 0x87, 0x90, 0x61, 0xbe, 0xdc, 0xfc, 0xbc, 0x95, 0xcf, 0xcd, 0x37, 0x3f, 0x5b, 0xd1,
+                      0x53, 0x39, 0x84, 0x3c, 0x41, 0xa2, 0x6d, 0x47, 0x14, 0x2a, 0x9e, 0x5d, 0x56, 0xf2, 0xd3, 0xab,
+                      0x44, 0x11, 0x92, 0xd9, 0x23, 0x20, 0x2e, 0x89, 0xb4, 0x7c, 0xb8, 0x26, 0x77, 0x99, 0xe3, 0xa5,
+                      0x67, 0x4a, 0xed, 0xde, 0xc5, 0x31, 0xfe, 0x18, 0x0d, 0x63, 0x8c, 0x80, 0xc0, 0xf7, 0x70, 0x07)
 
 def sub_bytes(data):
     return [SBOX[x] for x in data]
 
+def sub_bytes_inv(data):
+    return [SBOX_INV[x] for x in data]
+
 def rotate(data):
     return data[1:] + [data[0]]
 
@@ -160,30 +260,31 @@ def key_schedule_core(data, rcon_iteration):
 def xor(data1, data2):
     return [x^y for x, y in zip(data1, data2)]
 
-def mix_column(data):
+def rijndael_mul(a, b):
+    if(a==0 or b==0):
+        return 0
+    return RIJNDAEL_EXP_TABLE[(RIJNDAEL_LOG_TABLE[a] + RIJNDAEL_LOG_TABLE[b]) % 0xFF]
+
+def mix_column(data, matrix):
     data_mixed = []
     for row in range(4):
         mixed = 0
         for column in range(4):
-            addend = data[column]
-            if MIX_COLUMN_MATRIX[row][column] in (2,3):
-                addend <<= 1
-                if addend > 0xff:
-                    addend &= 0xff
-                    addend ^= 0x1b
-                if MIX_COLUMN_MATRIX[row][column] == 3:
-                    addend ^= data[column]
-            mixed ^= addend & 0xff
+            # xor is (+) and (-)
+            mixed ^= rijndael_mul(data[column], matrix[row][column])
         data_mixed.append(mixed)
     return data_mixed
 
-def mix_columns(data):
+def mix_columns(data, matrix=MIX_COLUMN_MATRIX):
     data_mixed = []
     for i in range(4):
         column = data[i*4 : (i+1)*4]
-        data_mixed += mix_column(column)
+        data_mixed += mix_column(column, matrix)
     return data_mixed
 
+def mix_columns_inv(data):
+    return mix_columns(data, MIX_COLUMN_MATRIX_INV)
+
 def shift_rows(data):
     data_shifted = []
     for column in range(4):
@@ -191,6 +292,13 @@ def shift_rows(data):
             data_shifted.append( data[((column + row) & 0b11) * 4 + row] )
     return data_shifted
 
+def shift_rows_inv(data):
+    data_shifted = []
+    for column in range(4):
+        for row in range(4):
+            data_shifted.append( data[((column - row) & 0b11) * 4 + row] )
+    return data_shifted
+
 def inc(data):
     data = data[:] # copy
     for i in range(len(data)-1,-1,-1):

youtube_dl/downloader/__init__.py

@@ -0,0 +1,29 @@
+from __future__ import unicode_literals
+
+from .common import FileDownloader
+from .hls import HlsFD
+from .http import HttpFD
+from .mplayer import MplayerFD
+from .rtmp import RtmpFD
+from .f4m import F4mFD
+
+from ..utils import (
+    determine_ext,
+)
+
+
+def get_suitable_downloader(info_dict):
+    """Get the downloader class that can handle the info dict."""
+    url = info_dict['url']
+    protocol = info_dict.get('protocol')
+
+    if url.startswith('rtmp'):
+        return RtmpFD
+    if (protocol == 'm3u8') or (protocol is None and determine_ext(url) == 'm3u8'):
+        return HlsFD
+    if url.startswith('mms') or url.startswith('rtsp'):
+        return MplayerFD
+    if determine_ext(url) == 'f4m':
+        return F4mFD
+    else:
+        return HttpFD

youtube_dl/downloader/common.py

@@ -0,0 +1,317 @@
+import os
+import re
+import sys
+import time
+
+from ..utils import (
+    compat_str,
+    encodeFilename,
+    format_bytes,
+    timeconvert,
+)
+
+
+class FileDownloader(object):
+    """File Downloader class.
+
+    File downloader objects are the ones responsible of downloading the
+    actual video file and writing it to disk.
+
+    File downloaders accept a lot of parameters. In order not to saturate
+    the object constructor with arguments, it receives a dictionary of
+    options instead.
+
+    Available options:
+
+    verbose:           Print additional info to stdout.
+    quiet:             Do not print messages to stdout.
+    ratelimit:         Download speed limit, in bytes/sec.
+    retries:           Number of times to retry for HTTP error 5xx
+    buffersize:        Size of download buffer in bytes.
+    noresizebuffer:    Do not automatically resize the download buffer.
+    continuedl:        Try to continue downloads if possible.
+    noprogress:        Do not print the progress bar.
+    logtostderr:       Log messages to stderr instead of stdout.
+    consoletitle:      Display progress in console window's titlebar.
+    nopart:            Do not use temporary .part files.
+    updatetime:        Use the Last-modified header to set output file timestamps.
+    test:              Download only first bytes to test the downloader.
+    min_filesize:      Skip files smaller than this size
+    max_filesize:      Skip files larger than this size
+
+    Subclasses of this one must re-define the real_download method.
+    """
+
+    params = None
+
+    def __init__(self, ydl, params):
+        """Create a FileDownloader object with the given options."""
+        self.ydl = ydl
+        self._progress_hooks = []
+        self.params = params
+
+    @staticmethod
+    def format_seconds(seconds):
+        (mins, secs) = divmod(seconds, 60)
+        (hours, mins) = divmod(mins, 60)
+        if hours > 99:
+            return '--:--:--'
+        if hours == 0:
+            return '%02d:%02d' % (mins, secs)
+        else:
+            return '%02d:%02d:%02d' % (hours, mins, secs)
+
+    @staticmethod
+    def calc_percent(byte_counter, data_len):
+        if data_len is None:
+            return None
+        return float(byte_counter) / float(data_len) * 100.0
+
+    @staticmethod
+    def format_percent(percent):
+        if percent is None:
+            return '---.-%'
+        return '%6s' % ('%3.1f%%' % percent)
+
+    @staticmethod
+    def calc_eta(start, now, total, current):
+        if total is None:
+            return None
+        dif = now - start
+        if current == 0 or dif < 0.001: # One millisecond
+            return None
+        rate = float(current) / dif
+        return int((float(total) - float(current)) / rate)
+
+    @staticmethod
+    def format_eta(eta):
+        if eta is None:
+            return '--:--'
+        return FileDownloader.format_seconds(eta)
+
+    @staticmethod
+    def calc_speed(start, now, bytes):
+        dif = now - start
+        if bytes == 0 or dif < 0.001: # One millisecond
+            return None
+        return float(bytes) / dif
+
+    @staticmethod
+    def format_speed(speed):
+        if speed is None:
+            return '%10s' % '---b/s'
+        return '%10s' % ('%s/s' % format_bytes(speed))
+
+    @staticmethod
+    def best_block_size(elapsed_time, bytes):
+        new_min = max(bytes / 2.0, 1.0)
+        new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB
+        if elapsed_time < 0.001:
+            return int(new_max)
+        rate = bytes / elapsed_time
+        if rate > new_max:
+            return int(new_max)
+        if rate < new_min:
+            return int(new_min)
+        return int(rate)
+
+    @staticmethod
+    def parse_bytes(bytestr):
+        """Parse a string indicating a byte quantity into an integer."""
+        matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr)
+        if matchobj is None:
+            return None
+        number = float(matchobj.group(1))
+        multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
+        return int(round(number * multiplier))
+
+    def to_screen(self, *args, **kargs):
+        self.ydl.to_screen(*args, **kargs)
+
+    def to_stderr(self, message):
+        self.ydl.to_screen(message)
+
+    def to_console_title(self, message):
+        self.ydl.to_console_title(message)
+
+    def trouble(self, *args, **kargs):
+        self.ydl.trouble(*args, **kargs)
+
+    def report_warning(self, *args, **kargs):
+        self.ydl.report_warning(*args, **kargs)
+
+    def report_error(self, *args, **kargs):
+        self.ydl.report_error(*args, **kargs)
+
+    def slow_down(self, start_time, byte_counter):
+        """Sleep if the download speed is over the rate limit."""
+        rate_limit = self.params.get('ratelimit', None)
+        if rate_limit is None or byte_counter == 0:
+            return
+        now = time.time()
+        elapsed = now - start_time
+        if elapsed <= 0.0:
+            return
+        speed = float(byte_counter) / elapsed
+        if speed > rate_limit:
+            time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit)
+
+    def temp_name(self, filename):
+        """Returns a temporary filename for the given filename."""
+        if self.params.get('nopart', False) or filename == u'-' or \
+                (os.path.exists(encodeFilename(filename)) and not os.path.isfile(encodeFilename(filename))):
+            return filename
+        return filename + u'.part'
+
+    def undo_temp_name(self, filename):
+        if filename.endswith(u'.part'):
+            return filename[:-len(u'.part')]
+        return filename
+
+    def try_rename(self, old_filename, new_filename):
+        try:
+            if old_filename == new_filename:
+                return
+            os.rename(encodeFilename(old_filename), encodeFilename(new_filename))
+        except (IOError, OSError) as err:
+            self.report_error(u'unable to rename file: %s' % compat_str(err))
+
+    def try_utime(self, filename, last_modified_hdr):
+        """Try to set the last-modified time of the given file."""
+        if last_modified_hdr is None:
+            return
+        if not os.path.isfile(encodeFilename(filename)):
+            return
+        timestr = last_modified_hdr
+        if timestr is None:
+            return
+        filetime = timeconvert(timestr)
+        if filetime is None:
+            return filetime
+        # Ignore obviously invalid dates
+        if filetime == 0:
+            return
+        try:
+            os.utime(filename, (time.time(), filetime))
+        except:
+            pass
+        return filetime
+
+    def report_destination(self, filename):
+        """Report destination filename."""
+        self.to_screen(u'[download] Destination: ' + filename)
+
+    def _report_progress_status(self, msg, is_last_line=False):
+        fullmsg = u'[download] ' + msg
+        if self.params.get('progress_with_newline', False):
+            self.to_screen(fullmsg)
+        else:
+            if os.name == 'nt':
+                prev_len = getattr(self, '_report_progress_prev_line_length',
+                                   0)
+                if prev_len > len(fullmsg):
+                    fullmsg += u' ' * (prev_len - len(fullmsg))
+                self._report_progress_prev_line_length = len(fullmsg)
+                clear_line = u'\r'
+            else:
+                clear_line = (u'\r\x1b[K' if sys.stderr.isatty() else u'\r')
+            self.to_screen(clear_line + fullmsg, skip_eol=not is_last_line)
+        self.to_console_title(u'youtube-dl ' + msg)
+
+    def report_progress(self, percent, data_len_str, speed, eta):
+        """Report download progress."""
+        if self.params.get('noprogress', False):
+            return
+        if eta is not None:
+            eta_str = self.format_eta(eta)
+        else:
+            eta_str = 'Unknown ETA'
+        if percent is not None:
+            percent_str = self.format_percent(percent)
+        else:
+            percent_str = 'Unknown %'
+        speed_str = self.format_speed(speed)
+
+        msg = (u'%s of %s at %s ETA %s' %
+               (percent_str, data_len_str, speed_str, eta_str))
+        self._report_progress_status(msg)
+
+    def report_progress_live_stream(self, downloaded_data_len, speed, elapsed):
+        if self.params.get('noprogress', False):
+            return
+        downloaded_str = format_bytes(downloaded_data_len)
+        speed_str = self.format_speed(speed)
+        elapsed_str = FileDownloader.format_seconds(elapsed)
+        msg = u'%s at %s (%s)' % (downloaded_str, speed_str, elapsed_str)
+        self._report_progress_status(msg)
+
+    def report_finish(self, data_len_str, tot_time):
+        """Report download finished."""
+        if self.params.get('noprogress', False):
+            self.to_screen(u'[download] Download completed')
+        else:
+            self._report_progress_status(
+                (u'100%% of %s in %s' %
+                 (data_len_str, self.format_seconds(tot_time))),
+                is_last_line=True)
+
+    def report_resuming_byte(self, resume_len):
+        """Report attempt to resume at given byte."""
+        self.to_screen(u'[download] Resuming download at byte %s' % resume_len)
+
+    def report_retry(self, count, retries):
+        """Report retry in case of HTTP error 5xx"""
+        self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries))
+
+    def report_file_already_downloaded(self, file_name):
+        """Report file has already been fully downloaded."""
+        try:
+            self.to_screen(u'[download] %s has already been downloaded' % file_name)
+        except UnicodeEncodeError:
+            self.to_screen(u'[download] The file has already been downloaded')
+
+    def report_unable_to_resume(self):
+        """Report it was impossible to resume download."""
+        self.to_screen(u'[download] Unable to resume')
+
+    def download(self, filename, info_dict):
+        """Download to a filename using the info from info_dict
+        Return True on success and False otherwise
+        """
+        # Check file already present
+        if self.params.get('continuedl', False) and os.path.isfile(encodeFilename(filename)) and not self.params.get('nopart', False):
+            self.report_file_already_downloaded(filename)
+            self._hook_progress({
+                'filename': filename,
+                'status': 'finished',
+                'total_bytes': os.path.getsize(encodeFilename(filename)),
+            })
+            return True
+
+        return self.real_download(filename, info_dict)
+
+    def real_download(self, filename, info_dict):
+        """Real download process. Redefine in subclasses."""
+        raise NotImplementedError(u'This method must be implemented by sublcasses')
+
+    def _hook_progress(self, status):
+        for ph in self._progress_hooks:
+            ph(status)
+
+    def add_progress_hook(self, ph):
+        """ ph gets called on download progress, with a dictionary with the entries
+        * filename: The final filename
+        * status: One of "downloading" and "finished"
+
+        It can also have some of the following entries:
+
+        * downloaded_bytes: Bytes on disks
+        * total_bytes: Total bytes, None if unknown
+        * tmpfilename: The filename we're currently writing to
+        * eta: The estimated time in seconds, None if unknown
+        * speed: The download speed in bytes/second, None if unknown
+
+        Hooks are guaranteed to be called at least once (with status "finished")
+        if the download is successful.
+        """
+        self._progress_hooks.append(ph)

youtube_dl/downloader/f4m.py

@@ -0,0 +1,315 @@
+from __future__ import unicode_literals
+
+import base64
+import io
+import itertools
+import os
+import time
+import xml.etree.ElementTree as etree
+
+from .common import FileDownloader
+from .http import HttpFD
+from ..utils import (
+    struct_pack,
+    struct_unpack,
+    compat_urlparse,
+    format_bytes,
+    encodeFilename,
+    sanitize_open,
+)
+
+
+class FlvReader(io.BytesIO):
+    """
+    Reader for Flv files
+    The file format is documented in https://www.adobe.com/devnet/f4v.html
+    """
+
+    # Utility functions for reading numbers and strings
+    def read_unsigned_long_long(self):
+        return struct_unpack('!Q', self.read(8))[0]
+
+    def read_unsigned_int(self):
+        return struct_unpack('!I', self.read(4))[0]
+
+    def read_unsigned_char(self):
+        return struct_unpack('!B', self.read(1))[0]
+
+    def read_string(self):
+        res = b''
+        while True:
+            char = self.read(1)
+            if char == b'\x00':
+                break
+            res += char
+        return res
+
+    def read_box_info(self):
+        """
+        Read a box and return the info as a tuple: (box_size, box_type, box_data)
+        """
+        real_size = size = self.read_unsigned_int()
+        box_type = self.read(4)
+        header_end = 8
+        if size == 1:
+            real_size = self.read_unsigned_long_long()
+            header_end = 16
+        return real_size, box_type, self.read(real_size-header_end)
+
+    def read_asrt(self):
+        # version
+        self.read_unsigned_char()
+        # flags
+        self.read(3)
+        quality_entry_count = self.read_unsigned_char()
+        # QualityEntryCount
+        for i in range(quality_entry_count):
+            self.read_string()
+
+        segment_run_count = self.read_unsigned_int()
+        segments = []
+        for i in range(segment_run_count):
+            first_segment = self.read_unsigned_int()
+            fragments_per_segment = self.read_unsigned_int()
+            segments.append((first_segment, fragments_per_segment))
+
+        return {
+            'segment_run': segments,
+        }
+
+    def read_afrt(self):
+        # version
+        self.read_unsigned_char()
+        # flags
+        self.read(3)
+        # time scale
+        self.read_unsigned_int()
+
+        quality_entry_count = self.read_unsigned_char()
+        # QualitySegmentUrlModifiers
+        for i in range(quality_entry_count):
+            self.read_string()
+
+        fragments_count = self.read_unsigned_int()
+        fragments = []
+        for i in range(fragments_count):
+            first = self.read_unsigned_int()
+            first_ts = self.read_unsigned_long_long()
+            duration = self.read_unsigned_int()
+            if duration == 0:
+                discontinuity_indicator = self.read_unsigned_char()
+            else:
+                discontinuity_indicator = None
+            fragments.append({
+                'first': first,
+                'ts': first_ts,
+                'duration': duration,
+                'discontinuity_indicator': discontinuity_indicator,
+            })
+
+        return {
+            'fragments': fragments,
+        }
+
+    def read_abst(self):
+        # version
+        self.read_unsigned_char()
+        # flags
+        self.read(3)
+
+        self.read_unsigned_int()  # BootstrapinfoVersion
+        # Profile,Live,Update,Reserved
+        self.read(1)
+        # time scale
+        self.read_unsigned_int()
+        # CurrentMediaTime
+        self.read_unsigned_long_long()
+        # SmpteTimeCodeOffset
+        self.read_unsigned_long_long()
+
+        self.read_string()  # MovieIdentifier
+        server_count = self.read_unsigned_char()
+        # ServerEntryTable
+        for i in range(server_count):
+            self.read_string()
+        quality_count = self.read_unsigned_char()
+        # QualityEntryTable
+        for i in range(quality_count):
+            self.read_string()
+        # DrmData
+        self.read_string()
+        # MetaData
+        self.read_string()
+
+        segments_count = self.read_unsigned_char()
+        segments = []
+        for i in range(segments_count):
+            box_size, box_type, box_data = self.read_box_info()
+            assert box_type == b'asrt'
+            segment = FlvReader(box_data).read_asrt()
+            segments.append(segment)
+        fragments_run_count = self.read_unsigned_char()
+        fragments = []
+        for i in range(fragments_run_count):
+            box_size, box_type, box_data = self.read_box_info()
+            assert box_type == b'afrt'
+            fragments.append(FlvReader(box_data).read_afrt())
+
+        return {
+            'segments': segments,
+            'fragments': fragments,
+        }
+
+    def read_bootstrap_info(self):
+        total_size, box_type, box_data = self.read_box_info()
+        assert box_type == b'abst'
+        return FlvReader(box_data).read_abst()
+
+
+def read_bootstrap_info(bootstrap_bytes):
+    return FlvReader(bootstrap_bytes).read_bootstrap_info()
+
+
+def build_fragments_list(boot_info):
+    """ Return a list of (segment, fragment) for each fragment in the video """
+    res = []
+    segment_run_table = boot_info['segments'][0]
+    # I've only found videos with one segment
+    segment_run_entry = segment_run_table['segment_run'][0]
+    n_frags = segment_run_entry[1]
+    fragment_run_entry_table = boot_info['fragments'][0]['fragments']
+    first_frag_number = fragment_run_entry_table[0]['first']
+    for (i, frag_number) in zip(range(1, n_frags+1), itertools.count(first_frag_number)):
+        res.append((1, frag_number))
+    return res
+
+
+def write_flv_header(stream, metadata):
+    """Writes the FLV header and the metadata to stream"""
+    # FLV header
+    stream.write(b'FLV\x01')
+    stream.write(b'\x05')
+    stream.write(b'\x00\x00\x00\x09')
+    # FLV File body
+    stream.write(b'\x00\x00\x00\x00')
+    # FLVTAG
+    # Script data
+    stream.write(b'\x12')
+    # Size of the metadata with 3 bytes
+    stream.write(struct_pack('!L', len(metadata))[1:])
+    stream.write(b'\x00\x00\x00\x00\x00\x00\x00')
+    stream.write(metadata)
+    # Magic numbers extracted from the output files produced by AdobeHDS.php
+    #(https://github.com/K-S-V/Scripts)
+    stream.write(b'\x00\x00\x01\x73')
+
+
+def _add_ns(prop):
+    return '{http://ns.adobe.com/f4m/1.0}%s' % prop
+
+
+class HttpQuietDownloader(HttpFD):
+    def to_screen(self, *args, **kargs):
+        pass
+
+
+class F4mFD(FileDownloader):
+    """
+    A downloader for f4m manifests or AdobeHDS.
+    """
+
+    def real_download(self, filename, info_dict):
+        man_url = info_dict['url']
+        self.to_screen('[download] Downloading f4m manifest')
+        manifest = self.ydl.urlopen(man_url).read()
+        self.report_destination(filename)
+        http_dl = HttpQuietDownloader(self.ydl,
+            {
+                'continuedl': True,
+                'quiet': True,
+                'noprogress': True,
+                'test': self.params.get('test', False),
+            })
+
+        doc = etree.fromstring(manifest)
+        formats = [(int(f.attrib.get('bitrate', -1)), f) for f in doc.findall(_add_ns('media'))]
+        formats = sorted(formats, key=lambda f: f[0])
+        rate, media = formats[-1]
+        base_url = compat_urlparse.urljoin(man_url, media.attrib['url'])
+        bootstrap = base64.b64decode(doc.find(_add_ns('bootstrapInfo')).text)
+        metadata = base64.b64decode(media.find(_add_ns('metadata')).text)
+        boot_info = read_bootstrap_info(bootstrap)
+        fragments_list = build_fragments_list(boot_info)
+        if self.params.get('test', False):
+            # We only download the first fragment
+            fragments_list = fragments_list[:1]
+        total_frags = len(fragments_list)
+
+        tmpfilename = self.temp_name(filename)
+        (dest_stream, tmpfilename) = sanitize_open(tmpfilename, 'wb')
+        write_flv_header(dest_stream, metadata)
+
+        # This dict stores the download progress, it's updated by the progress
+        # hook
+        state = {
+            'downloaded_bytes': 0,
+            'frag_counter': 0,
+        }
+        start = time.time()
+
+        def frag_progress_hook(status):
+            frag_total_bytes = status.get('total_bytes', 0)
+            estimated_size = (state['downloaded_bytes'] +
+                (total_frags - state['frag_counter']) * frag_total_bytes)
+            if status['status'] == 'finished':
+                state['downloaded_bytes'] += frag_total_bytes
+                state['frag_counter'] += 1
+                progress = self.calc_percent(state['frag_counter'], total_frags)
+                byte_counter = state['downloaded_bytes']
+            else:
+                frag_downloaded_bytes = status['downloaded_bytes']
+                byte_counter = state['downloaded_bytes'] + frag_downloaded_bytes
+                frag_progress = self.calc_percent(frag_downloaded_bytes,
+                    frag_total_bytes)
+                progress = self.calc_percent(state['frag_counter'], total_frags)
+                progress += frag_progress / float(total_frags)
+
+            eta = self.calc_eta(start, time.time(), estimated_size, byte_counter)
+            self.report_progress(progress, format_bytes(estimated_size),
+                status.get('speed'), eta)
+        http_dl.add_progress_hook(frag_progress_hook)
+
+        frags_filenames = []
+        for (seg_i, frag_i) in fragments_list:
+            name = 'Seg%d-Frag%d' % (seg_i, frag_i)
+            url = base_url + name
+            frag_filename = '%s-%s' % (tmpfilename, name)
+            success = http_dl.download(frag_filename, {'url': url})
+            if not success:
+                return False
+            with open(frag_filename, 'rb') as down:
+                down_data = down.read()
+                reader = FlvReader(down_data)
+                while True:
+                    _, box_type, box_data = reader.read_box_info()
+                    if box_type == b'mdat':
+                        dest_stream.write(box_data)
+                        break
+            frags_filenames.append(frag_filename)
+
+        dest_stream.close()
+        self.report_finish(format_bytes(state['downloaded_bytes']), time.time() - start)
+
+        self.try_rename(tmpfilename, filename)
+        for frag_file in frags_filenames:
+            os.remove(frag_file)
+
+        fsize = os.path.getsize(encodeFilename(filename))
+        self._hook_progress({
+            'downloaded_bytes': fsize,
+            'total_bytes': fsize,
+            'filename': filename,
+            'status': 'finished',
+        })
+
+        return True

youtube_dl/downloader/hls.py

@@ -0,0 +1,46 @@
+import os
+import subprocess
+
+from .common import FileDownloader
+from ..utils import (
+    encodeFilename,
+)
+
+
+class HlsFD(FileDownloader):
+    def real_download(self, filename, info_dict):
+        url = info_dict['url']
+        self.report_destination(filename)
+        tmpfilename = self.temp_name(filename)
+
+        args = [
+            '-y', '-i', url, '-f', 'mp4', '-c', 'copy',
+            '-bsf:a', 'aac_adtstoasc',
+            encodeFilename(tmpfilename, for_subprocess=True)]
+
+        for program in ['avconv', 'ffmpeg']:
+            try:
+                subprocess.call([program, '-version'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
+                break
+            except (OSError, IOError):
+                pass
+        else:
+            self.report_error(u'm3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
+        cmd = [program] + args
+
+        retval = subprocess.call(cmd)
+        if retval == 0:
+            fsize = os.path.getsize(encodeFilename(tmpfilename))
+            self.to_screen(u'\r[%s] %s bytes' % (cmd[0], fsize))
+            self.try_rename(tmpfilename, filename)
+            self._hook_progress({
+                'downloaded_bytes': fsize,
+                'total_bytes': fsize,
+                'filename': filename,
+                'status': 'finished',
+            })
+            return True
+        else:
+            self.to_stderr(u"\n")
+            self.report_error(u'ffmpeg exited with code %d' % retval)
+            return False

youtube_dl/downloader/http.py

@@ -0,0 +1,205 @@
+import os
+import time
+
+from .common import FileDownloader
+from ..utils import (
+    compat_urllib_request,
+    compat_urllib_error,
+    ContentTooShortError,
+
+    encodeFilename,
+    sanitize_open,
+    format_bytes,
+)
+
+
+class HttpFD(FileDownloader):
+    _TEST_FILE_SIZE = 10241
+
+    def real_download(self, filename, info_dict):
+        url = info_dict['url']
+        tmpfilename = self.temp_name(filename)
+        stream = None
+
+        # Do not include the Accept-Encoding header
+        headers = {'Youtubedl-no-compression': 'True'}
+        if 'user_agent' in info_dict:
+            headers['Youtubedl-user-agent'] = info_dict['user_agent']
+        if 'http_referer' in info_dict:
+            headers['Referer'] = info_dict['http_referer']
+        basic_request = compat_urllib_request.Request(url, None, headers)
+        request = compat_urllib_request.Request(url, None, headers)
+
+        is_test = self.params.get('test', False)
+
+        if is_test:
+            request.add_header('Range', 'bytes=0-%s' % str(self._TEST_FILE_SIZE - 1))
+
+        # Establish possible resume length
+        if os.path.isfile(encodeFilename(tmpfilename)):
+            resume_len = os.path.getsize(encodeFilename(tmpfilename))
+        else:
+            resume_len = 0
+
+        open_mode = 'wb'
+        if resume_len != 0:
+            if self.params.get('continuedl', False):
+                self.report_resuming_byte(resume_len)
+                request.add_header('Range', 'bytes=%d-' % resume_len)
+                open_mode = 'ab'
+            else:
+                resume_len = 0
+
+        count = 0
+        retries = self.params.get('retries', 0)
+        while count <= retries:
+            # Establish connection
+            try:
+                data = self.ydl.urlopen(request)
+                break
+            except (compat_urllib_error.HTTPError, ) as err:
+                if (err.code < 500 or err.code >= 600) and err.code != 416:
+                    # Unexpected HTTP error
+                    raise
+                elif err.code == 416:
+                    # Unable to resume (requested range not satisfiable)
+                    try:
+                        # Open the connection again without the range header
+                        data = self.ydl.urlopen(basic_request)
+                        content_length = data.info()['Content-Length']
+                    except (compat_urllib_error.HTTPError, ) as err:
+                        if err.code < 500 or err.code >= 600:
+                            raise
+                    else:
+                        # Examine the reported length
+                        if (content_length is not None and
+                                (resume_len - 100 < int(content_length) < resume_len + 100)):
+                            # The file had already been fully downloaded.
+                            # Explanation to the above condition: in issue #175 it was revealed that
+                            # YouTube sometimes adds or removes a few bytes from the end of the file,
+                            # changing the file size slightly and causing problems for some users. So
+                            # I decided to implement a suggested change and consider the file
+                            # completely downloaded if the file size differs less than 100 bytes from
+                            # the one in the hard drive.
+                            self.report_file_already_downloaded(filename)
+                            self.try_rename(tmpfilename, filename)
+                            self._hook_progress({
+                                'filename': filename,
+                                'status': 'finished',
+                            })
+                            return True
+                        else:
+                            # The length does not match, we start the download over
+                            self.report_unable_to_resume()
+                            resume_len = 0
+                            open_mode = 'wb'
+                            break
+            # Retry
+            count += 1
+            if count <= retries:
+                self.report_retry(count, retries)
+
+        if count > retries:
+            self.report_error(u'giving up after %s retries' % retries)
+            return False
+
+        data_len = data.info().get('Content-length', None)
+
+        # Range HTTP header may be ignored/unsupported by a webserver
+        # (e.g. extractor/scivee.py, extractor/bambuser.py).
+        # However, for a test we still would like to download just a piece of a file.
+        # To achieve this we limit data_len to _TEST_FILE_SIZE and manually control
+        # block size when downloading a file.
+        if is_test and (data_len is None or int(data_len) > self._TEST_FILE_SIZE):
+            data_len = self._TEST_FILE_SIZE
+
+        if data_len is not None:
+            data_len = int(data_len) + resume_len
+            min_data_len = self.params.get("min_filesize", None)
+            max_data_len = self.params.get("max_filesize", None)
+            if min_data_len is not None and data_len < min_data_len:
+                self.to_screen(u'\r[download] File is smaller than min-filesize (%s bytes < %s bytes). Aborting.' % (data_len, min_data_len))
+                return False
+            if max_data_len is not None and data_len > max_data_len:
+                self.to_screen(u'\r[download] File is larger than max-filesize (%s bytes > %s bytes). Aborting.' % (data_len, max_data_len))
+                return False
+
+        data_len_str = format_bytes(data_len)
+        byte_counter = 0 + resume_len
+        block_size = self.params.get('buffersize', 1024)
+        start = time.time()
+        while True:
+            # Download and write
+            before = time.time()
+            data_block = data.read(block_size if not is_test else min(block_size, data_len - byte_counter))
+            after = time.time()
+            if len(data_block) == 0:
+                break
+            byte_counter += len(data_block)
+
+            # Open file just in time
+            if stream is None:
+                try:
+                    (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode)
+                    assert stream is not None
+                    filename = self.undo_temp_name(tmpfilename)
+                    self.report_destination(filename)
+                except (OSError, IOError) as err:
+                    self.report_error(u'unable to open for writing: %s' % str(err))
+                    return False
+            try:
+                stream.write(data_block)
+            except (IOError, OSError) as err:
+                self.to_stderr(u"\n")
+                self.report_error(u'unable to write data: %s' % str(err))
+                return False
+            if not self.params.get('noresizebuffer', False):
+                block_size = self.best_block_size(after - before, len(data_block))
+
+            # Progress message
+            speed = self.calc_speed(start, time.time(), byte_counter - resume_len)
+            if data_len is None:
+                eta = percent = None
+            else:
+                percent = self.calc_percent(byte_counter, data_len)
+                eta = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
+            self.report_progress(percent, data_len_str, speed, eta)
+
+            self._hook_progress({
+                'downloaded_bytes': byte_counter,
+                'total_bytes': data_len,
+                'tmpfilename': tmpfilename,
+                'filename': filename,
+                'status': 'downloading',
+                'eta': eta,
+                'speed': speed,
+            })
+
+            if is_test and byte_counter == data_len:
+                break
+
+            # Apply rate limit
+            self.slow_down(start, byte_counter - resume_len)
+
+        if stream is None:
+            self.to_stderr(u"\n")
+            self.report_error(u'Did not get any data blocks')
+            return False
+        stream.close()
+        self.report_finish(data_len_str, (time.time() - start))
+        if data_len is not None and byte_counter != data_len:
+            raise ContentTooShortError(byte_counter, int(data_len))
+        self.try_rename(tmpfilename, filename)
+
+        # Update file modification time
+        if self.params.get('updatetime', True):
+            info_dict['filetime'] = self.try_utime(filename, data.info().get('last-modified', None))
+
+        self._hook_progress({
+            'downloaded_bytes': byte_counter,
+            'total_bytes': byte_counter,
+            'filename': filename,
+            'status': 'finished',
+        })
+
+        return True

youtube_dl/downloader/mplayer.py

@@ -0,0 +1,40 @@
+import os
+import subprocess
+
+from .common import FileDownloader
+from ..utils import (
+    encodeFilename,
+)
+
+
+class MplayerFD(FileDownloader):
+    def real_download(self, filename, info_dict):
+        url = info_dict['url']
+        self.report_destination(filename)
+        tmpfilename = self.temp_name(filename)
+
+        args = ['mplayer', '-really-quiet', '-vo', 'null', '-vc', 'dummy', '-dumpstream', '-dumpfile', tmpfilename, url]
+        # Check for mplayer first
+        try:
+            subprocess.call(['mplayer', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
+        except (OSError, IOError):
+            self.report_error(u'MMS or RTSP download detected but "%s" could not be run' % args[0])
+            return False
+
+        # Download using mplayer.
+        retval = subprocess.call(args)
+        if retval == 0:
+            fsize = os.path.getsize(encodeFilename(tmpfilename))
+            self.to_screen(u'\r[%s] %s bytes' % (args[0], fsize))
+            self.try_rename(tmpfilename, filename)
+            self._hook_progress({
+                'downloaded_bytes': fsize,
+                'total_bytes': fsize,
+                'filename': filename,
+                'status': 'finished',
+            })
+            return True
+        else:
+            self.to_stderr(u"\n")
+            self.report_error(u'mplayer exited with code %d' % retval)
+            return False

youtube_dl/downloader/rtmp.py

@@ -0,0 +1,202 @@
+from __future__ import unicode_literals
+
+import os
+import re
+import subprocess
+import sys
+import time
+
+from .common import FileDownloader
+from ..utils import (
+    encodeFilename,
+    format_bytes,
+    compat_str,
+)
+
+
+class RtmpFD(FileDownloader):
+    def real_download(self, filename, info_dict):
+        def run_rtmpdump(args):
+            start = time.time()
+            resume_percent = None
+            resume_downloaded_data_len = None
+            proc = subprocess.Popen(args, stderr=subprocess.PIPE)
+            cursor_in_new_line = True
+            proc_stderr_closed = False
+            while not proc_stderr_closed:
+                # read line from stderr
+                line = ''
+                while True:
+                    char = proc.stderr.read(1)
+                    if not char:
+                        proc_stderr_closed = True
+                        break
+                    if char in [b'\r', b'\n']:
+                        break
+                    line += char.decode('ascii', 'replace')
+                if not line:
+                    # proc_stderr_closed is True
+                    continue
+                mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec \(([0-9]{1,2}\.[0-9])%\)', line)
+                if mobj:
+                    downloaded_data_len = int(float(mobj.group(1))*1024)
+                    percent = float(mobj.group(2))
+                    if not resume_percent:
+                        resume_percent = percent
+                        resume_downloaded_data_len = downloaded_data_len
+                    eta = self.calc_eta(start, time.time(), 100-resume_percent, percent-resume_percent)
+                    speed = self.calc_speed(start, time.time(), downloaded_data_len-resume_downloaded_data_len)
+                    data_len = None
+                    if percent > 0:
+                        data_len = int(downloaded_data_len * 100 / percent)
+                    data_len_str = '~' + format_bytes(data_len)
+                    self.report_progress(percent, data_len_str, speed, eta)
+                    cursor_in_new_line = False
+                    self._hook_progress({
+                        'downloaded_bytes': downloaded_data_len,
+                        'total_bytes': data_len,
+                        'tmpfilename': tmpfilename,
+                        'filename': filename,
+                        'status': 'downloading',
+                        'eta': eta,
+                        'speed': speed,
+                    })
+                else:
+                    # no percent for live streams
+                    mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec', line)
+                    if mobj:
+                        downloaded_data_len = int(float(mobj.group(1))*1024)
+                        time_now = time.time()
+                        speed = self.calc_speed(start, time_now, downloaded_data_len)
+                        self.report_progress_live_stream(downloaded_data_len, speed, time_now - start)
+                        cursor_in_new_line = False
+                        self._hook_progress({
+                            'downloaded_bytes': downloaded_data_len,
+                            'tmpfilename': tmpfilename,
+                            'filename': filename,
+                            'status': 'downloading',
+                            'speed': speed,
+                        })
+                    elif self.params.get('verbose', False):
+                        if not cursor_in_new_line:
+                            self.to_screen('')
+                        cursor_in_new_line = True
+                        self.to_screen('[rtmpdump] '+line)
+            proc.wait()
+            if not cursor_in_new_line:
+                self.to_screen('')
+            return proc.returncode
+
+        url = info_dict['url']
+        player_url = info_dict.get('player_url', None)
+        page_url = info_dict.get('page_url', None)
+        app = info_dict.get('app', None)
+        play_path = info_dict.get('play_path', None)
+        tc_url = info_dict.get('tc_url', None)
+        flash_version = info_dict.get('flash_version', None)
+        live = info_dict.get('rtmp_live', False)
+        conn = info_dict.get('rtmp_conn', None)
+        protocol = info_dict.get('rtmp_protocol', None)
+
+        self.report_destination(filename)
+        tmpfilename = self.temp_name(filename)
+        test = self.params.get('test', False)
+
+        # Check for rtmpdump first
+        try:
+            subprocess.call(['rtmpdump', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
+        except (OSError, IOError):
+            self.report_error('RTMP download detected but "rtmpdump" could not be run. Please install it.')
+            return False
+
+        # Download using rtmpdump. rtmpdump returns exit code 2 when
+        # the connection was interrumpted and resuming appears to be
+        # possible. This is part of rtmpdump's normal usage, AFAIK.
+        basic_args = ['rtmpdump', '--verbose', '-r', url, '-o', tmpfilename]
+        if player_url is not None:
+            basic_args += ['--swfVfy', player_url]
+        if page_url is not None:
+            basic_args += ['--pageUrl', page_url]
+        if app is not None:
+            basic_args += ['--app', app]
+        if play_path is not None:
+            basic_args += ['--playpath', play_path]
+        if tc_url is not None:
+            basic_args += ['--tcUrl', url]
+        if test:
+            basic_args += ['--stop', '1']
+        if flash_version is not None:
+            basic_args += ['--flashVer', flash_version]
+        if live:
+            basic_args += ['--live']
+        if isinstance(conn, list):
+            for entry in conn:
+                basic_args += ['--conn', entry]
+        elif isinstance(conn, compat_str):
+            basic_args += ['--conn', conn]
+        if protocol is not None:
+            basic_args += ['--protocol', protocol]
+        args = basic_args + [[], ['--resume', '--skip', '1']][not live and self.params.get('continuedl', False)]
+
+        if sys.platform == 'win32' and sys.version_info < (3, 0):
+            # Windows subprocess module does not actually support Unicode
+            # on Python 2.x
+            # See http://stackoverflow.com/a/9951851/35070
+            subprocess_encoding = sys.getfilesystemencoding()
+            args = [a.encode(subprocess_encoding, 'ignore') for a in args]
+        else:
+            subprocess_encoding = None
+
+        if self.params.get('verbose', False):
+            if subprocess_encoding:
+                str_args = [
+                    a.decode(subprocess_encoding) if isinstance(a, bytes) else a
+                    for a in args]
+            else:
+                str_args = args
+            try:
+                import pipes
+                shell_quote = lambda args: ' '.join(map(pipes.quote, str_args))
+            except ImportError:
+                shell_quote = repr
+            self.to_screen('[debug] rtmpdump command line: ' + shell_quote(str_args))
+
+        RD_SUCCESS = 0
+        RD_FAILED = 1
+        RD_INCOMPLETE = 2
+        RD_NO_CONNECT = 3
+
+        retval = run_rtmpdump(args)
+
+        if retval == RD_NO_CONNECT:
+            self.report_error('[rtmpdump] Could not connect to RTMP server.')
+            return False
+
+        while (retval == RD_INCOMPLETE or retval == RD_FAILED) and not test and not live:
+            prevsize = os.path.getsize(encodeFilename(tmpfilename))
+            self.to_screen('[rtmpdump] %s bytes' % prevsize)
+            time.sleep(5.0) # This seems to be needed
+            retval = run_rtmpdump(basic_args + ['-e'] + [[], ['-k', '1']][retval == RD_FAILED])
+            cursize = os.path.getsize(encodeFilename(tmpfilename))
+            if prevsize == cursize and retval == RD_FAILED:
+                break
+             # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those
+            if prevsize == cursize and retval == RD_INCOMPLETE and cursize > 1024:
+                self.to_screen('[rtmpdump] Could not download the whole video. This can happen for some advertisements.')
+                retval = RD_SUCCESS
+                break
+        if retval == RD_SUCCESS or (test and retval == RD_INCOMPLETE):
+            fsize = os.path.getsize(encodeFilename(tmpfilename))
+            self.to_screen('[rtmpdump] %s bytes' % fsize)
+            self.try_rename(tmpfilename, filename)
+            self._hook_progress({
+                'downloaded_bytes': fsize,
+                'total_bytes': fsize,
+                'filename': filename,
+                'status': 'finished',
+            })
+            return True
+        else:
+            self.to_stderr('\n')
+            self.report_error('rtmpdump exited with code %d' % retval)
+            return False

youtube_dl/extractor/__init__.py

@@ -1,31 +1,61 @@
-from .appletrailers import AppleTrailersIE
+from .academicearth import AcademicEarthCourseIE
 from .addanime import AddAnimeIE
+from .adultswim import AdultSwimIE
+from .aftonbladet import AftonbladetIE
 from .anitube import AnitubeIE
+from .aol import AolIE
+from .allocine import AllocineIE
+from .aparat import AparatIE
+from .appletrailers import AppleTrailersIE
 from .archiveorg import ArchiveOrgIE
 from .ard import ARDIE
 from .arte import (
     ArteTvIE,
     ArteTVPlus7IE,
     ArteTVCreativeIE,
+    ArteTVConcertIE,
     ArteTVFutureIE,
+    ArteTVDDCIE,
+    ArteTVEmbedIE,
 )
 from .auengine import AUEngineIE
 from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE
+from .bbccouk import BBCCoUkIE
+from .bilibili import BiliBiliIE
+from .blinkx import BlinkxIE
 from .bliptv import BlipTVIE, BlipTVUserIE
 from .bloomberg import BloombergIE
+from .br import BRIE
 from .breakcom import BreakIE
 from .brightcove import BrightcoveIE
+from .byutv import BYUtvIE
 from .c56 import C56IE
+from .canal13cl import Canal13clIE
 from .canalplus import CanalplusIE
 from .canalc2 import Canalc2IE
+from .cbs import CBSIE
+from .cbsnews import CBSNewsIE
+from .ceskatelevize import CeskaTelevizeIE
+from .channel9 import Channel9IE
+from .chilloutzone import ChilloutzoneIE
 from .cinemassacre import CinemassacreIE
 from .clipfish import ClipfishIE
-from .cnn import CNNIE
+from .cliphunter import CliphunterIE
+from .clipsyndicate import ClipsyndicateIE
+from .clubic import ClubicIE
+from .cmt import CMTIE
+from .cnet import CNETIE
+from .cnn import (
+    CNNIE,
+    CNNBlogsIE,
+)
 from .collegehumor import CollegeHumorIE
 from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
 from .condenast import CondeNastIE
+from .cracked import CrackedIE
 from .criterion import CriterionIE
+from .crunchyroll import CrunchyrollIE
 from .cspan import CSpanIE
 from .d8 import D8IE
 from .dailymotion import (
@@ -34,160 +64,346 @@ from .dailymotion import (
     DailymotionUserIE,
 )
 from .daum import DaumIE
-from .depositfiles import DepositFilesIE
+from .dfb import DFBIE
 from .dotsub import DotsubIE
 from .dreisat import DreiSatIE
+from .drtv import DRTVIE
 from .defense import DefenseGouvFrIE
+from .discovery import DiscoveryIE
+from .divxstage import DivxStageIE
+from .dropbox import DropboxIE
 from .ebaumsworld import EbaumsWorldIE
 from .ehow import EHowIE
 from .eighttracks import EightTracksIE
 from .eitb import EitbIE
+from .elpais import ElPaisIE
+from .empflix import EmpflixIE
+from .engadget import EngadgetIE
 from .escapist import EscapistIE
+from .everyonesmixtape import EveryonesMixtapeIE
 from .exfm import ExfmIE
 from .extremetube import ExtremeTubeIE
 from .facebook import FacebookIE
 from .faz import FazIE
+from .fc2 import FC2IE
+from .firedrive import FiredriveIE
+from .firstpost import FirstpostIE
+from .firsttv import FirstTVIE
+from .fivemin import FiveMinIE
 from .fktv import (
     FKTVIE,
     FKTVPosteckeIE,
 )
 from .flickr import FlickrIE
+from .fourtube import FourTubeIE
+from .franceculture import FranceCultureIE
+from .franceinter import FranceInterIE
 from .francetv import (
     PluzzIE,
     FranceTvInfoIE,
-    France2IE,
-    GenerationQuoiIE
+    FranceTVIE,
+    GenerationQuoiIE,
+    CultureboxIE,
 )
 from .freesound import FreesoundIE
+from .freespeech import FreespeechIE
 from .funnyordie import FunnyOrDieIE
 from .gamekings import GamekingsIE
+from .gameone import GameOneIE
 from .gamespot import GameSpotIE
 from .gametrailers import GametrailersIE
+from .gdcvault import GDCVaultIE
 from .generic import GenericIE
 from .googleplus import GooglePlusIE
 from .googlesearch import GoogleSearchIE
+from .gorillavid import GorillaVidIE
+from .goshgay import GoshgayIE
 from .hark import HarkIE
+from .helsinki import HelsinkiIE
+from .hentaistigma import HentaiStigmaIE
 from .hotnewhiphop import HotNewHipHopIE
 from .howcast import HowcastIE
+from .huffpost import HuffPostIE
 from .hypem import HypemIE
+from .iconosquare import IconosquareIE
 from .ign import IGNIE, OneUPIE
+from .imdb import (
+    ImdbIE,
+    ImdbListIE
+)
 from .ina import InaIE
 from .infoq import InfoQIE
-from .instagram import InstagramIE
+from .instagram import InstagramIE, InstagramUserIE
 from .internetvideoarchive import InternetVideoArchiveIE
+from .iprima import IPrimaIE
+from .ivi import (
+    IviIE,
+    IviCompilationIE
+)
+from .jadorecettepub import JadoreCettePubIE
 from .jeuxvideo import JeuxVideoIE
 from .jukebox import JukeboxIE
 from .justintv import JustinTVIE
+from .jpopsukitv import JpopsukiIE
 from .kankan import KankanIE
 from .keezmovies import KeezMoviesIE
+from .khanacademy import KhanAcademyIE
 from .kickstarter import KickStarterIE
 from .keek import KeekIE
+from .kontrtube import KontrTubeIE
+from .ku6 import Ku6IE
+from .la7 import LA7IE
+from .lifenews import LifeNewsIE
 from .liveleak import LiveLeakIE
-from .livestream import LivestreamIE, LivestreamOriginalIE
+from .livestream import (
+    LivestreamIE,
+    LivestreamOriginalIE,
+    LivestreamShortenerIE,
+)
+from .lynda import (
+    LyndaIE,
+    LyndaCourseIE
+)
+from .m6 import M6IE
+from .macgamestore import MacGameStoreIE
+from .mailru import MailRuIE
+from .malemotion import MalemotionIE
+from .mdr import MDRIE
 from .metacafe import MetacafeIE
 from .metacritic import MetacriticIE
-from .mit import TechTVMITIE, MITIE
+from .mit import TechTVMITIE, MITIE, OCWMITIE
 from .mixcloud import MixcloudIE
+from .mlb import MLBIE
+from .mpora import MporaIE
 from .mofosex import MofosexIE
-from .mtv import MTVIE
+from .mooshare import MooshareIE
+from .morningstar import MorningstarIE
+from .motherless import MotherlessIE
+from .motorsport import MotorsportIE
+from .moviezine import MoviezineIE
+from .movshare import MovShareIE
+from .mtv import (
+    MTVIE,
+    MTVServicesEmbeddedIE,
+    MTVIggyIE,
+)
+from .musicplayon import MusicPlayOnIE
 from .muzu import MuzuTVIE
 from .myspace import MySpaceIE
 from .myspass import MySpassIE
 from .myvideo import MyVideoIE
 from .naver import NaverIE
 from .nba import NBAIE
-from .nbc import NBCNewsIE
+from .nbc import (
+    NBCIE,
+    NBCNewsIE,
+)
+from .ndr import NDRIE
+from .ndtv import NDTVIE
 from .newgrounds import NewgroundsIE
+from .newstube import NewstubeIE
+from .nfb import NFBIE
 from .nhl import NHLIE, NHLVideocenterIE
 from .niconico import NiconicoIE
+from .ninegag import NineGagIE
+from .noco import NocoIE
+from .normalboots import NormalbootsIE
+from .novamov import NovaMovIE
+from .nowness import NownessIE
 from .nowvideo import NowVideoIE
+from .npo import NPOIE
+from .nrk import (
+    NRKIE,
+    NRKTVIE,
+)
+from .ntv import NTVIE
+from .nytimes import NYTimesIE
+from .nuvid import NuvidIE
+from .oe1 import OE1IE
 from .ooyala import OoyalaIE
 from .orf import ORFIE
+from .parliamentliveuk import ParliamentLiveUKIE
 from .pbs import PBSIE
 from .photobucket import PhotobucketIE
+from .playvid import PlayvidIE
+from .podomatic import PodomaticIE
+from .pornhd import PornHdIE
 from .pornhub import PornHubIE
 from .pornotube import PornotubeIE
+from .prosiebensat1 import ProSiebenSat1IE
+from .pyvideo import PyvideoIE
+from .radiofrance import RadioFranceIE
+from .rai import RaiIE
 from .rbmaradio import RBMARadioIE
 from .redtube import RedTubeIE
+from .reverbnation import ReverbNationIE
 from .ringtv import RingTVIE
 from .ro220 import Ro220IE
 from .rottentomatoes import RottenTomatoesIE
 from .roxwel import RoxwelIE
+from .rtbf import RTBFIE
 from .rtlnow import RTLnowIE
-from .rutube import RutubeIE
+from .rts import RTSIE
+from .rtve import RTVEALaCartaIE
+from .ruhd import RUHDIE
+from .rutube import (
+    RutubeIE,
+    RutubeChannelIE,
+    RutubeMovieIE,
+    RutubePersonIE,
+)
+from .rutv import RUTVIE
+from .sapo import SapoIE
+from .savefrom import SaveFromIE
+from .scivee import SciVeeIE
+from .screencast import ScreencastIE
+from .servingsys import ServingSysIE
 from .sina import SinaIE
-from .slashdot import SlashdotIE
 from .slideshare import SlideshareIE
+from .slutload import SlutloadIE
+from .smotri import (
+    SmotriIE,
+    SmotriCommunityIE,
+    SmotriUserIE,
+    SmotriBroadcastIE,
+)
+from .snotr import SnotrIE
+from .sockshare import SockshareIE
 from .sohu import SohuIE
-from .soundcloud import SoundcloudIE, SoundcloudSetIE, SoundcloudUserIE
-from .southparkstudios import (
-    SouthParkStudiosIE,
+from .soundcloud import (
+    SoundcloudIE,
+    SoundcloudSetIE,
+    SoundcloudUserIE,
+    SoundcloudPlaylistIE
+)
+from .soundgasm import SoundgasmIE
+from .southpark import (
+    SouthParkIE,
     SouthparkDeIE,
 )
 from .space import SpaceIE
 from .spankwire import SpankwireIE
 from .spiegel import SpiegelIE
+from .spiegeltv import SpiegeltvIE
+from .spike import SpikeIE
 from .stanfordoc import StanfordOpenClassroomIE
-from .statigram import StatigramIE
 from .steam import SteamIE
 from .streamcloud import StreamcloudIE
+from .streamcz import StreamCZIE
+from .swrmediathek import SWRMediathekIE
+from .syfy import SyfyIE
 from .sztvhu import SztvHuIE
+from .tagesschau import TagesschauIE
+from .teachertube import (
+    TeacherTubeIE,
+    TeacherTubeUserIE,
+)
+from .teachingchannel import TeachingChannelIE
 from .teamcoco import TeamcocoIE
 from .techtalks import TechTalksIE
 from .ted import TEDIE
+from .tenplay import TenPlayIE
+from .testurl import TestURLIE
 from .tf1 import TF1IE
+from .theplatform import ThePlatformIE
 from .thisav import ThisAVIE
+from .tinypic import TinyPicIE
+from .tlc import TlcIE, TlcDeIE
 from .toutv import TouTvIE
+from .toypics import ToypicsUserIE, ToypicsIE
 from .traileraddict import TrailerAddictIE
 from .trilulilu import TriluliluIE
+from .trutube import TruTubeIE
 from .tube8 import Tube8IE
 from .tudou import TudouIE
 from .tumblr import TumblrIE
 from .tutv import TutvIE
+from .tvigle import TvigleIE
 from .tvp import TvpIE
+from .udemy import (
+    UdemyIE,
+    UdemyCourseIE
+)
 from .unistra import UnistraIE
+from .urort import UrortIE
 from .ustream import UstreamIE, UstreamChannelIE
 from .vbox7 import Vbox7IE
 from .veehd import VeeHDIE
 from .veoh import VeohIE
+from .vesti import VestiIE
 from .vevo import VevoIE
-from .vice import ViceIE
+from .vh1 import VH1IE
 from .viddler import ViddlerIE
+from .videobam import VideoBamIE
 from .videodetective import VideoDetectiveIE
+from .videolecturesnet import VideoLecturesNetIE
 from .videofyme import VideofyMeIE
 from .videopremium import VideoPremiumIE
-from .vimeo import VimeoIE, VimeoChannelIE
-from .vine import VineIE
+from .videott import VideoTtIE
+from .videoweed import VideoWeedIE
+from .vimeo import (
+    VimeoIE,
+    VimeoChannelIE,
+    VimeoUserIE,
+    VimeoAlbumIE,
+    VimeoGroupsIE,
+    VimeoReviewIE,
+    VimeoWatchLaterIE,
+)
+from .vimple import VimpleIE
+from .vine import (
+    VineIE,
+    VineUserIE,
+)
 from .viki import VikiIE
 from .vk import VKIE
+from .vodlocker import VodlockerIE
+from .vube import VubeIE
+from .vuclip import VuClipIE
+from .vulture import VultureIE
+from .washingtonpost import WashingtonPostIE
 from .wat import WatIE
-from .websurg import WeBSurgIE
+from .wdr import (
+    WDRIE,
+    WDRMobileIE,
+    WDRMausIE,
+)
 from .weibo import WeiboIE
 from .wimp import WimpIE
+from .wistia import WistiaIE
 from .worldstarhiphop import WorldStarHipHopIE
+from .wrzuta import WrzutaIE
+from .xbef import XBefIE
 from .xhamster import XHamsterIE
 from .xnxx import XNXXIE
 from .xvideos import XVideosIE
-from .xtube import XTubeIE
-from .yahoo import YahooIE, YahooSearchIE
+from .xtube import XTubeUserIE, XTubeIE
+from .yahoo import (
+    YahooIE,
+    YahooNewsIE,
+    YahooSearchIE,
+)
 from .youjizz import YouJizzIE
 from .youku import YoukuIE
 from .youporn import YouPornIE
 from .youtube import (
     YoutubeIE,
-    YoutubePlaylistIE,
-    YoutubeSearchIE,
-    YoutubeSearchDateIE,
-    YoutubeUserIE,
     YoutubeChannelIE,
-    YoutubeShowIE,
-    YoutubeSubscriptionsIE,
-    YoutubeRecommendedIE,
-    YoutubeTruncatedURLIE,
-    YoutubeWatchLaterIE,
     YoutubeFavouritesIE,
     YoutubeHistoryIE,
+    YoutubePlaylistIE,
+    YoutubeRecommendedIE,
+    YoutubeSearchDateIE,
+    YoutubeSearchIE,
+    YoutubeSearchURLIE,
+    YoutubeShowIE,
+    YoutubeSubscriptionsIE,
+    YoutubeTopListIE,
+    YoutubeTruncatedURLIE,
+    YoutubeUserIE,
+    YoutubeWatchLaterIE,
 )
+
 from .zdf import ZDFIE
 
 

youtube_dl/extractor/academicearth.py

@@ -0,0 +1,32 @@
+from __future__ import unicode_literals
+import re
+
+from .common import InfoExtractor
+
+
+class AcademicEarthCourseIE(InfoExtractor):
+    _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P<id>[^?#/]+)'
+    IE_NAME = 'AcademicEarth:Course'
+
+    def _real_extract(self, url):
+        m = re.match(self._VALID_URL, url)
+        playlist_id = m.group('id')
+
+        webpage = self._download_webpage(url, playlist_id)
+        title = self._html_search_regex(
+            r'<h1 class="playlist-name"[^>]*?>(.*?)</h1>', webpage, u'title')
+        description = self._html_search_regex(
+            r'<p class="excerpt"[^>]*?>(.*?)</p>',
+            webpage, u'description', fatal=False)
+        urls = re.findall(
+            r'<li class="lecture-preview">\s*?<a target="_blank" href="([^"]+)">',
+            webpage)
+        entries = [self.url_result(u) for u in urls]
+
+        return {
+            '_type': 'playlist',
+            'id': playlist_id,
+            'title': title,
+            'description': description,
+            'entries': entries,
+        }

youtube_dl/extractor/addanime.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -13,15 +15,15 @@ from ..utils import (
 
 class AddAnimeIE(InfoExtractor):
 
-    _VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video.php\?(?:.*?)v=(?P<video_id>[\w_]+)(?:.*)'
-    IE_NAME = u'AddAnime'
+    _VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video\.php\?(?:.*?)v=(?P<video_id>[\w_]+)(?:.*)'
     _TEST = {
-        u'url': u'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
-        u'file': u'24MR3YO5SAS9.mp4',
-        u'md5': u'72954ea10bc979ab5e2eb288b21425a0',
-        u'info_dict': {
-            u"description": u"One Piece 606",
-            u"title": u"One Piece 606"
+        'url': 'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
+        'md5': '72954ea10bc979ab5e2eb288b21425a0',
+        'info_dict': {
+            'id': '24MR3YO5SAS9',
+            'ext': 'mp4',
+            'description': 'One Piece 606',
+            'title': 'One Piece 606',
         }
     }
 
@@ -38,10 +40,10 @@ class AddAnimeIE(InfoExtractor):
             redir_webpage = ee.cause.read().decode('utf-8')
             action = self._search_regex(
                 r'<form id="challenge-form" action="([^"]+)"',
-                redir_webpage, u'Redirect form')
+                redir_webpage, 'Redirect form')
             vc = self._search_regex(
                 r'<input type="hidden" name="jschl_vc" value="([^"]+)"/>',
-                redir_webpage, u'redirect vc value')
+                redir_webpage, 'redirect vc value')
             av = re.search(
                 r'a\.value = ([0-9]+)[+]([0-9]+)[*]([0-9]+);',
                 redir_webpage)
@@ -52,19 +54,19 @@ class AddAnimeIE(InfoExtractor):
             parsed_url = compat_urllib_parse_urlparse(url)
             av_val = av_res + len(parsed_url.netloc)
             confirm_url = (
-                parsed_url.scheme + u'://' + parsed_url.netloc +
+                parsed_url.scheme + '://' + parsed_url.netloc +
                 action + '?' +
                 compat_urllib_parse.urlencode({
                     'jschl_vc': vc, 'jschl_answer': compat_str(av_val)}))
             self._download_webpage(
                 confirm_url, video_id,
-                note=u'Confirming after redirect')
+                note='Confirming after redirect')
             webpage = self._download_webpage(url, video_id)
 
         formats = []
         for format_id in ('normal', 'hq'):
             rex = r"var %s_video_file = '(.*?)';" % re.escape(format_id)
-            video_url = self._search_regex(rex, webpage, u'video file URLx',
+            video_url = self._search_regex(rex, webpage, 'video file URLx',
                                            fatal=False)
             if not video_url:
                 continue
@@ -72,14 +74,13 @@ class AddAnimeIE(InfoExtractor):
                 'format_id': format_id,
                 'url': video_url,
             })
-        if not formats:
-            raise ExtractorError(u'Cannot find any video format!')
+        self._sort_formats(formats)
         video_title = self._og_search_title(webpage)
         video_description = self._og_search_description(webpage)
 
         return {
             '_type': 'video',
-            'id':  video_id,
+            'id': video_id,
             'formats': formats,
             'title': video_title,
             'description': video_description

youtube_dl/extractor/adultswim.py

@@ -0,0 +1,139 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+class AdultSwimIE(InfoExtractor):
+    _VALID_URL = r'https?://video\.adultswim\.com/(?P<path>.+?)(?:\.html)?(?:\?.*)?(?:#.*)?$'
+    _TEST = {
+        'url': 'http://video.adultswim.com/rick-and-morty/close-rick-counters-of-the-rick-kind.html?x=y#title',
+        'playlist': [
+            {
+                'md5': '4da359ec73b58df4575cd01a610ba5dc',
+                'info_dict': {
+                    'id': '8a250ba1450996e901453d7f02ca02f5',
+                    'ext': 'flv',
+                    'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 1',
+                    'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?',
+                    'uploader': 'Rick and Morty',
+                    'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg'
+                }
+            },
+            {
+                'md5': 'ffbdf55af9331c509d95350bd0cc1819',
+                'info_dict': {
+                    'id': '8a250ba1450996e901453d7f4bd102f6',
+                    'ext': 'flv',
+                    'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 2',
+                    'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?',
+                    'uploader': 'Rick and Morty',
+                    'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg'
+                }
+            },
+            {
+                'md5': 'b92409635540304280b4b6c36bd14a0a',
+                'info_dict': {
+                    'id': '8a250ba1450996e901453d7fa73c02f7',
+                    'ext': 'flv',
+                    'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 3',
+                    'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?',
+                    'uploader': 'Rick and Morty',
+                    'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg'
+                }
+            },
+            {
+                'md5': 'e8818891d60e47b29cd89d7b0278156d',
+                'info_dict': {
+                    'id': '8a250ba1450996e901453d7fc8ba02f8',
+                    'ext': 'flv',
+                    'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 4',
+                    'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?',
+                    'uploader': 'Rick and Morty',
+                    'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg'
+                }
+            }
+        ]
+    }
+
+    _video_extensions = {
+        '3500': 'flv',
+        '640': 'mp4',
+        '150': 'mp4',
+        'ipad': 'm3u8',
+        'iphone': 'm3u8'
+    }
+    _video_dimensions = {
+        '3500': (1280, 720),
+        '640': (480, 270),
+        '150': (320, 180)
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_path = mobj.group('path')
+
+        webpage = self._download_webpage(url, video_path)
+        episode_id = self._html_search_regex(r'<link rel="video_src" href="http://i\.adultswim\.com/adultswim/adultswimtv/tools/swf/viralplayer.swf\?id=([0-9a-f]+?)"\s*/?\s*>', webpage, 'episode_id')
+        title = self._og_search_title(webpage)
+
+        index_url = 'http://asfix.adultswim.com/asfix-svc/episodeSearch/getEpisodesByIDs?networkName=AS&ids=%s' % episode_id
+        idoc = self._download_xml(index_url, title, 'Downloading episode index', 'Unable to download episode index')
+
+        episode_el = idoc.find('.//episode')
+        show_title = episode_el.attrib.get('collectionTitle')
+        episode_title = episode_el.attrib.get('title')
+        thumbnail = episode_el.attrib.get('thumbnailUrl')
+        description = episode_el.find('./description').text.strip()
+
+        entries = []
+        segment_els = episode_el.findall('./segments/segment')
+
+        for part_num, segment_el in enumerate(segment_els):
+            segment_id = segment_el.attrib.get('id')
+            segment_title = '%s %s part %d' % (show_title, episode_title, part_num + 1)
+            thumbnail = segment_el.attrib.get('thumbnailUrl')
+            duration = segment_el.attrib.get('duration')
+
+            segment_url = 'http://asfix.adultswim.com/asfix-svc/episodeservices/getCvpPlaylist?networkName=AS&id=%s' % segment_id
+            idoc = self._download_xml(segment_url, segment_title, 'Downloading segment information', 'Unable to download segment information')
+
+            formats = []
+            file_els = idoc.findall('.//files/file')
+
+            for file_el in file_els:
+                bitrate = file_el.attrib.get('bitrate')
+                type = file_el.attrib.get('type')
+                width, height = self._video_dimensions.get(bitrate, (None, None))
+                formats.append({
+                    'format_id': '%s-%s' % (bitrate, type),
+                    'url': file_el.text,
+                    'ext': self._video_extensions.get(bitrate, 'mp4'),
+                    # The bitrate may not be a number (for example: 'iphone')
+                    'tbr': int(bitrate) if bitrate.isdigit() else None,
+                    'height': height,
+                    'width': width
+                })
+
+            self._sort_formats(formats)
+
+            entries.append({
+                'id': segment_id,
+                'title': segment_title,
+                'formats': formats,
+                'uploader': show_title,
+                'thumbnail': thumbnail,
+                'duration': duration,
+                'description': description
+            })
+
+        return {
+            '_type': 'playlist',
+            'id': episode_id,
+            'display_id': video_path,
+            'entries': entries,
+            'title': '%s %s' % (show_title, episode_title),
+            'description': description,
+            'thumbnail': thumbnail
+        }

youtube_dl/extractor/aftonbladet.py

@@ -0,0 +1,66 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class AftonbladetIE(InfoExtractor):
+    _VALID_URL = r'^http://tv\.aftonbladet\.se/webbtv.+?(?P<video_id>article[0-9]+)\.ab(?:$|[?#])'
+    _TEST = {
+        'url': 'http://tv.aftonbladet.se/webbtv/nyheter/vetenskap/rymden/article36015.ab',
+        'info_dict': {
+            'id': 'article36015',
+            'ext': 'mp4',
+            'title': 'Vulkanutbrott i rymden - nu släpper NASA bilderna',
+            'description': 'Jupiters måne mest aktiv av alla himlakroppar',
+            'timestamp': 1394142732,
+            'upload_date': '20140306',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.search(self._VALID_URL, url)
+
+        video_id = mobj.group('video_id')
+        webpage = self._download_webpage(url, video_id)
+
+        # find internal video meta data
+        meta_url = 'http://aftonbladet-play.drlib.aptoma.no/video/%s.json'
+        internal_meta_id = self._html_search_regex(
+            r'data-aptomaId="([\w\d]+)"', webpage, 'internal_meta_id')
+        internal_meta_url = meta_url % internal_meta_id
+        internal_meta_json = self._download_json(
+            internal_meta_url, video_id, 'Downloading video meta data')
+
+        # find internal video formats
+        format_url = 'http://aftonbladet-play.videodata.drvideo.aptoma.no/actions/video/?id=%s'
+        internal_video_id = internal_meta_json['videoId']
+        internal_formats_url = format_url % internal_video_id
+        internal_formats_json = self._download_json(
+            internal_formats_url, video_id, 'Downloading video formats')
+
+        formats = []
+        for fmt in internal_formats_json['formats']['http']['pseudostreaming']['mp4']:
+            p = fmt['paths'][0]
+            formats.append({
+                'url': 'http://%s:%d/%s/%s' % (p['address'], p['port'], p['path'], p['filename']),
+                'ext': 'mp4',
+                'width': fmt['width'],
+                'height': fmt['height'],
+                'tbr': fmt['bitrate'],
+                'protocol': 'http',
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': internal_meta_json['title'],
+            'formats': formats,
+            'thumbnail': internal_meta_json['imageUrl'],
+            'description': internal_meta_json['shortPreamble'],
+            'timestamp': internal_meta_json['timePublished'],
+            'duration': internal_meta_json['duration'],
+            'view_count': internal_meta_json['views'],
+        }

youtube_dl/extractor/allocine.py

@@ -0,0 +1,89 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_str,
+    qualities,
+    determine_ext,
+)
+
+
+class AllocineIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?P<typ>article|video|film)/(fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=)(?P<id>[0-9]+)(?:\.html)?'
+
+    _TESTS = [{
+        'url': 'http://www.allocine.fr/article/fichearticle_gen_carticle=18635087.html',
+        'md5': '0c9fcf59a841f65635fa300ac43d8269',
+        'info_dict': {
+            'id': '19546517',
+            'ext': 'mp4',
+            'title': 'Astérix - Le Domaine des Dieux Teaser VF',
+            'description': 'md5:4a754271d9c6f16c72629a8a993ee884',
+            'thumbnail': 're:http://.*\.jpg',
+        },
+    }, {
+        'url': 'http://www.allocine.fr/video/player_gen_cmedia=19540403&cfilm=222257.html',
+        'md5': 'd0cdce5d2b9522ce279fdfec07ff16e0',
+        'info_dict': {
+            'id': '19540403',
+            'ext': 'mp4',
+            'title': 'Planes 2 Bande-annonce VF',
+            'description': 'md5:eeaffe7c2d634525e21159b93acf3b1e',
+            'thumbnail': 're:http://.*\.jpg',
+        },
+    }, {
+        'url': 'http://www.allocine.fr/film/fichefilm_gen_cfilm=181290.html',
+        'md5': '101250fb127ef9ca3d73186ff22a47ce',
+        'info_dict': {
+            'id': '19544709',
+            'ext': 'mp4',
+            'title': 'Dragons 2 - Bande annonce finale VF',
+            'description': 'md5:71742e3a74b0d692c7fce0dd2017a4ac',
+            'thumbnail': 're:http://.*\.jpg',
+        },
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        typ = mobj.group('typ')
+        display_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        if typ == 'film':
+            video_id = self._search_regex(r'href="/video/player_gen_cmedia=([0-9]+).+"', webpage, 'video id')
+        else:
+            player = self._search_regex(r'data-player=\'([^\']+)\'>', webpage, 'data player')
+
+            player_data = json.loads(player)
+            video_id = compat_str(player_data['refMedia'])
+
+        xml = self._download_xml('http://www.allocine.fr/ws/AcVisiondataV4.ashx?media=%s' % video_id, display_id)
+
+        video = xml.find('.//AcVisionVideo').attrib
+        quality = qualities(['ld', 'md', 'hd'])
+
+        formats = []
+        for k, v in video.items():
+            if re.match(r'.+_path', k):
+                format_id = k.split('_')[0]
+                formats.append({
+                    'format_id': format_id,
+                    'quality': quality(format_id),
+                    'url': v,
+                    'ext': determine_ext(v),
+                })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': video['videoTitle'],
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'formats': formats,
+            'description': self._og_search_description(webpage),
+        }

youtube_dl/extractor/anitube.py

@@ -1,23 +1,24 @@
+from __future__ import unicode_literals
+
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 
 
 class AnitubeIE(InfoExtractor):
-    IE_NAME = u'anitube.se'
+    IE_NAME = 'anitube.se'
     _VALID_URL = r'https?://(?:www\.)?anitube\.se/video/(?P<id>\d+)'
 
     _TEST = {
-        u'url': u'http://www.anitube.se/video/36621',
-        u'md5': u'59d0eeae28ea0bc8c05e7af429998d43',
-        u'file': u'36621.mp4',
-        u'info_dict': {
-            u'id': u'36621',
-            u'ext': u'mp4',
-            u'title': u'Recorder to Randoseru 01',
+        'url': 'http://www.anitube.se/video/36621',
+        'md5': '59d0eeae28ea0bc8c05e7af429998d43',
+        'info_dict': {
+            'id': '36621',
+            'ext': 'mp4',
+            'title': 'Recorder to Randoseru 01',
+            'duration': 180.19,
         },
-        u'skip': u'Blocked in the US',
+        'skip': 'Blocked in the US',
     }
 
     def _real_extract(self, url):
@@ -25,14 +26,15 @@ class AnitubeIE(InfoExtractor):
         video_id = mobj.group('id')
 
         webpage = self._download_webpage(url, video_id)
-        key = self._html_search_regex(r'http://www\.anitube\.se/embed/([A-Za-z0-9_-]*)',
-                                      webpage, u'key')
+        key = self._html_search_regex(
+            r'http://www\.anitube\.se/embed/([A-Za-z0-9_-]*)', webpage, 'key')
 
-        webpage_config = self._download_webpage('http://www.anitube.se/nuevo/econfig.php?key=%s' % key,
-                                                key)
-        config_xml = xml.etree.ElementTree.fromstring(webpage_config.encode('utf-8'))
+        config_xml = self._download_xml(
+            'http://www.anitube.se/nuevo/econfig.php?key=%s' % key, key)
 
         video_title = config_xml.find('title').text
+        thumbnail = config_xml.find('image').text
+        duration = float(config_xml.find('duration').text)
 
         formats = []
         video_url = config_xml.find('file')
@@ -51,5 +53,7 @@ class AnitubeIE(InfoExtractor):
         return {
             'id': video_id,
             'title': video_title,
+            'thumbnail': thumbnail,
+            'duration': duration,
             'formats': formats
         }

youtube_dl/extractor/aol.py

@@ -0,0 +1,65 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from .fivemin import FiveMinIE
+
+
+class AolIE(InfoExtractor):
+    IE_NAME = 'on.aol.com'
+    _VALID_URL = r'''(?x)
+        (?:
+            aol-video:|
+            http://on\.aol\.com/
+            (?:
+                video/.*-|
+                playlist/(?P<playlist_display_id>[^/?#]+?)-(?P<playlist_id>[0-9]+)[?#].*_videoid=
+            )
+        )
+        (?P<id>[0-9]+)
+        (?:$|\?)
+    '''
+
+    _TEST = {
+        'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img',
+        'md5': '18ef68f48740e86ae94b98da815eec42',
+        'info_dict': {
+            'id': '518167793',
+            'ext': 'mp4',
+            'title': 'U.S. Official Warns Of \'Largest Ever\' IRS Phone Scam',
+        },
+        'add_ie': ['FiveMin'],
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        playlist_id = mobj.group('playlist_id')
+        if playlist_id and not self._downloader.params.get('noplaylist'):
+            self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
+
+            webpage = self._download_webpage(url, playlist_id)
+            title = self._html_search_regex(
+                r'<h1 class="video-title[^"]*">(.+?)</h1>', webpage, 'title')
+            playlist_html = self._search_regex(
+                r"(?s)<ul\s+class='video-related[^']*'>(.*?)</ul>", webpage,
+                'playlist HTML')
+            entries = [{
+                '_type': 'url',
+                'url': 'aol-video:%s' % m.group('id'),
+                'ie_key': 'Aol',
+            } for m in re.finditer(
+                r"<a\s+href='.*videoid=(?P<id>[0-9]+)'\s+class='video-thumb'>",
+                playlist_html)]
+
+            return {
+                '_type': 'playlist',
+                'id': playlist_id,
+                'display_id': mobj.group('playlist_display_id'),
+                'title': title,
+                'entries': entries,
+            }
+
+        return FiveMinIE._build_result(video_id)

youtube_dl/extractor/aparat.py

@@ -0,0 +1,56 @@
+#coding: utf-8
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    HEADRequest,
+)
+
+
+class AparatIE(InfoExtractor):
+    _VALID_URL = r'^https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)'
+
+    _TEST = {
+        u'url': u'http://www.aparat.com/v/wP8On',
+        u'file': u'wP8On.mp4',
+        u'md5': u'6714e0af7e0d875c5a39c4dc4ab46ad1',
+        u'info_dict': {
+            u"title": u"تیم گلکسی 11 - زومیت",
+        },
+        #u'skip': u'Extremely unreliable',
+    }
+
+    def _real_extract(self, url):
+        m = re.match(self._VALID_URL, url)
+        video_id = m.group('id')
+
+        # Note: There is an easier-to-parse configuration at
+        # http://www.aparat.com/video/video/config/videohash/%video_id
+        # but the URL in there does not work
+        embed_url = (u'http://www.aparat.com/video/video/embed/videohash/' +
+                     video_id + u'/vt/frame')
+        webpage = self._download_webpage(embed_url, video_id)
+
+        video_urls = re.findall(r'fileList\[[0-9]+\]\s*=\s*"([^"]+)"', webpage)
+        for i, video_url in enumerate(video_urls):
+            req = HEADRequest(video_url)
+            res = self._request_webpage(
+                req, video_id, note=u'Testing video URL %d' % i, errnote=False)
+            if res:
+                break
+        else:
+            raise ExtractorError(u'No working video URLs found')
+
+        title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, u'title')
+        thumbnail = self._search_regex(
+            r'\s+image:\s*"([^"]+)"', webpage, u'thumbnail', fatal=False)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': video_url,
+            'ext': 'mp4',
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/appletrailers.py

@@ -1,59 +1,63 @@
+from __future__ import unicode_literals
+
 import re
-import xml.etree.ElementTree
 import json
 
 from .common import InfoExtractor
 from ..utils import (
     compat_urlparse,
-    determine_ext,
 )
 
 
 class AppleTrailersIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?trailers.apple.com/trailers/(?P<company>[^/]+)/(?P<movie>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/trailers/(?P<company>[^/]+)/(?P<movie>[^/]+)'
     _TEST = {
-        u"url": u"http://trailers.apple.com/trailers/wb/manofsteel/",
-        u"playlist": [
+        "url": "http://trailers.apple.com/trailers/wb/manofsteel/",
+        "playlist": [
             {
-                u"file": u"manofsteel-trailer4.mov",
-                u"md5": u"d97a8e575432dbcb81b7c3acb741f8a8",
-                u"info_dict": {
-                    u"duration": 111,
-                    u"title": u"Trailer 4",
-                    u"upload_date": u"20130523",
-                    u"uploader_id": u"wb",
+                "md5": "d97a8e575432dbcb81b7c3acb741f8a8",
+                "info_dict": {
+                    "id": "manofsteel-trailer4",
+                    "ext": "mov",
+                    "duration": 111,
+                    "title": "Trailer 4",
+                    "upload_date": "20130523",
+                    "uploader_id": "wb",
                 },
             },
             {
-                u"file": u"manofsteel-trailer3.mov",
-                u"md5": u"b8017b7131b721fb4e8d6f49e1df908c",
-                u"info_dict": {
-                    u"duration": 182,
-                    u"title": u"Trailer 3",
-                    u"upload_date": u"20130417",
-                    u"uploader_id": u"wb",
+                "md5": "b8017b7131b721fb4e8d6f49e1df908c",
+                "info_dict": {
+                    "id": "manofsteel-trailer3",
+                    "ext": "mov",
+                    "duration": 182,
+                    "title": "Trailer 3",
+                    "upload_date": "20130417",
+                    "uploader_id": "wb",
                 },
             },
             {
-                u"file": u"manofsteel-trailer.mov",
-                u"md5": u"d0f1e1150989b9924679b441f3404d48",
-                u"info_dict": {
-                    u"duration": 148,
-                    u"title": u"Trailer",
-                    u"upload_date": u"20121212",
-                    u"uploader_id": u"wb",
+                "md5": "d0f1e1150989b9924679b441f3404d48",
+                "info_dict": {
+                    "id": "manofsteel-trailer",
+                    "ext": "mov",
+                    "duration": 148,
+                    "title": "Trailer",
+                    "upload_date": "20121212",
+                    "uploader_id": "wb",
                 },
             },
             {
-                u"file": u"manofsteel-teaser.mov",
-                u"md5": u"5fe08795b943eb2e757fa95cb6def1cb",
-                u"info_dict": {
-                    u"duration": 93,
-                    u"title": u"Teaser",
-                    u"upload_date": u"20120721",
-                    u"uploader_id": u"wb",
+                "md5": "5fe08795b943eb2e757fa95cb6def1cb",
+                "info_dict": {
+                    "id": "manofsteel-teaser",
+                    "ext": "mov",
+                    "duration": 93,
+                    "title": "Teaser",
+                    "upload_date": "20120721",
+                    "uploader_id": "wb",
                 },
-            }
+            },
         ]
     }
 
@@ -64,24 +68,24 @@ class AppleTrailersIE(InfoExtractor):
         movie = mobj.group('movie')
         uploader_id = mobj.group('company')
 
-        playlist_url = compat_urlparse.urljoin(url, u'includes/playlists/itunes.inc')
-        playlist_snippet = self._download_webpage(playlist_url, movie)
-        playlist_cleaned = re.sub(r'(?s)<script[^<]*?>.*?</script>', u'', playlist_snippet)
-        playlist_cleaned = re.sub(r'<img ([^<]*?)>', r'<img \1/>', playlist_cleaned)
-        # The ' in the onClick attributes are not escaped, it couldn't be parsed
-        # with xml.etree.ElementTree.fromstring
-        # like: http://trailers.apple.com/trailers/wb/gravity/
-        def _clean_json(m):
-            return u'iTunes.playURL(%s);' % m.group(1).replace('\'', '&#39;')
-        playlist_cleaned = re.sub(self._JSON_RE, _clean_json, playlist_cleaned)
-        playlist_html = u'<html>' + playlist_cleaned + u'</html>'
+        playlist_url = compat_urlparse.urljoin(url, 'includes/playlists/itunes.inc')
+        def fix_html(s):
+            s = re.sub(r'(?s)<script[^<]*?>.*?</script>', '', s)
+            s = re.sub(r'<img ([^<]*?)>', r'<img \1/>', s)
+            # The ' in the onClick attributes are not escaped, it couldn't be parsed
+            # like: http://trailers.apple.com/trailers/wb/gravity/
+            def _clean_json(m):
+                return 'iTunes.playURL(%s);' % m.group(1).replace('\'', '&#39;')
+            s = re.sub(self._JSON_RE, _clean_json, s)
+            s = '<html>' + s + u'</html>'
+            return s
+        doc = self._download_xml(playlist_url, movie, transform_source=fix_html)
 
-        doc = xml.etree.ElementTree.fromstring(playlist_html)
         playlist = []
         for li in doc.findall('./div/ul/li'):
             on_click = li.find('.//a').attrib['onClick']
             trailer_info_json = self._search_regex(self._JSON_RE,
-                on_click, u'trailer info')
+                on_click, 'trailer info')
             trailer_info = json.loads(trailer_info_json)
             title = trailer_info['title']
             video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower()
@@ -97,8 +101,7 @@ class AppleTrailersIE(InfoExtractor):
             first_url = trailer_info['url']
             trailer_id = first_url.split('/')[-1].rpartition('_')[0].lower()
             settings_json_url = compat_urlparse.urljoin(url, 'includes/settings/%s.json' % trailer_id)
-            settings_json = self._download_webpage(settings_json_url, trailer_id, u'Downloading settings json')
-            settings = json.loads(settings_json)
+            settings = self._download_json(settings_json_url, trailer_id, 'Downloading settings json')
 
             formats = []
             for format in settings['metadata']['sizes']:
@@ -106,14 +109,14 @@ class AppleTrailersIE(InfoExtractor):
                 format_url = re.sub(r'_(\d*p.mov)', r'_h\1', format['src'])
                 formats.append({
                     'url': format_url,
-                    'ext': determine_ext(format_url),
                     'format': format['type'],
                     'width': format['width'],
                     'height': int(format['height']),
                 })
-            formats = sorted(formats, key=lambda f: (f['height'], f['width']))
 
-            info = {
+            self._sort_formats(formats)
+
+            playlist.append({
                 '_type': 'video',
                 'id': video_id,
                 'title': title,
@@ -124,12 +127,7 @@ class AppleTrailersIE(InfoExtractor):
                 'upload_date': upload_date,
                 'uploader_id': uploader_id,
                 'user_agent': 'QuickTime compatible (youtube-dl)',
-            }
-            # TODO: Remove when #980 has been merged
-            info['url'] = formats[-1]['url']
-            info['ext'] = formats[-1]['ext']
-
-            playlist.append(info)
+            })
 
         return {
             '_type': 'playlist',

youtube_dl/extractor/archiveorg.py

@@ -1,9 +1,10 @@
+from __future__ import unicode_literals
+
 import json
 import re
 
 from .common import InfoExtractor
 from ..utils import (
-    determine_ext,
     unified_strdate,
 )
 
@@ -11,25 +12,24 @@ from ..utils import (
 class ArchiveOrgIE(InfoExtractor):
     IE_NAME = 'archive.org'
     IE_DESC = 'archive.org videos'
-    _VALID_URL = r'(?:https?://)?(?:www\.)?archive.org/details/(?P<id>[^?/]+)(?:[?].*)?$'
+    _VALID_URL = r'(?:https?://)?(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$'
     _TEST = {
-        u"url": u"http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect",
-        u'file': u'XD300-23_68HighlightsAResearchCntAugHumanIntellect.ogv',
-        u'md5': u'8af1d4cf447933ed3c7f4871162602db',
-        u'info_dict': {
-            u"title": u"1968 Demo - FJCC Conference Presentation Reel #1",
-            u"description": u"Reel 1 of 3: Also known as the \"Mother of All Demos\", Doug Engelbart's presentation at the Fall Joint Computer Conference in San Francisco, December 9, 1968 titled \"A Research Center for Augmenting Human Intellect.\" For this presentation, Doug and his team astonished the audience by not only relating their research, but demonstrating it live. This was the debut of the mouse, interactive computing, hypermedia, computer supported software engineering, video teleconferencing, etc. See also <a href=\"http://dougengelbart.org/firsts/dougs-1968-demo.html\" rel=\"nofollow\">Doug's 1968 Demo page</a> for more background, highlights, links, and the detailed paper published in this conference proceedings. Filmed on 3 reels: Reel 1 | <a href=\"http://www.archive.org/details/XD300-24_68HighlightsAResearchCntAugHumanIntellect\" rel=\"nofollow\">Reel 2</a> | <a href=\"http://www.archive.org/details/XD300-25_68HighlightsAResearchCntAugHumanIntellect\" rel=\"nofollow\">Reel 3</a>",
-            u"upload_date": u"19681210",
-            u"uploader": u"SRI International"
+        "url": "http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect",
+        'file': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect.ogv',
+        'md5': '8af1d4cf447933ed3c7f4871162602db',
+        'info_dict': {
+            "title": "1968 Demo - FJCC Conference Presentation Reel #1",
+            "description": "Reel 1 of 3: Also known as the \"Mother of All Demos\", Doug Engelbart's presentation at the Fall Joint Computer Conference in San Francisco, December 9, 1968 titled \"A Research Center for Augmenting Human Intellect.\" For this presentation, Doug and his team astonished the audience by not only relating their research, but demonstrating it live. This was the debut of the mouse, interactive computing, hypermedia, computer supported software engineering, video teleconferencing, etc. See also <a href=\"http://dougengelbart.org/firsts/dougs-1968-demo.html\" rel=\"nofollow\">Doug's 1968 Demo page</a> for more background, highlights, links, and the detailed paper published in this conference proceedings. Filmed on 3 reels: Reel 1 | <a href=\"http://www.archive.org/details/XD300-24_68HighlightsAResearchCntAugHumanIntellect\" rel=\"nofollow\">Reel 2</a> | <a href=\"http://www.archive.org/details/XD300-25_68HighlightsAResearchCntAugHumanIntellect\" rel=\"nofollow\">Reel 3</a>",
+            "upload_date": "19681210",
+            "uploader": "SRI International"
         }
     }
 
-
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
 
-        json_url = url + (u'?' if u'?' in url else '&') + u'output=json'
+        json_url = url + ('?' if '?' in url else '&') + 'output=json'
         json_data = self._download_webpage(json_url, video_id)
         data = json.loads(json_data)
 
@@ -38,18 +38,18 @@ class ArchiveOrgIE(InfoExtractor):
         uploader = data['metadata']['creator'][0]
         upload_date = unified_strdate(data['metadata']['date'][0])
 
-        formats = [{
+        formats = [
+            {
                 'format': fdata['format'],
                 'url': 'http://' + data['server'] + data['dir'] + fn,
                 'file_size': int(fdata['size']),
             }
-            for fn,fdata in data['files'].items()
+            for fn, fdata in data['files'].items()
             if 'Video' in fdata['format']]
-        formats.sort(key=lambda fdata: fdata['file_size'])
-        for f in formats:
-            f['ext'] = determine_ext(f['url'])
 
-        info = {
+        self._sort_formats(formats)
+
+        return {
             '_type': 'video',
             'id': video_id,
             'title': title,
@@ -57,12 +57,5 @@ class ArchiveOrgIE(InfoExtractor):
             'description': description,
             'uploader': uploader,
             'upload_date': upload_date,
+            'thumbnail': data.get('misc', {}).get('image'),
         }
-        thumbnail = data.get('misc', {}).get('image')
-        if thumbnail:
-            info['thumbnail'] = thumbnail
-
-        # TODO: Remove when #980 has been merged
-        info.update(formats[-1])
-
-        return info

youtube_dl/extractor/ard.py

@@ -1,23 +1,38 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 from ..utils import (
+    determine_ext,
     ExtractorError,
+    qualities,
 )
 
+
 class ARDIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[^/\?]+)(?:\?.*)?'
-    _TITLE = r'<h1(?: class="boxTopHeadline")?>(?P<title>.*)</h1>'
-    _MEDIA_STREAM = r'mediaCollection\.addMediaStream\((?P<media_type>\d+), (?P<quality>\d+), "(?P<rtmp_url>[^"]*)", "(?P<video_url>[^"]*)", "[^"]*"\)'
-    _TEST = {
-        u'url': u'http://www.ardmediathek.de/das-erste/tagesschau-in-100-sek?documentId=14077640',
-        u'file': u'14077640.mp4',
-        u'md5': u'6ca8824255460c787376353f9e20bbd8',
-        u'info_dict': {
-            u"title": u"11.04.2013 09:23 Uhr - Tagesschau in 100 Sekunden"
+    _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
+
+    _TESTS = [{
+        'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht',
+        'file': '22429276.mp4',
+        'md5': '469751912f1de0816a9fc9df8336476c',
+        'info_dict': {
+            'title': 'Vertrauen ist gut, Spionieren ist besser - Geht so deutsch-amerikanische Freundschaft?',
+            'description': 'Das Erste Mediathek [ARD]: Vertrauen ist gut, Spionieren ist besser - Geht so deutsch-amerikanische Freundschaft?, Anne Will, Über die Spionage-Affäre diskutieren Clemens Binninger, Katrin Göring-Eckardt, Georg Mascolo, Andrew B. Denison und Constanze Kurz.. Das Video zur Sendung Anne Will am Mittwoch, 16.07.2014',
         },
-        u'skip': u'Requires rtmpdump'
-    }
+        'skip': 'Blocked outside of Germany',
+    }, {
+        'url': 'http://www.ardmediathek.de/tv/Tatort/Das-Wunder-von-Wolbeck-Video-tgl-ab-20/Das-Erste/Video?documentId=22490580&bcastId=602916',
+        'info_dict': {
+            'id': '22490580',
+            'ext': 'mp4',
+            'title': 'Das Wunder von Wolbeck (Video tgl. ab 20 Uhr)',
+            'description': 'Auf einem restaurierten Hof bei Wolbeck wird der Heilpraktiker Raffael Lembeck eines morgens von seiner Frau Stella tot aufgefunden. Das Opfer war offensichtlich in seiner Praxis zu Fall gekommen und ist dann verblutet, erklärt Prof. Boerne am Tatort.',
+        },
+        'skip': 'Blocked outside of Germany',
+    }]
 
     def _real_extract(self, url):
         # determine video id from url
@@ -29,26 +44,79 @@ class ARDIE(InfoExtractor):
         else:
             video_id = m.group('video_id')
 
-        # determine title and media streams from webpage
-        html = self._download_webpage(url, video_id)
-        title = re.search(self._TITLE, html).group('title')
-        streams = [mo.groupdict() for mo in re.finditer(self._MEDIA_STREAM, html)]
-        if not streams:
-            assert '"fsk"' in html
-            raise ExtractorError(u'This video is only available after 8:00 pm')
+        webpage = self._download_webpage(url, video_id)
 
-        # choose default media type and highest quality for now
-        stream = max([s for s in streams if int(s["media_type"]) == 0],
-                     key=lambda s: int(s["quality"]))
+        title = self._html_search_regex(
+            [r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>',
+             r'<meta name="dcterms.title" content="(.*?)"/>',
+             r'<h4 class="headline">(.*?)</h4>'],
+            webpage, 'title')
+        description = self._html_search_meta(
+            'dcterms.abstract', webpage, 'description', default=None)
+        if description is None:
+            description = self._html_search_meta(
+                'description', webpage, 'meta description')
 
-        # there's two possibilities: RTMP stream or HTTP download
-        info = {'id': video_id, 'title': title, 'ext': 'mp4'}
-        if stream['rtmp_url']:
-            self.to_screen(u'RTMP download detected')
-            assert stream['video_url'].startswith('mp4:')
-            info["url"] = stream["rtmp_url"]
-            info["play_path"] = stream['video_url']
-        else:
-            assert stream["video_url"].endswith('.mp4')
-            info["url"] = stream["video_url"]
-        return [info]
+        # Thumbnail is sometimes not present.
+        # It is in the mobile version, but that seems to use a different URL
+        # structure altogether.
+        thumbnail = self._og_search_thumbnail(webpage, default=None)
+
+        media_streams = re.findall(r'''(?x)
+            mediaCollection\.addMediaStream\([0-9]+,\s*[0-9]+,\s*"[^"]*",\s*
+            "([^"]+)"''', webpage)
+
+        if media_streams:
+            QUALITIES = qualities(['lo', 'hi', 'hq'])
+            formats = []
+            for furl in set(media_streams):
+                if furl.endswith('.f4m'):
+                    fid = 'f4m'
+                else:
+                    fid_m = re.match(r'.*\.([^.]+)\.[^.]+$', furl)
+                    fid = fid_m.group(1) if fid_m else None
+                formats.append({
+                    'quality': QUALITIES(fid),
+                    'format_id': fid,
+                    'url': furl,
+                })
+        else:  # request JSON file
+            media_info = self._download_json(
+                'http://www.ardmediathek.de/play/media/%s' % video_id, video_id)
+            # The second element of the _mediaArray contains the standard http urls
+            streams = media_info['_mediaArray'][1]['_mediaStreamArray']
+            if not streams:
+                if '"fsk"' in webpage:
+                    raise ExtractorError('This video is only available after 20:00')
+
+            formats = []
+            for s in streams:
+                if type(s['_stream']) == list:
+                    for index, url in enumerate(s['_stream'][::-1]):
+                        quality = s['_quality'] + index
+                        formats.append({
+                            'quality': quality,
+                            'url': url,
+                            'format_id': '%s-%s' % (determine_ext(url), quality)
+                        })
+                    continue
+
+                format = {
+                    'quality': s['_quality'],
+                    'url': s['_stream'],
+                }
+
+                format['format_id'] = '%s-%s' % (
+                    determine_ext(format['url']), format['quality'])
+
+                formats.append(format)
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'formats': formats,
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/arte.py

@@ -1,7 +1,7 @@
 # encoding: utf-8
+from __future__ import unicode_literals
+
 import re
-import json
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
@@ -11,123 +11,56 @@ from ..utils import (
     determine_ext,
     get_element_by_id,
     compat_str,
+    get_element_by_attribute,
 )
 
 # There are different sources of video in arte.tv, the extraction process 
 # is different for each one. The videos usually expire in 7 days, so we can't
 # add tests.
 
+
 class ArteTvIE(InfoExtractor):
-    _VIDEOS_URL = r'(?:http://)?videos.arte.tv/(?P<lang>fr|de)/.*-(?P<id>.*?).html'
-    _LIVEWEB_URL = r'(?:http://)?liveweb.arte.tv/(?P<lang>fr|de)/(?P<subpage>.+?)/(?P<name>.+)'
-    _LIVE_URL = r'index-[0-9]+\.html$'
-
-    IE_NAME = u'arte.tv'
-
-    @classmethod
-    def suitable(cls, url):
-        return any(re.match(regex, url) for regex in (cls._VIDEOS_URL, cls._LIVEWEB_URL))
-
-    # TODO implement Live Stream
-    # from ..utils import compat_urllib_parse
-    # def extractLiveStream(self, url):
-    #     video_lang = url.split('/')[-4]
-    #     info = self.grep_webpage(
-    #         url,
-    #         r'src="(.*?/videothek_js.*?\.js)',
-    #         0,
-    #         [
-    #             (1, 'url', u'Invalid URL: %s' % url)
-    #         ]
-    #     )
-    #     http_host = url.split('/')[2]
-    #     next_url = 'http://%s%s' % (http_host, compat_urllib_parse.unquote(info.get('url')))
-    #     info = self.grep_webpage(
-    #         next_url,
-    #         r'(s_artestras_scst_geoFRDE_' + video_lang + '.*?)\'.*?' +
-    #             '(http://.*?\.swf).*?' +
-    #             '(rtmp://.*?)\'',
-    #         re.DOTALL,
-    #         [
-    #             (1, 'path',   u'could not extract video path: %s' % url),
-    #             (2, 'player', u'could not extract video player: %s' % url),
-    #             (3, 'url',    u'could not extract video url: %s' % url)
-    #         ]
-    #     )
-    #     video_url = u'%s/%s' % (info.get('url'), info.get('path'))
+    _VALID_URL = r'http://videos\.arte\.tv/(?P<lang>fr|de)/.*-(?P<id>.*?)\.html'
+    IE_NAME = 'arte.tv'
 
     def _real_extract(self, url):
-        mobj = re.match(self._VIDEOS_URL, url)
-        if mobj is not None:
-            id = mobj.group('id')
-            lang = mobj.group('lang')
-            return self._extract_video(url, id, lang)
+        mobj = re.match(self._VALID_URL, url)
+        lang = mobj.group('lang')
+        video_id = mobj.group('id')
 
-        mobj = re.match(self._LIVEWEB_URL, url)
-        if mobj is not None:
-            name = mobj.group('name')
-            lang = mobj.group('lang')
-            return self._extract_liveweb(url, name, lang)
-
-        if re.search(self._LIVE_URL, url) is not None:
-            raise ExtractorError(u'Arte live streams are not yet supported, sorry')
-            # self.extractLiveStream(url)
-            # return
-
-    def _extract_video(self, url, video_id, lang):
-        """Extract from videos.arte.tv"""
         ref_xml_url = url.replace('/videos/', '/do_delegate/videos/')
         ref_xml_url = ref_xml_url.replace('.html', ',view,asPlayerXml.xml')
-        ref_xml = self._download_webpage(ref_xml_url, video_id, note=u'Downloading metadata')
-        ref_xml_doc = xml.etree.ElementTree.fromstring(ref_xml)
+        ref_xml_doc = self._download_xml(
+            ref_xml_url, video_id, note='Downloading metadata')
         config_node = find_xpath_attr(ref_xml_doc, './/video', 'lang', lang)
         config_xml_url = config_node.attrib['ref']
-        config_xml = self._download_webpage(config_xml_url, video_id, note=u'Downloading configuration')
+        config = self._download_xml(
+            config_xml_url, video_id, note='Downloading configuration')
 
-        video_urls = list(re.finditer(r'<url quality="(?P<quality>.*?)">(?P<url>.*?)</url>', config_xml))
-        def _key(m):
-            quality = m.group('quality')
-            if quality == 'hd':
-                return 2
-            else:
-                return 1
-        # We pick the best quality
-        video_urls = sorted(video_urls, key=_key)
-        video_url = list(video_urls)[-1].group('url')
-        
-        title = self._html_search_regex(r'<name>(.*?)</name>', config_xml, 'title')
-        thumbnail = self._html_search_regex(r'<firstThumbnailUrl>(.*?)</firstThumbnailUrl>',
-                                            config_xml, 'thumbnail')
-        return {'id': video_id,
-                'title': title,
-                'thumbnail': thumbnail,
-                'url': video_url,
-                'ext': 'flv',
-                }
+        formats = [{
+            'forma_id': q.attrib['quality'],
+            # The playpath starts at 'mp4:', if we don't manually
+            # split the url, rtmpdump will incorrectly parse them
+            'url': q.text.split('mp4:', 1)[0],
+            'play_path': 'mp4:' + q.text.split('mp4:', 1)[1],
+            'ext': 'flv',
+            'quality': 2 if q.attrib['quality'] == 'hd' else 1,
+        } for q in config.findall('./urls/url')]
+        self._sort_formats(formats)
 
-    def _extract_liveweb(self, url, name, lang):
-        """Extract form http://liveweb.arte.tv/"""
-        webpage = self._download_webpage(url, name)
-        video_id = self._search_regex(r'eventId=(\d+?)("|&)', webpage, u'event id')
-        config_xml = self._download_webpage('http://download.liveweb.arte.tv/o21/liveweb/events/event-%s.xml' % video_id,
-                                            video_id, u'Downloading information')
-        config_doc = xml.etree.ElementTree.fromstring(config_xml.encode('utf-8'))
-        event_doc = config_doc.find('event')
-        url_node = event_doc.find('video').find('urlHd')
-        if url_node is None:
-            url_node = event_doc.find('urlSd')
-
-        return {'id': video_id,
-                'title': event_doc.find('name%s' % lang.capitalize()).text,
-                'url': url_node.text.replace('MP4', 'mp4'),
-                'ext': 'flv',
-                'thumbnail': self._og_search_thumbnail(webpage),
-                }
+        title = config.find('.//name').text
+        thumbnail = config.find('.//firstThumbnailUrl').text
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }
 
 
 class ArteTVPlus7IE(InfoExtractor):
-    IE_NAME = u'arte.tv:+7'
-    _VALID_URL = r'https?://www\.arte.tv/guide/(?P<lang>fr|de)/(?:(?:sendungen|emissions)/)?(?P<id>.*?)/(?P<name>.*?)(\?.*)?'
+    IE_NAME = 'arte.tv:+7'
+    _VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de)/(?:(?:sendungen|emissions)/)?(?P<id>.*?)/(?P<name>.*?)(\?.*)?'
 
     @classmethod
     def _extract_url_info(cls, url):
@@ -144,11 +77,12 @@ class ArteTVPlus7IE(InfoExtractor):
         return self._extract_from_webpage(webpage, video_id, lang)
 
     def _extract_from_webpage(self, webpage, video_id, lang):
-        json_url = self._html_search_regex(r'arte_vp_url="(.*?)"', webpage, 'json url')
+        json_url = self._html_search_regex(
+            r'arte_vp_url="(.*?)"', webpage, 'json vp url')
+        return self._extract_from_json_url(json_url, video_id, lang)
 
-        json_info = self._download_webpage(json_url, video_id, 'Downloading info json')
-        self.report_extraction(video_id)
-        info = json.loads(json_info)
+    def _extract_from_json_url(self, json_url, video_id, lang):
+        info = self._download_json(json_url, video_id)
         player_info = info['videoJsonPlayer']
 
         info_dict = {
@@ -170,6 +104,8 @@ class ArteTVPlus7IE(InfoExtractor):
                 l = 'F'
             elif lang == 'de':
                 l = 'A'
+            else:
+                l = lang
             regexes = [r'VO?%s' % l, r'VO?.-ST%s' % l]
             return any(re.match(r, f['versionCode']) for r in regexes)
         # Some formats may not be in the same language as the url
@@ -178,7 +114,7 @@ class ArteTVPlus7IE(InfoExtractor):
         if not formats:
             # Some videos are only available in the 'Originalversion'
             # they aren't tagged as being in French or German
-            if all(f['versionCode'] == 'VO' for f in all_formats):
+            if all(f['versionCode'] == 'VO' or f['versionCode'] == 'VA' for f in all_formats):
                 formats = all_formats
             else:
                 raise ExtractorError(u'The formats list is empty')
@@ -188,14 +124,19 @@ class ArteTVPlus7IE(InfoExtractor):
                 return ['HQ', 'MQ', 'EQ', 'SQ'].index(f['quality'])
         else:
             def sort_key(f):
+                versionCode = f.get('versionCode')
+                if versionCode is None:
+                    versionCode = ''
                 return (
                     # Sort first by quality
-                    int(f.get('height',-1)),
-                    int(f.get('bitrate',-1)),
+                    int(f.get('height', -1)),
+                    int(f.get('bitrate', -1)),
                     # The original version with subtitles has lower relevance
-                    re.match(r'VO-ST(F|A)', f.get('versionCode', '')) is None,
+                    re.match(r'VO-ST(F|A)', versionCode) is None,
                     # The version with sourds/mal subtitles has also lower relevance
-                    re.match(r'VO?(F|A)-STM\1', f.get('versionCode', '')) is None,
+                    re.match(r'VO?(F|A)-STM\1', versionCode) is None,
+                    # Prefer http downloads over m3u8
+                    0 if f['url'].endswith('m3u8') else 1,
                 )
         formats = sorted(formats, key=sort_key)
         def _format(format_info):
@@ -207,7 +148,7 @@ class ArteTVPlus7IE(InfoExtractor):
             if bitrate is not None:
                 quality += '-%d' % bitrate
             if format_info.get('versionCode') is not None:
-                format_id = u'%s-%s' % (quality, format_info['versionCode'])
+                format_id = '%s-%s' % (quality, format_info['versionCode'])
             else:
                 format_id = quality
             info = {
@@ -216,7 +157,7 @@ class ArteTVPlus7IE(InfoExtractor):
                 'width': format_info.get('width'),
                 'height': height,
             }
-            if format_info['mediaType'] == u'rtmp':
+            if format_info['mediaType'] == 'rtmp':
                 info['url'] = format_info['streamer']
                 info['play_path'] = 'mp4:' + format_info['url']
                 info['ext'] = 'flv'
@@ -231,27 +172,30 @@ class ArteTVPlus7IE(InfoExtractor):
 
 # It also uses the arte_vp_url url from the webpage to extract the information
 class ArteTVCreativeIE(ArteTVPlus7IE):
-    IE_NAME = u'arte.tv:creative'
+    IE_NAME = 'arte.tv:creative'
     _VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de)/magazine?/(?P<id>.+)'
 
     _TEST = {
-        u'url': u'http://creative.arte.tv/de/magazin/agentur-amateur-corporate-design',
-        u'file': u'050489-002.mp4',
-        u'info_dict': {
-            u'title': u'Agentur Amateur / Agence Amateur #2 : Corporate Design',
+        'url': 'http://creative.arte.tv/de/magazin/agentur-amateur-corporate-design',
+        'info_dict': {
+            'id': '050489-002',
+            'ext': 'mp4',
+            'title': 'Agentur Amateur / Agence Amateur #2 : Corporate Design',
         },
     }
 
 
 class ArteTVFutureIE(ArteTVPlus7IE):
-    IE_NAME = u'arte.tv:future'
+    IE_NAME = 'arte.tv:future'
     _VALID_URL = r'https?://future\.arte\.tv/(?P<lang>fr|de)/(thema|sujet)/.*?#article-anchor-(?P<id>\d+)'
 
     _TEST = {
-        u'url': u'http://future.arte.tv/fr/sujet/info-sciences#article-anchor-7081',
-        u'file': u'050940-003.mp4',
-        u'info_dict': {
-            u'title': u'Les champignons au secours de la planète',
+        'url': 'http://future.arte.tv/fr/sujet/info-sciences#article-anchor-7081',
+        'info_dict': {
+            'id': '5201',
+            'ext': 'mp4',
+            'title': 'Les champignons au secours de la planète',
+            'upload_date': '20131101',
         },
     }
 
@@ -260,3 +204,57 @@ class ArteTVFutureIE(ArteTVPlus7IE):
         webpage = self._download_webpage(url, anchor_id)
         row = get_element_by_id(anchor_id, webpage)
         return self._extract_from_webpage(row, anchor_id, lang)
+
+
+class ArteTVDDCIE(ArteTVPlus7IE):
+    IE_NAME = 'arte.tv:ddc'
+    _VALID_URL = r'https?://ddc\.arte\.tv/(?P<lang>emission|folge)/(?P<id>.+)'
+
+    def _real_extract(self, url):
+        video_id, lang = self._extract_url_info(url)
+        if lang == 'folge':
+            lang = 'de'
+        elif lang == 'emission':
+            lang = 'fr'
+        webpage = self._download_webpage(url, video_id)
+        scriptElement = get_element_by_attribute('class', 'visu_video_block', webpage)
+        script_url = self._html_search_regex(r'src="(.*?)"', scriptElement, 'script url')
+        javascriptPlayerGenerator = self._download_webpage(script_url, video_id, 'Download javascript player generator')
+        json_url = self._search_regex(r"json_url=(.*)&rendering_place.*", javascriptPlayerGenerator, 'json url')
+        return self._extract_from_json_url(json_url, video_id, lang)
+
+
+class ArteTVConcertIE(ArteTVPlus7IE):
+    IE_NAME = 'arte.tv:concert'
+    _VALID_URL = r'https?://concert\.arte\.tv/(?P<lang>de|fr)/(?P<id>.+)'
+
+    _TEST = {
+        'url': 'http://concert.arte.tv/de/notwist-im-pariser-konzertclub-divan-du-monde',
+        'md5': '9ea035b7bd69696b67aa2ccaaa218161',
+        'info_dict': {
+            'id': '186',
+            'ext': 'mp4',
+            'title': 'The Notwist im Pariser Konzertclub "Divan du Monde"',
+            'upload_date': '20140128',
+            'description': 'md5:486eb08f991552ade77439fe6d82c305',
+        },
+    }
+
+
+class ArteTVEmbedIE(ArteTVPlus7IE):
+    IE_NAME = 'arte.tv:embed'
+    _VALID_URL = r'''(?x)
+        http://www\.arte\.tv
+        /playerv2/embed\.php\?json_url=
+        (?P<json_url>
+            http://arte\.tv/papi/tvguide/videos/stream/player/
+            (?P<lang>[^/]+)/(?P<id>[^/]+)[^&]*
+        )
+    '''
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        lang = mobj.group('lang')
+        json_url = mobj.group('json_url')
+        return self._extract_from_json_url(json_url, video_id, lang)

youtube_dl/extractor/auengine.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -7,23 +9,26 @@ from ..utils import (
     ExtractorError,
 )
 
+
 class AUEngineIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?auengine\.com/embed\.php\?.*?file=(?P<id>[^&]+).*?'
+
     _TEST = {
-        u'url': u'http://auengine.com/embed.php?file=lfvlytY6&w=650&h=370',
-        u'file': u'lfvlytY6.mp4',
-        u'md5': u'48972bdbcf1a3a2f5533e62425b41d4f',
-        u'info_dict': {
-            u"title": u"[Commie]The Legend of the Legendary Heroes - 03 - Replication Eye (Alpha Stigma)[F9410F5A]"
+        'url': 'http://auengine.com/embed.php?file=lfvlytY6&w=650&h=370',
+        'md5': '48972bdbcf1a3a2f5533e62425b41d4f',
+        'info_dict': {
+            'id': 'lfvlytY6',
+            'ext': 'mp4',
+            'title': '[Commie]The Legend of the Legendary Heroes - 03 - Replication Eye (Alpha Stigma)[F9410F5A]'
         }
     }
-    _VALID_URL = r'(?:http://)?(?:www\.)?auengine\.com/embed.php\?.*?file=([^&]+).*?'
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
+        video_id = mobj.group('id')
+
         webpage = self._download_webpage(url, video_id)
-        title = self._html_search_regex(r'<title>(?P<title>.+?)</title>',
-                webpage, u'title')
+        title = self._html_search_regex(r'<title>(?P<title>.+?)</title>', webpage, 'title')
         title = title.strip()
         links = re.findall(r'\s(?:file|url):\s*["\']([^\'"]+)["\']', webpage)
         links = map(compat_urllib_parse.unquote, links)
@@ -36,14 +41,15 @@ class AUEngineIE(InfoExtractor):
             elif '/videos/' in link:
                 video_url = link
         if not video_url:
-            raise ExtractorError(u'Could not find video URL')
-        ext = u'.' + determine_ext(video_url)
+            raise ExtractorError('Could not find video URL')
+        ext = '.' + determine_ext(video_url)
         if ext == title[-len(ext):]:
             title = title[:-len(ext)]
 
         return {
-            'id':        video_id,
-            'url':       video_url,
-            'title':     title,
+            'id': video_id,
+            'url': video_url,
+            'title': title,
             'thumbnail': thumbnail,
+            'http_referer': 'http://www.auengine.com/flowplayer/flowplayer.commercial-3.2.14.swf',
         }

youtube_dl/extractor/bambuser.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 import json
 import itertools
@@ -9,26 +11,26 @@ from ..utils import (
 
 
 class BambuserIE(InfoExtractor):
-    IE_NAME = u'bambuser'
+    IE_NAME = 'bambuser'
     _VALID_URL = r'https?://bambuser\.com/v/(?P<id>\d+)'
     _API_KEY = '005f64509e19a868399060af746a00aa'
 
     _TEST = {
-        u'url': u'http://bambuser.com/v/4050584',
+        'url': 'http://bambuser.com/v/4050584',
         # MD5 seems to be flaky, see https://travis-ci.org/rg3/youtube-dl/jobs/14051016#L388
-        #u'md5': u'fba8f7693e48fd4e8641b3fd5539a641',
-        u'info_dict': {
-            u'id': u'4050584',
-            u'ext': u'flv',
-            u'title': u'Education engineering days - lightning talks',
-            u'duration': 3741,
-            u'uploader': u'pixelversity',
-            u'uploader_id': u'344706',
+        #u'md5': 'fba8f7693e48fd4e8641b3fd5539a641',
+        'info_dict': {
+            'id': '4050584',
+            'ext': 'flv',
+            'title': 'Education engineering days - lightning talks',
+            'duration': 3741,
+            'uploader': 'pixelversity',
+            'uploader_id': '344706',
         },
-        u'params': {
+        'params': {
             # It doesn't respect the 'Range' header, it would download the whole video
             # caused the travis builds to fail: https://travis-ci.org/rg3/youtube-dl/jobs/14493845#L59
-            u'skip_download': True,
+            'skip_download': True,
         },
     }
 
@@ -53,8 +55,8 @@ class BambuserIE(InfoExtractor):
 
 
 class BambuserChannelIE(InfoExtractor):
-    IE_NAME = u'bambuser:channel'
-    _VALID_URL = r'http://bambuser.com/channel/(?P<user>.*?)(?:/|#|\?|$)'
+    IE_NAME = 'bambuser:channel'
+    _VALID_URL = r'https?://bambuser\.com/channel/(?P<user>.*?)(?:/|#|\?|$)'
     # The maximum number we can get with each request
     _STEP = 50
 
@@ -72,7 +74,7 @@ class BambuserChannelIE(InfoExtractor):
             # Without setting this header, we wouldn't get any result
             req.add_header('Referer', 'http://bambuser.com/channel/%s' % user)
             info_json = self._download_webpage(req, user,
-                u'Downloading page %d' % i)
+                'Downloading page %d' % i)
             results = json.loads(info_json)['result']
             if len(results) == 0:
                 break

youtube_dl/extractor/bandcamp.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import json
 import re
 
@@ -10,120 +12,131 @@ from ..utils import (
 
 
 class BandcampIE(InfoExtractor):
-    IE_NAME = u'Bandcamp'
-    _VALID_URL = r'http://.*?\.bandcamp\.com/track/(?P<title>.*)'
+    _VALID_URL = r'https?://.*?\.bandcamp\.com/track/(?P<title>.*)'
     _TESTS = [{
-        u'url': u'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
-        u'file': u'1812978515.mp3',
-        u'md5': u'cdeb30cdae1921719a3cbcab696ef53c',
-        u'info_dict': {
-            u"title": u"youtube-dl test song \"'/\\\u00e4\u21ad"
+        'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
+        'file': '1812978515.mp3',
+        'md5': 'c557841d5e50261777a6585648adf439',
+        'info_dict': {
+            "title": "youtube-dl  \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad",
+            "duration": 9.8485,
         },
-        u'skip': u'There is a limit of 200 free downloads / month for the test song'
+        '_skip': 'There is a limit of 200 free downloads / month for the test song'
     }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         title = mobj.group('title')
         webpage = self._download_webpage(url, title)
-        # We get the link to the free download page
         m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage)
-        if m_download is None:
+        if not m_download:
             m_trackinfo = re.search(r'trackinfo: (.+),\s*?\n', webpage)
-        if m_trackinfo:
-            json_code = m_trackinfo.group(1)
-            data = json.loads(json_code)
+            if m_trackinfo:
+                json_code = m_trackinfo.group(1)
+                data = json.loads(json_code)[0]
+
+                formats = []
+                for format_id, format_url in data['file'].items():
+                    ext, abr_str = format_id.split('-', 1)
+                    formats.append({
+                        'format_id': format_id,
+                        'url': format_url,
+                        'ext': ext,
+                        'vcodec': 'none',
+                        'acodec': ext,
+                        'abr': int(abr_str),
+                    })
+
+                self._sort_formats(formats)
 
-            for d in data:
-                formats = [{
-                    'format_id': 'format_id',
-                    'url': format_url,
-                    'ext': format_id.partition('-')[0]
-                } for format_id, format_url in sorted(d['file'].items())]
                 return {
-                    'id': compat_str(d['id']),
-                    'title': d['title'],
+                    'id': compat_str(data['id']),
+                    'title': data['title'],
                     'formats': formats,
+                    'duration': float(data['duration']),
                 }
-        else:
-            raise ExtractorError(u'No free songs found')
+            else:
+                raise ExtractorError('No free songs found')
 
         download_link = m_download.group(1)
-        id = re.search(r'var TralbumData = {(.*?)id: (?P<id>\d*?)$', 
-                       webpage, re.MULTILINE|re.DOTALL).group('id')
+        video_id = re.search(
+            r'var TralbumData = {(.*?)id: (?P<id>\d*?)$',
+            webpage, re.MULTILINE | re.DOTALL).group('id')
 
-        download_webpage = self._download_webpage(download_link, id,
-                                                  'Downloading free downloads page')
-        # We get the dictionary of the track from some javascrip code
-        info = re.search(r'items: (.*?),$',
-                         download_webpage, re.MULTILINE).group(1)
+        download_webpage = self._download_webpage(download_link, video_id, 'Downloading free downloads page')
+        # We get the dictionary of the track from some javascript code
+        info = re.search(r'items: (.*?),$', download_webpage, re.MULTILINE).group(1)
         info = json.loads(info)[0]
         # We pick mp3-320 for now, until format selection can be easily implemented.
-        mp3_info = info[u'downloads'][u'mp3-320']
+        mp3_info = info['downloads']['mp3-320']
         # If we try to use this url it says the link has expired
-        initial_url = mp3_info[u'url']
+        initial_url = mp3_info['url']
         re_url = r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$'
         m_url = re.match(re_url, initial_url)
         #We build the url we will use to get the final track url
         # This url is build in Bandcamp in the script download_bunde_*.js
-        request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), id, m_url.group('ts'))
-        final_url_webpage = self._download_webpage(request_url, id, 'Requesting download url')
+        request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), video_id, m_url.group('ts'))
+        final_url_webpage = self._download_webpage(request_url, video_id, 'Requesting download url')
         # If we could correctly generate the .rand field the url would be
         #in the "download_url" key
         final_url = re.search(r'"retry_url":"(.*?)"', final_url_webpage).group(1)
 
-        track_info = {'id':id,
-                      'title' : info[u'title'],
-                      'ext' :   'mp3',
-                      'url' :   final_url,
-                      'thumbnail' : info[u'thumb_url'],
-                      'uploader' :  info[u'artist']
-                      }
-
-        return [track_info]
+        return {
+            'id': video_id,
+            'title': info['title'],
+            'ext': 'mp3',
+            'vcodec': 'none',
+            'url': final_url,
+            'thumbnail': info.get('thumb_url'),
+            'uploader': info.get('artist'),
+        }
 
 
 class BandcampAlbumIE(InfoExtractor):
-    IE_NAME = u'Bandcamp:album'
-    _VALID_URL = r'http://.*?\.bandcamp\.com/album/(?P<title>.*)'
+    IE_NAME = 'Bandcamp:album'
+    _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<title>[^?#]+))'
 
     _TEST = {
-        u'url': u'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
-        u'playlist': [
+        'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
+        'playlist': [
             {
-                u'file': u'1353101989.mp3',
-                u'md5': u'39bc1eded3476e927c724321ddf116cf',
-                u'info_dict': {
-                    u'title': u'Intro',
+                'file': '1353101989.mp3',
+                'md5': '39bc1eded3476e927c724321ddf116cf',
+                'info_dict': {
+                    'title': 'Intro',
                 }
             },
             {
-                u'file': u'38097443.mp3',
-                u'md5': u'1a2c32e2691474643e912cc6cd4bffaa',
-                u'info_dict': {
-                    u'title': u'Kero One - Keep It Alive (Blazo remix)',
+                'file': '38097443.mp3',
+                'md5': '1a2c32e2691474643e912cc6cd4bffaa',
+                'info_dict': {
+                    'title': 'Kero One - Keep It Alive (Blazo remix)',
                 }
             },
         ],
-        u'params': {
-            u'playlistend': 2
+        'params': {
+            'playlistend': 2
         },
-        u'skip': u'Bancamp imposes download limits. See test_playlists:test_bandcamp_album for the playlist test'
+        'skip': 'Bandcamp imposes download limits. See test_playlists:test_bandcamp_album for the playlist test'
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
+        playlist_id = mobj.group('subdomain')
         title = mobj.group('title')
-        webpage = self._download_webpage(url, title)
+        display_id = title or playlist_id
+        webpage = self._download_webpage(url, display_id)
         tracks_paths = re.findall(r'<a href="(.*?)" itemprop="url">', webpage)
         if not tracks_paths:
-            raise ExtractorError(u'The page doesn\'t contain any track')
+            raise ExtractorError('The page doesn\'t contain any tracks')
         entries = [
             self.url_result(compat_urlparse.urljoin(url, t_path), ie=BandcampIE.ie_key())
             for t_path in tracks_paths]
-        title = self._search_regex(r'album_title : "(.*?)"', webpage, u'title')
+        title = self._search_regex(r'album_title : "(.*?)"', webpage, 'title')
         return {
             '_type': 'playlist',
+            'id': playlist_id,
+            'display_id': display_id,
             'title': title,
             'entries': entries,
         }

youtube_dl/extractor/bbccouk.py

@@ -0,0 +1,223 @@
+from __future__ import unicode_literals
+
+import re
+
+from .subtitles import SubtitlesInfoExtractor
+from ..utils import ExtractorError
+
+
+class BBCCoUkIE(SubtitlesInfoExtractor):
+    IE_NAME = 'bbc.co.uk'
+    IE_DESC = 'BBC iPlayer'
+    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:programmes|iplayer/episode)/(?P<id>[\da-z]{8})'
+
+    _TESTS = [
+        {
+            'url': 'http://www.bbc.co.uk/programmes/b039g8p7',
+            'info_dict': {
+                'id': 'b039d07m',
+                'ext': 'flv',
+                'title': 'Kaleidoscope: Leonard Cohen',
+                'description': 'md5:db4755d7a665ae72343779f7dacb402c',
+                'duration': 1740,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            }
+        },
+        {
+            'url': 'http://www.bbc.co.uk/iplayer/episode/b00yng5w/The_Man_in_Black_Series_3_The_Printed_Name/',
+            'info_dict': {
+                'id': 'b00yng1d',
+                'ext': 'flv',
+                'title': 'The Man in Black: Series 3: The Printed Name',
+                'description': "Mark Gatiss introduces Nicholas Pierpan's chilling tale of a writer's devilish pact with a mysterious man. Stars Ewan Bailey.",
+                'duration': 1800,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+            'skip': 'Episode is no longer available on BBC iPlayer Radio',
+        },
+        {
+            'url': 'http://www.bbc.co.uk/iplayer/episode/b03vhd1f/The_Voice_UK_Series_3_Blind_Auditions_5/',
+            'info_dict': {
+                'id': 'b00yng1d',
+                'ext': 'flv',
+                'title': 'The Voice UK: Series 3: Blind Auditions 5',
+                'description': "Emma Willis and Marvin Humes present the fifth set of blind auditions in the singing competition, as the coaches continue to build their teams based on voice alone.",
+                'duration': 5100,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+            'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
+        }
+    ]
+
+    def _extract_asx_playlist(self, connection, programme_id):
+        asx = self._download_xml(connection.get('href'), programme_id, 'Downloading ASX playlist')
+        return [ref.get('href') for ref in asx.findall('./Entry/ref')]
+
+    def _extract_connection(self, connection, programme_id):
+        formats = []
+        protocol = connection.get('protocol')
+        supplier = connection.get('supplier')
+        if protocol == 'http':
+            href = connection.get('href')
+            # ASX playlist
+            if supplier == 'asx':
+                for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)):
+                    formats.append({
+                        'url': ref,
+                        'format_id': 'ref%s_%s' % (i, supplier),
+                    })
+            # Direct link
+            else:
+                formats.append({
+                    'url': href,
+                    'format_id': supplier,
+                })
+        elif protocol == 'rtmp':
+            application = connection.get('application', 'ondemand')
+            auth_string = connection.get('authString')
+            identifier = connection.get('identifier')
+            server = connection.get('server')
+            formats.append({
+                'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string),
+                'play_path': identifier,
+                'app': '%s?%s' % (application, auth_string),
+                'page_url': 'http://www.bbc.co.uk',
+                'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf',
+                'rtmp_live': False,
+                'ext': 'flv',
+                'format_id': supplier,
+            })
+        return formats
+
+    def _extract_items(self, playlist):
+        return playlist.findall('./{http://bbc.co.uk/2008/emp/playlist}item')
+
+    def _extract_medias(self, media_selection):
+        return media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media')
+
+    def _extract_connections(self, media):
+        return media.findall('./{http://bbc.co.uk/2008/mp/mediaselection}connection')
+
+    def _extract_video(self, media, programme_id):
+        formats = []
+        vbr = int(media.get('bitrate'))
+        vcodec = media.get('encoding')
+        service = media.get('service')
+        width = int(media.get('width'))
+        height = int(media.get('height'))
+        file_size = int(media.get('media_file_size'))
+        for connection in self._extract_connections(media):
+            conn_formats = self._extract_connection(connection, programme_id)
+            for format in conn_formats:
+                format.update({
+                    'format_id': '%s_%s' % (service, format['format_id']),
+                    'width': width,
+                    'height': height,
+                    'vbr': vbr,
+                    'vcodec': vcodec,
+                    'filesize': file_size,
+                })
+            formats.extend(conn_formats)
+        return formats
+
+    def _extract_audio(self, media, programme_id):
+        formats = []
+        abr = int(media.get('bitrate'))
+        acodec = media.get('encoding')
+        service = media.get('service')
+        for connection in self._extract_connections(media):
+            conn_formats = self._extract_connection(connection, programme_id)
+            for format in conn_formats:
+                format.update({
+                    'format_id': '%s_%s' % (service, format['format_id']),
+                    'abr': abr,
+                    'acodec': acodec,
+                })
+            formats.extend(conn_formats)
+        return formats
+
+    def _extract_captions(self, media, programme_id):
+        subtitles = {}
+        for connection in self._extract_connections(media):
+            captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions')
+            lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en')
+            ps = captions.findall('./{0}body/{0}div/{0}p'.format('{http://www.w3.org/2006/10/ttaf1}'))
+            srt = ''
+            for pos, p in enumerate(ps):
+                srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (str(pos), p.get('begin'), p.get('end'),
+                                                          p.text.strip() if p.text is not None else '')
+            subtitles[lang] = srt
+        return subtitles
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        group_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, group_id, 'Downloading video page')
+        if re.search(r'id="emp-error" class="notinuk">', webpage):
+            raise ExtractorError('Currently BBC iPlayer TV programmes are available to play in the UK only',
+                expected=True)
+
+        playlist = self._download_xml('http://www.bbc.co.uk/iplayer/playlist/%s' % group_id, group_id,
+            'Downloading playlist XML')
+
+        no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems')
+        if no_items is not None:
+            reason = no_items.get('reason')
+            if reason == 'preAvailability':
+                msg = 'Episode %s is not yet available' % group_id
+            elif reason == 'postAvailability':
+                msg = 'Episode %s is no longer available' % group_id
+            else:
+                msg = 'Episode %s is not available: %s' % (group_id, reason)
+            raise ExtractorError(msg, expected=True)
+
+        formats = []
+        subtitles = None
+
+        for item in self._extract_items(playlist):
+            kind = item.get('kind')
+            if kind != 'programme' and kind != 'radioProgramme':
+                continue
+            title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text
+            description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text
+
+            programme_id = item.get('identifier')
+            duration = int(item.get('duration'))
+
+            media_selection = self._download_xml(
+                'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s'  % programme_id,
+                programme_id, 'Downloading media selection XML')
+
+            for media in self._extract_medias(media_selection):
+                kind = media.get('kind')
+                if kind == 'audio':
+                    formats.extend(self._extract_audio(media, programme_id))
+                elif kind == 'video':
+                    formats.extend(self._extract_video(media, programme_id))
+                elif kind == 'captions':
+                    subtitles = self._extract_captions(media, programme_id)
+
+        if self._downloader.params.get('listsubtitles', False):
+            self._list_available_subtitles(programme_id, subtitles)
+            return
+
+        self._sort_formats(formats)
+
+        return {
+            'id': programme_id,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'formats': formats,
+            'subtitles': subtitles,
+        }

youtube_dl/extractor/bilibili.py

@@ -0,0 +1,106 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_parse_qs,
+    ExtractorError,
+    int_or_none,
+    unified_strdate,
+)
+
+
+class BiliBiliIE(InfoExtractor):
+    _VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>[0-9]+)/'
+
+    _TEST = {
+        'url': 'http://www.bilibili.tv/video/av1074402/',
+        'md5': '2c301e4dab317596e837c3e7633e7d86',
+        'info_dict': {
+            'id': '1074402',
+            'ext': 'flv',
+            'title': '【金坷垃】金泡沫',
+            'duration': 308,
+            'upload_date': '20140420',
+            'thumbnail': 're:^https?://.+\.jpg',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        video_code = self._search_regex(
+            r'(?s)<div itemprop="video".*?>(.*?)</div>', webpage, 'video code')
+
+        title = self._html_search_meta(
+            'media:title', video_code, 'title', fatal=True)
+        duration_str = self._html_search_meta(
+            'duration', video_code, 'duration')
+        if duration_str is None:
+            duration = None
+        else:
+            duration_mobj = re.match(
+                r'^T(?:(?P<hours>[0-9]+)H)?(?P<minutes>[0-9]+)M(?P<seconds>[0-9]+)S$',
+                duration_str)
+            duration = (
+                int_or_none(duration_mobj.group('hours'), default=0) * 3600 +
+                int(duration_mobj.group('minutes')) * 60 +
+                int(duration_mobj.group('seconds')))
+        upload_date = unified_strdate(self._html_search_meta(
+            'uploadDate', video_code, fatal=False))
+        thumbnail = self._html_search_meta(
+            'thumbnailUrl', video_code, 'thumbnail', fatal=False)
+
+        player_params = compat_parse_qs(self._html_search_regex(
+            r'<iframe .*?class="player" src="https://secure\.bilibili\.(?:tv|com)/secure,([^"]+)"',
+            webpage, 'player params'))
+
+        if 'cid' in player_params:
+            cid = player_params['cid'][0]
+
+            lq_doc = self._download_xml(
+                'http://interface.bilibili.cn/v_cdn_play?cid=%s' % cid,
+                video_id,
+                note='Downloading LQ video info'
+            )
+            lq_durl = lq_doc.find('.//durl')
+            formats = [{
+                'format_id': 'lq',
+                'quality': 1,
+                'url': lq_durl.find('./url').text,
+                'filesize': int_or_none(
+                    lq_durl.find('./size'), get_attr='text'),
+            }]
+
+            hq_doc = self._download_xml(
+                'http://interface.bilibili.cn/playurl?cid=%s' % cid,
+                video_id,
+                note='Downloading HQ video info',
+                fatal=False,
+            )
+            if hq_doc is not False:
+                hq_durl = hq_doc.find('.//durl')
+                formats.append({
+                    'format_id': 'hq',
+                    'quality': 2,
+                    'ext': 'flv',
+                    'url': hq_durl.find('./url').text,
+                    'filesize': int_or_none(
+                        hq_durl.find('./size'), get_attr='text'),
+                })
+        else:
+            raise ExtractorError('Unsupported player parameters: %r' % (player_params,))
+
+        self._sort_formats(formats)
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'duration': duration,
+            'upload_date': upload_date,
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/blinkx.py

@@ -0,0 +1,89 @@
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import remove_start
+
+
+class BlinkxIE(InfoExtractor):
+    _VALID_URL = r'^(?:https?://(?:www\.)blinkx\.com/#?ce/|blinkx:)(?P<id>[^?]+)'
+    IE_NAME = 'blinkx'
+
+    _TEST = {
+        'url': 'http://www.blinkx.com/ce/8aQUy7GVFYgFzpKhT0oqsilwOGFRVXk3R1ZGWWdGenBLaFQwb3FzaWx3OGFRVXk3R1ZGWWdGenB',
+        'md5': '2e9a07364af40163a908edbf10bb2492',
+        'info_dict': {
+            'id': '8aQUy7GV',
+            'ext': 'mp4',
+            'title': 'Police Car Rolls Away',
+            'uploader': 'stupidvideos.com',
+            'upload_date': '20131215',
+            'timestamp': 1387068000,
+            'description': 'A police car gently rolls away from a fight. Maybe it felt weird being around a confrontation and just had to get out of there!',
+            'duration': 14.886,
+            'thumbnails': [{
+                'width': 100,
+                'height': 76,
+                'resolution': '100x76',
+                'url': 'http://cdn.blinkx.com/stream/b/41/StupidVideos/20131215/1873969261/1873969261_tn_0.jpg',
+            }],
+        },
+    }
+
+    def _real_extract(self, rl):
+        m = re.match(self._VALID_URL, rl)
+        video_id = m.group('id')
+        display_id = video_id[:8]
+
+        api_url = ('https://apib4.blinkx.com/api.php?action=play_video&' +
+                   'video=%s' % video_id)
+        data_json = self._download_webpage(api_url, display_id)
+        data = json.loads(data_json)['api']['results'][0]
+        duration = None
+        thumbnails = []
+        formats = []
+        for m in data['media']:
+            if m['type'] == 'jpg':
+                thumbnails.append({
+                    'url': m['link'],
+                    'width': int(m['w']),
+                    'height': int(m['h']),
+                })
+            elif m['type'] == 'original':
+                duration = m['d']
+            elif m['type'] == 'youtube':
+                yt_id = m['link']
+                self.to_screen('Youtube video detected: %s' % yt_id)
+                return self.url_result(yt_id, 'Youtube', video_id=yt_id)
+            elif m['type'] in ('flv', 'mp4'):
+                vcodec = remove_start(m['vcodec'], 'ff')
+                acodec = remove_start(m['acodec'], 'ff')
+                tbr = (int(m['vbr']) + int(m['abr'])) // 1000
+                format_id = '%s-%sk-%s' % (vcodec, tbr, m['w'])
+                formats.append({
+                    'format_id': format_id,
+                    'url': m['link'],
+                    'vcodec': vcodec,
+                    'acodec': acodec,
+                    'abr': int(m['abr']) // 1000,
+                    'vbr': int(m['vbr']) // 1000,
+                    'tbr': tbr,
+                    'width': int(m['w']),
+                    'height': int(m['h']),
+                })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': display_id,
+            'fullid': video_id,
+            'title': data['title'],
+            'formats': formats,
+            'uploader': data['channel_name'],
+            'timestamp': data['pubdate_epoch'],
+            'description': data.get('description'),
+            'thumbnails': thumbnails,
+            'duration': duration,
+        }

youtube_dl/extractor/bliptv.py

@@ -1,160 +1,169 @@
-import datetime
-import json
-import os
+from __future__ import unicode_literals
+
 import re
-import socket
 
 from .common import InfoExtractor
+from .subtitles import SubtitlesInfoExtractor
 from ..utils import (
-    compat_http_client,
-    compat_parse_qs,
-    compat_str,
-    compat_urllib_error,
-    compat_urllib_parse_urlparse,
     compat_urllib_request,
-
-    ExtractorError,
     unescapeHTML,
+    parse_iso8601,
+    compat_urlparse,
+    clean_html,
+    compat_str,
 )
 
 
-class BlipTVIE(InfoExtractor):
-    """Information extractor for blip.tv"""
+class BlipTVIE(SubtitlesInfoExtractor):
+    _VALID_URL = r'https?://(?:\w+\.)?blip\.tv/(?:(?:.+-|rss/flash/)(?P<id>\d+)|((?:play/|api\.swf#)(?P<lookup_id>[\da-zA-Z+]+)))'
 
-    _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv/((.+/)|(play/)|(api\.swf#))(.+)$'
-    _URL_EXT = r'^.*\.([a-z0-9]+)$'
-    IE_NAME = u'blip.tv'
-    _TEST = {
-        u'url': u'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352',
-        u'file': u'5779306.m4v',
-        u'md5': u'80baf1ec5c3d2019037c1c707d676b9f',
-        u'info_dict': {
-            u"upload_date": u"20111205", 
-            u"description": u"md5:9bc31f227219cde65e47eeec8d2dc596", 
-            u"uploader": u"Comic Book Resources - CBR TV", 
-            u"title": u"CBR EXCLUSIVE: \"Gotham City Imposters\" Bats VS Jokerz Short 3"
+    _TESTS = [
+        {
+            'url': 'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352',
+            'md5': 'c6934ad0b6acf2bd920720ec888eb812',
+            'info_dict': {
+                'id': '5779306',
+                'ext': 'mov',
+                'title': 'CBR EXCLUSIVE: "Gotham City Imposters" Bats VS Jokerz Short 3',
+                'description': 'md5:9bc31f227219cde65e47eeec8d2dc596',
+                'timestamp': 1323138843,
+                'upload_date': '20111206',
+                'uploader': 'cbr',
+                'uploader_id': '679425',
+                'duration': 81,
+            }
+        },
+        {
+            # https://github.com/rg3/youtube-dl/pull/2274
+            'note': 'Video with subtitles',
+            'url': 'http://blip.tv/play/h6Uag5OEVgI.html',
+            'md5': '309f9d25b820b086ca163ffac8031806',
+            'info_dict': {
+                'id': '6586561',
+                'ext': 'mp4',
+                'title': 'Red vs. Blue Season 11 Episode 1',
+                'description': 'One-Zero-One',
+                'timestamp': 1371261608,
+                'upload_date': '20130615',
+                'uploader': 'redvsblue',
+                'uploader_id': '792887',
+                'duration': 279,
+            }
         }
-    }
-
-    def report_direct_download(self, title):
-        """Report information extraction."""
-        self.to_screen(u'%s: Direct download detected' % title)
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
+        lookup_id = mobj.group('lookup_id')
 
         # See https://github.com/rg3/youtube-dl/issues/857
-        api_mobj = re.match(r'http://a\.blip\.tv/api\.swf#(?P<video_id>[\d\w]+)', url)
-        if api_mobj is not None:
-            url = 'http://blip.tv/play/g_%s' % api_mobj.group('video_id')
-        urlp = compat_urllib_parse_urlparse(url)
-        if urlp.path.startswith('/play/'):
-            request = compat_urllib_request.Request(url)
-            response = compat_urllib_request.urlopen(request)
-            redirecturl = response.geturl()
-            rurlp = compat_urllib_parse_urlparse(redirecturl)
-            file_id = compat_parse_qs(rurlp.fragment)['file'][0].rpartition('/')[2]
-            url = 'http://blip.tv/a/a-' + file_id
-            return self._real_extract(url)
-
-
-        if '?' in url:
-            cchar = '&'
+        if lookup_id:
+            info_page = self._download_webpage(
+                'http://blip.tv/play/%s.x?p=1' % lookup_id, lookup_id, 'Resolving lookup id')
+            video_id = self._search_regex(r'data-episode-id="([0-9]+)', info_page, 'video_id')
         else:
-            cchar = '?'
-        json_url = url + cchar + 'skin=json&version=2&no_wrap=1'
-        request = compat_urllib_request.Request(json_url)
-        request.add_header('User-Agent', 'iTunes/10.6.1')
-        self.report_extraction(mobj.group(1))
-        info = None
-        try:
-            urlh = compat_urllib_request.urlopen(request)
-            if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download
-                basename = url.split('/')[-1]
-                title,ext = os.path.splitext(basename)
-                title = title.decode('UTF-8')
-                ext = ext.replace('.', '')
-                self.report_direct_download(title)
-                info = {
-                    'id': title,
-                    'url': url,
-                    'uploader': None,
-                    'upload_date': None,
-                    'title': title,
-                    'ext': ext,
-                    'urlhandle': urlh
+            video_id = mobj.group('id')
+
+        rss = self._download_xml('http://blip.tv/rss/flash/%s' % video_id, video_id, 'Downloading video RSS')
+
+        def blip(s):
+            return '{http://blip.tv/dtd/blip/1.0}%s' % s
+
+        def media(s):
+            return '{http://search.yahoo.com/mrss/}%s' % s
+
+        def itunes(s):
+            return '{http://www.itunes.com/dtds/podcast-1.0.dtd}%s' % s
+
+        item = rss.find('channel/item')
+
+        video_id = item.find(blip('item_id')).text
+        title = item.find('./title').text
+        description = clean_html(compat_str(item.find(blip('puredescription')).text))
+        timestamp = parse_iso8601(item.find(blip('datestamp')).text)
+        uploader = item.find(blip('user')).text
+        uploader_id = item.find(blip('userid')).text
+        duration = int(item.find(blip('runtime')).text)
+        media_thumbnail = item.find(media('thumbnail'))
+        thumbnail = media_thumbnail.get('url') if media_thumbnail is not None else item.find(itunes('image')).text
+        categories = [category.text for category in item.findall('category')]
+
+        formats = []
+        subtitles = {}
+
+        media_group = item.find(media('group'))
+        for media_content in media_group.findall(media('content')):
+            url = media_content.get('url')
+            role = media_content.get(blip('role'))
+            msg = self._download_webpage(
+                url + '?showplayer=20140425131715&referrer=http://blip.tv&mask=7&skin=flashvars&view=url',
+                video_id, 'Resolving URL for %s' % role)
+            real_url = compat_urlparse.parse_qs(msg)['message'][0]
+
+            media_type = media_content.get('type')
+            if media_type == 'text/srt' or url.endswith('.srt'):
+                LANGS = {
+                    'english': 'en',
                 }
-        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-            raise ExtractorError(u'ERROR: unable to download video info webpage: %s' % compat_str(err))
-        if info is None: # Regular URL
-            try:
-                json_code_bytes = urlh.read()
-                json_code = json_code_bytes.decode('utf-8')
-            except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-                raise ExtractorError(u'Unable to read video info webpage: %s' % compat_str(err))
+                lang = role.rpartition('-')[-1].strip().lower()
+                langcode = LANGS.get(lang, lang)
+                subtitles[langcode] = url
+            elif media_type.startswith('video/'):
+                formats.append({
+                    'url': real_url,
+                    'format_id': role,
+                    'format_note': media_type,
+                    'vcodec': media_content.get(blip('vcodec')),
+                    'acodec': media_content.get(blip('acodec')),
+                    'filesize': media_content.get('filesize'),
+                    'width': int(media_content.get('width')),
+                    'height': int(media_content.get('height')),
+                })
+        self._sort_formats(formats)
 
-            try:
-                json_data = json.loads(json_code)
-                if 'Post' in json_data:
-                    data = json_data['Post']
-                else:
-                    data = json_data
+        # subtitles
+        video_subtitles = self.extract_subtitles(video_id, subtitles)
+        if self._downloader.params.get('listsubtitles', False):
+            self._list_available_subtitles(video_id, subtitles)
+            return
 
-                upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
-                if 'additionalMedia' in data:
-                    formats = sorted(data['additionalMedia'], key=lambda f: int(f['media_height']))
-                    best_format = formats[-1]
-                    video_url = best_format['url']
-                else:
-                    video_url = data['media']['url']
-                umobj = re.match(self._URL_EXT, video_url)
-                if umobj is None:
-                    raise ValueError('Can not determine filename extension')
-                ext = umobj.group(1)
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'timestamp': timestamp,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'duration': duration,
+            'thumbnail': thumbnail,
+            'categories': categories,
+            'formats': formats,
+            'subtitles': video_subtitles,
+        }
 
-                info = {
-                    'id': compat_str(data['item_id']),
-                    'url': video_url,
-                    'uploader': data['display_name'],
-                    'upload_date': upload_date,
-                    'title': data['title'],
-                    'ext': ext,
-                    'format': data['media']['mimeType'],
-                    'thumbnail': data['thumbnailUrl'],
-                    'description': data['description'],
-                    'player_url': data['embedUrl'],
-                    'user_agent': 'iTunes/10.6.1',
-                }
-            except (ValueError,KeyError) as err:
-                raise ExtractorError(u'Unable to parse video information: %s' % repr(err))
-
-        return [info]
+    def _download_subtitle_url(self, sub_lang, url):
+        # For some weird reason, blip.tv serves a video instead of subtitles
+        # when we request with a common UA
+        req = compat_urllib_request.Request(url)
+        req.add_header('Youtubedl-user-agent', 'youtube-dl')
+        return self._download_webpage(req, None, note=False)
 
 
 class BlipTVUserIE(InfoExtractor):
-    """Information Extractor for blip.tv users."""
-
     _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$'
     _PAGE_SIZE = 12
-    IE_NAME = u'blip.tv:user'
+    IE_NAME = 'blip.tv:user'
 
     def _real_extract(self, url):
-        # Extract username
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
-
         username = mobj.group(1)
 
         page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1'
 
-        page = self._download_webpage(url, username, u'Downloading user page')
+        page = self._download_webpage(url, username, 'Downloading user page')
         mobj = re.search(r'data-users-id="([^"]+)"', page)
         page_base = page_base % mobj.group(1)
 
-
         # Download video ids using BlipTV Ajax calls. Result size per
         # query is limited (currently to 12 videos) so we need to query
         # page by page until there are no video ids - it means we got
@@ -165,8 +174,8 @@ class BlipTVUserIE(InfoExtractor):
 
         while True:
             url = page_base + "&page=" + str(pagenum)
-            page = self._download_webpage(url, username,
-                                          u'Downloading video ids from page %d' % pagenum)
+            page = self._download_webpage(
+                url, username, 'Downloading video ids from page %d' % pagenum)
 
             # Extract video identifiers
             ids_in_page = []
@@ -188,6 +197,6 @@ class BlipTVUserIE(InfoExtractor):
 
             pagenum += 1
 
-        urls = [u'http://blip.tv/%s' % video_id for video_id in video_ids]
+        urls = ['http://blip.tv/%s' % video_id for video_id in video_ids]
         url_entries = [self.url_result(vurl, 'BlipTV') for vurl in urls]
-        return [self.playlist_result(url_entries, playlist_title = username)]
+        return [self.playlist_result(url_entries, playlist_title=username)]

youtube_dl/extractor/bloomberg.py

@@ -1,21 +1,21 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 
 
 class BloombergIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<name>.+?).html'
+    _VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<name>.+?)\.html'
 
     _TEST = {
-        u'url': u'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html',
-        u'file': u'12bzhqZTqQHmmlA8I-i0NpzJgcG5NNYX.mp4',
-        u'info_dict': {
-            u'title': u'Shah\'s Presentation on Foreign-Exchange Strategies',
-            u'description': u'md5:abc86e5236f9f0e4866c59ad36736686',
-        },
-        u'params': {
-            # Requires ffmpeg (m3u8 manifest)
-            u'skip_download': True,
+        'url': 'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html',
+        'md5': '7bf08858ff7c203c870e8a6190e221e5',
+        'info_dict': {
+            'id': 'qurhIVlJSB6hzkVi229d8g',
+            'ext': 'flv',
+            'title': 'Shah\'s Presentation on Foreign-Exchange Strategies',
+            'description': 'md5:0681e0d30dcdfc6abf34594961d8ea88',
         },
     }
 
@@ -23,5 +23,16 @@ class BloombergIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         name = mobj.group('name')
         webpage = self._download_webpage(url, name)
-        ooyala_url = self._og_search_video_url(webpage)
-        return self.url_result(ooyala_url, ie='Ooyala')
+        f4m_url = self._search_regex(
+            r'<source src="(https?://[^"]+\.f4m.*?)"', webpage,
+            'f4m url')
+        title = re.sub(': Video$', '', self._og_search_title(webpage))
+
+        return {
+            'id': name.split('-')[-1],
+            'title': title,
+            'url': f4m_url,
+            'ext': 'flv',
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }

youtube_dl/extractor/br.py

@@ -0,0 +1,137 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+)
+
+
+class BRIE(InfoExtractor):
+    IE_DESC = 'Bayerischer Rundfunk Mediathek'
+    _VALID_URL = r'https?://(?:www\.)?br\.de/(?:[a-z0-9\-_]+/)+(?P<id>[a-z0-9\-_]+)\.html'
+    _BASE_URL = 'http://www.br.de'
+
+    _TESTS = [
+        {
+            'url': 'http://www.br.de/mediathek/video/sendungen/heimatsound/heimatsound-festival-2014-trailer-100.html',
+            'md5': '93556dd2bcb2948d9259f8670c516d59',
+            'info_dict': {
+                'id': '25e279aa-1ffd-40fd-9955-5325bd48a53a',
+                'ext': 'mp4',
+                'title': 'Am 1. und 2. August in Oberammergau',
+                'description': 'md5:dfd224e5aa6819bc1fcbb7826a932021',
+            }
+        },
+        {
+            'url': 'http://www.br.de/mediathek/video/sendungen/unter-unserem-himmel/unter-unserem-himmel-alpen-ueber-den-pass-100.html',
+            'md5': 'ab451b09d861dbed7d7cc9ab0be19ebe',
+            'info_dict': {
+                'id': '2c060e69-3a27-4e13-b0f0-668fac17d812',
+                'ext': 'mp4',
+                'title': 'Über den Pass',
+                'description': 'Die Eroberung der Alpen: Über den Pass',
+            }
+        },
+        {
+            'url': 'http://www.br.de/nachrichten/schaeuble-haushaltsentwurf-bundestag-100.html',
+            'md5': '3db0df1a9a9cd9fa0c70e6ea8aa8e820',
+            'info_dict': {
+                'id': 'c6aae3de-2cf9-43f2-957f-f17fef9afaab',
+                'ext': 'aac',
+                'title': '"Keine neuen Schulden im nächsten Jahr"',
+                'description': 'Haushaltsentwurf: "Keine neuen Schulden im nächsten Jahr"',
+            }
+        },
+        {
+            'url': 'http://www.br.de/radio/bayern1/service/team/videos/team-video-erdelt100.html',
+            'md5': 'dbab0aef2e047060ea7a21fc1ce1078a',
+            'info_dict': {
+                'id': '6ba73750-d405-45d3-861d-1ce8c524e059',
+                'ext': 'mp4',
+                'title': 'Umweltbewusster Häuslebauer',
+                'description': 'Uwe Erdelt: Umweltbewusster Häuslebauer',
+            }
+        },
+        {
+            'url': 'http://www.br.de/fernsehen/br-alpha/sendungen/kant-fuer-anfaenger/kritik-der-reinen-vernunft/kant-kritik-01-metaphysik100.html',
+            'md5': '23bca295f1650d698f94fc570977dae3',
+            'info_dict': {
+                'id': 'd982c9ce-8648-4753-b358-98abb8aec43d',
+                'ext': 'mp4',
+                'title': 'Folge 1 - Metaphysik',
+                'description': 'Kant für Anfänger: Folge 1 - Metaphysik',
+                'uploader': 'Eva Maria Steimle',
+                'upload_date': '20140117',
+            }
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('id')
+        page = self._download_webpage(url, display_id)
+        xml_url = self._search_regex(
+            r"return BRavFramework\.register\(BRavFramework\('avPlayer_(?:[a-f0-9-]{36})'\)\.setup\({dataURL:'(/(?:[a-z0-9\-]+/)+[a-z0-9/~_.-]+)'}\)\);", page, 'XMLURL')
+        xml = self._download_xml(self._BASE_URL + xml_url, None)
+
+        medias = []
+
+        for xml_media in xml.findall('video') + xml.findall('audio'):
+            media = {
+                'id': xml_media.get('externalId'),
+                'title': xml_media.find('title').text,
+                'formats': self._extract_formats(xml_media.find('assets')),
+                'thumbnails': self._extract_thumbnails(xml_media.find('teaserImage/variants')),
+                'description': ' '.join(xml_media.find('shareTitle').text.splitlines()),
+                'webpage_url': xml_media.find('permalink').text
+            }
+            if xml_media.find('author').text:
+                media['uploader'] = xml_media.find('author').text
+            if xml_media.find('broadcastDate').text:
+                media['upload_date'] = ''.join(reversed(xml_media.find('broadcastDate').text.split('.')))
+            medias.append(media)
+
+        if len(medias) > 1:
+            self._downloader.report_warning(
+                'found multiple medias; please '
+                'report this with the video URL to http://yt-dl.org/bug')
+        if not medias:
+            raise ExtractorError('No media entries found')
+        return medias[0]
+
+    def _extract_formats(self, assets):
+
+        def text_or_none(asset, tag):
+            elem = asset.find(tag)
+            return None if elem is None else elem.text
+
+        formats = [{
+            'url': text_or_none(asset, 'downloadUrl'),
+            'ext': text_or_none(asset, 'mediaType'),
+            'format_id': asset.get('type'),
+            'width': int_or_none(text_or_none(asset, 'frameWidth')),
+            'height': int_or_none(text_or_none(asset, 'frameHeight')),
+            'tbr': int_or_none(text_or_none(asset, 'bitrateVideo')),
+            'abr': int_or_none(text_or_none(asset, 'bitrateAudio')),
+            'vcodec': text_or_none(asset, 'codecVideo'),
+            'acodec': text_or_none(asset, 'codecAudio'),
+            'container': text_or_none(asset, 'mediaType'),
+            'filesize': int_or_none(text_or_none(asset, 'size')),
+        } for asset in assets.findall('asset')
+            if asset.find('downloadUrl') is not None]
+
+        self._sort_formats(formats)
+        return formats
+
+    def _extract_thumbnails(self, variants):
+        thumbnails = [{
+            'url': self._BASE_URL + variant.find('url').text,
+            'width': int_or_none(variant.find('width').text),
+            'height': int_or_none(variant.find('height').text),
+        } for variant in variants.findall('variant')]
+        thumbnails.sort(key=lambda x: x['width'] * x['height'], reverse=True)
+        return thumbnails

youtube_dl/extractor/breakcom.py

@@ -1,18 +1,20 @@
+from __future__ import unicode_literals
+
 import re
 import json
 
 from .common import InfoExtractor
-from ..utils import determine_ext
 
 
 class BreakIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?break\.com/video/([^/]+)'
+    _VALID_URL = r'http://(?:www\.)?break\.com/video/([^/]+)'
     _TEST = {
-        u'url': u'http://www.break.com/video/when-girls-act-like-guys-2468056',
-        u'file': u'2468056.mp4',
-        u'md5': u'a3513fb1547fba4fb6cfac1bffc6c46b',
-        u'info_dict': {
-            u"title": u"When Girls Act Like D-Bags"
+        'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056',
+        'md5': 'a3513fb1547fba4fb6cfac1bffc6c46b',
+        'info_dict': {
+            'id': '2468056',
+            'ext': 'mp4',
+            'title': 'When Girls Act Like D-Bags',
         }
     }
 
@@ -21,18 +23,18 @@ class BreakIE(InfoExtractor):
         video_id = mobj.group(1).split("-")[-1]
         embed_url = 'http://www.break.com/embed/%s' % video_id
         webpage = self._download_webpage(embed_url, video_id)
-        info_json = self._search_regex(r'var embedVars = ({.*?});', webpage,
-                                       u'info json', flags=re.DOTALL)
+        info_json = self._search_regex(r'var embedVars = ({.*})\s*?</script>',
+            webpage, 'info json', flags=re.DOTALL)
         info = json.loads(info_json)
         video_url = info['videoUri']
-        m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', video_url)
-        if m_youtube is not None:
-            return self.url_result(m_youtube.group(1), 'Youtube')
+        youtube_id = info.get('youtubeId')
+        if youtube_id:
+            return self.url_result(youtube_id, 'Youtube')
+
         final_url = video_url + '?' + info['AuthToken']
-        return [{
-            'id':        video_id,
-            'url':       final_url,
-            'ext':       determine_ext(final_url),
-            'title':     info['contentName'],
+        return {
+            'id': video_id,
+            'url': final_url,
+            'title': info['contentName'],
             'thumbnail': info['thumbUri'],
-        }]
+        }

youtube_dl/extractor/brightcove.py

@@ -1,4 +1,5 @@
 # encoding: utf-8
+from __future__ import unicode_literals
 
 import re
 import json
@@ -8,51 +9,82 @@ from .common import InfoExtractor
 from ..utils import (
     compat_urllib_parse,
     find_xpath_attr,
+    fix_xml_ampersands,
     compat_urlparse,
     compat_str,
     compat_urllib_request,
+    compat_parse_qs,
 
+    determine_ext,
     ExtractorError,
+    unsmuggle_url,
+    unescapeHTML,
 )
 
 
 class BrightcoveIE(InfoExtractor):
     _VALID_URL = r'https?://.*brightcove\.com/(services|viewer).*\?(?P<query>.*)'
     _FEDERATED_URL_TEMPLATE = 'http://c.brightcove.com/services/viewer/htmlFederated?%s'
-    _PLAYLIST_URL_TEMPLATE = 'http://c.brightcove.com/services/json/experience/runtime/?command=get_programming_for_experience&playerKey=%s'
 
     _TESTS = [
         {
             # From http://www.8tv.cat/8aldia/videos/xavier-sala-i-martin-aquesta-tarda-a-8-al-dia/
-            u'url': u'http://c.brightcove.com/services/viewer/htmlFederated?playerID=1654948606001&flashID=myExperience&%40videoPlayer=2371591881001',
-            u'file': u'2371591881001.mp4',
-            u'md5': u'8eccab865181d29ec2958f32a6a754f5',
-            u'note': u'Test Brightcove downloads and detection in GenericIE',
-            u'info_dict': {
-                u'title': u'Xavier Sala i Martín: “Un banc que no presta és un banc zombi que no serveix per a res”',
-                u'uploader': u'8TV',
-                u'description': u'md5:a950cc4285c43e44d763d036710cd9cd',
+            'url': 'http://c.brightcove.com/services/viewer/htmlFederated?playerID=1654948606001&flashID=myExperience&%40videoPlayer=2371591881001',
+            'md5': '5423e113865d26e40624dce2e4b45d95',
+            'note': 'Test Brightcove downloads and detection in GenericIE',
+            'info_dict': {
+                'id': '2371591881001',
+                'ext': 'mp4',
+                'title': 'Xavier Sala i Martín: “Un banc que no presta és un banc zombi que no serveix per a res”',
+                'uploader': '8TV',
+                'description': 'md5:a950cc4285c43e44d763d036710cd9cd',
             }
         },
         {
             # From http://medianetwork.oracle.com/video/player/1785452137001
-            u'url': u'http://c.brightcove.com/services/viewer/htmlFederated?playerID=1217746023001&flashID=myPlayer&%40videoPlayer=1785452137001',
-            u'file': u'1785452137001.flv',
-            u'info_dict': {
-                u'title': u'JVMLS 2012: Arrays 2.0 - Opportunities and Challenges',
-                u'description': u'John Rose speaks at the JVM Language Summit, August 1, 2012.',
-                u'uploader': u'Oracle',
+            'url': 'http://c.brightcove.com/services/viewer/htmlFederated?playerID=1217746023001&flashID=myPlayer&%40videoPlayer=1785452137001',
+            'info_dict': {
+                'id': '1785452137001',
+                'ext': 'flv',
+                'title': 'JVMLS 2012: Arrays 2.0 - Opportunities and Challenges',
+                'description': 'John Rose speaks at the JVM Language Summit, August 1, 2012.',
+                'uploader': 'Oracle',
             },
         },
         {
             # From http://mashable.com/2013/10/26/thermoelectric-bracelet-lets-you-control-your-body-temperature/
-            u'url': u'http://c.brightcove.com/services/viewer/federated_f9?&playerID=1265504713001&publisherID=AQ%7E%7E%2CAAABBzUwv1E%7E%2CxP-xFHVUstiMFlNYfvF4G9yFnNaqCw_9&videoID=2750934548001',
-            u'info_dict': {
-                u'id': u'2750934548001',
-                u'ext': u'mp4',
-                u'title': u'This Bracelet Acts as a Personal Thermostat',
-                u'description': u'md5:547b78c64f4112766ccf4e151c20b6a0',
-                u'uploader': u'Mashable',
+            'url': 'http://c.brightcove.com/services/viewer/federated_f9?&playerID=1265504713001&publisherID=AQ%7E%7E%2CAAABBzUwv1E%7E%2CxP-xFHVUstiMFlNYfvF4G9yFnNaqCw_9&videoID=2750934548001',
+            'info_dict': {
+                'id': '2750934548001',
+                'ext': 'mp4',
+                'title': 'This Bracelet Acts as a Personal Thermostat',
+                'description': 'md5:547b78c64f4112766ccf4e151c20b6a0',
+                'uploader': 'Mashable',
+            },
+        },
+        {
+            # test that the default referer works
+            # from http://national.ballet.ca/interact/video/Lost_in_Motion_II/
+            'url': 'http://link.brightcove.com/services/player/bcpid756015033001?bckey=AQ~~,AAAApYJi_Ck~,GxhXCegT1Dp39ilhXuxMJxasUhVNZiil&bctid=2878862109001',
+            'info_dict': {
+                'id': '2878862109001',
+                'ext': 'mp4',
+                'title': 'Lost in Motion II',
+                'description': 'md5:363109c02998fee92ec02211bd8000df',
+                'uploader': 'National Ballet of Canada',
+            },
+        },
+        {
+            # test flv videos served by akamaihd.net
+            # From http://www.redbull.com/en/bike/stories/1331655643987/replay-uci-dh-world-cup-2014-from-fort-william
+            'url': 'http://c.brightcove.com/services/viewer/htmlFederated?%40videoPlayer=ref%3ABC2996102916001&linkBaseURL=http%3A%2F%2Fwww.redbull.com%2Fen%2Fbike%2Fvideos%2F1331655630249%2Freplay-uci-fort-william-2014-dh&playerKey=AQ%7E%7E%2CAAAApYJ7UqE%7E%2Cxqr_zXk0I-zzNndy8NlHogrCb5QdyZRf&playerID=1398061561001#__youtubedl_smuggle=%7B%22Referer%22%3A+%22http%3A%2F%2Fwww.redbull.com%2Fen%2Fbike%2Fstories%2F1331655643987%2Freplay-uci-dh-world-cup-2014-from-fort-william%22%7D',
+            # The md5 checksum changes on each download
+            'info_dict': {
+                'id': '2996102916001',
+                'ext': 'flv',
+                'title': 'UCI MTB World Cup 2014: Fort William, UK - Downhill Finals',
+                'uploader': 'Red Bull TV',
+                'description': 'UCI MTB World Cup 2014: Fort William, UK - Downhill Finals',
             },
         },
     ]
@@ -68,18 +100,34 @@ class BrightcoveIE(InfoExtractor):
         object_str = re.sub(r'(<param name="[^"]+" value="[^"]+")>',
                             lambda m: m.group(1) + '/>', object_str)
         # Fix up some stupid XML, see https://github.com/rg3/youtube-dl/issues/1608
-        object_str = object_str.replace(u'<--', u'<!--')
+        object_str = object_str.replace('<--', '<!--')
+        object_str = fix_xml_ampersands(object_str)
+
+        object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8'))
+
+        fv_el = find_xpath_attr(object_doc, './param', 'name', 'flashVars')
+        if fv_el is not None:
+            flashvars = dict(
+                (k, v[0])
+                for k, v in compat_parse_qs(fv_el.attrib['value']).items())
+        else:
+            flashvars = {}
 
-        object_doc = xml.etree.ElementTree.fromstring(object_str)
-        assert u'BrightcoveExperience' in object_doc.attrib['class']
-        params = {'flashID': object_doc.attrib['id'],
-                  'playerID': find_xpath_attr(object_doc, './param', 'name', 'playerID').attrib['value'],
-                  }
         def find_param(name):
+            if name in flashvars:
+                return flashvars[name]
             node = find_xpath_attr(object_doc, './param', 'name', name)
             if node is not None:
                 return node.attrib['value']
             return None
+
+        params = {}
+
+        playerID = find_param('playerID')
+        if playerID is None:
+            raise ExtractorError('Cannot find player ID')
+        params['playerID'] = playerID
+
         playerKey = find_param('playerKey')
         # Not all pages define this value
         if playerKey is not None:
@@ -96,18 +144,36 @@ class BrightcoveIE(InfoExtractor):
 
     @classmethod
     def _extract_brightcove_url(cls, webpage):
-        """Try to extract the brightcove url from the wepbage, returns None
+        """Try to extract the brightcove url from the webpage, returns None
         if it can't be found
         """
-        m_brightcove = re.search(
-            r'<object[^>]+?class=([\'"])[^>]*?BrightcoveExperience.*?\1.+?</object>',
-            webpage, re.DOTALL)
-        if m_brightcove is not None:
-            return cls._build_brighcove_url(m_brightcove.group())
-        else:
-            return None
+        urls = cls._extract_brightcove_urls(webpage)
+        return urls[0] if urls else None
+
+    @classmethod
+    def _extract_brightcove_urls(cls, webpage):
+        """Return a list of all Brightcove URLs from the webpage """
+
+        url_m = re.search(r'<meta\s+property="og:video"\s+content="(http://c.brightcove.com/[^"]+)"', webpage)
+        if url_m:
+            url = unescapeHTML(url_m.group(1))
+            # Some sites don't add it, we can't download with this url, for example:
+            # http://www.ktvu.com/videos/news/raw-video-caltrain-releases-video-of-man-almost/vCTZdY/
+            if 'playerKey' in url:
+                return [url]
+
+        matches = re.findall(
+            r'''(?sx)<object
+            (?:
+                [^>]+?class=[\'"][^>]*?BrightcoveExperience.*?[\'"] |
+                [^>]*?>\s*<param\s+name="movie"\s+value="https?://[^/]*brightcove\.com/
+            ).+?</object>''',
+            webpage)
+        return [cls._build_brighcove_url(m) for m in matches]
 
     def _real_extract(self, url):
+        url, smuggled_data = unsmuggle_url(url, {})
+
         # Change the 'videoId' and others field to '@videoPlayer'
         url = re.sub(r'(?<=[?&])(videoI(d|D)|bctid)', '%40videoPlayer', url)
         # Change bckey (used by bcove.me urls) to playerKey
@@ -118,33 +184,40 @@ class BrightcoveIE(InfoExtractor):
 
         videoPlayer = query.get('@videoPlayer')
         if videoPlayer:
-            return self._get_video_info(videoPlayer[0], query_str, query)
+            # We set the original url as the default 'Referer' header
+            referer = smuggled_data.get('Referer', url)
+            return self._get_video_info(
+                videoPlayer[0], query_str, query, referer=referer)
         else:
             player_key = query['playerKey']
             return self._get_playlist_info(player_key[0])
 
-    def _get_video_info(self, video_id, query_str, query):
+    def _get_video_info(self, video_id, query_str, query, referer=None):
         request_url = self._FEDERATED_URL_TEMPLATE % query_str
         req = compat_urllib_request.Request(request_url)
         linkBase = query.get('linkBaseURL')
         if linkBase is not None:
-            req.add_header('Referer', linkBase[0])
+            referer = linkBase[0]
+        if referer is not None:
+            req.add_header('Referer', referer)
         webpage = self._download_webpage(req, video_id)
 
         self.report_extraction(video_id)
-        info = self._search_regex(r'var experienceJSON = ({.*?});', webpage, 'json')
+        info = self._search_regex(r'var experienceJSON = ({.*});', webpage, 'json')
         info = json.loads(info)['data']
         video_info = info['programmedContent']['videoPlayer']['mediaDTO']
+        video_info['_youtubedl_adServerURL'] = info.get('adServerURL')
 
         return self._extract_video_info(video_info)
 
     def _get_playlist_info(self, player_key):
-        playlist_info = self._download_webpage(self._PLAYLIST_URL_TEMPLATE % player_key,
-                                               player_key, u'Downloading playlist information')
+        info_url = 'http://c.brightcove.com/services/json/experience/runtime/?command=get_programming_for_experience&playerKey=%s' % player_key
+        playlist_info = self._download_webpage(
+            info_url, player_key, 'Downloading playlist information')
 
         json_data = json.loads(playlist_info)
         if 'videoList' not in json_data:
-            raise ExtractorError(u'Empty playlist')
+            raise ExtractorError('Empty playlist')
         playlist_info = json_data['videoList']
         videos = [self._extract_video_info(video_info) for video_info in playlist_info['mediaCollectionDTO']['videoDTOs']]
 
@@ -154,7 +227,7 @@ class BrightcoveIE(InfoExtractor):
     def _extract_video_info(self, video_info):
         info = {
             'id': compat_str(video_info['id']),
-            'title': video_info['displayName'],
+            'title': video_info['displayName'].strip(),
             'description': video_info.get('shortDescription'),
             'thumbnail': video_info.get('videoStillURL') or video_info.get('thumbnailURL'),
             'uploader': video_info.get('publisherName'),
@@ -162,16 +235,47 @@ class BrightcoveIE(InfoExtractor):
 
         renditions = video_info.get('renditions')
         if renditions:
-            renditions = sorted(renditions, key=lambda r: r['size'])
-            info['formats'] = [{
-                'url': rend['defaultURL'],
-                'height': rend.get('frameHeight'),
-                'width': rend.get('frameWidth'),
-            } for rend in renditions]
+            formats = []
+            for rend in renditions:
+                url = rend['defaultURL']
+                if rend['remote']:
+                    # This type of renditions are served through akamaihd.net,
+                    # but they don't use f4m manifests
+                    url = url.replace('control/', '') + '?&v=3.3.0&fp=13&r=FEEFJ&g=RTSJIMBMPFPB'
+                    ext = 'flv'
+                else:
+                    ext = determine_ext(url)
+                size = rend.get('size')
+                formats.append({
+                    'url': url,
+                    'ext': ext,
+                    'height': rend.get('frameHeight'),
+                    'width': rend.get('frameWidth'),
+                    'filesize': size if size != 0 else None,
+                })
+            self._sort_formats(formats)
+            info['formats'] = formats
         elif video_info.get('FLVFullLengthURL') is not None:
             info.update({
                 'url': video_info['FLVFullLengthURL'],
             })
-        else:
-            raise ExtractorError(u'Unable to extract video url for %s' % info['id'])
+
+        if self._downloader.params.get('include_ads', False):
+            adServerURL = video_info.get('_youtubedl_adServerURL')
+            if adServerURL:
+                ad_info = {
+                    '_type': 'url',
+                    'url': adServerURL,
+                }
+                if 'url' in info:
+                    return {
+                        '_type': 'playlist',
+                        'title': info['title'],
+                        'entries': [ad_info, info],
+                    }
+                else:
+                    return ad_info
+
+        if 'url' not in info and not info.get('formats'):
+            raise ExtractorError('Unable to extract video url for %s' % info['id'])
         return info

youtube_dl/extractor/byutv.py

@@ -0,0 +1,48 @@
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class BYUtvIE(InfoExtractor):
+    _VALID_URL = r'^https?://(?:www\.)?byutv.org/watch/[0-9a-f-]+/(?P<video_id>[^/?#]+)'
+    _TEST = {
+        'url': 'http://www.byutv.org/watch/44e80f7b-e3ba-43ba-8c51-b1fd96c94a79/granite-flats-talking',
+        'info_dict': {
+            'id': 'granite-flats-talking',
+            'ext': 'mp4',
+            'description': 'md5:4e9a7ce60f209a33eca0ac65b4918e1c',
+            'title': 'Talking',
+            'thumbnail': 're:^https?://.*promo.*'
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('video_id')
+
+        webpage = self._download_webpage(url, video_id)
+        episode_code = self._search_regex(
+            r'(?s)episode:(.*?\}),\s*\n', webpage, 'episode information')
+        episode_json = re.sub(
+            r'(\n\s+)([a-zA-Z]+):\s+\'(.*?)\'', r'\1"\2": "\3"', episode_code)
+        ep = json.loads(episode_json)
+
+        if ep['providerType'] == 'Ooyala':
+            return {
+                '_type': 'url_transparent',
+                'ie_key': 'Ooyala',
+                'url': 'ooyala:%s' % ep['providerId'],
+                'id': video_id,
+                'title': ep['title'],
+                'description': ep.get('description'),
+                'thumbnail': ep.get('imageThumbnail'),
+            }
+        else:
+            raise ExtractorError('Unsupported provider %s' % ep['provider'])

youtube_dl/extractor/c56.py

@@ -1,36 +1,47 @@
 # coding: utf-8
+from __future__ import unicode_literals
 
 import re
-import json
 
 from .common import InfoExtractor
-from ..utils import determine_ext
+
 
 class C56IE(InfoExtractor):
-    _VALID_URL = r'https?://((www|player)\.)?56\.com/(.+?/)?(v_|(play_album.+-))(?P<textid>.+?)\.(html|swf)'
-    IE_NAME = u'56.com'
-
-    _TEST ={
-        u'url': u'http://www.56.com/u39/v_OTM0NDA3MTY.html',
-        u'file': u'93440716.flv',
-        u'md5': u'e59995ac63d0457783ea05f93f12a866',
-        u'info_dict': {
-            u'title': u'网事知多少 第32期：车怒',
+    _VALID_URL = r'https?://(?:(?:www|player)\.)?56\.com/(?:.+?/)?(?:v_|(?:play_album.+-))(?P<textid>.+?)\.(?:html|swf)'
+    IE_NAME = '56.com'
+    _TEST = {
+        'url': 'http://www.56.com/u39/v_OTM0NDA3MTY.html',
+        'md5': 'e59995ac63d0457783ea05f93f12a866',
+        'info_dict': {
+            'id': '93440716',
+            'ext': 'flv',
+            'title': '网事知多少 第32期：车怒',
+            'duration': 283.813,
         },
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
         text_id = mobj.group('textid')
-        info_page = self._download_webpage('http://vxml.56.com/json/%s/' % text_id,
-                                           text_id, u'Downloading video info')
-        info = json.loads(info_page)['info']
-        best_format = sorted(info['rfiles'], key=lambda f: int(f['filesize']))[-1]
-        video_url = best_format['url']
 
-        return {'id': info['vid'],
-                'title': info['Subject'],
-                'url': video_url,
-                'ext': determine_ext(video_url),
-                'thumbnail': info.get('bimg') or info.get('img'),
-                }
+        page = self._download_json(
+            'http://vxml.56.com/json/%s/' % text_id, text_id, 'Downloading video info')
+
+        info = page['info']
+
+        formats = [
+            {
+                'format_id': f['type'],
+                'filesize': int(f['filesize']),
+                'url': f['url']
+            } for f in info['rfiles']
+        ]
+        self._sort_formats(formats)
+
+        return {
+            'id': info['vid'],
+            'title': info['Subject'],
+            'duration': int(info['duration']) / 1000.0,
+            'formats': formats,
+            'thumbnail': info.get('bimg') or info.get('img'),
+        }

youtube_dl/extractor/canal13cl.py

@@ -0,0 +1,48 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class Canal13clIE(InfoExtractor):
+    _VALID_URL = r'^http://(?:www\.)?13\.cl/(?:[^/?#]+/)*(?P<id>[^/?#]+)'
+    _TEST = {
+        'url': 'http://www.13.cl/t13/nacional/el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda',
+        'md5': '4cb1fa38adcad8fea88487a078831755',
+        'info_dict': {
+            'id': '1403022125',
+            'display_id': 'el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda',
+            'ext': 'mp4',
+            'title': 'El "círculo de hierro" de Michelle Bachelet en su regreso a La Moneda',
+            'description': '(Foto: Agencia Uno) En nueve días más, Michelle Bachelet va a asumir por segunda vez como presidenta de la República. Entre aquellos que la acompañarán hay caras que se repiten y otras que se consolidan en su entorno de colaboradores más cercanos.',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        title = self._html_search_meta(
+            'twitter:title', webpage, 'title', fatal=True)
+        description = self._html_search_meta(
+            'twitter:description', webpage, 'description')
+        url = self._html_search_regex(
+            r'articuloVideo = \"(.*?)\"', webpage, 'url')
+        real_id = self._search_regex(
+            r'[^0-9]([0-9]{7,})[^0-9]', url, 'id', default=display_id)
+        thumbnail = self._html_search_regex(
+            r'articuloImagen = \"(.*?)\"', webpage, 'thumbnail')
+
+        return {
+            'id': real_id,
+            'display_id': display_id,
+            'url': url,
+            'title': title,
+            'description': description,
+            'ext': 'mp4',
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/canalc2.py

@@ -1,4 +1,6 @@
 # coding: utf-8
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -9,11 +11,12 @@ class Canalc2IE(InfoExtractor):
     _VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?.*?idVideo=(?P<id>\d+)'
 
     _TEST = {
-        u'url': u'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui',
-        u'file': u'12163.mp4',
-        u'md5': u'060158428b650f896c542dfbb3d6487f',
-        u'info_dict': {
-            u'title': u'Terrasses du Numérique'
+        'url': 'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui',
+        'md5': '060158428b650f896c542dfbb3d6487f',
+        'info_dict': {
+            'id': '12163',
+            'ext': 'mp4',
+            'title': 'Terrasses du Numérique'
         }
     }
 
@@ -28,10 +31,11 @@ class Canalc2IE(InfoExtractor):
         video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file_name
 
         title = self._html_search_regex(
-            r'class="evenement8">(.*?)</a>', webpage, u'title')
-        
-        return {'id': video_id,
-                'ext': 'mp4',
-                'url': video_url,
-                'title': title,
-                }
+            r'class="evenement8">(.*?)</a>', webpage, 'title')
+
+        return {
+            'id': video_id,
+            'ext': 'mp4',
+            'url': video_url,
+            'title': title,
+        }

youtube_dl/extractor/canalplus.py

@@ -1,55 +1,72 @@
 # encoding: utf-8
+from __future__ import unicode_literals
+
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
-from ..utils import unified_strdate
+from ..utils import (
+    unified_strdate,
+    url_basename,
+)
 
 
 class CanalplusIE(InfoExtractor):
-    _VALID_URL = r'https?://(www\.canalplus\.fr/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>\d+))'
+    _VALID_URL = r'https?://(?:www\.canalplus\.fr/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))'
     _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/cplus/%s'
-    IE_NAME = u'canalplus.fr'
+    IE_NAME = 'canalplus.fr'
 
     _TEST = {
-        u'url': u'http://www.canalplus.fr/c-infos-documentaires/pid1830-c-zapping.html?vid=922470',
-        u'file': u'922470.flv',
-        u'info_dict': {
-            u'title': u'Zapping - 26/08/13',
-            u'description': u'Le meilleur de toutes les chaînes, tous les jours.\nEmission du 26 août 2013',
-            u'upload_date': u'20130826',
-        },
-        u'params': {
-            u'skip_download': True,
+        'url': 'http://www.canalplus.fr/c-infos-documentaires/pid1830-c-zapping.html?vid=922470',
+        'md5': '3db39fb48b9685438ecf33a1078023e4',
+        'info_dict': {
+            'id': '922470',
+            'ext': 'flv',
+            'title': 'Zapping - 26/08/13',
+            'description': 'Le meilleur de toutes les chaînes, tous les jours.\nEmission du 26 août 2013',
+            'upload_date': '20130826',
         },
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.groupdict().get('id')
+
+        # Beware, some subclasses do not define an id group
+        display_id = url_basename(mobj.group('path'))
+
         if video_id is None:
-            webpage = self._download_webpage(url, mobj.group('path'))
-            video_id = self._search_regex(r'videoId = "(\d+)";', webpage, u'video id')
+            webpage = self._download_webpage(url, display_id)
+            video_id = self._search_regex(r'<canal:player videoId="(\d+)"', webpage, 'video id')
+
         info_url = self._VIDEO_INFO_TEMPLATE % video_id
-        info_page = self._download_webpage(info_url,video_id, 
-                                           u'Downloading video info')
+        doc = self._download_xml(info_url, video_id, 'Downloading video XML')
 
-        self.report_extraction(video_id)
-        doc = xml.etree.ElementTree.fromstring(info_page.encode('utf-8'))
         video_info = [video for video in doc if video.find('ID').text == video_id][0]
-        infos = video_info.find('INFOS')
         media = video_info.find('MEDIA')
-        formats = [media.find('VIDEOS/%s' % format)
-            for format in ['BAS_DEBIT', 'HAUT_DEBIT', 'HD']]
-        video_url = [format.text for format in formats if format is not None][-1]
+        infos = video_info.find('INFOS')
 
-        return {'id': video_id,
-                'title': u'%s - %s' % (infos.find('TITRAGE/TITRE').text,
-                                       infos.find('TITRAGE/SOUS_TITRE').text),
-                'url': video_url,
-                'ext': 'flv',
-                'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text),
-                'thumbnail': media.find('IMAGES/GRAND').text,
-                'description': infos.find('DESCRIPTION').text,
-                'view_count': int(infos.find('NB_VUES').text),
-                }
+        preferences = ['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD', 'HLS', 'HDS']
+
+        formats = [
+            {
+                'url': fmt.text + '?hdcore=2.11.3' if fmt.tag == 'HDS' else fmt.text,
+                'format_id': fmt.tag,
+                'ext': 'mp4' if fmt.tag == 'HLS' else 'flv',
+                'preference': preferences.index(fmt.tag) if fmt.tag in preferences else -1,
+            } for fmt in media.find('VIDEOS') if fmt.text
+        ]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': '%s - %s' % (infos.find('TITRAGE/TITRE').text,
+                                  infos.find('TITRAGE/SOUS_TITRE').text),
+            'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text),
+            'thumbnail': media.find('IMAGES/GRAND').text,
+            'description': infos.find('DESCRIPTION').text,
+            'view_count': int(infos.find('NB_VUES').text),
+            'like_count': int(infos.find('NB_LIKES').text),
+            'comment_count': int(infos.find('NB_COMMENTS').text),
+            'formats': formats,
+        }

youtube_dl/extractor/cbs.py

@@ -0,0 +1,48 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class CBSIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?cbs\.com/shows/[^/]+/(?:video|artist)/(?P<id>[^/]+)/.*'
+
+    _TESTS = [{
+        'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
+        'info_dict': {
+            'id': '4JUVEwq3wUT7',
+            'ext': 'flv',
+            'title': 'Connect Chat feat. Garth Brooks',
+            'description': 'Connect with country music singer Garth Brooks, as he chats with fans on Wednesday November 27, 2013. Be sure to tune in to Garth Brooks: Live from Las Vegas, Friday November 29, at 9/8c on CBS!',
+            'duration': 1495,
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+        '_skip': 'Blocked outside the US',
+    }, {
+        'url': 'http://www.cbs.com/shows/liveonletterman/artist/221752/st-vincent/',
+        'info_dict': {
+            'id': 'P9gjWjelt6iP',
+            'ext': 'flv',
+            'title': 'Live on Letterman - St. Vincent',
+            'description': 'Live On Letterman: St. Vincent in concert from New York\'s Ed Sullivan Theater on Tuesday, July 16, 2014.',
+            'duration': 3221,
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+        '_skip': 'Blocked outside the US',
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id)
+        real_id = self._search_regex(
+            r"video\.settings\.pid\s*=\s*'([^']+)';",
+            webpage, 'real video ID')
+        return self.url_result(u'theplatform:%s' % real_id)

youtube_dl/extractor/cbsnews.py

@@ -0,0 +1,87 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+import json
+
+from .common import InfoExtractor
+
+
+class CBSNewsIE(InfoExtractor):
+    IE_DESC = 'CBS News'
+    _VALID_URL = r'http://(?:www\.)?cbsnews\.com/(?:[^/]+/)+(?P<id>[\da-z_-]+)'
+
+    _TESTS = [
+        {
+            'url': 'http://www.cbsnews.com/news/tesla-and-spacex-elon-musks-industrial-empire/',
+            'info_dict': {
+                'id': 'tesla-and-spacex-elon-musks-industrial-empire',
+                'ext': 'flv',
+                'title': 'Tesla and SpaceX: Elon Musk\'s industrial empire',
+                'thumbnail': 'http://beta.img.cbsnews.com/i/2014/03/30/60147937-2f53-4565-ad64-1bdd6eb64679/60-0330-pelley-640x360.jpg',
+                'duration': 791,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://www.cbsnews.com/videos/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/',
+            'info_dict': {
+                'id': 'fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack',
+                'ext': 'flv',
+                'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
+                'thumbnail': 'http://cbsnews2.cbsistatic.com/hub/i/r/2014/04/04/0c9fbc66-576b-41ca-8069-02d122060dd2/thumbnail/140x90/6dad7a502f88875ceac38202984b6d58/en-0404-werner-replace-640x360.jpg',
+                'duration': 205,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_info = json.loads(self._html_search_regex(
+            r'(?:<ul class="media-list items" id="media-related-items"><li data-video-info|<div id="cbsNewsVideoPlayer" data-video-player-options)=\'({.+?})\'',
+            webpage, 'video JSON info'))
+
+        item = video_info['item'] if 'item' in video_info else video_info
+        title = item.get('articleTitle') or item.get('hed')
+        duration = item.get('duration')
+        thumbnail = item.get('mediaImage') or item.get('thumbnail')
+
+        formats = []
+        for format_id in ['RtmpMobileLow', 'RtmpMobileHigh', 'Hls', 'RtmpDesktop']:
+            uri = item.get('media' + format_id + 'URI')
+            if not uri:
+                continue
+            fmt = {
+                'url': uri,
+                'format_id': format_id,
+            }
+            if uri.startswith('rtmp'):
+                fmt.update({
+                    'app': 'ondemand?auth=cbs',
+                    'play_path': 'mp4:' + uri.split('<break>')[-1],
+                    'player_url': 'http://www.cbsnews.com/[[IMPORT]]/vidtech.cbsinteractive.com/player/3_3_0/CBSI_PLAYER_HD.swf',
+                    'page_url': 'http://www.cbsnews.com',
+                    'ext': 'flv',
+                })
+            elif uri.endswith('.m3u8'):
+                fmt['ext'] = 'mp4'
+            formats.append(fmt)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/ceskatelevize.py

@@ -0,0 +1,126 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_request,
+    compat_urllib_parse,
+    compat_urllib_parse_urlparse,
+    ExtractorError,
+)
+
+
+class CeskaTelevizeIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(.+/)?(?P<id>[^?#]+)'
+
+    _TESTS = [
+        {
+            'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/213512120230004-spanelska-chripka',
+            'info_dict': {
+                'id': '213512120230004',
+                'ext': 'flv',
+                'title': 'První republika: Španělská chřipka',
+                'duration': 3107.4,
+            },
+            'params': {
+                'skip_download': True,  # requires rtmpdump
+            },
+            'skip': 'Works only from Czech Republic.',
+        },
+        {
+            'url': 'http://www.ceskatelevize.cz/ivysilani/1030584952-tsatsiki-maminka-a-policajt',
+            'info_dict': {
+                'id': '20138143440',
+                'ext': 'flv',
+                'title': 'Tsatsiki, maminka a policajt',
+                'duration': 6754.1,
+            },
+            'params': {
+                'skip_download': True,  # requires rtmpdump
+            },
+            'skip': 'Works only from Czech Republic.',
+        },
+        {
+            'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/bonus/14716-zpevacka-z-duparny-bobina',
+            'info_dict': {
+                'id': '14716',
+                'ext': 'flv',
+                'title': 'První republika: Zpěvačka z Dupárny Bobina',
+                'duration': 90,
+            },
+            'params': {
+                'skip_download': True,  # requires rtmpdump
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        url = url.replace('/porady/', '/ivysilani/').replace('/video/', '')
+
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        NOT_AVAILABLE_STRING = 'This content is not available at your territory due to limited copyright.'
+        if '%s</p>' % NOT_AVAILABLE_STRING in webpage:
+            raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
+
+        typ = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],', webpage, 'type')
+        episode_id = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],', webpage, 'episode_id')
+
+        data = {
+            'playlist[0][type]': typ,
+            'playlist[0][id]': episode_id,
+            'requestUrl': compat_urllib_parse_urlparse(url).path,
+            'requestSource': 'iVysilani',
+        }
+
+        req = compat_urllib_request.Request('http://www.ceskatelevize.cz/ivysilani/ajax/get-playlist-url',
+                                            data=compat_urllib_parse.urlencode(data))
+
+        req.add_header('Content-type', 'application/x-www-form-urlencoded')
+        req.add_header('x-addr', '127.0.0.1')
+        req.add_header('X-Requested-With', 'XMLHttpRequest')
+        req.add_header('Referer', url)
+
+        playlistpage = self._download_json(req, video_id)
+
+        req = compat_urllib_request.Request(compat_urllib_parse.unquote(playlistpage['url']))
+        req.add_header('Referer', url)
+
+        playlist = self._download_xml(req, video_id)
+        
+        formats = []
+        for i in playlist.find('smilRoot/body'):
+            if 'AD' not in i.attrib['id']:
+                base_url = i.attrib['base']
+                parsedurl = compat_urllib_parse_urlparse(base_url)
+                duration = i.attrib['duration']
+
+                for video in i.findall('video'):
+                    if video.attrib['label'] != 'AD':
+                        format_id = video.attrib['label']
+                        play_path = video.attrib['src']
+                        vbr = int(video.attrib['system-bitrate'])
+
+                        formats.append({
+                            'format_id': format_id,
+                            'url': base_url,
+                            'vbr': vbr,
+                            'play_path': play_path,
+                            'app': parsedurl.path[1:] + '?' + parsedurl.query,
+                            'rtmp_live': True,
+                            'ext': 'flv',
+                        })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': episode_id,
+            'title': self._html_search_regex(r'<title>(.+?) — iVysílání — Česká televize</title>', webpage, 'title'),
+            'duration': float(duration),
+            'formats': formats,
+        }

youtube_dl/extractor/channel9.py

@@ -0,0 +1,273 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+class Channel9IE(InfoExtractor):
+    '''
+    Common extractor for channel9.msdn.com.
+
+    The type of provided URL (video or playlist) is determined according to
+    meta Search.PageType from web page HTML rather than URL itself, as it is
+    not always possible to do.
+    '''
+    IE_DESC = 'Channel 9'
+    IE_NAME = 'channel9'
+    _VALID_URL = r'https?://(?:www\.)?channel9\.msdn\.com/(?P<contentpath>.+)/?'
+
+    _TESTS = [
+        {
+            'url': 'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002',
+            'md5': 'bbd75296ba47916b754e73c3a4bbdf10',
+            'info_dict': {
+                'id': 'Events/TechEd/Australia/2013/KOS002',
+                'ext': 'mp4',
+                'title': 'Developer Kick-Off Session: Stuff We Love',
+                'description': 'md5:c08d72240b7c87fcecafe2692f80e35f',
+                'duration': 4576,
+                'thumbnail': 'http://media.ch9.ms/ch9/9d51/03902f2d-fc97-4d3c-b195-0bfe15a19d51/KOS002_220.jpg',
+                'session_code': 'KOS002',
+                'session_day': 'Day 1',
+                'session_room': 'Arena 1A',
+                'session_speakers': [ 'Ed Blankenship', 'Andrew Coates', 'Brady Gaster', 'Patrick Klug', 'Mads Kristensen' ],
+            },
+        },
+        {
+            'url': 'http://channel9.msdn.com/posts/Self-service-BI-with-Power-BI-nuclear-testing',
+            'md5': 'b43ee4529d111bc37ba7ee4f34813e68',
+            'info_dict': {
+                'id': 'posts/Self-service-BI-with-Power-BI-nuclear-testing',
+                'ext': 'mp4',
+                'title': 'Self-service BI with Power BI - nuclear testing',
+                'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b',
+                'duration': 1540,
+                'thumbnail': 'http://media.ch9.ms/ch9/87e1/0300391f-a455-4c72-bec3-4422f19287e1/selfservicenuk_512.jpg',
+                'authors': [ 'Mike Wilmot' ],
+            },
+        }
+    ]
+
+    _RSS_URL = 'http://channel9.msdn.com/%s/RSS'
+
+    # Sorted by quality
+    _known_formats = ['MP3', 'MP4', 'Mid Quality WMV', 'Mid Quality MP4', 'High Quality WMV', 'High Quality MP4']
+
+    def _restore_bytes(self, formatted_size):
+        if not formatted_size:
+            return 0
+        m = re.match(r'^(?P<size>\d+(?:\.\d+)?)\s+(?P<units>[a-zA-Z]+)', formatted_size)
+        if not m:
+            return 0
+        units = m.group('units')
+        try:
+            exponent = ['B', 'KB', 'MB', 'GB', 'TB', 'PB', 'EB', 'ZB', 'YB'].index(units.upper())
+        except ValueError:
+            return 0
+        size = float(m.group('size'))
+        return int(size * (1024 ** exponent))
+
+    def _formats_from_html(self, html):
+        FORMAT_REGEX = r'''
+            (?x)
+            <a\s+href="(?P<url>[^"]+)">(?P<quality>[^<]+)</a>\s*
+            <span\s+class="usage">\((?P<note>[^\)]+)\)</span>\s*
+            (?:<div\s+class="popup\s+rounded">\s*
+            <h3>File\s+size</h3>\s*(?P<filesize>.*?)\s*
+            </div>)?                                                # File size part may be missing
+        '''
+        # Extract known formats
+        formats = [{
+            'url': x.group('url'),
+            'format_id': x.group('quality'),
+            'format_note': x.group('note'),
+            'format': '%s (%s)' % (x.group('quality'), x.group('note')),
+            'filesize': self._restore_bytes(x.group('filesize')), # File size is approximate
+            'preference': self._known_formats.index(x.group('quality')),
+            'vcodec': 'none' if x.group('note') == 'Audio only' else None,
+        } for x in list(re.finditer(FORMAT_REGEX, html)) if x.group('quality') in self._known_formats]
+
+        self._sort_formats(formats)
+
+        return formats
+
+    def _extract_title(self, html):
+        title = self._html_search_meta('title', html, 'title')
+        if title is None:           
+            title = self._og_search_title(html)
+            TITLE_SUFFIX = ' (Channel 9)'
+            if title is not None and title.endswith(TITLE_SUFFIX):
+                title = title[:-len(TITLE_SUFFIX)]
+        return title
+
+    def _extract_description(self, html):
+        DESCRIPTION_REGEX = r'''(?sx)
+            <div\s+class="entry-content">\s*
+            <div\s+id="entry-body">\s*
+            (?P<description>.+?)\s*
+            </div>\s*
+            </div>
+        '''
+        m = re.search(DESCRIPTION_REGEX, html)
+        if m is not None:
+            return m.group('description')
+        return self._html_search_meta('description', html, 'description')
+
+    def _extract_duration(self, html):
+        m = re.search(r'data-video_duration="(?P<hours>\d{2}):(?P<minutes>\d{2}):(?P<seconds>\d{2})"', html)
+        return ((int(m.group('hours')) * 60 * 60) + (int(m.group('minutes')) * 60) + int(m.group('seconds'))) if m else None
+
+    def _extract_slides(self, html):
+        m = re.search(r'<a href="(?P<slidesurl>[^"]+)" class="slides">Slides</a>', html)
+        return m.group('slidesurl') if m is not None else None
+
+    def _extract_zip(self, html):
+        m = re.search(r'<a href="(?P<zipurl>[^"]+)" class="zip">Zip</a>', html)
+        return m.group('zipurl') if m is not None else None
+
+    def _extract_avg_rating(self, html):
+        m = re.search(r'<p class="avg-rating">Avg Rating: <span>(?P<avgrating>[^<]+)</span></p>', html)
+        return float(m.group('avgrating')) if m is not None else 0
+
+    def _extract_rating_count(self, html):
+        m = re.search(r'<div class="rating-count">\((?P<ratingcount>[^<]+)\)</div>', html)
+        return int(self._fix_count(m.group('ratingcount'))) if m is not None else 0
+
+    def _extract_view_count(self, html):
+        m = re.search(r'<li class="views">\s*<span class="count">(?P<viewcount>[^<]+)</span> Views\s*</li>', html)
+        return int(self._fix_count(m.group('viewcount'))) if m is not None else 0
+
+    def _extract_comment_count(self, html):
+        m = re.search(r'<li class="comments">\s*<a href="#comments">\s*<span class="count">(?P<commentcount>[^<]+)</span> Comments\s*</a>\s*</li>', html)
+        return int(self._fix_count(m.group('commentcount'))) if m is not None else 0
+
+    def _fix_count(self, count):
+        return int(str(count).replace(',', '')) if count is not None else None
+
+    def _extract_authors(self, html):
+        m = re.search(r'(?s)<li class="author">(.*?)</li>', html)
+        if m is None:
+            return None
+        return re.findall(r'<a href="/Niners/[^"]+">([^<]+)</a>', m.group(1))
+
+    def _extract_session_code(self, html):
+        m = re.search(r'<li class="code">\s*(?P<code>.+?)\s*</li>', html)
+        return m.group('code') if m is not None else None
+
+    def _extract_session_day(self, html):
+        m = re.search(r'<li class="day">\s*<a href="/Events/[^"]+">(?P<day>[^<]+)</a>\s*</li>', html)
+        return m.group('day') if m is not None else None
+
+    def _extract_session_room(self, html):
+        m = re.search(r'<li class="room">\s*(?P<room>.+?)\s*</li>', html)
+        return m.group('room') if m is not None else None
+
+    def _extract_session_speakers(self, html):
+        return re.findall(r'<a href="/Events/Speakers/[^"]+">([^<]+)</a>', html)
+
+    def _extract_content(self, html, content_path):
+        # Look for downloadable content        
+        formats = self._formats_from_html(html)
+        slides = self._extract_slides(html)
+        zip_ = self._extract_zip(html)
+
+        # Nothing to download
+        if len(formats) == 0 and slides is None and zip_ is None:
+            self._downloader.report_warning('None of recording, slides or zip are available for %s' % content_path)
+            return
+
+        # Extract meta
+        title = self._extract_title(html)
+        description = self._extract_description(html)
+        thumbnail = self._og_search_thumbnail(html)
+        duration = self._extract_duration(html)
+        avg_rating = self._extract_avg_rating(html)
+        rating_count = self._extract_rating_count(html)
+        view_count = self._extract_view_count(html)
+        comment_count = self._extract_comment_count(html)
+
+        common = {'_type': 'video',
+                  'id': content_path,
+                  'description': description,
+                  'thumbnail': thumbnail,
+                  'duration': duration,
+                  'avg_rating': avg_rating,
+                  'rating_count': rating_count,
+                  'view_count': view_count,
+                  'comment_count': comment_count,
+                }
+
+        result = []
+
+        if slides is not None:
+            d = common.copy()
+            d.update({ 'title': title + '-Slides', 'url': slides })
+            result.append(d)
+
+        if zip_ is not None:
+            d = common.copy()
+            d.update({ 'title': title + '-Zip', 'url': zip_ })
+            result.append(d)
+
+        if len(formats) > 0:
+            d = common.copy()
+            d.update({ 'title': title, 'formats': formats })
+            result.append(d)
+
+        return result
+
+    def _extract_entry_item(self, html, content_path):
+        contents = self._extract_content(html, content_path)
+        if contents is None:
+            return contents
+
+        authors = self._extract_authors(html)
+
+        for content in contents:
+            content['authors'] = authors
+
+        return contents
+
+    def _extract_session(self, html, content_path):
+        contents = self._extract_content(html, content_path)
+        if contents is None:
+            return contents
+
+        session_meta = {'session_code': self._extract_session_code(html),
+                        'session_day': self._extract_session_day(html),
+                        'session_room': self._extract_session_room(html),
+                        'session_speakers': self._extract_session_speakers(html),
+                        }
+
+        for content in contents:
+            content.update(session_meta)
+
+        return contents
+
+    def _extract_list(self, content_path):
+        rss = self._download_xml(self._RSS_URL % content_path, content_path, 'Downloading RSS')
+        entries = [self.url_result(session_url.text, 'Channel9')
+                   for session_url in rss.findall('./channel/item/link')]
+        title_text = rss.find('./channel/title').text
+        return self.playlist_result(entries, content_path, title_text)
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        content_path = mobj.group('contentpath')
+
+        webpage = self._download_webpage(url, content_path, 'Downloading web page')
+
+        page_type_m = re.search(r'<meta name="Search.PageType" content="(?P<pagetype>[^"]+)"/>', webpage)
+        if page_type_m is None:
+            raise ExtractorError('Search.PageType not found, don\'t know how to process this page', expected=True)
+
+        page_type = page_type_m.group('pagetype')
+        if page_type == 'List':         # List page, may contain list of 'item'-like objects
+            return self._extract_list(content_path)
+        elif page_type == 'Entry.Item': # Any 'item'-like page, may contain downloadable content
+            return self._extract_entry_item(webpage, content_path)
+        elif page_type == 'Session':    # Event session page, may contain downloadable content
+            return self._extract_session(webpage, content_path)
+        else:
+            raise ExtractorError('Unexpected Search.PageType %s' % page_type, expected=True)

youtube_dl/extractor/chilloutzone.py

@@ -0,0 +1,97 @@
+from __future__ import unicode_literals
+
+import re
+import base64
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    ExtractorError
+)
+
+
+class ChilloutzoneIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?chilloutzone\.net/video/(?P<id>[\w|-]+)\.html'
+    _TESTS = [{
+        'url': 'http://www.chilloutzone.net/video/enemene-meck-alle-katzen-weg.html',
+        'md5': 'a76f3457e813ea0037e5244f509e66d1',
+        'info_dict': {
+            'id': 'enemene-meck-alle-katzen-weg',
+            'ext': 'mp4',
+            'title': 'Enemene Meck - Alle Katzen weg',
+            'description': 'Ist das der Umkehrschluss des Niesenden Panda-Babys?',
+        },
+    }, {
+        'note': 'Video hosted at YouTube',
+        'url': 'http://www.chilloutzone.net/video/eine-sekunde-bevor.html',
+        'info_dict': {
+            'id': '1YVQaAgHyRU',
+            'ext': 'mp4',
+            'title': '16 Photos Taken 1 Second Before Disaster',
+            'description': 'md5:58a8fcf6a459fe0a08f54140f0ad1814',
+            'uploader': 'BuzzFeedVideo',
+            'uploader_id': 'BuzzFeedVideo',
+            'upload_date': '20131105',
+        },
+    }, {
+        'note': 'Video hosted at Vimeo',
+        'url': 'http://www.chilloutzone.net/video/icon-blending.html',
+        'md5': '2645c678b8dc4fefcc0e1b60db18dac1',
+        'info_dict': {
+            'id': '85523671',
+            'ext': 'mp4',
+            'title': 'The Sunday Times - Icons',
+            'description': 'md5:a5f7ff82e2f7a9ed77473fe666954e84',
+            'uploader': 'Us',
+            'uploader_id': 'usfilms',
+            'upload_date': '20140131'
+        },
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        base64_video_info = self._html_search_regex(
+            r'var cozVidData = "(.+?)";', webpage, 'video data')
+        decoded_video_info = base64.b64decode(base64_video_info).decode("utf-8")
+        video_info_dict = json.loads(decoded_video_info)
+
+        # get video information from dict
+        video_url = video_info_dict['mediaUrl']
+        description = clean_html(video_info_dict.get('description'))
+        title = video_info_dict['title']
+        native_platform = video_info_dict['nativePlatform']
+        native_video_id = video_info_dict['nativeVideoId']
+        source_priority = video_info_dict['sourcePriority']
+
+        # If nativePlatform is None a fallback mechanism is used (i.e. youtube embed)
+        if native_platform is None:
+            youtube_url = self._html_search_regex(
+                r'<iframe.* src="((?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"',
+                webpage, 'fallback video URL', default=None)
+            if youtube_url is not None:
+                return self.url_result(youtube_url, ie='Youtube')
+
+        # Non Fallback: Decide to use native source (e.g. youtube or vimeo) or
+        # the own CDN
+        if source_priority == 'native':
+            if native_platform == 'youtube':
+                return self.url_result(native_video_id, ie='Youtube')
+            if native_platform == 'vimeo':
+                return self.url_result(
+                    'http://vimeo.com/' + native_video_id, ie='Vimeo')
+
+        if not video_url:
+            raise ExtractorError('No video found')
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'title': title,
+            'description': description,
+        }

youtube_dl/extractor/cinemassacre.py

@@ -1,84 +1,94 @@
 # encoding: utf-8
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
+    int_or_none,
 )
 
 
 class CinemassacreIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?(?P<url>cinemassacre\.com/(?P<date_Y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/.+?)(?:[/?].*)?'
-    _TESTS = [{
-        u'url': u'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
-        u'file': u'19911.flv',
-        u'info_dict': {
-            u'upload_date': u'20121110',
-            u'title': u'“Angry Video Game Nerd: The Movie” – Trailer',
-            u'description': u'md5:fb87405fcb42a331742a0dce2708560b',
+    _VALID_URL = r'http://(?:www\.)?cinemassacre\.com/(?P<date_Y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/(?P<display_id>[^?#/]+)'
+    _TESTS = [
+        {
+            'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
+            'md5': 'fde81fbafaee331785f58cd6c0d46190',
+            'info_dict': {
+                'id': '19911',
+                'ext': 'mp4',
+                'upload_date': '20121110',
+                'title': '“Angry Video Game Nerd: The Movie” – Trailer',
+                'description': 'md5:fb87405fcb42a331742a0dce2708560b',
+            },
         },
-        u'params': {
-            # rtmp download
-            u'skip_download': True,
-        },
-    },
-    {
-        u'url': u'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
-        u'file': u'521be8ef82b16.flv',
-        u'info_dict': {
-            u'upload_date': u'20131002',
-            u'title': u'The Mummy’s Hand (1940)',
-        },
-        u'params': {
-            # rtmp download
-            u'skip_download': True,
-        },
-    }]
+        {
+            'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
+            'md5': 'd72f10cd39eac4215048f62ab477a511',
+            'info_dict': {
+                'id': '521be8ef82b16',
+                'ext': 'mp4',
+                'upload_date': '20131002',
+                'title': 'The Mummy’s Hand (1940)',
+            },
+        }
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('display_id')
 
-        webpage_url = u'http://' + mobj.group('url')
-        webpage = self._download_webpage(webpage_url, None) # Don't know video id yet
+        webpage = self._download_webpage(url, display_id)
         video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d')
         mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?id=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage)
         if not mobj:
-            raise ExtractorError(u'Can\'t extract embed url and video id')
-        playerdata_url = mobj.group(u'embed_url')
-        video_id = mobj.group(u'video_id')
+            raise ExtractorError('Can\'t extract embed url and video id')
+        playerdata_url = mobj.group('embed_url')
+        video_id = mobj.group('video_id')
 
-        video_title = self._html_search_regex(r'<title>(?P<title>.+?)\|',
-            webpage, u'title')
-        video_description = self._html_search_regex(r'<div class="entry-content">(?P<description>.+?)</div>',
-            webpage, u'description', flags=re.DOTALL, fatal=False)
-        if len(video_description) == 0:
-            video_description = None
+        video_title = self._html_search_regex(
+            r'<title>(?P<title>.+?)\|', webpage, 'title')
+        video_description = self._html_search_regex(
+            r'<div class="entry-content">(?P<description>.+?)</div>',
+            webpage, 'description', flags=re.DOTALL, fatal=False)
 
-        playerdata = self._download_webpage(playerdata_url, video_id)
-        url = self._html_search_regex(r'\'streamer\': \'(?P<url>[^\']+)\'', playerdata, u'url')
+        playerdata = self._download_webpage(playerdata_url, video_id, 'Downloading player webpage')
+        video_thumbnail = self._search_regex(
+            r'image: \'(?P<thumbnail>[^\']+)\'', playerdata, 'thumbnail', fatal=False)
+        sd_url = self._search_regex(r'file: \'([^\']+)\', label: \'SD\'', playerdata, 'sd_file')
+        videolist_url = self._search_regex(r'file: \'([^\']+\.smil)\'}', playerdata, 'videolist_url')
 
-        sd_file = self._html_search_regex(r'\'file\': \'(?P<sd_file>[^\']+)\'', playerdata, u'sd_file')
-        hd_file = self._html_search_regex(r'\'?file\'?: "(?P<hd_file>[^"]+)"', playerdata, u'hd_file')
-        video_thumbnail = self._html_search_regex(r'\'image\': \'(?P<thumbnail>[^\']+)\'', playerdata, u'thumbnail', fatal=False)
+        videolist = self._download_xml(videolist_url, video_id, 'Downloading videolist XML')
 
-        formats = [
-            {
-                'url': url,
-                'play_path': 'mp4:' + sd_file,
-                'rtmp_live': True, # workaround
-                'ext': 'flv',
-                'format': 'sd',
-                'format_id': 'sd',
-            },
-            {
-                'url': url,
-                'play_path': 'mp4:' + hd_file,
-                'rtmp_live': True, # workaround
-                'ext': 'flv',
-                'format': 'hd',
-                'format_id': 'hd',
-            },
-        ]
+        formats = []
+        baseurl = sd_url[:sd_url.rfind('/')+1]
+        for video in videolist.findall('.//video'):
+            src = video.get('src')
+            if not src:
+                continue
+            file_ = src.partition(':')[-1]
+            width = int_or_none(video.get('width'))
+            height = int_or_none(video.get('height'))
+            bitrate = int_or_none(video.get('system-bitrate'))
+            format = {
+                'url': baseurl + file_,
+                'format_id': src.rpartition('.')[0].rpartition('_')[-1],
+            }
+            if width or height:
+                format.update({
+                    'tbr': bitrate // 1000 if bitrate else None,
+                    'width': width,
+                    'height': height,
+                })
+            else:
+                format.update({
+                    'abr': bitrate // 1000 if bitrate else None,
+                    'vcodec': 'none',
+                })
+            formats.append(format)
+        self._sort_formats(formats)
 
         return {
             'id': video_id,

youtube_dl/extractor/clipfish.py

@@ -1,22 +1,30 @@
+from __future__ import unicode_literals
+
 import re
 import time
 import xml.etree.ElementTree
 
 from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    parse_duration,
+)
 
 
 class ClipfishIE(InfoExtractor):
-    IE_NAME = u'clipfish'
+    IE_NAME = 'clipfish'
 
     _VALID_URL = r'^https?://(?:www\.)?clipfish\.de/.*?/video/(?P<id>[0-9]+)/'
     _TEST = {
-        u'url': u'http://www.clipfish.de/special/supertalent/video/4028320/supertalent-2013-ivana-opacak-singt-nobodys-perfect/',
-        u'file': u'4028320.f4v',
-        u'md5': u'5e38bda8c329fbfb42be0386a3f5a382',
-        u'info_dict': {
-            u'title': u'Supertalent 2013: Ivana Opacak singt Nobody\'s Perfect',
-            u'duration': 399,
-        }
+        'url': 'http://www.clipfish.de/special/game-trailer/video/3966754/fifa-14-e3-2013-trailer/',
+        'md5': '2521cd644e862936cf2e698206e47385',
+        'info_dict': {
+            'id': '3966754',
+            'ext': 'mp4',
+            'title': 'FIFA 14 - E3 2013 Trailer',
+            'duration': 82,
+        },
+        u'skip': 'Blocked in the US'
     }
 
     def _real_extract(self, url):
@@ -25,24 +33,16 @@ class ClipfishIE(InfoExtractor):
 
         info_url = ('http://www.clipfish.de/devxml/videoinfo/%s?ts=%d' %
                     (video_id, int(time.time())))
-        info_xml = self._download_webpage(
+        doc = self._download_xml(
             info_url, video_id, note=u'Downloading info page')
-        doc = xml.etree.ElementTree.fromstring(info_xml)
         title = doc.find('title').text
         video_url = doc.find('filename').text
+        if video_url is None:
+            xml_bytes = xml.etree.ElementTree.tostring(doc)
+            raise ExtractorError('Cannot find video URL in document %r' %
+                                 xml_bytes)
         thumbnail = doc.find('imageurl').text
-        duration_str = doc.find('duration').text
-        m = re.match(
-            r'^(?P<hours>[0-9]+):(?P<minutes>[0-9]{2}):(?P<seconds>[0-9]{2}):(?P<ms>[0-9]*)$',
-            duration_str)
-        if m:
-            duration = (
-                (int(m.group('hours')) * 60 * 60) +
-                (int(m.group('minutes')) * 60) +
-                (int(m.group('seconds')))
-            )
-        else:
-            duration = None
+        duration = parse_duration(doc.find('duration').text)
 
         return {
             'id': video_id,

youtube_dl/extractor/cliphunter.py

@@ -0,0 +1,56 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+translation_table = {
+    'a': 'h', 'd': 'e', 'e': 'v', 'f': 'o', 'g': 'f', 'i': 'd', 'l': 'n',
+    'm': 'a', 'n': 'm', 'p': 'u', 'q': 't', 'r': 's', 'v': 'p', 'x': 'r',
+    'y': 'l', 'z': 'i',
+    '$': ':', '&': '.', '(': '=', '^': '&', '=': '/',
+}
+
+
+class CliphunterIE(InfoExtractor):
+    IE_NAME = 'cliphunter'
+
+    _VALID_URL = r'''(?x)http://(?:www\.)?cliphunter\.com/w/
+        (?P<id>[0-9]+)/
+        (?P<seo>.+?)(?:$|[#\?])
+    '''
+    _TEST = {
+        'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
+        'file': '1012420.flv',
+        'md5': '15e7740f30428abf70f4223478dc1225',
+        'info_dict': {
+            'title': 'Fun Jynx Maze solo',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        pl_fiji = self._search_regex(
+            r'pl_fiji = \'([^\']+)\'', webpage, 'video data')
+        pl_c_qual = self._search_regex(
+            r'pl_c_qual = "(.)"', webpage, 'video quality')
+        video_title = self._search_regex(
+            r'mediaTitle = "([^"]+)"', webpage, 'title')
+
+        video_url = ''.join(translation_table.get(c, c) for c in pl_fiji)
+
+        formats = [{
+            'url': video_url,
+            'format_id': pl_c_qual,
+        }]
+
+        return {
+            'id': video_id,
+            'title': video_title,
+            'formats': formats,
+        }

youtube_dl/extractor/clipsyndicate.py

@@ -0,0 +1,53 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    find_xpath_attr,
+    fix_xml_ampersands
+)
+
+
+class ClipsyndicateIE(InfoExtractor):
+    _VALID_URL = r'http://www\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://www.clipsyndicate.com/video/play/4629301/brick_briscoe',
+        'md5': '4d7d549451bad625e0ff3d7bd56d776c',
+        'info_dict': {
+            'id': '4629301',
+            'ext': 'mp4',
+            'title': 'Brick Briscoe',
+            'duration': 612,
+            'thumbnail': 're:^https?://.+\.jpg',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        js_player = self._download_webpage(
+            'http://eplayer.clipsyndicate.com/embed/player.js?va_id=%s' % video_id,
+            video_id, 'Downlaoding player')
+        # it includes a required token
+        flvars = self._search_regex(r'flvars: "(.*?)"', js_player, 'flvars')
+
+        pdoc = self._download_xml(
+            'http://eplayer.clipsyndicate.com/osmf/playlist?%s' % flvars,
+            video_id, 'Downloading video info',
+            transform_source=fix_xml_ampersands)
+
+        track_doc = pdoc.find('trackList/track')
+        def find_param(name):
+            node = find_xpath_attr(track_doc, './/param', 'name', name)
+            if node is not None:
+                return node.attrib['value']
+
+        return {
+            'id': video_id,
+            'title': find_param('title'),
+            'url': track_doc.find('location').text,
+            'thumbnail': find_param('thumbnail'),
+            'duration': int(find_param('duration')),
+        }

youtube_dl/extractor/clubic.py

@@ -0,0 +1,58 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    qualities,
+)
+
+
+class ClubicIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?clubic\.com/video/[^/]+/video.*-(?P<id>[0-9]+)\.html'
+
+    _TEST = {
+        'url': 'http://www.clubic.com/video/clubic-week/video-clubic-week-2-0-le-fbi-se-lance-dans-la-photo-d-identite-448474.html',
+        'md5': '1592b694ba586036efac1776b0b43cd3',
+        'info_dict': {
+            'id': '448474',
+            'ext': 'mp4',
+            'title': 'Clubic Week 2.0 : le FBI se lance dans la photo d\u0092identité',
+            'description': 're:Gueule de bois chez Nokia. Le constructeur a indiqué cette.*',
+            'thumbnail': 're:^http://img\.clubic\.com/.*\.jpg$',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        player_url = 'http://player.m6web.fr/v1/player/clubic/%s.html' % video_id
+        player_page = self._download_webpage(player_url, video_id)
+
+        config_json = self._search_regex(
+            r'(?m)M6\.Player\.config\s*=\s*(\{.+?\});$', player_page,
+            'configuration')
+        config = json.loads(config_json)
+
+        video_info = config['videoInfo']
+        sources = config['sources']
+        quality_order = qualities(['sd', 'hq'])
+
+        formats = [{
+            'format_id': src['streamQuality'],
+            'url': src['src'],
+            'quality': quality_order(src['streamQuality']),
+        } for src in sources]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': video_info['title'],
+            'formats': formats,
+            'description': clean_html(video_info.get('description')),
+            'thumbnail': config.get('poster'),
+        }

youtube_dl/extractor/cmt.py

@@ -0,0 +1,19 @@
+from __future__ import unicode_literals
+from .mtv import MTVIE
+
+
+class CMTIE(MTVIE):
+    IE_NAME = 'cmt.com'
+    _VALID_URL = r'https?://www\.cmt\.com/videos/.+?/(?P<videoid>[^/]+)\.jhtml'
+    _FEED_URL = 'http://www.cmt.com/sitewide/apps/player/embed/rss/'
+
+    _TESTS = [{
+        'url': 'http://www.cmt.com/videos/garth-brooks/989124/the-call-featuring-trisha-yearwood.jhtml#artist=30061',
+        'md5': 'e6b7ef3c4c45bbfae88061799bbba6c2',
+        'info_dict': {
+            'id': '989124',
+            'ext': 'mp4',
+            'title': 'Garth Brooks - "The Call (featuring Trisha Yearwood)"',
+            'description': 'Blame It All On My Roots',
+        },
+    }]

youtube_dl/extractor/cnet.py

@@ -0,0 +1,79 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+)
+
+
+class CNETIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/'
+    _TEST = {
+        'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/',
+        'md5': '041233212a0d06b179c87cbcca1577b8',
+        'info_dict': {
+            'id': '56f4ea68-bd21-4852-b08c-4de5b8354c60',
+            'ext': 'mp4',
+            'title': 'Hands-on with Microsoft Windows 8.1 Update',
+            'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.',
+            'thumbnail': 're:^http://.*/flmswindows8.jpg$',
+            'uploader_id': 'sarah.mitroff@cbsinteractive.com',
+            'uploader': 'Sarah Mitroff',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, display_id)
+        data_json = self._html_search_regex(
+            r"<div class=\"cnetVideoPlayer\"\s+.*?data-cnet-video-options='([^']+)'",
+            webpage, 'data json')
+        data = json.loads(data_json)
+        vdata = data['video']
+        if not vdata:
+            vdata = data['videos'][0]
+        if not vdata:
+            raise ExtractorError('Cannot find video data')
+
+        video_id = vdata['id']
+        title = vdata.get('headline')
+        if title is None:
+            title = vdata.get('title')
+        if title is None:
+            raise ExtractorError('Cannot find title!')
+        description = vdata.get('dek')
+        thumbnail = vdata.get('image', {}).get('path')
+        author = vdata.get('author')
+        if author:
+            uploader = '%s %s' % (author['firstName'], author['lastName'])
+            uploader_id = author.get('email')
+        else:
+            uploader = None
+            uploader_id = None
+
+        formats = [{
+            'format_id': '%s-%s-%s' % (
+                f['type'], f['format'],
+                int_or_none(f.get('bitrate'), 1000, default='')),
+            'url': f['uri'],
+            'tbr': int_or_none(f.get('bitrate'), 1000),
+        } for f in vdata['files']['data']]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'formats': formats,
+            'description': description,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/cnn.py

@@ -1,8 +1,13 @@
+from __future__ import unicode_literals
+
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
-from ..utils import determine_ext
+from ..utils import (
+    int_or_none,
+    parse_duration,
+    url_basename,
+)
 
 
 class CNNIE(InfoExtractor):
@@ -10,21 +15,24 @@ class CNNIE(InfoExtractor):
         (?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn|(?=&)))'''
 
     _TESTS = [{
-        u'url': u'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',
-        u'file': u'sports_2013_06_09_nadal-1-on-1.cnn.mp4',
-        u'md5': u'3e6121ea48df7e2259fe73a0628605c4',
-        u'info_dict': {
-            u'title': u'Nadal wins 8th French Open title',
-            u'description': u'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.',
+        'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',
+        'file': 'sports_2013_06_09_nadal-1-on-1.cnn.mp4',
+        'md5': '3e6121ea48df7e2259fe73a0628605c4',
+        'info_dict': {
+            'title': 'Nadal wins 8th French Open title',
+            'description': 'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.',
+            'duration': 135,
+            'upload_date': '20130609',
         },
     },
     {
-        u"url": u"http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29",
-        u"file": u"us_2013_08_21_sot-student-gives-epic-speech.georgia-institute-of-technology.mp4",
-        u"md5": u"b5cc60c60a3477d185af8f19a2a26f4e",
-        u"info_dict": {
-            u"title": "Student's epic speech stuns new freshmen",
-            u"description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\""
+        "url": "http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29",
+        "file": "us_2013_08_21_sot-student-gives-epic-speech.georgia-institute-of-technology.mp4",
+        "md5": "b5cc60c60a3477d185af8f19a2a26f4e",
+        "info_dict": {
+            "title": "Student's epic speech stuns new freshmen",
+            "description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"",
+            "upload_date": "20130821",
         }
     }]
 
@@ -32,27 +40,89 @@ class CNNIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         path = mobj.group('path')
         page_title = mobj.group('title')
-        info_url = u'http://cnn.com/video/data/3.0/%s/index.xml' % path
-        info_xml = self._download_webpage(info_url, page_title)
-        info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
+        info_url = 'http://cnn.com/video/data/3.0/%s/index.xml' % path
+        info = self._download_xml(info_url, page_title)
 
         formats = []
+        rex = re.compile(r'''(?x)
+            (?P<width>[0-9]+)x(?P<height>[0-9]+)
+            (?:_(?P<bitrate>[0-9]+)k)?
+        ''')
         for f in info.findall('files/file'):
-            mf = re.match(r'(\d+)x(\d+)(?:_(.*)k)?',f.attrib['bitrate'])
-            if mf is not None:
-                formats.append((int(mf.group(1)), int(mf.group(2)), int(mf.group(3) or 0), f.text))
-        formats = sorted(formats)
-        (_,_,_, video_path) = formats[-1]
-        video_url = 'http://ht.cdn.turner.com/cnn/big%s' % video_path
-
-        thumbnails = sorted([((int(t.attrib['height']),int(t.attrib['width'])), t.text) for t in info.findall('images/image')])
-        thumbs_dict = [{'resolution': res, 'url': t_url} for (res, t_url) in thumbnails]
-
-        return {'id': info.attrib['id'],
-                'title': info.find('headline').text,
+            video_url = 'http://ht.cdn.turner.com/cnn/big%s' % (f.text.strip())
+            fdct = {
+                'format_id': f.attrib['bitrate'],
                 'url': video_url,
-                'ext': determine_ext(video_url),
-                'thumbnail': thumbnails[-1][1],
-                'thumbnails': thumbs_dict,
-                'description': info.find('description').text,
-                }
+            }
+
+            mf = rex.match(f.attrib['bitrate'])
+            if mf:
+                fdct['width'] = int(mf.group('width'))
+                fdct['height'] = int(mf.group('height'))
+                fdct['tbr'] = int_or_none(mf.group('bitrate'))
+            else:
+                mf = rex.search(f.text)
+                if mf:
+                    fdct['width'] = int(mf.group('width'))
+                    fdct['height'] = int(mf.group('height'))
+                    fdct['tbr'] = int_or_none(mf.group('bitrate'))
+                else:
+                    mi = re.match(r'ios_(audio|[0-9]+)$', f.attrib['bitrate'])
+                    if mi:
+                        if mi.group(1) == 'audio':
+                            fdct['vcodec'] = 'none'
+                            fdct['ext'] = 'm4a'
+                        else:
+                            fdct['tbr'] = int(mi.group(1))
+
+            formats.append(fdct)
+
+        self._sort_formats(formats)
+
+        thumbnails = [{
+            'height': int(t.attrib['height']),
+            'width': int(t.attrib['width']),
+            'url': t.text,
+        } for t in info.findall('images/image')]
+
+        metas_el = info.find('metas')
+        upload_date = (
+            metas_el.attrib.get('version') if metas_el is not None else None)
+
+        duration_el = info.find('length')
+        duration = parse_duration(duration_el.text)
+
+        return {
+            'id': info.attrib['id'],
+            'title': info.find('headline').text,
+            'formats': formats,
+            'thumbnails': thumbnails,
+            'description': info.find('description').text,
+            'duration': duration,
+            'upload_date': upload_date,
+        }
+
+
+class CNNBlogsIE(InfoExtractor):
+    _VALID_URL = r'https?://[^\.]+\.blogs\.cnn\.com/.+'
+    _TEST = {
+        'url': 'http://reliablesources.blogs.cnn.com/2014/02/09/criminalizing-journalism/',
+        'md5': '3e56f97b0b6ffb4b79f4ea0749551084',
+        'info_dict': {
+            'id': 'bestoftv/2014/02/09/criminalizing-journalism.cnn',
+            'ext': 'mp4',
+            'title': 'Criminalizing journalism?',
+            'description': 'Glenn Greenwald responds to comments made this week on Capitol Hill that journalists could be criminal accessories.',
+            'upload_date': '20140209',
+        },
+        'add_ie': ['CNN'],
+    }
+
+    def _real_extract(self, url):
+        webpage = self._download_webpage(url, url_basename(url))
+        cnn_url = self._html_search_regex(r'data-url="(.+?)"', webpage, 'cnn url')
+        return {
+            '_type': 'url',
+            'url': cnn_url,
+            'ie_key': CNNIE.ie_key(),
+        }

youtube_dl/extractor/collegehumor.py

@@ -1,82 +1,102 @@
+from __future__ import unicode_literals
+
+import json
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    compat_urllib_parse_urlparse,
-    determine_ext,
-
-    ExtractorError,
-)
+from ..utils import int_or_none
 
 
 class CollegeHumorIE(InfoExtractor):
     _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/(video|embed|e)/(?P<videoid>[0-9]+)/?(?P<shorttitle>.*)$'
 
     _TESTS = [{
-        u'url': u'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe',
-        u'file': u'6902724.mp4',
-        u'md5': u'1264c12ad95dca142a9f0bf7968105a0',
-        u'info_dict': {
-            u'title': u'Comic-Con Cosplay Catastrophe',
-            u'description': u'Fans get creative this year at San Diego.  Too creative.  And yes, that\'s really Joss Whedon.',
+        'url': 'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe',
+        'md5': 'dcc0f5c1c8be98dc33889a191f4c26bd',
+        'info_dict': {
+            'id': '6902724',
+            'ext': 'mp4',
+            'title': 'Comic-Con Cosplay Catastrophe',
+            'description': "Fans get creative this year at San Diego.  Too creative.  And yes, that's really Joss Whedon.",
+            'age_limit': 13,
+            'duration': 187,
         },
     },
     {
-        u'url': u'http://www.collegehumor.com/video/3505939/font-conference',
-        u'file': u'3505939.mp4',
-        u'md5': u'c51ca16b82bb456a4397987791a835f5',
-        u'info_dict': {
-            u'title': u'Font Conference',
-            u'description': u'This video wasn\'t long enough, so we made it double-spaced.',
+        'url': 'http://www.collegehumor.com/video/3505939/font-conference',
+        'md5': '72fa701d8ef38664a4dbb9e2ab721816',
+        'info_dict': {
+            'id': '3505939',
+            'ext': 'mp4',
+            'title': 'Font Conference',
+            'description': "This video wasn't long enough, so we made it double-spaced.",
+            'age_limit': 10,
+            'duration': 179,
         },
-    }]
+    },
+    # embedded youtube video
+    {
+        'url': 'http://www.collegehumor.com/embed/6950306',
+        'info_dict': {
+            'id': 'Z-bao9fg6Yc',
+            'ext': 'mp4',
+            'title': 'Young Americans Think President John F. Kennedy Died THIS MORNING IN A CAR ACCIDENT!!!',
+            'uploader': 'Mark Dice',
+            'uploader_id': 'MarkDice',
+            'description': 'md5:62c3dab9351fac7bb44b53b69511d87f',
+            'upload_date': '20140127',
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'add_ie': ['Youtube'],
+    },
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
         video_id = mobj.group('videoid')
 
-        info = {
-            'id': video_id,
-            'uploader': None,
-            'upload_date': None,
-        }
+        jsonUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id + '.json'
+        data = json.loads(self._download_webpage(
+            jsonUrl, video_id, 'Downloading info JSON'))
+        vdata = data['video']
+        if vdata.get('youtubeId') is not None:
+            return {
+                '_type': 'url',
+                'url': vdata['youtubeId'],
+                'ie_key': 'Youtube',
+            }
 
-        self.report_extraction(video_id)
-        xmlUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id
-        mdoc = self._download_xml(xmlUrl, video_id,
-                                         u'Downloading info XML',
-                                         u'Unable to download video info XML')
-
-        try:
-            videoNode = mdoc.findall('./video')[0]
-            youtubeIdNode = videoNode.find('./youtubeID')
-            if youtubeIdNode is not None:
-                return self.url_result(youtubeIdNode.text, 'Youtube')
-            info['description'] = videoNode.findall('./description')[0].text
-            info['title'] = videoNode.findall('./caption')[0].text
-            info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
-            next_url = videoNode.findall('./file')[0].text
-        except IndexError:
-            raise ExtractorError(u'Invalid metadata XML file')
-
-        if next_url.endswith(u'manifest.f4m'):
-            manifest_url = next_url + '?hdcore=2.10.3'
-            adoc = self._download_xml(manifest_url, video_id,
-                                         u'Downloading XML manifest',
-                                         u'Unable to download video info XML')
-
-            try:
-                video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text
-            except IndexError:
-                raise ExtractorError(u'Invalid manifest file')
-            url_pr = compat_urllib_parse_urlparse(info['thumbnail'])
-            info['url'] = url_pr.scheme + '://' + url_pr.netloc + video_id[:-2].replace('.csmil','').replace(',','')
-            info['ext'] = 'mp4'
+        AGE_LIMITS = {'nc17': 18, 'r': 18, 'pg13': 13, 'pg': 10, 'g': 0}
+        rating = vdata.get('rating')
+        if rating:
+            age_limit = AGE_LIMITS.get(rating.lower())
         else:
-            # Old-style direct links
-            info['url'] = next_url
-            info['ext'] = determine_ext(info['url'])
+            age_limit = None  # None = No idea
 
-        return info
+        PREFS = {'high_quality': 2, 'low_quality': 0}
+        formats = []
+        for format_key in ('mp4', 'webm'):
+            for qname, qurl in vdata.get(format_key, {}).items():
+                formats.append({
+                    'format_id': format_key + '_' + qname,
+                    'url': qurl,
+                    'format': format_key,
+                    'preference': PREFS.get(qname),
+                })
+        self._sort_formats(formats)
+
+        duration = int_or_none(vdata.get('duration'), 1000)
+        like_count = int_or_none(vdata.get('likes'))
+
+        return {
+            'id': video_id,
+            'title': vdata['title'],
+            'description': vdata.get('description'),
+            'thumbnail': vdata.get('thumbnail'),
+            'formats': formats,
+            'age_limit': age_limit,
+            'duration': duration,
+            'like_count': like_count,
+        }

youtube_dl/extractor/comedycentral.py

@@ -1,73 +1,65 @@
+from __future__ import unicode_literals
+
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
-from .mtv import MTVIE, _media_xml_tag
+from .mtv import MTVServicesInfoExtractor
 from ..utils import (
     compat_str,
     compat_urllib_parse,
-
     ExtractorError,
+    float_or_none,
     unified_strdate,
 )
 
 
-class ComedyCentralIE(MTVIE):
-    _VALID_URL = r'http://www.comedycentral.com/(video-clips|episodes|cc-studios)/(?P<title>.*)'
-    _FEED_URL = u'http://comedycentral.com/feeds/mrss/'
+class ComedyCentralIE(MTVServicesInfoExtractor):
+    _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
+        (video-clips|episodes|cc-studios|video-collections|full-episodes)
+        /(?P<title>.*)'''
+    _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
 
     _TEST = {
-        u'url': u'http://www.comedycentral.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
-        u'md5': u'4167875aae411f903b751a21f357f1ee',
-        u'info_dict': {
-            u'id': u'cef0cbb3-e776-4bc9-b62e-8016deccb354',
-            u'ext': u'mp4',
-            u'title': u'Uncensored - Greg Fitzsimmons - Too Good of a Mother',
-            u'description': u'After a certain point, breastfeeding becomes c**kblocking.',
+        'url': 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
+        'md5': 'c4f48e9eda1b16dd10add0744344b6d8',
+        'info_dict': {
+            'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354',
+            'ext': 'mp4',
+            'title': 'CC:Stand-Up|Greg Fitzsimmons: Life on Stage|Uncensored - Too Good of a Mother',
+            'description': 'After a certain point, breastfeeding becomes c**kblocking.',
         },
     }
-    # Overwrite MTVIE properties we don't want
-    _TESTS = []
-
-    def _get_thumbnail_url(self, uri, itemdoc):
-        search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail'))
-        return itemdoc.find(search_path).attrib['url']
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        title = mobj.group('title')
-        webpage = self._download_webpage(url, title)
-        mgid = self._search_regex(r'data-mgid="(?P<mgid>mgid:.*?)"',
-                                  webpage, u'mgid')
-        return self._get_videos_info(mgid)
 
 
 class ComedyCentralShowsIE(InfoExtractor):
-    IE_DESC = u'The Daily Show / Colbert Report'
+    IE_DESC = 'The Daily Show / The Colbert Report'
     # urls can be abbreviations like :thedailyshow or :colbert
     # urls for episodes like:
     # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day
     #                     or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news
     #                     or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524
-    _VALID_URL = r"""^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport)
-                      |(https?://)?(www\.)?
-                          (?P<showname>thedailyshow|colbertnation)\.com/
-                         (full-episodes/(?P<episode>.*)|
+    _VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport)
+                      |https?://(:www\.)?
+                          (?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/
+                         ((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)|
                           (?P<clip>
-                              (the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
-                              |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)))|
+                              (?:(?:guests/[^/]+|videos|video-playlists|special-editions)/[^/]+/(?P<videotitle>[^/?#]+))
+                              |(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
+                              |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))
+                          )|
                           (?P<interview>
-                              extended-interviews/(?P<interID>[0-9]+)/playlist_tds_extended_(?P<interview_title>.*?)/.*?)))
-                     $"""
+                              extended-interviews/(?P<interID>[0-9a-z]+)/(?:playlist_tds_extended_)?(?P<interview_title>.*?)(/.*?)?)))
+                     (?:[?#].*|$)'''
     _TEST = {
-        u'url': u'http://www.thedailyshow.com/watch/thu-december-13-2012/kristen-stewart',
-        u'file': u'422212.mp4',
-        u'md5': u'4e2f5cb088a83cd8cdb7756132f9739d',
-        u'info_dict': {
-            u"upload_date": u"20121214", 
-            u"description": u"Kristen Stewart", 
-            u"uploader": u"thedailyshow", 
-            u"title": u"thedailyshow-kristen-stewart part 1"
+        'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart',
+        'md5': '4e2f5cb088a83cd8cdb7756132f9739d',
+        'info_dict': {
+            'id': 'ab9ab3e7-5a98-4dbe-8b21-551dc0523d55',
+            'ext': 'mp4',
+            'upload_date': '20121213',
+            'description': 'Kristen Stewart learns to let loose in "On the Road."',
+            'uploader': 'thedailyshow',
+            'title': 'thedailyshow kristen-stewart part 1',
         }
     }
 
@@ -90,34 +82,31 @@ class ComedyCentralShowsIE(InfoExtractor):
         '400': (384, 216),
     }
 
-    @classmethod
-    def suitable(cls, url):
-        """Receives a URL and returns True if suitable for this IE."""
-        return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
-
     @staticmethod
     def _transform_rtmp_url(rtmp_video_url):
-        m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp.comedystor/.*)$', rtmp_video_url)
+        m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\.comedystor/.*)$', rtmp_video_url)
         if not m:
-            raise ExtractorError(u'Cannot transform RTMP url')
+            raise ExtractorError('Cannot transform RTMP url')
         base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
         return base + m.group('finalid')
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url, re.VERBOSE)
         if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
+            raise ExtractorError('Invalid URL: %s' % url)
 
         if mobj.group('shortname'):
             if mobj.group('shortname') in ('tds', 'thedailyshow'):
-                url = u'http://www.thedailyshow.com/full-episodes/'
+                url = 'http://thedailyshow.cc.com/full-episodes/'
             else:
-                url = u'http://www.colbertnation.com/full-episodes/'
+                url = 'http://thecolbertreport.cc.com/full-episodes/'
             mobj = re.match(self._VALID_URL, url, re.VERBOSE)
             assert mobj is not None
 
         if mobj.group('clip'):
-            if mobj.group('showname') == 'thedailyshow':
+            if mobj.group('videotitle'):
+                epTitle = mobj.group('videotitle')
+            elif mobj.group('showname') == 'thedailyshow':
                 epTitle = mobj.group('tdstitle')
             else:
                 epTitle = mobj.group('cntitle')
@@ -131,88 +120,96 @@ class ComedyCentralShowsIE(InfoExtractor):
                 epTitle = mobj.group('showname')
             else:
                 epTitle = mobj.group('episode')
+        show_name = mobj.group('showname')
 
-        self.report_extraction(epTitle)
-        webpage,htmlHandle = self._download_webpage_handle(url, epTitle)
+        webpage, htmlHandle = self._download_webpage_handle(url, epTitle)
         if dlNewest:
             url = htmlHandle.geturl()
             mobj = re.match(self._VALID_URL, url, re.VERBOSE)
             if mobj is None:
-                raise ExtractorError(u'Invalid redirected URL: ' + url)
+                raise ExtractorError('Invalid redirected URL: ' + url)
             if mobj.group('episode') == '':
-                raise ExtractorError(u'Redirected URL is still not specific: ' + url)
-            epTitle = mobj.group('episode')
+                raise ExtractorError('Redirected URL is still not specific: ' + url)
+            epTitle = (mobj.group('episode') or mobj.group('videotitle')).rpartition('/')[-1]
 
         mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage)
-
         if len(mMovieParams) == 0:
             # The Colbert Report embeds the information in a without
             # a URL prefix; so extract the alternate reference
             # and then add the URL prefix manually.
 
-            altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage)
+            altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video|playlist).*?:.*?)"', webpage)
             if len(altMovieParams) == 0:
-                raise ExtractorError(u'unable to find Flash URL in webpage ' + url)
+                raise ExtractorError('unable to find Flash URL in webpage ' + url)
             else:
                 mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
 
         uri = mMovieParams[0][1]
-        indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri})
-        indexXml = self._download_webpage(indexUrl, epTitle,
-                                          u'Downloading show index',
-                                          u'unable to download episode index')
+        # Correct cc.com in uri
+        uri = re.sub(r'(episode:[^.]+)(\.cc)?\.com', r'\1.cc.com', uri)
 
-        results = []
+        index_url = 'http://%s.cc.com/feeds/mrss?%s' % (show_name, compat_urllib_parse.urlencode({'uri': uri}))
+        idoc = self._download_xml(
+            index_url, epTitle,
+            'Downloading show index', 'Unable to download episode index')
 
-        idoc = xml.etree.ElementTree.fromstring(indexXml)
-        itemEls = idoc.findall('.//item')
-        for partNum,itemEl in enumerate(itemEls):
-            mediaId = itemEl.findall('./guid')[0].text
-            shortMediaId = mediaId.split(':')[-1]
-            showId = mediaId.split(':')[-2].replace('.com', '')
-            officialTitle = itemEl.findall('./title')[0].text
-            officialDate = unified_strdate(itemEl.findall('./pubDate')[0].text)
+        title = idoc.find('./channel/title').text
+        description = idoc.find('./channel/description').text
 
-            configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
-                        compat_urllib_parse.urlencode({'uri': mediaId}))
-            configXml = self._download_webpage(configUrl, epTitle,
-                                               u'Downloading configuration for %s' % shortMediaId)
+        entries = []
+        item_els = idoc.findall('.//item')
+        for part_num, itemEl in enumerate(item_els):
+            upload_date = unified_strdate(itemEl.findall('./pubDate')[0].text)
+            thumbnail = itemEl.find('.//{http://search.yahoo.com/mrss/}thumbnail').attrib.get('url')
+
+            content = itemEl.find('.//{http://search.yahoo.com/mrss/}content')
+            duration = float_or_none(content.attrib.get('duration'))
+            mediagen_url = content.attrib['url']
+            guid = itemEl.find('./guid').text.rpartition(':')[-1]
+
+            cdoc = self._download_xml(
+                mediagen_url, epTitle,
+                'Downloading configuration for segment %d / %d' % (part_num + 1, len(item_els)))
 
-            cdoc = xml.etree.ElementTree.fromstring(configXml)
             turls = []
             for rendition in cdoc.findall('.//rendition'):
                 finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
                 turls.append(finfo)
 
-            if len(turls) == 0:
-                self._downloader.report_error(u'unable to download ' + mediaId + ': No videos found')
-                continue
-
             formats = []
             for format, rtmp_video_url in turls:
                 w, h = self._video_dimensions.get(format, (None, None))
                 formats.append({
+                    'format_id': 'vhttp-%s' % format,
                     'url': self._transform_rtmp_url(rtmp_video_url),
                     'ext': self._video_extensions.get(format, 'mp4'),
-                    'format_id': format,
                     'height': h,
                     'width': w,
                 })
+                formats.append({
+                    'format_id': 'rtmp-%s' % format,
+                    'url': rtmp_video_url.replace('viacomccstrm', 'viacommtvstrm'),
+                    'ext': self._video_extensions.get(format, 'mp4'),
+                    'height': h,
+                    'width': w,
+                })
+                self._sort_formats(formats)
 
-            effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1)
-            info = {
-                'id': shortMediaId,
+            virtual_id = show_name + ' ' + epTitle + ' part ' + compat_str(part_num + 1)
+            entries.append({
+                'id': guid,
+                'title': virtual_id,
                 'formats': formats,
-                'uploader': showId,
-                'upload_date': officialDate,
-                'title': effTitle,
-                'thumbnail': None,
-                'description': compat_str(officialTitle),
-            }
+                'uploader': show_name,
+                'upload_date': upload_date,
+                'duration': duration,
+                'thumbnail': thumbnail,
+                'description': description,
+            })
 
-            # TODO: Remove when #980 has been merged
-            info.update(info['formats'][-1])
-
-            results.append(info)
-
-        return results
+        return {
+            '_type': 'playlist',
+            'entries': entries,
+            'title': show_name + ' ' + title,
+            'description': description,
+        }

youtube_dl/extractor/common.py

@@ -1,14 +1,18 @@
 import base64
+import hashlib
+import json
+import netrc
 import os
 import re
 import socket
 import sys
-import netrc
+import time
 import xml.etree.ElementTree
 
 from ..utils import (
     compat_http_client,
     compat_urllib_error,
+    compat_urllib_parse_urlparse,
     compat_str,
 
     clean_html,
@@ -18,6 +22,7 @@ from ..utils import (
     sanitize_filename,
     unescapeHTML,
 )
+_NO_DEFAULT = object()
 
 
 class InfoExtractor(object):
@@ -34,52 +39,88 @@ class InfoExtractor(object):
     The dictionaries must include the following fields:
 
     id:             Video identifier.
-    url:            Final video URL.
     title:          Video title, unescaped.
-    ext:            Video filename extension.
 
-    Instead of url and ext, formats can also specified.
+    Additionally, it must contain either a formats entry or a url one:
+
+    formats:        A list of dictionaries for each format available, ordered
+                    from worst to best quality.
+
+                    Potential fields:
+                    * url        Mandatory. The URL of the video file
+                    * ext        Will be calculated from url if missing
+                    * format     A human-readable description of the format
+                                 ("mp4 container with h264/opus").
+                                 Calculated from the format_id, width, height.
+                                 and format_note fields if missing.
+                    * format_id  A short description of the format
+                                 ("mp4_h264_opus" or "19").
+                                Technically optional, but strongly recommended.
+                    * format_note Additional info about the format
+                                 ("3D" or "DASH video")
+                    * width      Width of the video, if known
+                    * height     Height of the video, if known
+                    * resolution Textual description of width and height
+                    * tbr        Average bitrate of audio and video in KBit/s
+                    * abr        Average audio bitrate in KBit/s
+                    * acodec     Name of the audio codec in use
+                    * asr        Audio sampling rate in Hertz
+                    * vbr        Average video bitrate in KBit/s
+                    * vcodec     Name of the video codec in use
+                    * container  Name of the container format
+                    * filesize   The number of bytes, if known in advance
+                    * filesize_approx  An estimate for the number of bytes
+                    * player_url SWF Player URL (used for rtmpdump).
+                    * protocol   The protocol that will be used for the actual
+                                 download, lower-case.
+                                 "http", "https", "rtsp", "rtmp", "m3u8" or so.
+                    * preference Order number of this format. If this field is
+                                 present and not None, the formats get sorted
+                                 by this field, regardless of all other values.
+                                 -1 for default (order by other properties),
+                                 -2 or smaller for less than default.
+                    * quality    Order number of the video quality of this
+                                 format, irrespective of the file format.
+                                 -1 for default (order by other properties),
+                                 -2 or smaller for less than default.
+    url:            Final video URL.
+    ext:            Video filename extension.
+    format:         The video format, defaults to ext (used for --get-format)
+    player_url:     SWF Player URL (used for rtmpdump).
 
     The following fields are optional:
 
-    format:         The video format, defaults to ext (used for --get-format)
-    thumbnails:     A list of dictionaries (with the entries "resolution" and
-                    "url") for the varying thumbnails
+    display_id      An alternative identifier for the video, not necessarily
+                    unique, but available before title. Typically, id is
+                    something like "4234987", title "Dancing naked mole rats",
+                    and display_id "dancing-naked-mole-rats"
+    thumbnails:     A list of dictionaries, with the following entries:
+                        * "url"
+                        * "width" (optional, int)
+                        * "height" (optional, int)
+                        * "resolution" (optional, string "{width}x{height"},
+                                        deprecated)
     thumbnail:      Full URL to a video thumbnail image.
     description:    One-line video description.
     uploader:       Full name of the video uploader.
+    timestamp:      UNIX timestamp of the moment the video became available.
     upload_date:    Video upload date (YYYYMMDD).
+                    If not explicitly set, calculated from timestamp.
     uploader_id:    Nickname or id of the video uploader.
     location:       Physical location of the video.
-    player_url:     SWF Player URL (used for rtmpdump).
     subtitles:      The subtitle file contents as a dictionary in the format
                     {language: subtitles}.
+    duration:       Length of the video in seconds, as an integer.
     view_count:     How many users have watched the video on the platform.
-    urlhandle:      [internal] The urlHandle to be used to download the file,
-                    like returned by urllib.request.urlopen
+    like_count:     Number of positive ratings of the video
+    dislike_count:  Number of negative ratings of the video
+    comment_count:  Number of comments on the video
     age_limit:      Age restriction for the video, as an integer (years)
-    formats:        A list of dictionaries for each format available, it must
-                    be ordered from worst to best quality. Potential fields:
-                    * url       Mandatory. The URL of the video file
-                    * ext       Will be calculated from url if missing
-                    * format    A human-readable description of the format
-                                ("mp4 container with h264/opus").
-                                Calculated from the format_id, width, height.
-                                and format_note fields if missing.
-                    * format_id A short description of the format
-                                ("mp4_h264_opus" or "19")
-                    * format_note Additional info about the format
-                                ("3D" or "DASH video")
-                    * width     Width of the video, if known
-                    * height    Height of the video, if known
-                    * abr       Average audio bitrate in KBit/s
-                    * acodec    Name of the audio codec in use
-                    * vbr       Average video bitrate in KBit/s
-                    * vcodec    Name of the video codec in use
-                    * filesize  The number of bytes, if known in advance
     webpage_url:    The url to the video webpage, if given to youtube-dl it
                     should allow to get the same result again. (It will be set
                     by YoutubeDL if it's missing)
+    categories:     A list of categories that the video falls in, for example
+                    ["Sports", "Berlin"]
 
     Unless mentioned otherwise, the fields should be Unicode strings.
 
@@ -87,9 +128,6 @@ class InfoExtractor(object):
     _real_extract() methods and define a _VALID_URL regexp.
     Probably, they should also be added to the list of extractors.
 
-    _real_extract() must return a *list* of information dictionaries as
-    described above.
-
     Finally, the _WORKING attribute should be set to False for broken IEs
     in order to warn the users and skip the tests.
     """
@@ -151,27 +189,40 @@ class InfoExtractor(object):
     def IE_NAME(self):
         return type(self).__name__[:-2]
 
-    def _request_webpage(self, url_or_request, video_id, note=None, errnote=None):
+    def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
         """ Returns the response handle """
         if note is None:
             self.report_download_webpage(video_id)
         elif note is not False:
-            self.to_screen(u'%s: %s' % (video_id, note))
+            if video_id is None:
+                self.to_screen(u'%s' % (note,))
+            else:
+                self.to_screen(u'%s: %s' % (video_id, note))
         try:
             return self._downloader.urlopen(url_or_request)
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+            if errnote is False:
+                return False
             if errnote is None:
                 errnote = u'Unable to download webpage'
-            raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2], cause=err)
+            errmsg = u'%s: %s' % (errnote, compat_str(err))
+            if fatal:
+                raise ExtractorError(errmsg, sys.exc_info()[2], cause=err)
+            else:
+                self._downloader.report_warning(errmsg)
+                return False
 
-    def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None):
+    def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
         """ Returns a tuple (page content as string, URL handle) """
 
         # Strip hashes from the URL (#1038)
         if isinstance(url_or_request, (compat_str, str)):
             url_or_request = url_or_request.partition('#')[0]
 
-        urlh = self._request_webpage(url_or_request, video_id, note, errnote)
+        urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal)
+        if urlh is False:
+            assert not fatal
+            return False
         content_type = urlh.headers.get('Content-Type', '')
         webpage_bytes = urlh.read()
         m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
@@ -182,6 +233,8 @@ class InfoExtractor(object):
                           webpage_bytes[:1024])
             if m:
                 encoding = m.group(1).decode('ascii')
+            elif webpage_bytes.startswith(b'\xff\xfe'):
+                encoding = 'utf-16'
             else:
                 encoding = 'utf-8'
         if self._downloader.params.get('dump_intermediate_pages', False):
@@ -197,24 +250,75 @@ class InfoExtractor(object):
                 url = url_or_request.get_full_url()
             except AttributeError:
                 url = url_or_request
-            raw_filename = ('%s_%s.dump' % (video_id, url))
+            basen = '%s_%s' % (video_id, url)
+            if len(basen) > 240:
+                h = u'___' + hashlib.md5(basen.encode('utf-8')).hexdigest()
+                basen = basen[:240 - len(h)] + h
+            raw_filename = basen + '.dump'
             filename = sanitize_filename(raw_filename, restricted=True)
             self.to_screen(u'Saving request to ' + filename)
             with open(filename, 'wb') as outf:
                 outf.write(webpage_bytes)
 
-        content = webpage_bytes.decode(encoding, 'replace')
+        try:
+            content = webpage_bytes.decode(encoding, 'replace')
+        except LookupError:
+            content = webpage_bytes.decode('utf-8', 'replace')
+
+        if (u'<title>Access to this site is blocked</title>' in content and
+                u'Websense' in content[:512]):
+            msg = u'Access to this webpage has been blocked by Websense filtering software in your network.'
+            blocked_iframe = self._html_search_regex(
+                r'<iframe src="([^"]+)"', content,
+                u'Websense information URL', default=None)
+            if blocked_iframe:
+                msg += u' Visit %s for more details' % blocked_iframe
+            raise ExtractorError(msg, expected=True)
+
         return (content, urlh)
 
-    def _download_webpage(self, url_or_request, video_id, note=None, errnote=None):
+    def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
         """ Returns the data of the page as a string """
-        return self._download_webpage_handle(url_or_request, video_id, note, errnote)[0]
+        res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal)
+        if res is False:
+            return res
+        else:
+            content, _ = res
+            return content
 
-    def _download_xml(self, url_or_request, video_id, note=u'Downloading XML', errnote=u'Unable to downloand XML'):
+    def _download_xml(self, url_or_request, video_id,
+                      note=u'Downloading XML', errnote=u'Unable to download XML',
+                      transform_source=None, fatal=True):
         """Return the xml as an xml.etree.ElementTree.Element"""
-        xml_string = self._download_webpage(url_or_request, video_id, note, errnote)
+        xml_string = self._download_webpage(
+            url_or_request, video_id, note, errnote, fatal=fatal)
+        if xml_string is False:
+            return xml_string
+        if transform_source:
+            xml_string = transform_source(xml_string)
         return xml.etree.ElementTree.fromstring(xml_string.encode('utf-8'))
 
+    def _download_json(self, url_or_request, video_id,
+                       note=u'Downloading JSON metadata',
+                       errnote=u'Unable to download JSON metadata',
+                       transform_source=None,
+                       fatal=True):
+        json_string = self._download_webpage(
+            url_or_request, video_id, note, errnote, fatal=fatal)
+        if (not fatal) and json_string is False:
+            return None
+        if transform_source:
+            json_string = transform_source(json_string)
+        try:
+            return json.loads(json_string)
+        except ValueError as ve:
+            raise ExtractorError('Failed to download JSON', cause=ve)
+
+    def report_warning(self, msg, video_id=None):
+        idstr = u'' if video_id is None else u'%s: ' % video_id
+        self._downloader.report_warning(
+            u'[%s] %s%s' % (self.IE_NAME, idstr, msg))
+
     def to_screen(self, msg):
         """Print msg to screen, prefixing it with '[ie_name]'"""
         self._downloader.to_screen(u'[%s] %s' % (self.IE_NAME, msg))
@@ -236,7 +340,8 @@ class InfoExtractor(object):
         self.to_screen(u'Logging in')
 
     #Methods for following #608
-    def url_result(self, url, ie=None, video_id=None):
+    @staticmethod
+    def url_result(url, ie=None, video_id=None):
         """Returns a url that points to a page that should be processed"""
         #TODO: ie should be the class used for getting the info
         video_info = {'_type': 'url',
@@ -245,7 +350,8 @@ class InfoExtractor(object):
         if video_id is not None:
             video_info['id'] = video_id
         return video_info
-    def playlist_result(self, entries, playlist_id=None, playlist_title=None):
+    @staticmethod
+    def playlist_result(entries, playlist_id=None, playlist_title=None):
         """Returns a playlist"""
         video_info = {'_type': 'playlist',
                       'entries': entries}
@@ -255,7 +361,7 @@ class InfoExtractor(object):
             video_info['title'] = playlist_title
         return video_info
 
-    def _search_regex(self, pattern, string, name, default=None, fatal=True, flags=0):
+    def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0):
         """
         Perform a regex search on the given string, using a single or a list of
         patterns returning the first matching group.
@@ -269,7 +375,7 @@ class InfoExtractor(object):
                 mobj = re.search(p, string, flags)
                 if mobj: break
 
-        if sys.stderr.isatty() and os.name != 'nt':
+        if os.name != 'nt' and sys.stderr.isatty():
             _name = u'\033[0;34m%s\033[0m' % name
         else:
             _name = name
@@ -277,7 +383,7 @@ class InfoExtractor(object):
         if mobj:
             # return the first matching group
             return next(g for g in mobj.groups() if g is not None)
-        elif default is not None:
+        elif default is not _NO_DEFAULT:
             return default
         elif fatal:
             raise RegexNotFoundError(u'Unable to extract %s' % _name)
@@ -286,7 +392,7 @@ class InfoExtractor(object):
                 u'please report this issue on http://yt-dl.org/bug' % _name)
             return None
 
-    def _html_search_regex(self, pattern, string, name, default=None, fatal=True, flags=0):
+    def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0):
         """
         Like _search_regex, but strips HTML tags and unescapes entities.
         """
@@ -329,8 +435,8 @@ class InfoExtractor(object):
     # Helper functions for extracting OpenGraph info
     @staticmethod
     def _og_regexes(prop):
-        content_re = r'content=(?:"([^>]+?)"|\'(.+?)\')'
-        property_re = r'property=[\'"]og:%s[\'"]' % re.escape(prop)
+        content_re = r'content=(?:"([^>]+?)"|\'([^>]+?)\')'
+        property_re = r'(?:name|property)=[\'"]og:%s[\'"]' % re.escape(prop)
         template = r'<meta[^>]+?%s[^>]+?%s'
         return [
             template % (property_re, content_re),
@@ -359,13 +465,17 @@ class InfoExtractor(object):
         if secure: regexes = self._og_regexes('video:secure_url') + regexes
         return self._html_search_regex(regexes, html, name, **kargs)
 
-    def _html_search_meta(self, name, html, display_name=None):
+    def _og_search_url(self, html, **kargs):
+        return self._og_search_property('url', html, **kargs)
+
+    def _html_search_meta(self, name, html, display_name=None, fatal=False, **kwargs):
         if display_name is None:
             display_name = name
         return self._html_search_regex(
-            r'''(?ix)<meta(?=[^>]+(?:name|property)=["\']%s["\'])
+            r'''(?ix)<meta
+                    (?=[^>]+(?:itemprop|name|property)=["\']?%s["\']?)
                     [^>]+content=["\']([^"\']+)["\']''' % re.escape(name),
-            html, display_name, fatal=False)
+            html, display_name, fatal=fatal, **kwargs)
 
     def _dc_search_uploader(self, html):
         return self._html_search_meta('dc.creator', html, 'uploader')
@@ -394,6 +504,90 @@ class InfoExtractor(object):
         }
         return RATING_TABLE.get(rating.lower(), None)
 
+    def _twitter_search_player(self, html):
+        return self._html_search_meta('twitter:player', html,
+            'twitter card player')
+
+    def _sort_formats(self, formats):
+        if not formats:
+            raise ExtractorError(u'No video formats found')
+
+        def _formats_key(f):
+            # TODO remove the following workaround
+            from ..utils import determine_ext
+            if not f.get('ext') and 'url' in f:
+                f['ext'] = determine_ext(f['url'])
+
+            preference = f.get('preference')
+            if preference is None:
+                proto = f.get('protocol')
+                if proto is None:
+                    proto = compat_urllib_parse_urlparse(f.get('url', '')).scheme
+
+                preference = 0 if proto in ['http', 'https'] else -0.1
+                if f.get('ext') in ['f4f', 'f4m']:  # Not yet supported
+                    preference -= 0.5
+
+            if f.get('vcodec') == 'none':  # audio only
+                if self._downloader.params.get('prefer_free_formats'):
+                    ORDER = [u'aac', u'mp3', u'm4a', u'webm', u'ogg', u'opus']
+                else:
+                    ORDER = [u'webm', u'opus', u'ogg', u'mp3', u'aac', u'm4a']
+                ext_preference = 0
+                try:
+                    audio_ext_preference = ORDER.index(f['ext'])
+                except ValueError:
+                    audio_ext_preference = -1
+            else:
+                if self._downloader.params.get('prefer_free_formats'):
+                    ORDER = [u'flv', u'mp4', u'webm']
+                else:
+                    ORDER = [u'webm', u'flv', u'mp4']
+                try:
+                    ext_preference = ORDER.index(f['ext'])
+                except ValueError:
+                    ext_preference = -1
+                audio_ext_preference = 0
+
+            return (
+                preference,
+                f.get('quality') if f.get('quality') is not None else -1,
+                f.get('height') if f.get('height') is not None else -1,
+                f.get('width') if f.get('width') is not None else -1,
+                ext_preference,
+                f.get('tbr') if f.get('tbr') is not None else -1,
+                f.get('vbr') if f.get('vbr') is not None else -1,
+                f.get('abr') if f.get('abr') is not None else -1,
+                audio_ext_preference,
+                f.get('filesize') if f.get('filesize') is not None else -1,
+                f.get('filesize_approx') if f.get('filesize_approx') is not None else -1,
+                f.get('format_id'),
+            )
+        formats.sort(key=_formats_key)
+
+    def http_scheme(self):
+        """ Either "https:" or "https:", depending on the user's preferences """
+        return (
+            'http:'
+            if self._downloader.params.get('prefer_insecure', False)
+            else 'https:')
+
+    def _proto_relative_url(self, url, scheme=None):
+        if url is None:
+            return url
+        if url.startswith('//'):
+            if scheme is None:
+                scheme = self.http_scheme()
+            return scheme + url
+        else:
+            return url
+
+    def _sleep(self, timeout, video_id, msg_template=None):
+        if msg_template is None:
+            msg_template = u'%(video_id)s: Waiting for %(timeout)s seconds'
+        msg = msg_template % {'video_id': video_id, 'timeout': timeout}
+        self.to_screen(msg)
+        time.sleep(timeout)
 
 
 class SearchInfoExtractor(InfoExtractor):