release 2015.08.23

videobam.com redirects to sendvid.com now

.travis.yml

@@ -2,11 +2,10 @@ language: python
 python:
   - "2.6"
   - "2.7"
+  - "3.2"
   - "3.3"
   - "3.4"
-before_install:
-  - sudo apt-get update -qq
-  - sudo apt-get install -yqq rtmpdump
+sudo: false
 script: nosetests test --verbose
 notifications:
   email:

AUTHORS

@@ -112,3 +112,31 @@ Frans de Jonge
 Robin de Rooij
 Ryan Schmidt
 Leslie P. Polzer
+Duncan Keall
+Alexander Mamay
+Devin J. Pohly
+Eduardo Ferro Aldama
+Jeff Buchbinder
+Amish Bhadeshia
+Joram Schrijver
+Will W.
+Mohammad Teimori Pabandi
+Roman Le Négrate
+Matthias Küch
+Julian Richen
+Ping O.
+Mister Hat
+Peter Ding
+jackyzy823
+George Brighton
+Remita Amine
+Aurélio A. Heckert
+Bernhard Minks
+sceext
+Zach Bruggeman
+Tjark Saul
+slangangular
+Behrouz Abbasi
+ngld
+nyuszika7h
+Shaun Walbridge

CONTRIBUTING.md

@@ -18,7 +18,9 @@ If your report is shorter than two lines, it is almost certainly missing some of
 
 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.
+If your server has multiple IPs or you suspect censorship, adding --call-home may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/).
+
+**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?
 
@@ -123,7 +125,7 @@ If you want to add support for a new site, you can follow this quick list (assum
     ```
 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. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
-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.
+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 and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L62-L200). Add tests and code for as many as you want.
 8. If you can, check the code with [flake8](https://pypi.python.org/pypi/flake8).
 9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
 

Makefile

@@ -2,6 +2,7 @@ all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bas
 
 clean:
 	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 youtube-dl.zsh youtube-dl.fish *.dump *.part *.info.json *.mp4 *.flv *.mp3 *.avi CONTRIBUTING.md.tmp youtube-dl youtube-dl.exe
+	find . -name "*.pyc" -delete
 
 PREFIX ?= /usr/local
 BINDIR ?= $(PREFIX)/bin

README.md

@@ -5,6 +5,7 @@ youtube-dl - download videos from youtube.com or other video platforms
 - [OPTIONS](#options)
 - [CONFIGURATION](#configuration)
 - [OUTPUT TEMPLATE](#output-template)
+- [FORMAT SELECTION](#format-selection)
 - [VIDEO SELECTION](#video-selection)
 - [FAQ](#faq)
 - [DEVELOPER INSTRUCTIONS](#developer-instructions)
@@ -16,12 +17,12 @@ youtube-dl - download videos from youtube.com or other video platforms
 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
+    sudo chmod a+rx /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
+    sudo chmod a+rx /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).
 
@@ -45,371 +46,224 @@ which means you can modify it, redistribute it or use it however you like.
     youtube-dl [OPTIONS] URL [URL...]
 
 # 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
-                                     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
-    --list-extractors                List all supported extractors and the URLs
-                                     they would handle
-    --extractor-descriptions         Output descriptions of all supported
-                                     extractors
-    --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 ("auto_warning" to emit a
-                                     warning when guessing). "error" just throws
-                                     an error. The default value "fixup_error"
-                                     repairs broken URLs, but emits an error if
-                                     this is not possible instead of searching.
-    --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/config (%APPDATA%/youtube-dl/config.txt
-                                     on Windows)
-    --flat-playlist                  Do not extract the videos of a playlist,
-                                     only list them.
-    --no-color                       Do not emit color codes in output.
+    -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
+    --list-extractors                List all supported extractors
+    --extractor-descriptions         Output descriptions of all supported extractors
+    --force-generic-extractor        Force extraction to use the generic extractor
+    --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 ("auto_warning" to emit a warning when guessing). "error" just throws an error. The
+                                     default value "fixup_error" repairs broken URLs, but emits an error if this is not possible instead of searching.
+    --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/config (%APPDATA%/youtube-dl/config.txt on Windows)
+    --flat-playlist                  Do not extract the videos of a playlist, only list them.
+    --no-color                       Do not emit color codes in output
 
 ## Network Options:
-    --proxy URL                      Use the specified HTTP/HTTPS proxy. Pass in
-                                     an empty string (--proxy "") for direct
-                                     connection
+    --proxy URL                      Use the specified HTTP/HTTPS proxy. Pass in an empty string (--proxy "") for direct connection
     --socket-timeout SECONDS         Time to wait before giving up, in seconds
-    --source-address IP              Client-side IP address to bind to
-                                     (experimental)
-    -4, --force-ipv4                 Make all connections via IPv4
-                                     (experimental)
-    -6, --force-ipv6                 Make all connections via IPv6
-                                     (experimental)
+    --source-address IP              Client-side IP address to bind to (experimental)
+    -4, --force-ipv4                 Make all connections via IPv4 (experimental)
+    -6, --force-ipv6                 Make all connections via IPv6 (experimental)
+    --cn-verification-proxy URL      Use this proxy to verify the IP address for some Chinese sites. The default proxy specified by --proxy (or none, if the options is
+                                     not present) is used for the actual downloading. (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)
-    --playlist-items ITEM_SPEC       playlist video items to download. Specify
-                                     indices of the videos in the playlist
-                                     seperated by commas like: "--playlist-items
-                                     1,2,5,8" if you want to download videos
-                                     indexed 1, 2, 5, 8 in the playlist. You can
-                                     specify range: "--playlist-items
-                                     1-3,7,10-13", it will download the videos
-                                     at index 1, 2, 3, 7, 10, 11, 12 and 13.
-    --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)
+    --playlist-start NUMBER          Playlist video to start at (default is 1)
+    --playlist-end NUMBER            Playlist video to end at (default is last)
+    --playlist-items ITEM_SPEC       Playlist video items to download. Specify indices of the videos in the playlist separated by commas like: "--playlist-items 1,2,5,8"
+                                     if you want to download videos indexed 1, 2, 5, 8 in the playlist. You can specify range: "--playlist-items 1-3,7,10-13", it will
+                                     download the videos at index 1, 2, 3, 7, 10, 11, 12 and 13.
+    --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
-    --match-filter FILTER            (Experimental) Generic video filter.
-                                     Specify any key (see help for -o for a list
-                                     of available keys) to match if the key is
-                                     present, !key to check if the key is not
-                                     present,key > NUMBER (like "comment_count >
-                                     12", also works with >=, <, <=, !=, =) to
-                                     compare against a number, and & to require
-                                     multiple matches. Values which are not
-                                     known are excluded unless you put a
-                                     question mark (?) after the operator.For
-                                     example, to only match videos that have
-                                     been liked more than 100 times and disliked
-                                     less than 50 times (or the dislike
-                                     functionality is not available at the given
-                                     service), but who also have a description,
-                                     use  --match-filter "like_count > 100 &
+    --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
+    --match-filter FILTER            Generic video filter (experimental). Specify any key (see help for -o for a list of available keys) to match if the key is present,
+                                     !key to check if the key is not present,key > NUMBER (like "comment_count > 12", also works with >=, <, <=, !=, =) to compare against
+                                     a number, and & to require multiple matches. Values which are not known are excluded unless you put a question mark (?) after the
+                                     operator.For example, to only match videos that have been liked more than 100 times and disliked less than 50 times (or the dislike
+                                     functionality is not available at the given service), but who also have a description, use  --match-filter "like_count > 100 &
                                      dislike_count <? 50 & description" .
-    --no-playlist                    If the URL refers to a video and a
-                                     playlist, download only the 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)
+    --no-playlist                    Download only the video, if the URL refers to a video and a playlist.
+    --yes-playlist                   Download the playlist, if the URL refers to a video and a playlist.
+    --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)
 
 ## 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), or
-                                     "infinite".
-    --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), or "infinite".
+    --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.
     --playlist-reverse               Download playlist videos in reverse order
-    --xattr-set-filesize             (experimental) set file xattribute
-                                     ytdl.filesize with expected filesize
-    --hls-prefer-native              (experimental) Use the native HLS
-                                     downloader instead of ffmpeg.
-    --external-downloader COMMAND    (experimental) Use the specified external
-                                     downloader. Currently supports
-                                     aria2c,curl,wget
+    --xattr-set-filesize             Set file xattribute ytdl.filesize with expected filesize (experimental)
+    --hls-prefer-native              Use the native HLS downloader instead of ffmpeg (experimental)
+    --external-downloader COMMAND    Use the specified external downloader. Currently supports aria2c,axel,curl,httpie,wget
+    --external-downloader-args ARGS  Give these arguments to the external downloader
 
 ## Filesystem Options:
-    -a, --batch-file FILE            file containing URLs to download ('-' for
-                                     stdin)
-    --id                             use only video ID in file name
-    -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_title)s,
-                                     %(playlist_id)s, or %(playlist)s (=title if
-                                     present, ID otherwise) for the playlist the
-                                     video is in, %(playlist_index)s for the
-                                     position in the playlist. %(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. %% for a literal percent. 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' .
-    --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, --auto-number                [deprecated; use  -o
-                                     "%(autonumber)s-%(title)s.%(ext)s" ] number
-                                     downloaded files starting from 00000
-    -t, --title                      [deprecated] use title in file name
-                                     (default)
-    -l, --literal                    [deprecated] alias of --title
-    -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)
-    --no-part                        do not use .part files - write directly
-                                     into output file
-    --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
-    --load-info FILE                 json file containing the video information
-                                     (created with the "--write-json" option)
-    --cookies FILE                   file to read cookies from and dump cookie
-                                     jar in
-    --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.
+    -a, --batch-file FILE            File containing URLs to download ('-' for stdin)
+    --id                             Use only video ID in file name
+    -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_title)s, %(playlist_id)s, or %(playlist)s (=title if present, ID otherwise) for the playlist the video is in,
+                                     %(playlist_index)s for the position in the playlist. %(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. %% for a literal percent. 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' .
+    --autonumber-size NUMBER         Specify 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, --auto-number                [deprecated; use  -o "%(autonumber)s-%(title)s.%(ext)s" ] Number downloaded files starting from 00000
+    -t, --title                      [deprecated] Use title in file name (default)
+    -l, --literal                    [deprecated] Alias of --title
+    -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)
+    --no-part                        Do not use .part files - write directly into output file
+    --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 .annotations.xml file
+    --load-info FILE                 JSON file containing the video information (created with the "--write-info-json" option)
+    --cookies FILE                   File to read cookies from and dump cookie jar in
+    --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
     --rm-cache-dir                   Delete all filesystem cache files
 
 ## Thumbnail images:
-    --write-thumbnail                write thumbnail image to disk
-    --write-all-thumbnails           write all thumbnail image formats to disk
-    --list-thumbnails                Simulate and list all available thumbnail
-                                     formats
+    --write-thumbnail                Write thumbnail image to disk
+    --write-all-thumbnails           Write all thumbnail image formats to disk
+    --list-thumbnails                Simulate and list all available thumbnail formats
 
 ## Verbosity / Simulation Options:
-    -q, --quiet                      activates quiet mode
+    -q, --quiet                      Activate 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.
-    -J, --dump-single-json           simulate, quiet but print JSON information
-                                     for each command-line argument. If the URL
-                                     refers to a playlist, dump the whole
-                                     playlist information in a single line.
-    --print-json                     Be quiet and print the video information as
-                                     JSON (video is still being downloaded).
-    --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
+    -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.
+    -J, --dump-single-json           Simulate, quiet but print JSON information for each command-line argument. If the URL refers to a playlist, dump the whole playlist
+                                     information in a single line.
+    --print-json                     Be quiet and print the video information as JSON (video is still being downloaded).
+    --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-pages                     Print downloaded pages encoded using base64 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
-    -C, --call-home                  Contact the youtube-dl server for
-                                     debugging.
-    --no-call-home                   Do NOT contact the youtube-dl server for
-                                     debugging.
+    -C, --call-home                  Contact the youtube-dl server for debugging
+    --no-call-home                   Do NOT contact the youtube-dl server for debugging
 
 ## Workarounds:
     --encoding ENCODING              Force the specified encoding (experimental)
-    --no-check-certificate           Suppress HTTPS certificate validation.
-    --prefer-insecure                Use an unencrypted connection to retrieve
-                                     information about the video. (Currently
-                                     supported only for YouTube)
-    --user-agent UA                  specify a custom user agent
-    --referer URL                    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
-    --bidi-workaround                Work around terminals that lack
-                                     bidirectional text support. Requires bidiv
-                                     or fribidi executable in PATH
-    --sleep-interval SECONDS         Number of seconds to sleep before each
-                                     download.
+    --no-check-certificate           Suppress HTTPS certificate validation
+    --prefer-insecure                Use an unencrypted connection to retrieve information about the video. (Currently supported only for YouTube)
+    --user-agent UA                  Specify a custom user agent
+    --referer URL                    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
+    --bidi-workaround                Work around terminals that lack bidirectional text support. Requires bidiv or fribidi executable in PATH
+    --sleep-interval SECONDS         Number of seconds to sleep before each download.
 
 ## Video Format Options:
-    -f, --format FORMAT              video format code, specify the order of
-                                     preference using slashes, as in -f 22/17/18
-                                     .  Instead of format codes, you can select
-                                     by extension for the extensions aac, m4a,
-                                     mp3, mp4, ogg, wav, webm. You can also use
-                                     the special names "best", "bestvideo",
-                                     "bestaudio", "worst".  You can filter the
-                                     video results by putting a condition in
-                                     brackets, as in -f "best[height=720]" (or
-                                     -f "[filesize>10M]").  This works for
-                                     filesize, height, width, tbr, abr, vbr,
-                                     asr, and fps and the comparisons <, <=, >,
-                                     >=, =, != and for ext, acodec, vcodec,
-                                     container, and protocol and the comparisons
-                                     =, != . Formats for which the value is not
-                                     known are excluded unless you put a
-                                     question mark (?) after the operator. You
-                                     can combine format filters, so  -f "[height
-                                     <=? 720][tbr>500]" selects up to 720p
-                                     videos (or videos where the height is not
-                                     known) with a bitrate of at least 500
-                                     KBit/s. By default, youtube-dl will pick
-                                     the best quality. Use commas to download
-                                     multiple audio formats, such as -f
-                                     136/137/mp4/bestvideo,140/m4a/bestaudio.
-                                     You can merge the video and audio of two
-                                     formats into a single file using -f <video-
-                                     format>+<audio-format> (requires ffmpeg or
-                                     avconv), for example -f
-                                     bestvideo+bestaudio.
-    --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
-    --youtube-skip-dash-manifest     Do not download the DASH manifest on
-                                     YouTube videos
-    --merge-output-format FORMAT     If a merge is required (e.g.
-                                     bestvideo+bestaudio), output to given
-                                     container format. One of mkv, mp4, ogg,
-                                     webm, flv.Ignored if no merge is required
+    -f, --format FORMAT              Video format code, see the "FORMAT SELECTION" for all the info
+    --all-formats                    Download all available video formats
+    --prefer-free-formats            Prefer free video formats unless a specific one is requested
+    -F, --list-formats               List all available formats
+    --youtube-skip-dash-manifest     Do not download the DASH manifests and related data on YouTube videos
+    --merge-output-format FORMAT     If a merge is required (e.g. bestvideo+bestaudio), output to given container format. One of mkv, mp4, ogg, webm, flv. Ignored if no
+                                     merge is required
 
 ## 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, accepts formats
-                                     preference, for example: "ass/srt/best"
-    --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                       Download all the available subtitles of the video
+    --list-subs                      List all available subtitles for the video
+    --sub-format FORMAT              Subtitle format, accepts formats preference, for example: "srt" or "ass/srt/best"
+    --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          login with this account ID
-    -p, --password PASSWORD          account password. If this option is left
-                                     out, youtube-dl will ask interactively.
-    -2, --twofactor TWOFACTOR        two-factor auth code
-    -n, --netrc                      use .netrc authentication data
-    --video-password PASSWORD        video password (vimeo, smotri)
+    -u, --username USERNAME          Login with this account ID
+    -p, --password PASSWORD          Account password. If this option is left out, youtube-dl will ask interactively.
+    -2, --twofactor TWOFACTOR        Two-factor auth code
+    -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|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)
-    --fixup POLICY                   Automatically correct known faults of the
-                                     file. One of never (do nothing), warn (only
-                                     emit a warning), detect_or_warn(the
-                                     default; fix file if we can, warn
-                                     otherwise)
-    --prefer-avconv                  Prefer avconv over ffmpeg for running the
-                                     postprocessors (default)
-    --prefer-ffmpeg                  Prefer ffmpeg over avconv for running the
-                                     postprocessors
-    --ffmpeg-location PATH           Location of the ffmpeg/avconv binary;
-                                     either the path to the binary or its
-                                     containing directory.
-    --exec CMD                       Execute a command on the file after
-                                     downloading, similar to find's -exec
-                                     syntax. Example: --exec 'adb push {}
-                                     /sdcard/Music/ && rm {}'
+    -x, --extract-audio              Convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)
+    --audio-format FORMAT            Specify audio format: "best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; "best" by default
+    --audio-quality QUALITY          Specify ffmpeg/avconv audio quality, 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|avi)
+    --postprocessor-args ARGS        Give these arguments to the postprocessor
+    -k, --keep-video                 Keep 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 mkv and mp4 videos)
+    --embed-thumbnail                Embed thumbnail in the audio as cover art
+    --add-metadata                   Write metadata to the video file
+    --metadata-from-title FORMAT     Parse additional metadata like song title / artist from the video title. The format syntax is the same as --output, the parsed
+                                     parameters replace existing values. Additional templates: %(album)s, %(artist)s. Example: --metadata-from-title "%(artist)s -
+                                     %(title)s" matches a title like "Coldplay - Paradise"
+    --xattrs                         Write metadata to the video file's xattrs (using dublin core and xdg standards)
+    --fixup POLICY                   Automatically correct known faults of the file. One of never (do nothing), warn (only emit a warning), detect_or_warn (the default;
+                                     fix file if we can, warn otherwise)
+    --prefer-avconv                  Prefer avconv over ffmpeg for running the postprocessors (default)
+    --prefer-ffmpeg                  Prefer ffmpeg over avconv for running the postprocessors
+    --ffmpeg-location PATH           Location of the ffmpeg/avconv binary; either the path to the binary or its containing directory.
+    --exec CMD                       Execute a command on the file after downloading, similar to find's -exec syntax. Example: --exec 'adb push {} /sdcard/Music/ && rm
+                                     {}'
+    --convert-subtitles FORMAT       Convert the subtitles to other format (currently supported: srt|ass|vtt)
 
 # 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/config`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<user name>\youtube-dl.conf`.
+You can configure youtube-dl by placing any supported command line option to a configuration file. On Linux, system wide configuration file is located at `/etc/youtube-dl.conf` and user wide configuration file at `~/.config/youtube-dl/config`. On Windows, the user wide configuration file locations are `%APPDATA%\youtube-dl\config.txt` or `C:\Users\<user name>\youtube-dl.conf`. For example, with the following configration file youtube-dl will always extract the audio, not copy the mtime and use proxy:
+```
+--extract-audio
+--no-mtime
+--proxy 127.0.0.1:3128
+```
+
+You can use `--ignore-config` if you want to disable configuration file for a particular youtube-dl run.
+
+### Authentication with `.netrc` file ###
+
+You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every youtube-dl execution and prevent tracking plain text passwords in shell command history. You can achieve this using [`.netrc` file](http://stackoverflow.com/tags/.netrc/info) on per extractor basis. For that you will need to create `.netrc` file in your `$HOME` and restrict permissions to read/write by you only:
+```
+touch $HOME/.netrc
+chmod a-rwx,u+rw $HOME/.netrc
+```
+After that you can add credentials for extractor in the following format, where *extractor* is the name of extractor in lowercase:
+```
+machine <extractor> login <login> password <password>
+```
+For example:
+```
+machine youtube login myaccount@gmail.com password my_youtube_password
+machine twitch login my_twitch_account_name password my_twitch_password
+```
+To activate authentication with `.netrc` file you should pass `--netrc` to youtube-dl or to place it in [configuration file](#configuration).
+
+On Windows you may also need to setup `%HOME%` environment variable manually.
 
 # OUTPUT TEMPLATE
 
@@ -425,6 +279,7 @@ The `-o` option allows users to indicate a template for the output file names. T
  - `autonumber`: The sequence will be replaced by a five-digit number that will be increased with each download, starting at zero.
  - `playlist`: The name or the id of the playlist that contains the video.
  - `playlist_index`: The index of the video in the playlist, a five-digit number.
+ - `format_id`: The sequence will be replaced by the format code specified by `--format`.
 
 The current default template is `%(title)s-%(id)s.%(ext)s`.
 
@@ -437,6 +292,17 @@ $ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc --restrict-filena
 youtube-dl_test_video_.mp4          # A simple file name
 ```
 
+# FORMAT SELECTION
+
+By default youtube-dl tries to download the best quality, but sometimes you may want to download other format.
+The simplest case is requesting a specific format, for example `-f 22`. You can get the list of available formats using `--list-formats`, you can also use a file extension (currently it supports aac, m4a, mp3, mp4, ogg, wav, webm) or the special names `best`, `bestvideo`, `bestaudio` and `worst`.
+
+If you want to download multiple videos and they don't have the same formats available, you can specify the order of preference using slashes, as in `-f 22/17/18`. You can also filter the video results by putting a condition in brackets, as in `-f "best[height=720]"` (or `-f "[filesize>10M]"`).  This works for filesize, height, width, tbr, abr, vbr, asr, and fps and the comparisons <, <=, >, >=, =, != and for ext, acodec, vcodec, container, and protocol and the comparisons =, != . Formats for which the value is not known are excluded unless you put a question mark (?) after the operator. You can combine format filters, so  `-f "[height <=? 720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s. Use commas to download multiple formats, such as `-f 136/137/mp4/bestvideo,140/m4a/bestaudio`. You can merge the video and audio of two formats into a single file using `-f <video-format>+<audio-format>` (requires ffmpeg or avconv), for example `-f bestvideo+bestaudio`. Format selectors can also be grouped using parentheses, for example if you want to download the best mp4 and webm formats with a height lower than 480 you can use `-f '(mp4,webm)[height<480]'`.
+
+Since the end of April 2015 and version 2015.04.26 youtube-dl uses `-f bestvideo+bestaudio/best` as default format selection (see #5447, #5456). If ffmpeg or avconv are installed this results in downloading `bestvideo` and `bestaudio` separately and muxing them together into a single file giving the best overall quality available. Otherwise it falls back to `best` and results in downloading best available quality served as a single file. `best` is also needed for videos that don't come from YouTube because they don't provide the audio and video in two different files. If you want to only download some dash formats (for example if you are not interested in getting videos with a resolution higher than 1080p), you can add `-f bestvideo[height<=?1080]+bestaudio/best` to your configuration file. Note that if you use youtube-dl to stream to `stdout` (and most likely to pipe it to your media player then), i.e. you explicitly specify output template as `-o -`, youtube-dl still uses `-f best` format selection in order to start content delivery immediately to your player and not to wait until `bestvideo` and `bestaudio` are downloaded and muxed.
+
+If you want to preserve the old format selection behavior (prior to youtube-dl 2015.04.26), i.e. you want to download best available quality media served as a single file, you should explicitly specify your choice with `-f best`. You may want to add it to the [configuration file](#configuration) in order not to type it every time you run youtube-dl.
+
 # VIDEO SELECTION
 
 Videos can be filtered by their upload date using the options `--date`, `--datebefore` or `--dateafter`, they accept dates in two formats:
@@ -487,9 +353,9 @@ YouTube changed their playlist format in March 2014 and later on, so you'll need
 
 If you have installed youtube-dl with a package manager, pip, setup.py or a tarball, please use that to update. Note that Ubuntu packages do not seem to get updated anymore. Since we are not affiliated with Ubuntu, there is little we can do. Feel free to [report bugs](https://bugs.launchpad.net/ubuntu/+source/youtube-dl/+filebug) to the [Ubuntu packaging guys](mailto:ubuntu-motu@lists.ubuntu.com?subject=outdated%20version%20of%20youtube-dl) - all they have to do is update the package to a somewhat recent version. See above for a way to update.
 
-### Do I always have to pass in `--max-quality FORMAT`, or `-citw`?
+### Do I always have to pass `-citw`?
 
-By default, youtube-dl intends to have the best options (incidentally, if you have a convincing case that these should be different, [please file an issue where you explain that](https://yt-dl.org/bug)). Therefore, it is unnecessary and sometimes harmful to copy long option strings from webpages. In particular, `--max-quality` *limits* the video quality (so if you want the best quality, do NOT pass it in), and the only option out of `-citw` that is regularly useful is `-i`.
+By default, youtube-dl intends to have the best options (incidentally, if you have a convincing case that these should be different, [please file an issue where you explain that](https://yt-dl.org/bug)). Therefore, it is unnecessary and sometimes harmful to copy long option strings from webpages. In particular, the only option out of `-citw` that is regularly useful is `-i`.
 
 ### Can you please put the -b option back?
 
@@ -521,10 +387,30 @@ YouTube has switched to a new video info format in July 2011 which is not suppor
 
 YouTube requires an additional signature since September 2012 which is not supported by old versions of youtube-dl. See [above](#how-do-i-update-youtube-dl) for how to update youtube-dl.
 
+### Video URL contains an ampersand and I'm getting some strange output `[1] 2839` or `'v' is not recognized as an internal or external command` ###
+
+That's actually the output from your shell. Since ampersand is one of the special shell characters it's interpreted by shell preventing you from passing the whole URL to youtube-dl. To disable your shell from interpreting the ampersands (or any other special characters) you have to either put the whole URL in quotes or escape them with a backslash (which approach will work depends on your shell).
+
+For example if your URL is https://www.youtube.com/watch?t=4&v=BaW_jenozKc you should end up with following command:
+
+```youtube-dl 'https://www.youtube.com/watch?t=4&v=BaW_jenozKc'```
+
+or
+
+```youtube-dl https://www.youtube.com/watch?t=4\&v=BaW_jenozKc```
+
+For Windows you have to use the double quotes:
+
+```youtube-dl "https://www.youtube.com/watch?t=4&v=BaW_jenozKc"```
+
 ### ExtractorError: Could not find JS function u'OF'
 
 In February 2015, the new YouTube player contained a character sequence in a string that was misinterpreted by old versions of youtube-dl. See [above](#how-do-i-update-youtube-dl) for how to update youtube-dl.
 
+### HTTP Error 429: Too Many Requests or 402: Payment Required
+
+These two error codes indicate that the service is blocking your IP address because of overuse. Contact the service and ask them to unblock your IP address, or - if you have acquired a whitelisted IP address already - use the [`--proxy` or `--source-address` options](#network-options) to select another IP address.
+
 ### SyntaxError: Non-ASCII character ###
 
 The error
@@ -561,6 +447,12 @@ Either prepend `http://www.youtube.com/watch?v=` or separate the ID from the opt
     youtube-dl -- -wNyEUrxzFU
     youtube-dl "http://www.youtube.com/watch?v=-wNyEUrxzFU"
 
+### How do I pass cookies to youtube-dl?
+
+Use the `--cookies` option, for example `--cookies /path/to/cookies/file.txt`. Note that cookies file must be in Mozilla/Netscape format and the first line of cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in cookies file and convert newlines if necessary to correspond your OS, namely `CRLF` (`\r\n`) for Windows, `LF` (`\n`) for Linux and `CR` (`\r`) for Mac OS. `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format.
+
+Passing cookies to youtube-dl is a good way to workaround login when particular extractor does not implement it explicitly.
+
 ### Can you add support for this anime video site, or site which shows current movies for free?
 
 As a matter of policy (as well as legality), youtube-dl does not include support for services that specialize in infringing copyright. As a rule of thumb, if you cannot easily find a video that the service is quite obviously allowed to distribute (i.e. that has been uploaded by the creator, the creator's distributor, or is published under a free license), the service is probably unfit for inclusion to youtube-dl.
@@ -569,6 +461,18 @@ A note on the service that they don't host the infringing content, but just link
 
 Support requests for services that **do** purchase the rights to distribute their content are perfectly fine though. If in doubt, you can simply include a source that mentions the legitimate purchase of content.
 
+### How can I speed up work on my issue?
+
+(Also known as: Help, my important issue not being solved!) The youtube-dl core developer team is quite small. While we do our best to solve as many issues as possible, sometimes that can take quite a while. To speed up your issue, here's what you can do:
+
+First of all, please do report the issue [at our issue tracker](https://yt-dl.org/bugs). That allows us to coordinate all efforts by users and developers, and serves as a unified point. Unfortunately, the youtube-dl project has grown too large to use personal email as an effective communication channel.
+
+Please read the [bug reporting instructions](#bugs) below. A lot of bugs lack all the necessary information. If you can, offer proxy, VPN, or shell access to the youtube-dl developers. If you are able to, test the issue from multiple computers in multiple countries to exclude local censorship or misconfiguration issues.
+
+If nobody is interested in solving your issue, you are welcome to take matters into your own hands and submit a pull request (or coerce/pay somebody else to do so).
+
+Feel free to bump the issue from time to time by writing a small comment ("Issue is still present in youtube-dl version ...from France, but fixed from Belgium"), but please not more than once a month. Please do not declare your issue as `important` or `urgent`.
+
 ### How can I detect whether a given URL is supported by youtube-dl?
 
 For one, have a look at the [list of supported sites](docs/supportedsites.md). Note that it can sometimes happen that the site changes its URL scheme (say, from http://example.com/video/1234567 to http://example.com/v/1234567 ) and youtube-dl reports an URL of a service in that list as unsupported. In that case, simply report a bug.
@@ -648,7 +552,7 @@ If you want to add support for a new site, you can follow this quick list (assum
     ```
 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. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
-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.
+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 and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L62-L200). Add tests and code for as many as you want.
 8. If you can, check the code with [flake8](https://pypi.python.org/pypi/flake8).
 9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
 
@@ -668,6 +572,7 @@ youtube-dl makes the best effort to be a good command-line program, and thus sho
 From a Python program, you can embed youtube-dl in a more powerful fashion, like this:
 
 ```python
+from __future__ import unicode_literals
 import youtube_dl
 
 ydl_opts = {}
@@ -675,11 +580,12 @@ with youtube_dl.YoutubeDL(ydl_opts) as ydl:
     ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc'])
 ```
 
-Most likely, you'll want to use various options. For a list of what can be done, have a look at [youtube_dl/YoutubeDL.py](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L69). For a start, if you want to intercept youtube-dl's output, set a `logger` object.
+Most likely, you'll want to use various options. For a list of what can be done, have a look at [youtube_dl/YoutubeDL.py](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L117-L265). For a start, if you want to intercept youtube-dl's output, set a `logger` object.
 
 Here's a more complete example of a program that outputs only errors (and a short message after the download is finished), and downloads/converts the video to an mp3 file:
 
 ```python
+from __future__ import unicode_literals
 import youtube_dl
 
 
@@ -737,7 +643,9 @@ If your report is shorter than two lines, it is almost certainly missing some of
 
 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.
+If your server has multiple IPs or you suspect censorship, adding --call-home may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/).
+
+**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?
 

devscripts/check-porn.py

@@ -28,7 +28,7 @@ for test in get_testcases():
     if METHOD == 'EURISTIC':
         try:
             webpage = compat_urllib_request.urlopen(test['url'], timeout=10).read()
-        except:
+        except Exception:
             print('\nFail: {0}'.format(test['name']))
             continue
 

devscripts/generate_aes_testdata.py

@@ -0,0 +1,42 @@
+from __future__ import unicode_literals
+
+import codecs
+import subprocess
+
+import os
+import sys
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from youtube_dl.utils import intlist_to_bytes
+from youtube_dl.aes import aes_encrypt, key_expansion
+
+secret_msg = b'Secret message goes here'
+
+
+def hex_str(int_list):
+    return codecs.encode(intlist_to_bytes(int_list), 'hex')
+
+
+def openssl_encode(algo, key, iv):
+    cmd = ['openssl', 'enc', '-e', '-' + algo, '-K', hex_str(key), '-iv', hex_str(iv)]
+    prog = subprocess.Popen(cmd, stdin=subprocess.PIPE, stdout=subprocess.PIPE)
+    out, _ = prog.communicate(secret_msg)
+    return out
+
+iv = key = [0x20, 0x15] + 14 * [0]
+
+r = openssl_encode('aes-128-cbc', key, iv)
+print('aes_cbc_decrypt')
+print(repr(r))
+
+password = key
+new_key = aes_encrypt(password, key_expansion(password))
+r = openssl_encode('aes-128-ctr', new_key, iv)
+print('aes_decrypt_text 16')
+print(repr(r))
+
+password = key + 16 * [0]
+new_key = aes_encrypt(password, key_expansion(password)) * (32 // 16)
+r = openssl_encode('aes-256-ctr', new_key, iv)
+print('aes_decrypt_text 32')
+print(repr(r))

docs/supportedsites.md

@@ -2,29 +2,34 @@
  - **1tv**: Первый канал
  - **1up.com**
  - **220.ro**
+ - **22tracks:genre**
+ - **22tracks:track**
  - **24video**
  - **3sat**
  - **4tube**
  - **56.com**
  - **5min**
  - **8tracks**
+ - **91porn**
  - **9gag**
  - **abc.net.au**
  - **Abc7News**
  - **AcademicEarth:Course**
  - **AddAnime**
  - **AdobeTV**
+ - **AdobeTVVideo**
  - **AdultSwim**
  - **Aftenposten**
  - **Aftonbladet**
+ - **AirMozilla**
  - **AlJazeera**
  - **Allocine**
  - **AlphaPorno**
  - **anitube.se**
  - **AnySex**
  - **Aparat**
- - **AppleDailyAnimationNews**
- - **AppleDailyRealtimeNews**
+ - **AppleConnect**
+ - **AppleDaily**: 臺灣蘋果日報
  - **AppleTrailers**
  - **archive.org**: archive.org videos
  - **ARD**
@@ -41,11 +46,14 @@
  - **audiomack**
  - **audiomack:album**
  - **Azubu**
+ - **BaiduVideo**: 百度视频
  - **bambuser**
  - **bambuser:channel**
  - **Bandcamp**
  - **Bandcamp:album**
+ - **bbc**: BBC
  - **bbc.co.uk**: BBC iPlayer
+ - **BeatportPro**
  - **Beeg**
  - **BehindKink**
  - **Bet**
@@ -59,6 +67,8 @@
  - **BR**: Bayerischer Rundfunk Mediathek
  - **Break**
  - **Brightcove**
+ - **bt:article**: Bergens Tidende Articles
+ - **bt:vestlendingen**: Bergens Tidende - Vestlendingen
  - **BuzzFeed**
  - **BYUtv**
  - **Camdemy**
@@ -76,7 +86,7 @@
  - **chirbit:profile**
  - **Cinchcast**
  - **Cinemassacre**
- - **clipfish**
+ - **Clipfish**
  - **cliphunter**
  - **Clipsyndicate**
  - **Cloudy**
@@ -94,28 +104,37 @@
  - **CondeNast**: Condé Nast media group: Condé Nast, GQ, Glamour, Vanity Fair, Vogue, W Magazine, WIRED
  - **Cracked**
  - **Criterion**
+ - **CrooksAndLiars**
  - **Crunchyroll**
  - **crunchyroll:playlist**
  - **CSpan**: C-SPAN
- - **CtsNews**
+ - **CtsNews**: 華視新聞
  - **culturebox.francetvinfo.fr**
  - **dailymotion**
  - **dailymotion:playlist**
  - **dailymotion:user**
+ - **DailymotionCloud**
  - **daum.net**
  - **DBTV**
+ - **DCN**
  - **DctpTv**
  - **DeezerPlaylist**
  - **defense.gouv.fr**
+ - **DHM**: Filmarchiv - Deutsches Historisches Museum
  - **Discovery**
  - **divxstage**: DivxStage
  - **Dotsub**
+ - **DouyuTV**: 斗鱼
+ - **dramafever**
+ - **dramafever:series**
  - **DRBonanza**
  - **Dropbox**
  - **DrTuber**
  - **DRTV**
  - **Dump**
+ - **Dumpert**
  - **dvtv**: http://video.aktualne.cz/
+ - **EaglePlatform**
  - **EbaumsWorld**
  - **EchoMsk**
  - **eHow**
@@ -130,6 +149,8 @@
  - **Eporner**
  - **EroProfile**
  - **Escapist**
+ - **ESPN** (Currently broken)
+ - **EsriVideo**
  - **EveryonesMixtape**
  - **exfm**: ex.fm
  - **ExpoTV**
@@ -139,12 +160,14 @@
  - **fc2**
  - **fernsehkritik.tv**
  - **fernsehkritik.tv:postecke**
- - **Firedrive**
  - **Firstpost**
+ - **FiveTV**
  - **Flickr**
  - **Folketinget**: Folketinget (ft.dk; Danish parliament)
+ - **FootyRoom**
  - **Foxgay**
  - **FoxNews**
+ - **FoxSports**
  - **france2.fr:generation-quoi**
  - **FranceCulture**
  - **FranceInter**
@@ -157,11 +180,14 @@
  - **Gamekings**
  - **GameOne**
  - **gameone:playlist**
+ - **Gamersyde**
  - **GameSpot**
  - **GameStar**
  - **Gametrailers**
+ - **Gazeta**
  - **GDCVault**
  - **generic**: Generic downloader that works on some sites
+ - **Gfycat**
  - **GiantBomb**
  - **Giga**
  - **Glide**: Glide mobile video messages (glide.me)
@@ -169,9 +195,8 @@
  - **GodTube**
  - **GoldenMoustache**
  - **Golem**
- - **GorillaVid**: GorillaVid.in, daclips.in, movpod.in and fastvideo.in
+ - **GorillaVid**: GorillaVid.in, daclips.in, movpod.in, fastvideo.in and realvid.net
  - **Goshgay**
- - **Grooveshark**
  - **Groupon**
  - **Hark**
  - **HearThisAt**
@@ -196,11 +221,15 @@
  - **imdb:list**: Internet Movie Database lists
  - **Imgur**
  - **Ina**
+ - **Indavideo**
+ - **IndavideoEmbed**
  - **InfoQ**
  - **Instagram**
  - **instagram:user**: Instagram user profile
  - **InternetVideoArchive**
  - **IPrima**
+ - **iqiyi**: 爱奇艺
+ - **Ir90Tv**
  - **ivi**: ivi.ru
  - **ivi:compilation**: ivi.ru compilations
  - **Izlesene**
@@ -209,8 +238,11 @@
  - **Jove**
  - **jpopsuki.tv**
  - **Jukebox**
+ - **Kaltura**
+ - **KanalPlay**: Kanal 5/9/11 Play
  - **Kankan**
  - **Karaoketv**
+ - **KarriereVideos**
  - **keek**
  - **KeezMovies**
  - **KhanAcademy**
@@ -218,8 +250,20 @@
  - **kontrtube**: KontrTube.ru - Труба зовёт
  - **KrasView**: Красвью
  - **Ku6**
+ - **kuwo:album**: 酷我音乐 - 专辑
+ - **kuwo:category**: 酷我音乐 - 分类
+ - **kuwo:chart**: 酷我音乐 - 排行榜
+ - **kuwo:mv**: 酷我音乐 - MV
+ - **kuwo:singer**: 酷我音乐 - 歌手
+ - **kuwo:song**: 酷我音乐
  - **la7.tv**
  - **Laola1Tv**
+ - **Lecture2Go**
+ - **Letv**: 乐视网
+ - **LetvPlaylist**
+ - **LetvTv**
+ - **Libsyn**
+ - **life:embed**
  - **lifenews**: LIFE | NEWS
  - **LiveLeak**
  - **livestream**
@@ -234,11 +278,13 @@
  - **Malemotion**
  - **MDR**
  - **media.ccc.de**
+ - **MegaVideoz**
  - **metacafe**
  - **Metacritic**
  - **Mgoon**
  - **Minhateca**
  - **MinistryGrid**
+ - **miomio.tv**
  - **mitele.es**
  - **mixcloud**
  - **MLB**
@@ -251,9 +297,11 @@
  - **Motherless**
  - **Motorsport**: motorsport.com
  - **MovieClips**
+ - **MovieFap**
  - **Moviezine**
  - **movshare**: MovShare
  - **MPORA**
+ - **MSNBC**
  - **MTV**
  - **mtviggy.com**
  - **mtvservices:embedded**
@@ -261,26 +309,38 @@
  - **MusicPlayOn**
  - **MusicVault**
  - **muzu.tv**
+ - **Mwave**
  - **MySpace**
  - **MySpace:album**
  - **MySpass**
+ - **Myvi**
  - **myvideo**
  - **MyVidster**
+ - **N-JOY**
  - **n-tv.de**
  - **NationalGeographic**
  - **Naver**
  - **NBA**
  - **NBC**
  - **NBCNews**
+ - **NBCSports**
+ - **NBCSportsVPlayer**
  - **ndr**: NDR.de - Mediathek
  - **NDTV**
  - **NerdCubedFeed**
  - **Nerdist**
+ - **netease:album**: 网易云音乐 - 专辑
+ - **netease:djradio**: 网易云音乐 - 电台
+ - **netease:mv**: 网易云音乐 - MV
+ - **netease:playlist**: 网易云音乐 - 歌单
+ - **netease:program**: 网易云音乐 - 电台节目
+ - **netease:singer**: 网易云音乐 - 歌手
+ - **netease:song**: 网易云音乐
  - **Netzkino**
  - **Newgrounds**
  - **Newstube**
- - **NextMedia**
- - **NextMediaActionNews**
+ - **NextMedia**: 蘋果日報
+ - **NextMediaActionNews**: 蘋果日報 - 動新聞
  - **nfb**: National Film Board of Canada
  - **nfl.com**
  - **nhl.com**
@@ -291,35 +351,51 @@
  - **Noco**
  - **Normalboots**
  - **NosVideo**
+ - **Nova**: TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz
  - **novamov**: NovaMov
  - **Nowness**
+ - **NowTV**
  - **nowvideo**: NowVideo
- - **npo.nl**
+ - **npo**: npo.nl and ntr.nl
  - **npo.nl:live**
  - **npo.nl:radio**
  - **npo.nl:radio:fragment**
  - **NRK**
- - **NRKTV**
+ - **NRKPlaylist**
+ - **NRKTV**: NRK TV and NRK Radio
  - **ntv.ru**
  - **Nuvid**
  - **NYTimes**
+ - **NYTimesArticle**
  - **ocw.mit.edu**
+ - **Odnoklassniki**
  - **OktoberfestTV**
  - **on.aol.com**
+ - **OnionStudios**
  - **Ooyala**
+ - **OoyalaExternal**
  - **OpenFilm**
  - **orf:fm4**: radio FM4
+ - **orf:iptv**: iptv.ORF.at
  - **orf:oe1**: Radio Österreich 1
  - **orf:tvthek**: ORF TVthek
  - **parliamentlive.tv**: UK parliament videos
  - **Patreon**
  - **PBS**
+ - **Periscope**: Periscope
+ - **PhilharmonieDeParis**: Philharmonie de Paris
  - **Phoenix**
  - **Photobucket**
+ - **Pinkbike**
+ - **Pladform**
  - **PlanetaPlay**
  - **play.fm**
  - **played.to**
+ - **Playtvak**: Playtvak.cz, iDNES.cz and Lidovky.cz
  - **Playvid**
+ - **Playwire**
+ - **pluralsight**
+ - **pluralsight:course**
  - **plus.google**: Google Plus
  - **pluzz.francetv.fr**
  - **podomatic**
@@ -327,17 +403,28 @@
  - **PornHub**
  - **PornHubPlaylist**
  - **Pornotube**
+ - **PornoVoisines**
  - **PornoXO**
+ - **PrimeShareTV**
  - **PromptFile**
  - **prosiebensat1**: ProSiebenSat.1 Digital
+ - **Puls4**
  - **Pyvideo**
+ - **qqmusic**: QQ音乐
+ - **qqmusic:album**: QQ音乐 - 专辑
+ - **qqmusic:playlist**: QQ音乐 - 歌单
+ - **qqmusic:singer**: QQ音乐 - 歌手
+ - **qqmusic:toplist**: QQ音乐 - 排行榜
+ - **Quickscope**: Quick Scope
  - **QuickVid**
  - **R7**
  - **radio.de**
  - **radiobremen**
  - **radiofrance**
+ - **RadioJavan**
  - **Rai**
  - **RBMARadio**
+ - **RDS**: RDS.ca
  - **RedTube**
  - **Restudy**
  - **ReverbNation**
@@ -348,11 +435,12 @@
  - **Rte**
  - **rtl.nl**: rtl.nl and rtlxl.nl
  - **RTL2**
- - **RTLnow**
  - **RTP**
  - **RTS**: RTS.ch
  - **rtve.es:alacarta**: RTVE a la carta
+ - **rtve.es:infantil**: RTVE infantil
  - **rtve.es:live**: RTVE.es live streams
+ - **RTVNH**
  - **RUHD**
  - **rutube**: Rutube videos
  - **rutube:channel**: Rutube channels
@@ -360,6 +448,9 @@
  - **rutube:movie**: Rutube movies
  - **rutube:person**: Rutube person videos
  - **RUTV**: RUTV.RU
+ - **Ruutu**
+ - **safari**: safaribooksonline.com online video
+ - **safari:course**: safaribooksonline.com online courses
  - **Sandia**: Sandia National Laboratories
  - **Sapo**: SAPO Vídeos
  - **savefrom.net**
@@ -369,9 +460,11 @@
  - **Screencast**
  - **ScreencastOMatic**
  - **ScreenwaveMedia**
+ - **SenateISVP**
  - **ServingSys**
  - **Sexu**
  - **SexyKarma**: Sexy Karma and Watch Indian Porn
+ - **Shahid**
  - **Shared**
  - **ShareSix**
  - **Sina**
@@ -381,9 +474,12 @@
  - **smotri:broadcast**: Smotri.com broadcasts
  - **smotri:community**: Smotri.com community videos
  - **smotri:user**: Smotri.com user videos
+ - **SnagFilms**
+ - **SnagFilmsEmbed**
  - **Snotr**
- - **Sockshare**
  - **Sohu**
+ - **soompi**
+ - **soompi:show**
  - **soundcloud**
  - **soundcloud:playlist**
  - **soundcloud:set**
@@ -391,8 +487,12 @@
  - **soundgasm**
  - **soundgasm:profile**
  - **southpark.cc.com**
+ - **southpark.cc.com:español**
  - **southpark.de**
+ - **southpark.nl**
+ - **southparkstudios.dk**
  - **Space**
+ - **SpankBang**
  - **Spankwire**
  - **Spiegel**
  - **Spiegel:Article**: Articles on spiegel.de
@@ -400,15 +500,20 @@
  - **Spike**
  - **Sport5**
  - **SportBox**
+ - **SportBoxEmbed**
  - **SportDeutschland**
+ - **Sportschau**
+ - **Srf**
  - **SRMediathek**: Saarländischer Rundfunk
+ - **SSA**
  - **stanfordoc**: Stanford Open ClassRoom
  - **Steam**
  - **streamcloud.eu**
  - **StreamCZ**
  - **StreetVoice**
  - **SunPorno**
- - **SVTPlay**
+ - **SVT**
+ - **SVTPlay**: SVT Play and Öppet arkiv
  - **SWRMediathek**
  - **Syfy**
  - **SztvHu**
@@ -422,10 +527,10 @@
  - **TeamFour**
  - **TechTalks**
  - **techtv.mit.edu**
- - **TED**
- - **tegenlicht.vpro.nl**
+ - **ted**
  - **TeleBruxelles**
  - **telecinco.es**
+ - **Telegraaf**
  - **TeleMB**
  - **TeleTask**
  - **TenPlay**
@@ -433,7 +538,9 @@
  - **TF1**
  - **TheOnion**
  - **ThePlatform**
+ - **ThePlatformFeed**
  - **TheSixtyOne**
+ - **ThisAmericanLife**
  - **ThisAV**
  - **THVideo**
  - **THVideoPlaylist**
@@ -441,6 +548,7 @@
  - **tlc.com**
  - **tlc.de**
  - **TMZ**
+ - **TMZArticle**
  - **TNAFlix**
  - **tou.tv**
  - **Toypics**: Toypics user profile
@@ -449,13 +557,18 @@
  - **Trilulilu**
  - **TruTube**
  - **Tube8**
+ - **TubiTv**
  - **Tudou**
  - **Tumblr**
  - **TuneIn**
  - **Turbo**
  - **Tutv**
  - **tv.dfb.de**
+ - **TV2**
+ - **TV2Article**
  - **TV4**: tv4.se and tv4play.se
+ - **TVC**
+ - **TVCArticle**
  - **tvigle**: Интернет-телевидение Tvigle.ru
  - **tvp.pl**
  - **tvp.pl:Series**
@@ -468,25 +581,29 @@
  - **twitch:stream**
  - **twitch:video**
  - **twitch:vod**
+ - **TwitterCard**
  - **Ubu**
  - **udemy**
  - **udemy:course**
+ - **UDNEmbed**: 聯合影音
+ - **Ultimedia**
  - **Unistra**
  - **Urort**: NRK P3 Urørt
  - **ustream**
  - **ustream:channel**
+ - **Varzesh3**
  - **Vbox7**
  - **VeeHD**
  - **Veoh**
+ - **Vessel**
  - **Vesti**: Вести.Ru
  - **Vevo**
- - **VGTV**
+ - **VGTV**: VGTV and BTTV
  - **vh1.com**
  - **Vice**
  - **Viddler**
  - **video.google:search**: Google Video search
  - **video.mit.edu**
- - **VideoBam**
  - **VideoDetective**
  - **videofy.me**
  - **videolectures.net**
@@ -498,7 +615,9 @@
  - **Vidzi**
  - **vier**
  - **vier:videos**
+ - **Viewster**
  - **viki**
+ - **viki:channel**
  - **vimeo**
  - **vimeo:album**
  - **vimeo:channel**
@@ -507,13 +626,15 @@
  - **vimeo:review**: Review pages on vimeo
  - **vimeo:user**
  - **vimeo:watchlater**: Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)
- - **Vimple**: Vimple.ru
+ - **Vimple**: Vimple - one-click video hosting
  - **Vine**
  - **vine:user**
- - **vk.com**
- - **vk.com:user-videos**: vk.com:All of a user's videos
+ - **vk**: VK
+ - **vk:uservideos**: VK - User's Videos
  - **Vodlocker**
+ - **VoiceRepublic**
  - **Vporn**
+ - **vpro**: npo.nl and ntr.nl
  - **VRT**
  - **vube**: Vube.com
  - **VuClip**
@@ -526,28 +647,36 @@
  - **wdr:mobile**
  - **WDRMaus**: Sendung mit der Maus
  - **WebOfStories**
+ - **WebOfStoriesPlaylist**
  - **Weibo**
  - **Wimp**
  - **Wistia**
+ - **WNL**
  - **WorldStarHipHop**
  - **wrzuta.pl**
  - **WSJ**: Wall Street Journal
  - **XBef**
  - **XboxClips**
  - **XHamster**
+ - **XHamsterEmbed**
  - **XMinus**
  - **XNXX**
+ - **Xstream**
  - **XTube**
  - **XTubeUser**: XTube user profile
- - **Xuite**
+ - **Xuite**: 隨意窩Xuite影音
  - **XVideos**
  - **XXXYMovies**
  - **Yahoo**: Yahoo screen and movies
- - **Yam**
+ - **Yam**: 蕃薯藤yam天空部落
+ - **yandexmusic:album**: Яндекс.Музыка - Альбом
+ - **yandexmusic:playlist**: Яндекс.Музыка - Плейлист
+ - **yandexmusic:track**: Яндекс.Музыка - Трек
  - **YesJapan**
+ - **yinyuetai:video**: 音悦Tai
  - **Ynet**
  - **YouJizz**
- - **Youku**
+ - **youku**: 优酷
  - **YouPorn**
  - **YourUpload**
  - **youtube**: YouTube.com
@@ -562,7 +691,7 @@
  - **youtube:show**: YouTube.com (multi-season) shows
  - **youtube:subscriptions**: YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)
  - **youtube:user**: YouTube.com user videos (URL or "ytuser" keyword)
- - **youtube:watch_later**: Youtube watch later list, ":ytwatchlater" for short (requires authentication)
+ - **youtube:watchlater**: Youtube watch later list, ":ytwatchlater" for short (requires authentication)
  - **Zapiks**
  - **ZDF**
  - **ZDFChannel**

test/helper.py

@@ -133,8 +133,8 @@ def expect_info_dict(self, got_dict, expected_dict):
             elif isinstance(expected, compat_str) and expected.startswith('mincount:'):
                 got = got_dict.get(info_field)
                 self.assertTrue(
-                    isinstance(got, list),
-                    'Expected field %s to be a list, but it is of type %s' % (
+                    isinstance(got, (list, dict)),
+                    'Expected field %s to be a list or a dict, but it is of type %s' % (
                         info_field, type(got).__name__))
                 expected_num = int(expected.partition(':')[2])
                 assertGreaterEqual(
@@ -150,7 +150,7 @@ def expect_info_dict(self, got_dict, expected_dict):
                              'invalid value for field %s, expected %r, got %r' % (info_field, expected, got))
 
     # Check for the presence of mandatory fields
-    if got_dict.get('_type') != 'playlist':
+    if got_dict.get('_type') not in ('playlist', 'multi_video'):
         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
@@ -160,7 +160,7 @@ def expect_info_dict(self, got_dict, expected_dict):
     # 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 ('id', 'title', 'description', 'uploader', 'upload_date', 'timestamp', 'uploader_id', 'location'))
+                          if value and key in ('id', 'title', 'description', 'uploader', 'upload_date', 'timestamp', 'uploader_id', 'location', 'age_limit'))
     missing_keys = set(test_info_dict.keys()) - set(expected_dict.keys())
     if missing_keys:
         def _repr(v):

test/parameters.json

@@ -7,8 +7,7 @@
     "forcethumbnail": false, 
     "forcetitle": false, 
     "forceurl": false, 
-    "format": null, 
-    "format_limit": null, 
+    "format": "best",
     "ignoreerrors": false, 
     "listformats": null, 
     "logtostderr": false, 

test/test_YoutubeDL.py

@@ -12,8 +12,12 @@ import copy
 
 from test.helper import FakeYDL, assertRegexpMatches
 from youtube_dl import YoutubeDL
+from youtube_dl.compat import compat_str
 from youtube_dl.extractor import YoutubeIE
 from youtube_dl.postprocessor.common import PostProcessor
+from youtube_dl.utils import ExtractorError, match_filter_func
+
+TEST_URL = 'http://localhost/sample.mp4'
 
 
 class YDL(FakeYDL):
@@ -46,8 +50,8 @@ class TestFormatSelection(unittest.TestCase):
         ydl = YDL()
         ydl.params['prefer_free_formats'] = True
         formats = [
-            {'ext': 'webm', 'height': 460, 'url': 'x'},
-            {'ext': 'mp4', 'height': 460, 'url': 'y'},
+            {'ext': 'webm', 'height': 460, 'url': TEST_URL},
+            {'ext': 'mp4', 'height': 460, 'url': TEST_URL},
         ]
         info_dict = _make_result(formats)
         yie = YoutubeIE(ydl)
@@ -60,8 +64,8 @@ class TestFormatSelection(unittest.TestCase):
         ydl = YDL()
         ydl.params['prefer_free_formats'] = True
         formats = [
-            {'ext': 'webm', 'height': 720, 'url': 'a'},
-            {'ext': 'mp4', 'height': 1080, 'url': 'b'},
+            {'ext': 'webm', 'height': 720, 'url': TEST_URL},
+            {'ext': 'mp4', 'height': 1080, 'url': TEST_URL},
         ]
         info_dict['formats'] = formats
         yie = YoutubeIE(ydl)
@@ -74,9 +78,9 @@ class TestFormatSelection(unittest.TestCase):
         ydl = YDL()
         ydl.params['prefer_free_formats'] = False
         formats = [
-            {'ext': 'webm', 'height': 720, 'url': '_'},
-            {'ext': 'mp4', 'height': 720, 'url': '_'},
-            {'ext': 'flv', 'height': 720, 'url': '_'},
+            {'ext': 'webm', 'height': 720, 'url': TEST_URL},
+            {'ext': 'mp4', 'height': 720, 'url': TEST_URL},
+            {'ext': 'flv', 'height': 720, 'url': TEST_URL},
         ]
         info_dict['formats'] = formats
         yie = YoutubeIE(ydl)
@@ -88,8 +92,8 @@ class TestFormatSelection(unittest.TestCase):
         ydl = YDL()
         ydl.params['prefer_free_formats'] = False
         formats = [
-            {'ext': 'flv', 'height': 720, 'url': '_'},
-            {'ext': 'webm', 'height': 720, 'url': '_'},
+            {'ext': 'flv', 'height': 720, 'url': TEST_URL},
+            {'ext': 'webm', 'height': 720, 'url': TEST_URL},
         ]
         info_dict['formats'] = formats
         yie = YoutubeIE(ydl)
@@ -98,45 +102,13 @@ class TestFormatSelection(unittest.TestCase):
         downloaded = ydl.downloaded_info_dicts[0]
         self.assertEqual(downloaded['ext'], 'flv')
 
-    def test_format_limit(self):
-        formats = [
-            {'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 = _make_result(formats)
-
-        ydl = YDL()
-        ydl.process_ie_result(info_dict)
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], 'excellent')
-
-        ydl = YDL({'format_limit': 'good'})
-        assert ydl.params['format_limit'] == 'good'
-        ydl.process_ie_result(info_dict.copy())
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], 'good')
-
-        ydl = YDL({'format_limit': 'great', 'format': 'all'})
-        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.copy())
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], 'excellent')
-
     def test_format_selection(self):
         formats = [
-            {'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': '_'},
+            {'format_id': '35', 'ext': 'mp4', 'preference': 1, 'url': TEST_URL},
+            {'format_id': 'example-with-dashes', 'ext': 'webm', 'preference': 1, 'url': TEST_URL},
+            {'format_id': '45', 'ext': 'webm', 'preference': 2, 'url': TEST_URL},
+            {'format_id': '47', 'ext': 'webm', 'preference': 3, 'url': TEST_URL},
+            {'format_id': '2', 'ext': 'flv', 'preference': 4, 'url': TEST_URL},
         ]
         info_dict = _make_result(formats)
 
@@ -165,12 +137,17 @@ class TestFormatSelection(unittest.TestCase):
         downloaded = ydl.downloaded_info_dicts[0]
         self.assertEqual(downloaded['format_id'], '35')
 
+        ydl = YDL({'format': 'example-with-dashes'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'example-with-dashes')
+
     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': '_'},
+            {'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none', 'url': TEST_URL},
+            {'format_id': 'audio-mid', 'ext': 'webm', 'preference': 2, 'vcodec': 'none', 'url': TEST_URL},
+            {'format_id': 'audio-high', 'ext': 'flv', 'preference': 3, 'vcodec': 'none', 'url': TEST_URL},
+            {'format_id': 'vid', 'ext': 'mp4', 'preference': 4, 'url': TEST_URL},
         ]
         info_dict = _make_result(formats)
 
@@ -185,8 +162,8 @@ class TestFormatSelection(unittest.TestCase):
         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': '_'},
+            {'format_id': 'vid-low', 'ext': 'mp4', 'preference': 1, 'url': TEST_URL},
+            {'format_id': 'vid-high', 'ext': 'mp4', 'preference': 2, 'url': TEST_URL},
         ]
         info_dict = _make_result(formats)
 
@@ -228,9 +205,9 @@ class TestFormatSelection(unittest.TestCase):
 
     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': '_'},
+            {'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': TEST_URL},
+            {'format_id': 'dash-video-high', 'ext': 'mp4', 'preference': 2, 'acodec': 'none', 'url': TEST_URL},
+            {'format_id': 'vid', 'ext': 'mp4', 'preference': 3, 'url': TEST_URL},
         ]
         info_dict = _make_result(formats)
 
@@ -258,29 +235,89 @@ class TestFormatSelection(unittest.TestCase):
             '141', '172', '140', '171', '139',
         ]
 
-        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
+        def format_info(f_id):
+            info = YoutubeIE._formats[f_id].copy()
+            info['format_id'] = f_id
+            info['url'] = 'url:' + f_id
+            return info
+        formats_order = [format_info(f_id) for f_id in order]
 
+        info_dict = _make_result(list(formats_order), extractor='youtube')
+        ydl = YDL({'format': 'bestvideo+bestaudio'})
+        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'], '137+141')
+        self.assertEqual(downloaded['ext'], 'mp4')
+
+        info_dict = _make_result(list(formats_order), extractor='youtube')
+        ydl = YDL({'format': 'bestvideo[height>=999999]+bestaudio/best'})
+        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'], '38')
+
+        info_dict = _make_result(list(formats_order), extractor='youtube')
+        ydl = YDL({'format': 'bestvideo/best,bestaudio'})
+        yie = YoutubeIE(ydl)
+        yie._sort_formats(info_dict['formats'])
+        ydl.process_ie_result(info_dict)
+        downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
+        self.assertEqual(downloaded_ids, ['137', '141'])
+
+        info_dict = _make_result(list(formats_order), extractor='youtube')
+        ydl = YDL({'format': '(bestvideo[ext=mp4],bestvideo[ext=webm])+bestaudio'})
+        yie = YoutubeIE(ydl)
+        yie._sort_formats(info_dict['formats'])
+        ydl.process_ie_result(info_dict)
+        downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
+        self.assertEqual(downloaded_ids, ['137+141', '248+141'])
+
+        info_dict = _make_result(list(formats_order), extractor='youtube')
+        ydl = YDL({'format': '(bestvideo[ext=mp4],bestvideo[ext=webm])[height<=720]+bestaudio'})
+        yie = YoutubeIE(ydl)
+        yie._sort_formats(info_dict['formats'])
+        ydl.process_ie_result(info_dict)
+        downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
+        self.assertEqual(downloaded_ids, ['136+141', '247+141'])
+
+        info_dict = _make_result(list(formats_order), extractor='youtube')
+        ydl = YDL({'format': '(bestvideo[ext=none]/bestvideo[ext=webm])+bestaudio'})
+        yie = YoutubeIE(ydl)
+        yie._sort_formats(info_dict['formats'])
+        ydl.process_ie_result(info_dict)
+        downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
+        self.assertEqual(downloaded_ids, ['248+141'])
+
+        for f1, f2 in zip(formats_order, formats_order[1:]):
             info_dict = _make_result([f1, f2], extractor='youtube')
-            ydl = YDL()
+            ydl = YDL({'format': 'best/bestvideo'})
             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)
+            self.assertEqual(downloaded['format_id'], f1['format_id'])
 
             info_dict = _make_result([f2, f1], extractor='youtube')
-            ydl = YDL()
+            ydl = YDL({'format': 'best/bestvideo'})
             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)
+            self.assertEqual(downloaded['format_id'], f1['format_id'])
+
+    def test_invalid_format_specs(self):
+        def assert_syntax_error(format_spec):
+            ydl = YDL({'format': format_spec})
+            info_dict = _make_result([{'format_id': 'foo', 'url': TEST_URL}])
+            self.assertRaises(SyntaxError, ydl.process_ie_result, info_dict)
+
+        assert_syntax_error('bestvideo,,best')
+        assert_syntax_error('+bestaudio')
+        assert_syntax_error('bestvideo+')
+        assert_syntax_error('/')
 
     def test_format_filtering(self):
         formats = [
@@ -337,6 +374,20 @@ class TestFormatSelection(unittest.TestCase):
         downloaded = ydl.downloaded_info_dicts[0]
         self.assertEqual(downloaded['format_id'], 'G')
 
+        ydl = YDL({'format': 'all[width>=400][width<=600]'})
+        ydl.process_ie_result(info_dict)
+        downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
+        self.assertEqual(downloaded_ids, ['B', 'C', 'D'])
+
+        ydl = YDL({'format': 'best[height<40]'})
+        try:
+            ydl.process_ie_result(info_dict)
+        except ExtractorError:
+            pass
+        self.assertEqual(ydl.downloaded_info_dicts, [])
+
+
+class TestYoutubeDL(unittest.TestCase):
     def test_subtitles(self):
         def s_formats(lang, autocaption=False):
             return [{
@@ -438,27 +489,148 @@ class TestFormatSelection(unittest.TestCase):
             def run(self, info):
                 with open(audiofile, 'wt') as f:
                     f.write('EXAMPLE')
-                info['filepath']
-                return False, info
+                return [info['filepath']], info
 
-        def run_pp(params):
+        def run_pp(params, PP):
             with open(filename, 'wt') as f:
                 f.write('EXAMPLE')
             ydl = YoutubeDL(params)
-            ydl.add_post_processor(SimplePP())
+            ydl.add_post_processor(PP())
             ydl.post_process(filename, {'filepath': filename})
 
-        run_pp({'keepvideo': True})
+        run_pp({'keepvideo': True}, SimplePP)
         self.assertTrue(os.path.exists(filename), '%s doesn\'t exist' % filename)
         self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
         os.unlink(filename)
         os.unlink(audiofile)
 
-        run_pp({'keepvideo': False})
+        run_pp({'keepvideo': False}, SimplePP)
         self.assertFalse(os.path.exists(filename), '%s exists' % filename)
         self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
         os.unlink(audiofile)
 
+        class ModifierPP(PostProcessor):
+            def run(self, info):
+                with open(info['filepath'], 'wt') as f:
+                    f.write('MODIFIED')
+                return [], info
+
+        run_pp({'keepvideo': False}, ModifierPP)
+        self.assertTrue(os.path.exists(filename), '%s doesn\'t exist' % filename)
+        os.unlink(filename)
+
+    def test_match_filter(self):
+        class FilterYDL(YDL):
+            def __init__(self, *args, **kwargs):
+                super(FilterYDL, self).__init__(*args, **kwargs)
+                self.params['simulate'] = True
+
+            def process_info(self, info_dict):
+                super(YDL, self).process_info(info_dict)
+
+            def _match_entry(self, info_dict, incomplete):
+                res = super(FilterYDL, self)._match_entry(info_dict, incomplete)
+                if res is None:
+                    self.downloaded_info_dicts.append(info_dict)
+                return res
+
+        first = {
+            'id': '1',
+            'url': TEST_URL,
+            'title': 'one',
+            'extractor': 'TEST',
+            'duration': 30,
+            'filesize': 10 * 1024,
+        }
+        second = {
+            'id': '2',
+            'url': TEST_URL,
+            'title': 'two',
+            'extractor': 'TEST',
+            'duration': 10,
+            'description': 'foo',
+            'filesize': 5 * 1024,
+        }
+        videos = [first, second]
+
+        def get_videos(filter_=None):
+            ydl = FilterYDL({'match_filter': filter_})
+            for v in videos:
+                ydl.process_ie_result(v, download=True)
+            return [v['id'] for v in ydl.downloaded_info_dicts]
+
+        res = get_videos()
+        self.assertEqual(res, ['1', '2'])
+
+        def f(v):
+            if v['id'] == '1':
+                return None
+            else:
+                return 'Video id is not 1'
+        res = get_videos(f)
+        self.assertEqual(res, ['1'])
+
+        f = match_filter_func('duration < 30')
+        res = get_videos(f)
+        self.assertEqual(res, ['2'])
+
+        f = match_filter_func('description = foo')
+        res = get_videos(f)
+        self.assertEqual(res, ['2'])
+
+        f = match_filter_func('description =? foo')
+        res = get_videos(f)
+        self.assertEqual(res, ['1', '2'])
+
+        f = match_filter_func('filesize > 5KiB')
+        res = get_videos(f)
+        self.assertEqual(res, ['1'])
+
+    def test_playlist_items_selection(self):
+        entries = [{
+            'id': compat_str(i),
+            'title': compat_str(i),
+            'url': TEST_URL,
+        } for i in range(1, 5)]
+        playlist = {
+            '_type': 'playlist',
+            'id': 'test',
+            'entries': entries,
+            'extractor': 'test:playlist',
+            'extractor_key': 'test:playlist',
+            'webpage_url': 'http://example.com',
+        }
+
+        def get_ids(params):
+            ydl = YDL(params)
+            # make a copy because the dictionary can be modified
+            ydl.process_ie_result(playlist.copy())
+            return [int(v['id']) for v in ydl.downloaded_info_dicts]
+
+        result = get_ids({})
+        self.assertEqual(result, [1, 2, 3, 4])
+
+        result = get_ids({'playlistend': 10})
+        self.assertEqual(result, [1, 2, 3, 4])
+
+        result = get_ids({'playlistend': 2})
+        self.assertEqual(result, [1, 2])
+
+        result = get_ids({'playliststart': 10})
+        self.assertEqual(result, [])
+
+        result = get_ids({'playliststart': 2})
+        self.assertEqual(result, [2, 3, 4])
+
+        result = get_ids({'playlist_items': '2-4'})
+        self.assertEqual(result, [2, 3, 4])
+
+        result = get_ids({'playlist_items': '2,4'})
+        self.assertEqual(result, [2, 4])
+
+        result = get_ids({'playlist_items': '10'})
+        self.assertEqual(result, [])
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_aes.py

@@ -0,0 +1,55 @@
+#!/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 youtube_dl.aes import aes_decrypt, aes_encrypt, aes_cbc_decrypt, aes_decrypt_text
+from youtube_dl.utils import bytes_to_intlist, intlist_to_bytes
+import base64
+
+# the encrypted data can be generate with 'devscripts/generate_aes_testdata.py'
+
+
+class TestAES(unittest.TestCase):
+    def setUp(self):
+        self.key = self.iv = [0x20, 0x15] + 14 * [0]
+        self.secret_msg = b'Secret message goes here'
+
+    def test_encrypt(self):
+        msg = b'message'
+        key = list(range(16))
+        encrypted = aes_encrypt(bytes_to_intlist(msg), key)
+        decrypted = intlist_to_bytes(aes_decrypt(encrypted, key))
+        self.assertEqual(decrypted, msg)
+
+    def test_cbc_decrypt(self):
+        data = bytes_to_intlist(
+            b"\x97\x92+\xe5\x0b\xc3\x18\x91ky9m&\xb3\xb5@\xe6'\xc2\x96.\xc8u\x88\xab9-[\x9e|\xf1\xcd"
+        )
+        decrypted = intlist_to_bytes(aes_cbc_decrypt(data, self.key, self.iv))
+        self.assertEqual(decrypted.rstrip(b'\x08'), self.secret_msg)
+
+    def test_decrypt_text(self):
+        password = intlist_to_bytes(self.key).decode('utf-8')
+        encrypted = base64.b64encode(
+            intlist_to_bytes(self.iv[:8]) +
+            b'\x17\x15\x93\xab\x8d\x80V\xcdV\xe0\t\xcdo\xc2\xa5\xd8ksM\r\xe27N\xae'
+        ).decode('utf-8')
+        decrypted = (aes_decrypt_text(encrypted, password, 16))
+        self.assertEqual(decrypted, self.secret_msg)
+
+        password = intlist_to_bytes(self.key).decode('utf-8')
+        encrypted = base64.b64encode(
+            intlist_to_bytes(self.iv[:8]) +
+            b'\x0b\xe6\xa4\xd9z\x0e\xb8\xb9\xd0\xd4i_\x85\x1d\x99\x98_\xe5\x80\xe7.\xbf\xa5\x83'
+        ).decode('utf-8')
+        decrypted = (aes_decrypt_text(encrypted, password, 32))
+        self.assertEqual(decrypted, self.secret_msg)
+
+if __name__ == '__main__':
+    unittest.main()

test/test_all_urls.py

@@ -59,7 +59,7 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertMatch('www.youtube.com/NASAgovVideo/videos', ['youtube:user'])
 
     def test_youtube_feeds(self):
-        self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:watch_later'])
+        self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:watchlater'])
         self.assertMatch('https://www.youtube.com/feed/subscriptions', ['youtube:subscriptions'])
         self.assertMatch('https://www.youtube.com/feed/recommended', ['youtube:recommended'])
         self.assertMatch('https://www.youtube.com/my_favorites', ['youtube:favorites'])
@@ -104,11 +104,11 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertMatch(':tds', ['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/channels/tributes', ['vimeo:channel'])
+        self.assertMatch('https://vimeo.com/channels/31259', ['vimeo:channel'])
+        self.assertMatch('https://vimeo.com/channels/31259/53576664', ['vimeo'])
+        self.assertMatch('https://vimeo.com/user7108434', ['vimeo:user'])
+        self.assertMatch('https://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

test/test_compat.py

@@ -14,6 +14,8 @@ from youtube_dl.utils import get_filesystem_encoding
 from youtube_dl.compat import (
     compat_getenv,
     compat_expanduser,
+    compat_urllib_parse_unquote,
+    compat_urllib_parse_unquote_plus,
 )
 
 
@@ -42,5 +44,28 @@ class TestCompat(unittest.TestCase):
             dir(youtube_dl.compat))) - set(['unicode_literals'])
         self.assertEqual(all_names, sorted(present_names))
 
+    def test_compat_urllib_parse_unquote(self):
+        self.assertEqual(compat_urllib_parse_unquote('abc%20def'), 'abc def')
+        self.assertEqual(compat_urllib_parse_unquote('%7e/abc+def'), '~/abc+def')
+        self.assertEqual(compat_urllib_parse_unquote(''), '')
+        self.assertEqual(compat_urllib_parse_unquote('%'), '%')
+        self.assertEqual(compat_urllib_parse_unquote('%%'), '%%')
+        self.assertEqual(compat_urllib_parse_unquote('%%%'), '%%%')
+        self.assertEqual(compat_urllib_parse_unquote('%2F'), '/')
+        self.assertEqual(compat_urllib_parse_unquote('%2f'), '/')
+        self.assertEqual(compat_urllib_parse_unquote('%E6%B4%A5%E6%B3%A2'), '津波')
+        self.assertEqual(
+            compat_urllib_parse_unquote('''<meta property="og:description" content="%E2%96%81%E2%96%82%E2%96%83%E2%96%84%25%E2%96%85%E2%96%86%E2%96%87%E2%96%88" />
+%<a href="https://ar.wikipedia.org/wiki/%D8%AA%D8%B3%D9%88%D9%86%D8%A7%D9%85%D9%8A">%a'''),
+            '''<meta property="og:description" content="▁▂▃▄%▅▆▇█" />
+%<a href="https://ar.wikipedia.org/wiki/تسونامي">%a''')
+        self.assertEqual(
+            compat_urllib_parse_unquote('''%28%5E%E2%97%A3_%E2%97%A2%5E%29%E3%81%A3%EF%B8%BB%E3%83%87%E2%95%90%E4%B8%80    %E2%87%80    %E2%87%80    %E2%87%80    %E2%87%80    %E2%87%80    %E2%86%B6%I%Break%25Things%'''),
+            '''(^◣_◢^)っ︻デ═一    ⇀    ⇀    ⇀    ⇀    ⇀    ↶%I%Break%Things%''')
+
+    def test_compat_urllib_parse_unquote_plus(self):
+        self.assertEqual(compat_urllib_parse_unquote_plus('abc%20def'), 'abc def')
+        self.assertEqual(compat_urllib_parse_unquote_plus('%7e/abc+def'), '~/abc def')
+
 if __name__ == '__main__':
     unittest.main()

test/test_download.py

@@ -136,7 +136,9 @@ def generator(test_case):
                     # We're not using .download here sine that is just a shim
                     # for outside error handling, and returns the exit code
                     # instead of the result dict.
-                    res_dict = ydl.extract_info(test_case['url'])
+                    res_dict = ydl.extract_info(
+                        test_case['url'],
+                        force_generic_extractor=params.get('force_generic_extractor', False))
                 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, compat_http_client.BadStatusLine) or (err.exc_info[0] == compat_HTTPError and err.exc_info[1].code == 503):
@@ -153,7 +155,7 @@ def generator(test_case):
                     break
 
             if is_playlist:
-                self.assertEqual(res_dict['_type'], 'playlist')
+                self.assertTrue(res_dict['_type'] in ['playlist', 'multi_video'])
                 self.assertTrue('entries' in res_dict)
                 expect_info_dict(self, res_dict, test_case.get('info_dict', {}))
 

test/test_execution.py

@@ -1,4 +1,6 @@
 #!/usr/bin/env python
+# coding: utf-8
+
 from __future__ import unicode_literals
 
 import unittest
@@ -6,6 +8,9 @@ import unittest
 import sys
 import os
 import subprocess
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from youtube_dl.utils import encodeArgument
 
 rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 
@@ -27,5 +32,12 @@ class TestExecution(unittest.TestCase):
     def test_main_exec(self):
         subprocess.check_call([sys.executable, 'youtube_dl/__main__.py', '--version'], cwd=rootDir, stdout=_DEV_NULL)
 
+    def test_cmdline_umlauts(self):
+        p = subprocess.Popen(
+            [sys.executable, 'youtube_dl/__main__.py', encodeArgument('ä'), '--version'],
+            cwd=rootDir, stdout=_DEV_NULL, stderr=subprocess.PIPE)
+        _, stderr = p.communicate()
+        self.assertFalse(stderr)
+
 if __name__ == '__main__':
     unittest.main()

test/test_http.py

@@ -8,7 +8,7 @@ import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from youtube_dl import YoutubeDL
-from youtube_dl.compat import compat_http_server
+from youtube_dl.compat import compat_http_server, compat_urllib_request
 import ssl
 import threading
 
@@ -68,5 +68,52 @@ class TestHTTP(unittest.TestCase):
         r = ydl.extract_info('https://localhost:%d/video.html' % self.port)
         self.assertEqual(r['url'], 'https://localhost:%d/vid.mp4' % self.port)
 
+
+def _build_proxy_handler(name):
+    class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
+        proxy_name = name
+
+        def log_message(self, format, *args):
+            pass
+
+        def do_GET(self):
+            self.send_response(200)
+            self.send_header('Content-Type', 'text/plain; charset=utf-8')
+            self.end_headers()
+            self.wfile.write('{self.proxy_name}: {self.path}'.format(self=self).encode('utf-8'))
+    return HTTPTestRequestHandler
+
+
+class TestProxy(unittest.TestCase):
+    def setUp(self):
+        self.proxy = compat_http_server.HTTPServer(
+            ('localhost', 0), _build_proxy_handler('normal'))
+        self.port = self.proxy.socket.getsockname()[1]
+        self.proxy_thread = threading.Thread(target=self.proxy.serve_forever)
+        self.proxy_thread.daemon = True
+        self.proxy_thread.start()
+
+        self.cn_proxy = compat_http_server.HTTPServer(
+            ('localhost', 0), _build_proxy_handler('cn'))
+        self.cn_port = self.cn_proxy.socket.getsockname()[1]
+        self.cn_proxy_thread = threading.Thread(target=self.cn_proxy.serve_forever)
+        self.cn_proxy_thread.daemon = True
+        self.cn_proxy_thread.start()
+
+    def test_proxy(self):
+        cn_proxy = 'localhost:{0}'.format(self.cn_port)
+        ydl = YoutubeDL({
+            'proxy': 'localhost:{0}'.format(self.port),
+            'cn_verification_proxy': cn_proxy,
+        })
+        url = 'http://foo.com/bar'
+        response = ydl.urlopen(url).read().decode('utf-8')
+        self.assertEqual(response, 'normal: {0}'.format(url))
+
+        req = compat_urllib_request.Request(url)
+        req.add_header('Ytdl-request-proxy', cn_proxy)
+        response = ydl.urlopen(req).read().decode('utf-8')
+        self.assertEqual(response, 'cn: {0}'.format(url))
+
 if __name__ == '__main__':
     unittest.main()

test/test_netrc.py

@@ -0,0 +1,26 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+
+from youtube_dl.extractor import (
+    gen_extractors,
+)
+
+
+class TestNetRc(unittest.TestCase):
+    def test_netrc_present(self):
+        for ie in gen_extractors():
+            if not hasattr(ie, '_login'):
+                continue
+            self.assertTrue(
+                hasattr(ie, '_NETRC_MACHINE'),
+                'Extractor %s supports login, but is missing a _NETRC_MACHINE property' % ie.IE_NAME)
+
+
+if __name__ == '__main__':
+    unittest.main()

test/test_postprocessors.py

@@ -0,0 +1,17 @@
+#!/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 youtube_dl.postprocessor import MetadataFromTitlePP
+
+
+class TestMetadataFromTitle(unittest.TestCase):
+    def test_format_to_regex(self):
+        pp = MetadataFromTitlePP(None, '%(title)s - %(artist)s')
+        self.assertEqual(pp._titleregex, '(?P<title>.+)\ \-\ (?P<artist>.+)')

test/test_subtitles.py

@@ -25,6 +25,9 @@ from youtube_dl.extractor import (
     RaiIE,
     VikiIE,
     ThePlatformIE,
+    ThePlatformFeedIE,
+    RTVEALaCartaIE,
+    FunnyOrDieIE,
 )
 
 
@@ -264,7 +267,7 @@ class TestNRKSubtitles(BaseTestSubtitles):
         self.DL.params['allsubtitles'] = True
         subtitles = self.getSubtitles()
         self.assertEqual(set(subtitles.keys()), set(['no']))
-        self.assertEqual(md5(subtitles['no']), '1d221e6458c95c5494dcd38e6a1f129a')
+        self.assertEqual(md5(subtitles['no']), '544fa917d3197fcbee64634559221cc2')
 
 
 class TestRaiSubtitles(BaseTestSubtitles):
@@ -305,5 +308,43 @@ class TestThePlatformSubtitles(BaseTestSubtitles):
         self.assertEqual(md5(subtitles['en']), '97e7670cbae3c4d26ae8bcc7fdd78d4b')
 
 
+class TestThePlatformFeedSubtitles(BaseTestSubtitles):
+    url = 'http://feed.theplatform.com/f/7wvmTC/msnbc_video-p-test?form=json&pretty=true&range=-40&byGuid=n_hardball_5biden_140207'
+    IE = ThePlatformFeedIE
+
+    def test_allsubtitles(self):
+        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']), '48649a22e82b2da21c9a67a395eedade')
+
+
+class TestRtveSubtitles(BaseTestSubtitles):
+    url = 'http://www.rtve.es/alacarta/videos/los-misterios-de-laura/misterios-laura-capitulo-32-misterio-del-numero-17-2-parte/2428621/'
+    IE = RTVEALaCartaIE
+
+    def test_allsubtitles(self):
+        print('Skipping, only available from Spain')
+        return
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(set(subtitles.keys()), set(['es']))
+        self.assertEqual(md5(subtitles['es']), '69e70cae2d40574fb7316f31d6eb7fca')
+
+
+class TestFunnyOrDieSubtitles(BaseTestSubtitles):
+    url = 'http://www.funnyordie.com/videos/224829ff6d/judd-apatow-will-direct-your-vine'
+    IE = FunnyOrDieIE
+
+    def test_allsubtitles(self):
+        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']), 'c5593c193eacd353596c11c2d4f9ecc4')
+
+
 if __name__ == '__main__':
     unittest.main()

test/test_unicode_literals.py

@@ -17,13 +17,22 @@ IGNORED_FILES = [
     'buildserver.py',
 ]
 
+IGNORED_DIRS = [
+    '.git',
+    '.tox',
+]
 
 from test.helper import assertRegexpMatches
 
 
 class TestUnicodeLiterals(unittest.TestCase):
     def test_all_files(self):
-        for dirpath, _, filenames in os.walk(rootDir):
+        for dirpath, dirnames, filenames in os.walk(rootDir):
+            for ignore_dir in IGNORED_DIRS:
+                if ignore_dir in dirnames:
+                    # If we remove the directory from dirnames os.walk won't
+                    # recurse into it
+                    dirnames.remove(ignore_dir)
             for basename in filenames:
                 if not basename.endswith('.py'):
                     continue

test/test_utils.py

@@ -24,6 +24,7 @@ from youtube_dl.utils import (
     encodeFilename,
     escape_rfc3986,
     escape_url,
+    ExtractorError,
     find_xpath_attr,
     fix_xml_ampersands,
     InAdvancePagedList,
@@ -38,6 +39,9 @@ from youtube_dl.utils import (
     parse_iso8601,
     read_batch_urls,
     sanitize_filename,
+    sanitize_path,
+    prepend_extension,
+    replace_extension,
     shell_quote,
     smuggle_url,
     str_to_int,
@@ -48,12 +52,16 @@ from youtube_dl.utils import (
     unified_strdate,
     unsmuggle_url,
     uppercase_escape,
+    lowercase_escape,
     url_basename,
     urlencode_postdata,
     version_tuple,
     xpath_with_ns,
+    xpath_text,
     render_table,
     match_str,
+    parse_dfxp_time_expr,
+    dfxp2srt,
 )
 
 
@@ -86,6 +94,11 @@ class TestUtil(unittest.TestCase):
             sanitize_filename('New World record at 0:12:34'),
             'New World record at 0_12_34')
 
+        self.assertEqual(sanitize_filename('--gasdgf'), '_-gasdgf')
+        self.assertEqual(sanitize_filename('--gasdgf', is_id=True), '--gasdgf')
+        self.assertEqual(sanitize_filename('.gasdgf'), 'gasdgf')
+        self.assertEqual(sanitize_filename('.gasdgf', is_id=True), '.gasdgf')
+
         forbidden = '"\0\\/'
         for fc in forbidden:
             for fbc in forbidden:
@@ -126,6 +139,58 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
         self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
 
+    def test_sanitize_path(self):
+        if sys.platform != 'win32':
+            return
+
+        self.assertEqual(sanitize_path('abc'), 'abc')
+        self.assertEqual(sanitize_path('abc/def'), 'abc\\def')
+        self.assertEqual(sanitize_path('abc\\def'), 'abc\\def')
+        self.assertEqual(sanitize_path('abc|def'), 'abc#def')
+        self.assertEqual(sanitize_path('<>:"|?*'), '#######')
+        self.assertEqual(sanitize_path('C:/abc/def'), 'C:\\abc\\def')
+        self.assertEqual(sanitize_path('C?:/abc/def'), 'C##\\abc\\def')
+
+        self.assertEqual(sanitize_path('\\\\?\\UNC\\ComputerName\\abc'), '\\\\?\\UNC\\ComputerName\\abc')
+        self.assertEqual(sanitize_path('\\\\?\\UNC/ComputerName/abc'), '\\\\?\\UNC\\ComputerName\\abc')
+
+        self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
+        self.assertEqual(sanitize_path('\\\\?\\C:/abc'), '\\\\?\\C:\\abc')
+        self.assertEqual(sanitize_path('\\\\?\\C:\\ab?c\\de:f'), '\\\\?\\C:\\ab#c\\de#f')
+        self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
+
+        self.assertEqual(
+            sanitize_path('youtube/%(uploader)s/%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s'),
+            'youtube\\%(uploader)s\\%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s')
+
+        self.assertEqual(
+            sanitize_path('youtube/TheWreckingYard ./00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part'),
+            'youtube\\TheWreckingYard #\\00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part')
+        self.assertEqual(sanitize_path('abc/def...'), 'abc\\def..#')
+        self.assertEqual(sanitize_path('abc.../def'), 'abc..#\\def')
+        self.assertEqual(sanitize_path('abc.../def...'), 'abc..#\\def..#')
+
+        self.assertEqual(sanitize_path('../abc'), '..\\abc')
+        self.assertEqual(sanitize_path('../../abc'), '..\\..\\abc')
+        self.assertEqual(sanitize_path('./abc'), 'abc')
+        self.assertEqual(sanitize_path('./../abc'), '..\\abc')
+
+    def test_prepend_extension(self):
+        self.assertEqual(prepend_extension('abc.ext', 'temp'), 'abc.temp.ext')
+        self.assertEqual(prepend_extension('abc.ext', 'temp', 'ext'), 'abc.temp.ext')
+        self.assertEqual(prepend_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
+        self.assertEqual(prepend_extension('abc', 'temp'), 'abc.temp')
+        self.assertEqual(prepend_extension('.abc', 'temp'), '.abc.temp')
+        self.assertEqual(prepend_extension('.abc.ext', 'temp'), '.abc.temp.ext')
+
+    def test_replace_extension(self):
+        self.assertEqual(replace_extension('abc.ext', 'temp'), 'abc.temp')
+        self.assertEqual(replace_extension('abc.ext', 'temp', 'ext'), 'abc.temp')
+        self.assertEqual(replace_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
+        self.assertEqual(replace_extension('abc', 'temp'), 'abc.temp')
+        self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
+        self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
+
     def test_ordered_set(self):
         self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
         self.assertEqual(orderedSet([]), [])
@@ -135,6 +200,8 @@ class TestUtil(unittest.TestCase):
 
     def test_unescape_html(self):
         self.assertEqual(unescapeHTML('%20;'), '%20;')
+        self.assertEqual(unescapeHTML('&#x2F;'), '/')
+        self.assertEqual(unescapeHTML('&#47;'), '/')
         self.assertEqual(
             unescapeHTML('&eacute;'), 'é')
 
@@ -160,6 +227,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(
             unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
             '20150202')
+        self.assertEqual(unified_strdate('25-09-2014'), '20140925')
 
     def test_find_xpath_attr(self):
         testxml = '''<root>
@@ -167,12 +235,21 @@ class TestUtil(unittest.TestCase):
             <node x="a"/>
             <node x="a" y="c" />
             <node x="b" y="d" />
+            <node x="" />
         </root>'''
         doc = xml.etree.ElementTree.fromstring(testxml)
 
+        self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n'), None)
         self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
+        self.assertEqual(find_xpath_attr(doc, './/node', 'n'), None)
+        self.assertEqual(find_xpath_attr(doc, './/node', 'n', 'v'), None)
+        self.assertEqual(find_xpath_attr(doc, './/node', 'x'), doc[1])
         self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
+        self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'b'), doc[3])
+        self.assertEqual(find_xpath_attr(doc, './/node', 'y'), doc[2])
         self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
+        self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'd'), doc[3])
+        self.assertEqual(find_xpath_attr(doc, './/node', 'x', ''), doc[4])
 
     def test_xpath_with_ns(self):
         testxml = '''<root xmlns:media="http://example.com/">
@@ -187,6 +264,17 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(find('media:song/media:author').text, 'The Author')
         self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
 
+    def test_xpath_text(self):
+        testxml = '''<root>
+            <div>
+                <p>Foo</p>
+            </div>
+        </root>'''
+        doc = xml.etree.ElementTree.fromstring(testxml)
+        self.assertEqual(xpath_text(doc, 'div/p'), 'Foo')
+        self.assertTrue(xpath_text(doc, 'div/bar') is None)
+        self.assertRaises(ExtractorError, xpath_text, doc, 'div/bar', fatal=True)
+
     def test_smuggle_url(self):
         data = {"ö": "ö", "abc": [3]}
         url = 'https://foo.bar/baz?x=y#a'
@@ -244,6 +332,8 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(parse_duration('2.5 hours'), 9000)
         self.assertEqual(parse_duration('02:03:04'), 7384)
         self.assertEqual(parse_duration('01:02:03:04'), 93784)
+        self.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
+        self.assertEqual(parse_duration('87 Min.'), 5220)
 
     def test_fix_xml_ampersands(self):
         self.assertEqual(
@@ -318,6 +408,10 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(uppercase_escape('aä'), 'aä')
         self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
 
+    def test_lowercase_escape(self):
+        self.assertEqual(lowercase_escape('aä'), 'aä')
+        self.assertEqual(lowercase_escape('\\u0026'), '&')
+
     def test_limit_length(self):
         self.assertEqual(limit_length(None, 12), None)
         self.assertEqual(limit_length('foo', 12), 'foo')
@@ -391,6 +485,12 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(d['x'], 1)
         self.assertEqual(d['y'], 'a')
 
+        on = js_to_json('["abc", "def",]')
+        self.assertEqual(json.loads(on), ['abc', 'def'])
+
+        on = js_to_json('{"abc": "def",}')
+        self.assertEqual(json.loads(on), {'abc': 'def'})
+
     def test_clean_html(self):
         self.assertEqual(clean_html('a:\nb'), 'a: b')
         self.assertEqual(clean_html('a:\n   "b"'), 'a:    "b"')
@@ -495,6 +595,57 @@ ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
             'like_count > 100 & dislike_count <? 50 & description',
             {'like_count': 190, 'dislike_count': 10}))
 
+    def test_parse_dfxp_time_expr(self):
+        self.assertEqual(parse_dfxp_time_expr(None), 0.0)
+        self.assertEqual(parse_dfxp_time_expr(''), 0.0)
+        self.assertEqual(parse_dfxp_time_expr('0.1'), 0.1)
+        self.assertEqual(parse_dfxp_time_expr('0.1s'), 0.1)
+        self.assertEqual(parse_dfxp_time_expr('00:00:01'), 1.0)
+        self.assertEqual(parse_dfxp_time_expr('00:00:01.100'), 1.1)
+
+    def test_dfxp2srt(self):
+        dfxp_data = '''<?xml version="1.0" encoding="UTF-8"?>
+            <tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
+            <body>
+                <div xml:lang="en">
+                    <p begin="0" end="1">The following line contains Chinese characters and special symbols</p>
+                    <p begin="1" end="2">第二行<br/>♪♪</p>
+                    <p begin="2" dur="1"><span>Third<br/>Line</span></p>
+                </div>
+            </body>
+            </tt>'''
+        srt_data = '''1
+00:00:00,000 --> 00:00:01,000
+The following line contains Chinese characters and special symbols
+
+2
+00:00:01,000 --> 00:00:02,000
+第二行
+♪♪
+
+3
+00:00:02,000 --> 00:00:03,000
+Third
+Line
+
+'''
+        self.assertEqual(dfxp2srt(dfxp_data), srt_data)
+
+        dfxp_data_no_default_namespace = '''<?xml version="1.0" encoding="UTF-8"?>
+            <tt xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
+            <body>
+                <div xml:lang="en">
+                    <p begin="0" end="1">The first line</p>
+                </div>
+            </body>
+            </tt>'''
+        srt_data = '''1
+00:00:00,000 --> 00:00:01,000
+The first line
+
+'''
+        self.assertEqual(dfxp2srt(dfxp_data_no_default_namespace), srt_data)
+
 
 if __name__ == '__main__':
     unittest.main()

tox.ini

@@ -1,8 +1,13 @@
 [tox]
-envlist = py26,py27,py33
+envlist = py26,py27,py33,py34
 [testenv]
 deps =
    nose
    coverage
-commands = nosetests --verbose {posargs:test}  # --with-coverage --cover-package=youtube_dl --cover-html
+# We need a valid $HOME for test_compat_expanduser
+passenv = HOME
+defaultargs = test --exclude test_download.py --exclude test_age_restriction.py
+    --exclude test_subtitles.py --exclude test_write_annotations.py
+    --exclude test_youtube_lists.py
+commands = nosetests --verbose {posargs:{[testenv]defaultargs}}  # --with-coverage --cover-package=youtube_dl --cover-html
                                                # test.test_download:TestDownload.test_NowVideo

youtube_dl/YoutubeDL.py

@@ -4,8 +4,10 @@
 from __future__ import absolute_import, unicode_literals
 
 import collections
+import contextlib
 import datetime
 import errno
+import fileinput
 import io
 import itertools
 import json
@@ -19,23 +21,24 @@ import subprocess
 import socket
 import sys
 import time
+import tokenize
 import traceback
 
 if os.name == 'nt':
     import ctypes
 
 from .compat import (
-    compat_basestring,
     compat_cookiejar,
     compat_expanduser,
+    compat_get_terminal_size,
     compat_http_client,
     compat_kwargs,
     compat_str,
+    compat_tokenize_tokenize,
     compat_urllib_error,
     compat_urllib_request,
 )
 from .utils import (
-    escape_url,
     ContentTooShortError,
     date_from_str,
     DateRange,
@@ -46,21 +49,21 @@ from .utils import (
     ExtractorError,
     format_bytes,
     formatSeconds,
-    get_term_width,
     locked_file,
     make_HTTPS_handler,
     MaxDownloadsReached,
     PagedList,
     parse_filesize,
+    PerRequestProxyHandler,
     PostProcessingError,
     platform_name,
     preferredencoding,
     render_table,
     SameFileError,
     sanitize_filename,
+    sanitize_path,
     std_headers,
     subtitles_filename,
-    takewhile_inclusive,
     UnavailableVideoError,
     url_basename,
     version_tuple,
@@ -68,6 +71,7 @@ from .utils import (
     write_string,
     YoutubeDLHandler,
     prepend_extension,
+    replace_extension,
     args_to_str,
     age_restricted,
 )
@@ -114,7 +118,7 @@ class YoutubeDL(object):
 
     username:          Username for authentication purposes.
     password:          Password for authentication purposes.
-    videopassword:     Password for acces a video.
+    videopassword:     Password for accessing a video.
     usenetrc:          Use netrc for authentication instead.
     verbose:           Print additional info to stdout.
     quiet:             Do not print messages to stdout.
@@ -131,10 +135,10 @@ class YoutubeDL(object):
                        (or video) as a single JSON line.
     simulate:          Do not download the video files.
     format:            Video format code. See options.py for more information.
-    format_limit:      Highest quality format to try.
     outtmpl:           Template for output names.
     restrictfilenames: Do not allow "&" and spaces in file names
     ignoreerrors:      Do not stop on download errors.
+    force_generic_extractor: Force downloader to use the generic extractor
     nooverwrites:      Prevent overwriting files.
     playliststart:     Playlist item to start at.
     playlistend:       Playlist item to end at.
@@ -181,6 +185,8 @@ class YoutubeDL(object):
     prefer_insecure:   Use HTTP instead of HTTPS to retrieve information.
                        At the moment, this is only supported by YouTube.
     proxy:             URL of the proxy server to use
+    cn_verification_proxy:  URL of the proxy to use for IP address verification
+                       on Chinese sites. (Experimental)
     socket_timeout:    Time to wait for unresponsive hosts, in seconds
     bidi_workaround:   Work around buggy terminals without bidirectional text
                        support, using fridibi
@@ -247,15 +253,16 @@ class YoutubeDL(object):
     hls_prefer_native: Use the native HLS downloader instead of ffmpeg/avconv.
 
     The following parameters are not used by YoutubeDL itself, they are used by
-    the FileDownloader:
+    the downloader (see youtube_dl/downloader/common.py):
     nopart, updatetime, buffersize, ratelimit, min_filesize, max_filesize, test,
     noresizebuffer, retries, continuedl, noprogress, consoletitle,
-    xattr_set_filesize.
+    xattr_set_filesize, external_downloader_args.
 
     The following options are used by the post processors:
     prefer_ffmpeg:     If True, use ffmpeg instead of avconv if both are available,
                        otherwise prefer avconv.
-    exec_cmd:          Arbitrary command to run after downloading
+    postprocessor_args: A list of additional command-line arguments for the
+                        postprocessor.
     """
 
     params = None
@@ -284,7 +291,7 @@ class YoutubeDL(object):
             try:
                 import pty
                 master, slave = pty.openpty()
-                width = get_term_width()
+                width = compat_get_terminal_size().columns
                 if width is None:
                     width_args = []
                 else:
@@ -317,8 +324,10 @@ class YoutubeDL(object):
                 'Set the LC_ALL environment variable to fix this.')
             self.params['restrictfilenames'] = True
 
-        if '%(stitle)s' in self.params.get('outtmpl', ''):
-            self.report_warning('%(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.')
+        if isinstance(params.get('outtmpl'), bytes):
+            self.report_warning(
+                'Parameter outtmpl is bytes, but should be a unicode string. '
+                'Put  from __future__ import unicode_literals  at the top of your code file or consider switching to Python 3.x.')
 
         self._setup_opener()
 
@@ -557,7 +566,7 @@ class YoutubeDL(object):
                                  if v is not None)
             template_dict = collections.defaultdict(lambda: 'NA', template_dict)
 
-            outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
+            outtmpl = sanitize_path(self.params.get('outtmpl', DEFAULT_OUTTMPL))
             tmpl = compat_expanduser(outtmpl)
             filename = tmpl % template_dict
             # Temporary fix for #4787
@@ -619,12 +628,15 @@ class YoutubeDL(object):
             info_dict.setdefault(key, value)
 
     def extract_info(self, url, download=True, ie_key=None, extra_info={},
-                     process=True):
+                     process=True, force_generic_extractor=False):
         '''
         Returns a list with a dictionary for each video we find.
         If 'download', also downloads the videos.
         extra_info is a dict containing the extra values to add to each result
-         '''
+        '''
+
+        if not ie_key and force_generic_extractor:
+            ie_key = 'Generic'
 
         if ie_key:
             ies = [self.get_info_extractor(ie_key)]
@@ -753,7 +765,9 @@ class YoutubeDL(object):
             if isinstance(ie_entries, list):
                 n_all_entries = len(ie_entries)
                 if playlistitems:
-                    entries = [ie_entries[i - 1] for i in playlistitems]
+                    entries = [
+                        ie_entries[i - 1] for i in playlistitems
+                        if -n_all_entries <= i - 1 < n_all_entries]
                 else:
                     entries = ie_entries[playliststart:playlistend]
                 n_entries = len(entries)
@@ -838,8 +852,8 @@ class YoutubeDL(object):
         else:
             raise Exception('Invalid result type: %s' % result_type)
 
-    def _apply_format_filter(self, format_spec, available_formats):
-        " Returns a tuple of the remaining format_spec and filtered formats "
+    def _build_format_filter(self, filter_spec):
+        " Returns a function to filter the formats according to the filter_spec "
 
         OPERATORS = {
             '<': operator.lt,
@@ -849,13 +863,13 @@ class YoutubeDL(object):
             '=': operator.eq,
             '!=': operator.ne,
         }
-        operator_rex = re.compile(r'''(?x)\s*\[
+        operator_rex = re.compile(r'''(?x)\s*
             (?P<key>width|height|tbr|abr|vbr|asr|filesize|fps)
             \s*(?P<op>%s)(?P<none_inclusive>\s*\?)?\s*
             (?P<value>[0-9.]+(?:[kKmMgGtTpPeEzZyY]i?[Bb]?)?)
-            \]$
+            $
             ''' % '|'.join(map(re.escape, OPERATORS.keys())))
-        m = operator_rex.search(format_spec)
+        m = operator_rex.search(filter_spec)
         if m:
             try:
                 comparison_value = int(m.group('value'))
@@ -866,7 +880,7 @@ class YoutubeDL(object):
                 if comparison_value is None:
                     raise ValueError(
                         'Invalid value %r in format specification %r' % (
-                            m.group('value'), format_spec))
+                            m.group('value'), filter_spec))
             op = OPERATORS[m.group('op')]
 
         if not m:
@@ -874,78 +888,283 @@ class YoutubeDL(object):
                 '=': operator.eq,
                 '!=': operator.ne,
             }
-            str_operator_rex = re.compile(r'''(?x)\s*\[
+            str_operator_rex = re.compile(r'''(?x)
                 \s*(?P<key>ext|acodec|vcodec|container|protocol)
                 \s*(?P<op>%s)(?P<none_inclusive>\s*\?)?
                 \s*(?P<value>[a-zA-Z0-9_-]+)
-                \s*\]$
+                \s*$
                 ''' % '|'.join(map(re.escape, STR_OPERATORS.keys())))
-            m = str_operator_rex.search(format_spec)
+            m = str_operator_rex.search(filter_spec)
             if m:
                 comparison_value = m.group('value')
                 op = STR_OPERATORS[m.group('op')]
 
         if not m:
-            raise ValueError('Invalid format specification %r' % format_spec)
+            raise ValueError('Invalid filter specification %r' % filter_spec)
 
         def _filter(f):
             actual_value = f.get(m.group('key'))
             if actual_value is None:
                 return m.group('none_inclusive')
             return op(actual_value, comparison_value)
-        new_formats = [f for f in available_formats if _filter(f)]
+        return _filter
 
-        new_format_spec = format_spec[:-len(m.group(0))]
-        if not new_format_spec:
-            new_format_spec = 'best'
+    def build_format_selector(self, format_spec):
+        def syntax_error(note, start):
+            message = (
+                'Invalid format specification: '
+                '{0}\n\t{1}\n\t{2}^'.format(note, format_spec, ' ' * start[1]))
+            return SyntaxError(message)
 
-        return (new_format_spec, new_formats)
+        PICKFIRST = 'PICKFIRST'
+        MERGE = 'MERGE'
+        SINGLE = 'SINGLE'
+        GROUP = 'GROUP'
+        FormatSelector = collections.namedtuple('FormatSelector', ['type', 'selector', 'filters'])
 
-    def select_format(self, format_spec, available_formats):
-        while format_spec.endswith(']'):
-            format_spec, available_formats = self._apply_format_filter(
-                format_spec, available_formats)
-        if not available_formats:
-            return None
+        def _parse_filter(tokens):
+            filter_parts = []
+            for type, string, start, _, _ in tokens:
+                if type == tokenize.OP and string == ']':
+                    return ''.join(filter_parts)
+                else:
+                    filter_parts.append(string)
 
-        if format_spec == 'best' or format_spec is None:
-            return available_formats[-1]
-        elif format_spec == 'worst':
-            return available_formats[0]
-        elif format_spec == 'bestaudio':
-            audio_formats = [
-                f for f in available_formats
-                if f.get('vcodec') == 'none']
-            if audio_formats:
-                return audio_formats[-1]
-        elif format_spec == 'worstaudio':
-            audio_formats = [
-                f for f in available_formats
-                if f.get('vcodec') == 'none']
-            if audio_formats:
-                return audio_formats[0]
-        elif format_spec == 'bestvideo':
-            video_formats = [
-                f for f in available_formats
-                if f.get('acodec') == 'none']
-            if video_formats:
-                return video_formats[-1]
-        elif format_spec == 'worstvideo':
-            video_formats = [
-                f for f in available_formats
-                if f.get('acodec') == 'none']
-            if video_formats:
-                return video_formats[0]
-        else:
-            extensions = ['mp4', 'flv', 'webm', '3gp', 'm4a', 'mp3', 'ogg', 'aac', 'wav']
-            if format_spec in extensions:
-                filter_f = lambda f: f['ext'] == format_spec
-            else:
-                filter_f = lambda f: f['format_id'] == format_spec
-            matches = list(filter(filter_f, available_formats))
-            if matches:
-                return matches[-1]
-        return None
+        def _remove_unused_ops(tokens):
+            # Remove operators that we don't use and join them with the sourrounding strings
+            # for example: 'mp4' '-' 'baseline' '-' '16x9' is converted to 'mp4-baseline-16x9'
+            ALLOWED_OPS = ('/', '+', ',', '(', ')')
+            last_string, last_start, last_end, last_line = None, None, None, None
+            for type, string, start, end, line in tokens:
+                if type == tokenize.OP and string == '[':
+                    if last_string:
+                        yield tokenize.NAME, last_string, last_start, last_end, last_line
+                        last_string = None
+                    yield type, string, start, end, line
+                    # everything inside brackets will be handled by _parse_filter
+                    for type, string, start, end, line in tokens:
+                        yield type, string, start, end, line
+                        if type == tokenize.OP and string == ']':
+                            break
+                elif type == tokenize.OP and string in ALLOWED_OPS:
+                    if last_string:
+                        yield tokenize.NAME, last_string, last_start, last_end, last_line
+                        last_string = None
+                    yield type, string, start, end, line
+                elif type in [tokenize.NAME, tokenize.NUMBER, tokenize.OP]:
+                    if not last_string:
+                        last_string = string
+                        last_start = start
+                        last_end = end
+                    else:
+                        last_string += string
+            if last_string:
+                yield tokenize.NAME, last_string, last_start, last_end, last_line
+
+        def _parse_format_selection(tokens, inside_merge=False, inside_choice=False, inside_group=False):
+            selectors = []
+            current_selector = None
+            for type, string, start, _, _ in tokens:
+                # ENCODING is only defined in python 3.x
+                if type == getattr(tokenize, 'ENCODING', None):
+                    continue
+                elif type in [tokenize.NAME, tokenize.NUMBER]:
+                    current_selector = FormatSelector(SINGLE, string, [])
+                elif type == tokenize.OP:
+                    if string == ')':
+                        if not inside_group:
+                            # ')' will be handled by the parentheses group
+                            tokens.restore_last_token()
+                        break
+                    elif inside_merge and string in ['/', ',']:
+                        tokens.restore_last_token()
+                        break
+                    elif inside_choice and string == ',':
+                        tokens.restore_last_token()
+                        break
+                    elif string == ',':
+                        if not current_selector:
+                            raise syntax_error('"," must follow a format selector', start)
+                        selectors.append(current_selector)
+                        current_selector = None
+                    elif string == '/':
+                        if not current_selector:
+                            raise syntax_error('"/" must follow a format selector', start)
+                        first_choice = current_selector
+                        second_choice = _parse_format_selection(tokens, inside_choice=True)
+                        current_selector = FormatSelector(PICKFIRST, (first_choice, second_choice), [])
+                    elif string == '[':
+                        if not current_selector:
+                            current_selector = FormatSelector(SINGLE, 'best', [])
+                        format_filter = _parse_filter(tokens)
+                        current_selector.filters.append(format_filter)
+                    elif string == '(':
+                        if current_selector:
+                            raise syntax_error('Unexpected "("', start)
+                        group = _parse_format_selection(tokens, inside_group=True)
+                        current_selector = FormatSelector(GROUP, group, [])
+                    elif string == '+':
+                        video_selector = current_selector
+                        audio_selector = _parse_format_selection(tokens, inside_merge=True)
+                        if not video_selector or not audio_selector:
+                            raise syntax_error('"+" must be between two format selectors', start)
+                        current_selector = FormatSelector(MERGE, (video_selector, audio_selector), [])
+                    else:
+                        raise syntax_error('Operator not recognized: "{0}"'.format(string), start)
+                elif type == tokenize.ENDMARKER:
+                    break
+            if current_selector:
+                selectors.append(current_selector)
+            return selectors
+
+        def _build_selector_function(selector):
+            if isinstance(selector, list):
+                fs = [_build_selector_function(s) for s in selector]
+
+                def selector_function(formats):
+                    for f in fs:
+                        for format in f(formats):
+                            yield format
+                return selector_function
+            elif selector.type == GROUP:
+                selector_function = _build_selector_function(selector.selector)
+            elif selector.type == PICKFIRST:
+                fs = [_build_selector_function(s) for s in selector.selector]
+
+                def selector_function(formats):
+                    for f in fs:
+                        picked_formats = list(f(formats))
+                        if picked_formats:
+                            return picked_formats
+                    return []
+            elif selector.type == SINGLE:
+                format_spec = selector.selector
+
+                def selector_function(formats):
+                    formats = list(formats)
+                    if not formats:
+                        return
+                    if format_spec == 'all':
+                        for f in formats:
+                            yield f
+                    elif format_spec in ['best', 'worst', None]:
+                        format_idx = 0 if format_spec == 'worst' else -1
+                        audiovideo_formats = [
+                            f for f in formats
+                            if f.get('vcodec') != 'none' and f.get('acodec') != 'none']
+                        if audiovideo_formats:
+                            yield audiovideo_formats[format_idx]
+                        # for audio only (soundcloud) or video only (imgur) urls, select the best/worst audio format
+                        elif (all(f.get('acodec') != 'none' for f in formats) or
+                              all(f.get('vcodec') != 'none' for f in formats)):
+                            yield formats[format_idx]
+                    elif format_spec == 'bestaudio':
+                        audio_formats = [
+                            f for f in formats
+                            if f.get('vcodec') == 'none']
+                        if audio_formats:
+                            yield audio_formats[-1]
+                    elif format_spec == 'worstaudio':
+                        audio_formats = [
+                            f for f in formats
+                            if f.get('vcodec') == 'none']
+                        if audio_formats:
+                            yield audio_formats[0]
+                    elif format_spec == 'bestvideo':
+                        video_formats = [
+                            f for f in formats
+                            if f.get('acodec') == 'none']
+                        if video_formats:
+                            yield video_formats[-1]
+                    elif format_spec == 'worstvideo':
+                        video_formats = [
+                            f for f in formats
+                            if f.get('acodec') == 'none']
+                        if video_formats:
+                            yield video_formats[0]
+                    else:
+                        extensions = ['mp4', 'flv', 'webm', '3gp', 'm4a', 'mp3', 'ogg', 'aac', 'wav']
+                        if format_spec in extensions:
+                            filter_f = lambda f: f['ext'] == format_spec
+                        else:
+                            filter_f = lambda f: f['format_id'] == format_spec
+                        matches = list(filter(filter_f, formats))
+                        if matches:
+                            yield matches[-1]
+            elif selector.type == MERGE:
+                def _merge(formats_info):
+                    format_1, format_2 = [f['format_id'] for f in formats_info]
+                    # The first format must contain the video and the
+                    # second the audio
+                    if formats_info[0].get('vcodec') == 'none':
+                        self.report_error('The first format must '
+                                          'contain the video, try using '
+                                          '"-f %s+%s"' % (format_2, format_1))
+                        return
+                    output_ext = (
+                        formats_info[0]['ext']
+                        if self.params.get('merge_output_format') is None
+                        else self.params['merge_output_format'])
+                    return {
+                        'requested_formats': formats_info,
+                        'format': '%s+%s' % (formats_info[0].get('format'),
+                                             formats_info[1].get('format')),
+                        'format_id': '%s+%s' % (formats_info[0].get('format_id'),
+                                                formats_info[1].get('format_id')),
+                        'width': formats_info[0].get('width'),
+                        'height': formats_info[0].get('height'),
+                        'resolution': formats_info[0].get('resolution'),
+                        'fps': formats_info[0].get('fps'),
+                        'vcodec': formats_info[0].get('vcodec'),
+                        'vbr': formats_info[0].get('vbr'),
+                        'stretched_ratio': formats_info[0].get('stretched_ratio'),
+                        'acodec': formats_info[1].get('acodec'),
+                        'abr': formats_info[1].get('abr'),
+                        'ext': output_ext,
+                    }
+                video_selector, audio_selector = map(_build_selector_function, selector.selector)
+
+                def selector_function(formats):
+                    formats = list(formats)
+                    for pair in itertools.product(video_selector(formats), audio_selector(formats)):
+                        yield _merge(pair)
+
+            filters = [self._build_format_filter(f) for f in selector.filters]
+
+            def final_selector(formats):
+                for _filter in filters:
+                    formats = list(filter(_filter, formats))
+                return selector_function(formats)
+            return final_selector
+
+        stream = io.BytesIO(format_spec.encode('utf-8'))
+        try:
+            tokens = list(_remove_unused_ops(compat_tokenize_tokenize(stream.readline)))
+        except tokenize.TokenError:
+            raise syntax_error('Missing closing/opening brackets or parenthesis', (0, len(format_spec)))
+
+        class TokenIterator(object):
+            def __init__(self, tokens):
+                self.tokens = tokens
+                self.counter = 0
+
+            def __iter__(self):
+                return self
+
+            def __next__(self):
+                if self.counter >= len(self.tokens):
+                    raise StopIteration()
+                value = self.tokens[self.counter]
+                self.counter += 1
+                return value
+
+            next = __next__
+
+            def restore_last_token(self):
+                self.counter -= 1
+
+        parsed_selector = _parse_format_selection(iter(TokenIterator(tokens)))
+        return _build_selector_function(parsed_selector)
 
     def _calc_headers(self, info_dict):
         res = std_headers.copy()
@@ -988,7 +1207,7 @@ class YoutubeDL(object):
                 t.get('preference'), t.get('width'), t.get('height'),
                 t.get('id'), t.get('url')))
             for i, t in enumerate(thumbnails):
-                if 'width' in t and 'height' in t:
+                if t.get('width') and t.get('height'):
                     t['resolution'] = '%dx%d' % (t['width'], t['height'])
                 if t.get('id') is None:
                     t['id'] = '%d' % i
@@ -1000,13 +1219,13 @@ class YoutubeDL(object):
             info_dict['display_id'] = info_dict['id']
 
         if info_dict.get('upload_date') is None and info_dict.get('timestamp') is not None:
-            # Working around negative timestamps in Windows
-            # (see http://bugs.python.org/issue1646728)
-            if info_dict['timestamp'] < 0 and os.name == 'nt':
-                info_dict['timestamp'] = 0
-            upload_date = datetime.datetime.utcfromtimestamp(
-                info_dict['timestamp'])
-            info_dict['upload_date'] = upload_date.strftime('%Y%m%d')
+            # Working around out-of-range timestamp values (e.g. negative ones on Windows,
+            # see http://bugs.python.org/issue1646728)
+            try:
+                upload_date = datetime.datetime.utcfromtimestamp(info_dict['timestamp'])
+                info_dict['upload_date'] = upload_date.strftime('%Y%m%d')
+            except (ValueError, OverflowError, OSError):
+                pass
 
         if self.params.get('listsubtitles', False):
             if 'automatic_captions' in info_dict:
@@ -1017,12 +1236,6 @@ class YoutubeDL(object):
             info_dict['id'], info_dict.get('subtitles'),
             info_dict.get('automatic_captions'))
 
-        # This extractors handle format selection themselves
-        if info_dict['extractor'] in ['Youku']:
-            if download:
-                self.process_info(info_dict)
-            return info_dict
-
         # We now pick which formats have to be downloaded
         if info_dict.get('formats') is None:
             # There's only one format available
@@ -1033,6 +1246,8 @@ class YoutubeDL(object):
         if not formats:
             raise ExtractorError('No video formats found!')
 
+        formats_dict = {}
+
         # We check that all the formats have the format and format_id fields
         for i, format in enumerate(formats):
             if 'url' not in format:
@@ -1040,6 +1255,18 @@ class YoutubeDL(object):
 
             if format.get('format_id') is None:
                 format['format_id'] = compat_str(i)
+            format_id = format['format_id']
+            if format_id not in formats_dict:
+                formats_dict[format_id] = []
+            formats_dict[format_id].append(format)
+
+        # Make sure all formats have unique format_id
+        for format_id, ambiguous_formats in formats_dict.items():
+            if len(ambiguous_formats) > 1:
+                for i, format in enumerate(ambiguous_formats):
+                    format['format_id'] = '%s-%d' % (format_id, i)
+
+        for i, format in enumerate(formats):
             if format.get('format') is None:
                 format['format'] = '{id} - {res}{note}'.format(
                     id=format['format_id'],
@@ -1055,12 +1282,6 @@ class YoutubeDL(object):
             full_format_info.update(format)
             format['http_headers'] = self._calc_headers(full_format_info)
 
-        format_limit = self.params.get('format_limit', None)
-        if format_limit:
-            formats = list(takewhile_inclusive(
-                lambda f: f['format_id'] != format_limit, formats
-            ))
-
         # TODO Central sorting goes here
 
         if formats[0] is not info_dict:
@@ -1078,58 +1299,17 @@ class YoutubeDL(object):
 
         req_format = self.params.get('format')
         if req_format is None:
-            req_format = 'best'
-        formats_to_download = []
-        # The -1 is for supporting YoutubeIE
-        if req_format in ('-1', 'all'):
-            formats_to_download = formats
-        else:
-            for rfstr in req_format.split(','):
-                # We can accept formats requested in the format: 34/5/best, we pick
-                # the first that is available, starting from left
-                req_formats = rfstr.split('/')
-                for rf in req_formats:
-                    if re.match(r'.+?\+.+?', rf) is not None:
-                        # Two formats have been requested like '137+139'
-                        format_1, format_2 = rf.split('+')
-                        formats_info = (self.select_format(format_1, formats),
-                                        self.select_format(format_2, formats))
-                        if all(formats_info):
-                            # The first format must contain the video and the
-                            # second the audio
-                            if formats_info[0].get('vcodec') == 'none':
-                                self.report_error('The first format must '
-                                                  'contain the video, try using '
-                                                  '"-f %s+%s"' % (format_2, format_1))
-                                return
-                            output_ext = (
-                                formats_info[0]['ext']
-                                if self.params.get('merge_output_format') is None
-                                else self.params['merge_output_format'])
-                            selected_format = {
-                                'requested_formats': formats_info,
-                                'format': '%s+%s' % (formats_info[0].get('format'),
-                                                     formats_info[1].get('format')),
-                                'format_id': '%s+%s' % (formats_info[0].get('format_id'),
-                                                        formats_info[1].get('format_id')),
-                                'width': formats_info[0].get('width'),
-                                'height': formats_info[0].get('height'),
-                                'resolution': formats_info[0].get('resolution'),
-                                'fps': formats_info[0].get('fps'),
-                                'vcodec': formats_info[0].get('vcodec'),
-                                'vbr': formats_info[0].get('vbr'),
-                                'stretched_ratio': formats_info[0].get('stretched_ratio'),
-                                'acodec': formats_info[1].get('acodec'),
-                                'abr': formats_info[1].get('abr'),
-                                'ext': output_ext,
-                            }
-                        else:
-                            selected_format = None
-                    else:
-                        selected_format = self.select_format(rf, formats)
-                    if selected_format is not None:
-                        formats_to_download.append(selected_format)
-                        break
+            req_format_list = []
+            if (self.params.get('outtmpl', DEFAULT_OUTTMPL) != '-' and
+                    info_dict['extractor'] in ['youtube', 'ted'] and
+                    not info_dict.get('is_live')):
+                merger = FFmpegMergerPP(self)
+                if merger.available and merger.can_merge():
+                    req_format_list.append('bestvideo+bestaudio')
+            req_format_list.append('best')
+            req_format = '/'.join(req_format_list)
+        format_selector = self.build_format_selector(req_format)
+        formats_to_download = list(format_selector(formats))
         if not formats_to_download:
             raise ExtractorError('requested format not available',
                                  expected=True)
@@ -1208,9 +1388,6 @@ class YoutubeDL(object):
         if len(info_dict['title']) > 200:
             info_dict['title'] = info_dict['title'][:197] + '...'
 
-        # Keep for backwards compatibility
-        info_dict['stitle'] = info_dict['title']
-
         if 'format' not in info_dict:
             info_dict['format'] = info_dict['ext']
 
@@ -1256,7 +1433,7 @@ class YoutubeDL(object):
             return
 
         try:
-            dn = os.path.dirname(encodeFilename(filename))
+            dn = os.path.dirname(sanitize_path(encodeFilename(filename)))
             if dn and not os.path.exists(dn):
                 os.makedirs(dn)
         except (OSError, IOError) as err:
@@ -1264,7 +1441,7 @@ class YoutubeDL(object):
             return
 
         if self.params.get('writedescription', False):
-            descfn = filename + '.description'
+            descfn = replace_extension(filename, 'description', info_dict.get('ext'))
             if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(descfn)):
                 self.to_screen('[info] Video description is already present')
             elif info_dict.get('description') is None:
@@ -1279,7 +1456,7 @@ class YoutubeDL(object):
                     return
 
         if self.params.get('writeannotations', False):
-            annofn = filename + '.annotations.xml'
+            annofn = replace_extension(filename, 'annotations.xml', info_dict.get('ext'))
             if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(annofn)):
                 self.to_screen('[info] Video annotations are already present')
             else:
@@ -1300,17 +1477,18 @@ class YoutubeDL(object):
             # subtitles download errors are already managed as troubles in relevant IE
             # that way it will silently go on when used with unsupporting IE
             subtitles = info_dict['requested_subtitles']
+            ie = self.get_info_extractor(info_dict['extractor_key'])
             for sub_lang, sub_info in subtitles.items():
                 sub_format = sub_info['ext']
                 if sub_info.get('data') is not None:
                     sub_data = sub_info['data']
                 else:
                     try:
-                        uf = self.urlopen(sub_info['url'])
-                        sub_data = uf.read().decode('utf-8')
-                    except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+                        sub_data = ie._download_webpage(
+                            sub_info['url'], info_dict['id'], note=False)
+                    except ExtractorError as err:
                         self.report_warning('Unable to download subtitle for "%s": %s' %
-                                            (sub_lang, compat_str(err)))
+                                            (sub_lang, compat_str(err.cause)))
                         continue
                 try:
                     sub_filename = subtitles_filename(filename, sub_lang, sub_format)
@@ -1325,13 +1503,13 @@ class YoutubeDL(object):
                     return
 
         if self.params.get('writeinfojson', False):
-            infofn = os.path.splitext(filename)[0] + '.info.json'
+            infofn = replace_extension(filename, 'info.json', info_dict.get('ext'))
             if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(infofn)):
                 self.to_screen('[info] Video description metadata is already present')
             else:
                 self.to_screen('[info] Writing video description metadata as JSON to: ' + infofn)
                 try:
-                    write_json_file(info_dict, infofn)
+                    write_json_file(self.filter_requested_info(info_dict), infofn)
                 except (OSError, IOError):
                     self.report_error('Cannot write metadata to JSON file ' + infofn)
                     return
@@ -1351,24 +1529,57 @@ class YoutubeDL(object):
                 if info_dict.get('requested_formats') is not None:
                     downloaded = []
                     success = True
-                    merger = FFmpegMergerPP(self, not self.params.get('keepvideo'))
+                    merger = FFmpegMergerPP(self)
                     if not merger.available:
                         postprocessors = []
                         self.report_warning('You have requested multiple '
                                             'formats but ffmpeg or avconv are not installed.'
-                                            ' The formats won\'t be merged')
+                                            ' The formats won\'t be merged.')
                     else:
                         postprocessors = [merger]
-                    for f in info_dict['requested_formats']:
-                        new_info = dict(info_dict)
-                        new_info.update(f)
-                        fname = self.prepare_filename(new_info)
-                        fname = prepend_extension(fname, 'f%s' % f['format_id'])
-                        downloaded.append(fname)
-                        partial_success = dl(fname, new_info)
-                        success = success and partial_success
-                    info_dict['__postprocessors'] = postprocessors
-                    info_dict['__files_to_merge'] = downloaded
+
+                    def compatible_formats(formats):
+                        video, audio = formats
+                        # Check extension
+                        video_ext, audio_ext = audio.get('ext'), video.get('ext')
+                        if video_ext and audio_ext:
+                            COMPATIBLE_EXTS = (
+                                ('mp3', 'mp4', 'm4a', 'm4p', 'm4b', 'm4r', 'm4v'),
+                                ('webm')
+                            )
+                            for exts in COMPATIBLE_EXTS:
+                                if video_ext in exts and audio_ext in exts:
+                                    return True
+                        # TODO: Check acodec/vcodec
+                        return False
+
+                    filename_real_ext = os.path.splitext(filename)[1][1:]
+                    filename_wo_ext = (
+                        os.path.splitext(filename)[0]
+                        if filename_real_ext == info_dict['ext']
+                        else filename)
+                    requested_formats = info_dict['requested_formats']
+                    if self.params.get('merge_output_format') is None and not compatible_formats(requested_formats):
+                        info_dict['ext'] = 'mkv'
+                        self.report_warning(
+                            'Requested formats are incompatible for merge and will be merged into mkv.')
+                    # Ensure filename always has a correct extension for successful merge
+                    filename = '%s.%s' % (filename_wo_ext, info_dict['ext'])
+                    if os.path.exists(encodeFilename(filename)):
+                        self.to_screen(
+                            '[download] %s has already been downloaded and '
+                            'merged' % filename)
+                    else:
+                        for f in requested_formats:
+                            new_info = dict(info_dict)
+                            new_info.update(f)
+                            fname = self.prepare_filename(new_info)
+                            fname = prepend_extension(fname, 'f%s' % f['format_id'], new_info['ext'])
+                            downloaded.append(fname)
+                            partial_success = dl(fname, new_info)
+                            success = success and partial_success
+                        info_dict['__postprocessors'] = postprocessors
+                        info_dict['__files_to_merge'] = downloaded
                 else:
                     # Just a single file
                     success = dl(filename, info_dict)
@@ -1438,7 +1649,8 @@ class YoutubeDL(object):
         for url in url_list:
             try:
                 # It also downloads the videos
-                res = self.extract_info(url)
+                res = self.extract_info(
+                    url, force_generic_extractor=self.params.get('force_generic_extractor', False))
             except UnavailableVideoError:
                 self.report_error('unable to download video')
             except MaxDownloadsReached:
@@ -1451,8 +1663,11 @@ class YoutubeDL(object):
         return self._download_retcode
 
     def download_with_info_file(self, info_filename):
-        with io.open(info_filename, 'r', encoding='utf-8') as f:
-            info = json.load(f)
+        with contextlib.closing(fileinput.FileInput(
+                [info_filename], mode='r',
+                openhook=fileinput.hook_encoded('utf-8'))) as f:
+            # FileInput doesn't have a read method, we can't call json.load
+            info = self.filter_requested_info(json.loads('\n'.join(f)))
         try:
             self.process_ie_result(info, download=True)
         except DownloadError:
@@ -1464,6 +1679,12 @@ class YoutubeDL(object):
                 raise
         return self._download_retcode
 
+    @staticmethod
+    def filter_requested_info(info_dict):
+        return dict(
+            (k, v) for k, v in info_dict.items()
+            if k not in ['requested_formats', 'requested_subtitles'])
+
     def post_process(self, filename, ie_info):
         """Run all the postprocessors on the given file."""
         info = dict(ie_info)
@@ -1473,24 +1694,18 @@ class YoutubeDL(object):
             pps_chain.extend(ie_info['__postprocessors'])
         pps_chain.extend(self._pps)
         for pp in pps_chain:
-            keep_video = None
-            old_filename = info['filepath']
+            files_to_delete = []
             try:
-                keep_video_wish, info = pp.run(info)
-                if keep_video_wish is not None:
-                    if keep_video_wish:
-                        keep_video = keep_video_wish
-                    elif keep_video is None:
-                        # No clear decision yet, let IE decide
-                        keep_video = keep_video_wish
+                files_to_delete, info = pp.run(info)
             except PostProcessingError as e:
                 self.report_error(e.msg)
-            if keep_video is False and not self.params.get('keepvideo', False):
-                try:
+            if files_to_delete and not self.params.get('keepvideo', False):
+                for old_filename in files_to_delete:
                     self.to_screen('Deleting original file %s (pass -k to keep)' % old_filename)
-                    os.remove(encodeFilename(old_filename))
-                except (IOError, OSError):
-                    self.report_warning('Unable to remove downloaded video file')
+                    try:
+                        os.remove(encodeFilename(old_filename))
+                    except (IOError, OSError):
+                        self.report_warning('Unable to remove downloaded original file')
 
     def _make_archive_id(self, info_dict):
         # Future-proof against any change in case
@@ -1642,26 +1857,6 @@ class YoutubeDL(object):
 
     def urlopen(self, req):
         """ Start an HTTP download """
-
-        # According to RFC 3986, URLs can not contain non-ASCII characters, however this is not
-        # always respected by websites, some tend to give out URLs with non percent-encoded
-        # non-ASCII characters (see telemb.py, ard.py [#3412])
-        # urllib chokes on URLs with non-ASCII characters (see http://bugs.python.org/issue3991)
-        # To work around aforementioned issue we will replace request's original URL with
-        # percent-encoded one
-        req_is_string = isinstance(req, compat_basestring)
-        url = req if req_is_string else req.get_full_url()
-        url_escaped = escape_url(url)
-
-        # Substitute URL if any change after escaping
-        if url != url_escaped:
-            if req_is_string:
-                req = url_escaped
-            else:
-                req = compat_urllib_request.Request(
-                    url_escaped, data=req.data, headers=req.headers,
-                    origin_req_host=req.origin_req_host, unverifiable=req.unverifiable)
-
         return self._opener.open(req, timeout=self._socket_timeout)
 
     def print_debug_header(self):
@@ -1693,10 +1888,10 @@ class YoutubeDL(object):
             out = out.decode().strip()
             if re.match('[0-9a-f]+', out):
                 self._write_string('[debug] Git HEAD: ' + out + '\n')
-        except:
+        except Exception:
             try:
                 sys.exc_clear()
-            except:
+            except Exception:
                 pass
         self._write_string('[debug] Python version %s - %s\n' % (
             platform.python_version(), platform_name()))
@@ -1756,13 +1951,14 @@ class YoutubeDL(object):
             # Set HTTPS proxy to HTTP one if given (https://github.com/rg3/youtube-dl/issues/805)
             if 'http' in proxies and 'https' not in proxies:
                 proxies['https'] = proxies['http']
-        proxy_handler = compat_urllib_request.ProxyHandler(proxies)
+        proxy_handler = PerRequestProxyHandler(proxies)
 
         debuglevel = 1 if self.params.get('debug_printtraffic') else 0
         https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel)
         ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel)
         opener = compat_urllib_request.build_opener(
-            https_handler, proxy_handler, cookie_processor, ydlh)
+            proxy_handler, https_handler, cookie_processor, ydlh)
+
         # Delete the default user-agent header, which would otherwise apply in
         # cases where our custom HTTP handler doesn't come into play
         # (See https://github.com/rg3/youtube-dl/issues/1309 for details)
@@ -1803,7 +1999,7 @@ class YoutubeDL(object):
             thumb_ext = determine_ext(t['url'], 'jpg')
             suffix = '_%s' % t['id'] if len(thumbnails) > 1 else ''
             thumb_display_id = '%s ' % t['id'] if len(thumbnails) > 1 else ''
-            thumb_filename = os.path.splitext(filename)[0] + suffix + '.' + thumb_ext
+            t['filename'] = thumb_filename = os.path.splitext(filename)[0] + suffix + '.' + thumb_ext
 
             if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)):
                 self.to_screen('[%s] %s: Thumbnail %sis already present' %

youtube_dl/__init__.py

@@ -9,6 +9,7 @@ import codecs
 import io
 import os
 import random
+import shlex
 import sys
 
 
@@ -168,8 +169,11 @@ def _real_main(argv=None):
         if not opts.audioquality.isdigit():
             parser.error('invalid audio quality specified')
     if opts.recodevideo is not None:
-        if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']:
+        if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv', 'avi']:
             parser.error('invalid video recode format specified')
+    if opts.convertsubtitles is not None:
+        if opts.convertsubtitles not in ['srt', 'vtt', 'ass']:
+            parser.error('invalid subtitle format specified')
 
     if opts.date is not None:
         date = DateRange.day(opts.date)
@@ -185,10 +189,6 @@ def _real_main(argv=None):
     if opts.allsubtitles and not opts.writeautomaticsub:
         opts.writesubtitles = True
 
-    if sys.version_info < (3,):
-        # In Python 2, sys.argv is a bytestring (also note http://bugs.python.org/issue2128 for Windows systems)
-        if opts.outtmpl is not None:
-            opts.outtmpl = opts.outtmpl.decode(preferredencoding())
     outtmpl = ((opts.outtmpl is not None and opts.outtmpl) or
                (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s') or
                (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s') or
@@ -209,6 +209,11 @@ def _real_main(argv=None):
     # PostProcessors
     postprocessors = []
     # Add the metadata pp first, the other pps will copy it
+    if opts.metafromtitle:
+        postprocessors.append({
+            'key': 'MetadataFromTitle',
+            'titleformat': opts.metafromtitle
+        })
     if opts.addmetadata:
         postprocessors.append({'key': 'FFmpegMetadata'})
     if opts.extractaudio:
@@ -223,6 +228,11 @@ def _real_main(argv=None):
             'key': 'FFmpegVideoConvertor',
             'preferedformat': opts.recodevideo,
         })
+    if opts.convertsubtitles:
+        postprocessors.append({
+            'key': 'FFmpegSubtitlesConvertor',
+            'format': opts.convertsubtitles,
+        })
     if opts.embedsubtitles:
         postprocessors.append({
             'key': 'FFmpegEmbedSubtitle',
@@ -230,15 +240,18 @@ def _real_main(argv=None):
     if opts.xattrs:
         postprocessors.append({'key': 'XAttrMetadata'})
     if opts.embedthumbnail:
-        if not opts.addmetadata:
-            postprocessors.append({'key': 'FFmpegAudioFix'})
-        postprocessors.append({'key': 'AtomicParsley'})
+        already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
+        postprocessors.append({
+            'key': 'EmbedThumbnail',
+            'already_have_thumbnail': already_have_thumbnail
+        })
+        if not already_have_thumbnail:
+            opts.writethumbnail = True
     # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
     # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
     if opts.exec_cmd:
         postprocessors.append({
             'key': 'ExecAfterDownload',
-            'verboseOutput': opts.verbose,
             'exec_cmd': opts.exec_cmd,
         })
     if opts.xattr_set_filesize:
@@ -247,6 +260,12 @@ def _real_main(argv=None):
             xattr  # Confuse flake8
         except ImportError:
             parser.error('setting filesize xattr requested but python-xattr is not available')
+    external_downloader_args = None
+    if opts.external_downloader_args:
+        external_downloader_args = shlex.split(opts.external_downloader_args)
+    postprocessor_args = None
+    if opts.postprocessor_args:
+        postprocessor_args = shlex.split(opts.postprocessor_args)
     match_filter = (
         None if opts.match_filter is None
         else match_filter_func(opts.match_filter))
@@ -272,12 +291,12 @@ def _real_main(argv=None):
         'simulate': opts.simulate or any_getting,
         'skip_download': opts.skip_download,
         'format': opts.format,
-        'format_limit': opts.format_limit,
         'listformats': opts.listformats,
         'outtmpl': outtmpl,
         'autonumber_size': opts.autonumber_size,
         'restrictfilenames': opts.restrictfilenames,
         'ignoreerrors': opts.ignoreerrors,
+        'force_generic_extractor': opts.force_generic_extractor,
         'ratelimit': opts.ratelimit,
         'nooverwrites': opts.nooverwrites,
         'retries': opts_retries,
@@ -335,7 +354,6 @@ def _real_main(argv=None):
         'default_search': opts.default_search,
         'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
         'encoding': opts.encoding,
-        'exec_cmd': opts.exec_cmd,
         'extract_flat': opts.extract_flat,
         'merge_output_format': opts.merge_output_format,
         'postprocessors': postprocessors,
@@ -351,6 +369,9 @@ def _real_main(argv=None):
         'no_color': opts.no_color,
         'ffmpeg_location': opts.ffmpeg_location,
         'hls_prefer_native': opts.hls_prefer_native,
+        'external_downloader_args': external_downloader_args,
+        'postprocessor_args': postprocessor_args,
+        'cn_verification_proxy': opts.cn_verification_proxy,
     }
 
     with YoutubeDL(ydl_opts) as ydl:

youtube_dl/aes.py

@@ -152,7 +152,7 @@ def aes_decrypt_text(data, password, key_size_bytes):
     """
     NONCE_LENGTH_BYTES = 8
 
-    data = bytes_to_intlist(base64.b64decode(data))
+    data = bytes_to_intlist(base64.b64decode(data.encode('utf-8')))
     password = bytes_to_intlist(password.encode('utf-8'))
 
     key = password[:key_size_bytes] + [0] * (key_size_bytes - len(password))

youtube_dl/compat.py

@@ -1,12 +1,15 @@
 from __future__ import unicode_literals
 
+import collections
 import getpass
 import optparse
 import os
 import re
+import shutil
 import socket
 import subprocess
 import sys
+import itertools
 
 
 try:
@@ -39,16 +42,16 @@ try:
 except ImportError:  # Python 2
     import cookielib as compat_cookiejar
 
+try:
+    import http.cookies as compat_cookies
+except ImportError:  # Python 2
+    import Cookie as compat_cookies
+
 try:
     import html.entities as compat_html_entities
 except ImportError:  # Python 2
     import htmlentitydefs as compat_html_entities
 
-try:
-    import html.parser as compat_html_parser
-except ImportError:  # Python 2
-    import HTMLParser as compat_html_parser
-
 try:
     import http.client as compat_http_client
 except ImportError:  # Python 2
@@ -77,42 +80,74 @@ except ImportError:
     import BaseHTTPServer as compat_http_server
 
 try:
+    from urllib.parse import unquote_to_bytes as compat_urllib_parse_unquote_to_bytes
     from urllib.parse import unquote as compat_urllib_parse_unquote
-except ImportError:
-    def compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'):
-        if string == '':
+    from urllib.parse import unquote_plus as compat_urllib_parse_unquote_plus
+except ImportError:  # Python 2
+    _asciire = (compat_urllib_parse._asciire if hasattr(compat_urllib_parse, '_asciire')
+                else re.compile('([\x00-\x7f]+)'))
+
+    # HACK: The following are the correct unquote_to_bytes, unquote and unquote_plus
+    # implementations from cpython 3.4.3's stdlib. Python 2's version
+    # is apparently broken (see https://github.com/rg3/youtube-dl/pull/6244)
+
+    def compat_urllib_parse_unquote_to_bytes(string):
+        """unquote_to_bytes('abc%20def') -> b'abc def'."""
+        # Note: strings are encoded as UTF-8. This is only an issue if it contains
+        # unescaped non-ASCII characters, which URIs should not.
+        if not string:
+            # Is it a string-like object?
+            string.split
+            return b''
+        if isinstance(string, unicode):
+            string = string.encode('utf-8')
+        bits = string.split(b'%')
+        if len(bits) == 1:
             return string
-        res = string.split('%')
-        if len(res) == 1:
+        res = [bits[0]]
+        append = res.append
+        for item in bits[1:]:
+            try:
+                append(compat_urllib_parse._hextochr[item[:2]])
+                append(item[2:])
+            except KeyError:
+                append(b'%')
+                append(item)
+        return b''.join(res)
+
+    def compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'):
+        """Replace %xx escapes by their single-character equivalent. The optional
+        encoding and errors parameters specify how to decode percent-encoded
+        sequences into Unicode characters, as accepted by the bytes.decode()
+        method.
+        By default, percent-encoded sequences are decoded with UTF-8, and invalid
+        sequences are replaced by a placeholder character.
+
+        unquote('abc%20def') -> 'abc def'.
+        """
+        if '%' not in string:
+            string.split
             return string
         if encoding is None:
             encoding = 'utf-8'
         if errors is None:
             errors = 'replace'
-        # pct_sequence: contiguous sequence of percent-encoded bytes, decoded
-        pct_sequence = b''
-        string = res[0]
-        for item in res[1:]:
-            try:
-                if not item:
-                    raise ValueError
-                pct_sequence += item[:2].decode('hex')
-                rest = item[2:]
-                if not rest:
-                    # This segment was just a single percent-encoded character.
-                    # May be part of a sequence of code units, so delay decoding.
-                    # (Stored in pct_sequence).
-                    continue
-            except ValueError:
-                rest = '%' + item
-            # Encountered non-percent-encoded characters. Flush the current
-            # pct_sequence.
-            string += pct_sequence.decode(encoding, errors) + rest
-            pct_sequence = b''
-        if pct_sequence:
-            # Flush the final pct_sequence
-            string += pct_sequence.decode(encoding, errors)
-        return string
+        bits = _asciire.split(string)
+        res = [bits[0]]
+        append = res.append
+        for i in range(1, len(bits), 2):
+            append(compat_urllib_parse_unquote_to_bytes(bits[i]).decode(encoding, errors))
+            append(bits[i + 1])
+        return ''.join(res)
+
+    def compat_urllib_parse_unquote_plus(string, encoding='utf-8', errors='replace'):
+        """Like unquote(), but also replace plus signs by spaces, as required for
+        unquoting HTML form values.
+
+        unquote_plus('%7e/abc+def') -> '~/abc def'
+        """
+        string = string.replace('+', ' ')
+        return compat_urllib_parse_unquote(string, encoding, errors)
 
 try:
     compat_str = unicode  # Python 2
@@ -364,19 +399,62 @@ def workaround_optparse_bug9161():
             return real_add_option(self, *bargs, **bkwargs)
         optparse.OptionGroup.add_option = _compat_add_option
 
+if hasattr(shutil, 'get_terminal_size'):  # Python >= 3.3
+    compat_get_terminal_size = shutil.get_terminal_size
+else:
+    _terminal_size = collections.namedtuple('terminal_size', ['columns', 'lines'])
+
+    def compat_get_terminal_size():
+        columns = compat_getenv('COLUMNS', None)
+        if columns:
+            columns = int(columns)
+        else:
+            columns = None
+        lines = compat_getenv('LINES', None)
+        if lines:
+            lines = int(lines)
+        else:
+            lines = None
+
+        try:
+            sp = subprocess.Popen(
+                ['stty', 'size'],
+                stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+            out, err = sp.communicate()
+            lines, columns = map(int, out.split())
+        except Exception:
+            pass
+        return _terminal_size(columns, lines)
+
+try:
+    itertools.count(start=0, step=1)
+    compat_itertools_count = itertools.count
+except TypeError:  # Python 2.6
+    def compat_itertools_count(start=0, step=1):
+        n = start
+        while True:
+            yield n
+            n += step
+
+if sys.version_info >= (3, 0):
+    from tokenize import tokenize as compat_tokenize_tokenize
+else:
+    from tokenize import generate_tokens as compat_tokenize_tokenize
 
 __all__ = [
     'compat_HTTPError',
     'compat_basestring',
     'compat_chr',
     'compat_cookiejar',
+    'compat_cookies',
     'compat_expanduser',
+    'compat_get_terminal_size',
     'compat_getenv',
     'compat_getpass',
     'compat_html_entities',
-    'compat_html_parser',
     'compat_http_client',
     'compat_http_server',
+    'compat_itertools_count',
     'compat_kwargs',
     'compat_ord',
     'compat_parse_qs',
@@ -384,9 +462,12 @@ __all__ = [
     'compat_socket_create_connection',
     'compat_str',
     'compat_subprocess_get_DEVNULL',
+    'compat_tokenize_tokenize',
     'compat_urllib_error',
     'compat_urllib_parse',
     'compat_urllib_parse_unquote',
+    'compat_urllib_parse_unquote_plus',
+    'compat_urllib_parse_unquote_to_bytes',
     'compat_urllib_parse_urlparse',
     'compat_urllib_request',
     'compat_urlparse',

youtube_dl/downloader/__init__.py

@@ -6,8 +6,9 @@ from .f4m import F4mFD
 from .hls import HlsFD
 from .hls import NativeHlsFD
 from .http import HttpFD
-from .mplayer import MplayerFD
+from .rtsp import RtspFD
 from .rtmp import RtmpFD
+from .dash import DashSegmentsFD
 
 from ..utils import (
     determine_protocol,
@@ -17,9 +18,10 @@ PROTOCOL_MAP = {
     'rtmp': RtmpFD,
     'm3u8_native': NativeHlsFD,
     'm3u8': HlsFD,
-    'mms': MplayerFD,
-    'rtsp': MplayerFD,
+    'mms': RtspFD,
+    'rtsp': RtspFD,
     'f4m': F4mFD,
+    'http_dash_segments': DashSegmentsFD,
 }
 
 

youtube_dl/downloader/common.py

@@ -8,6 +8,7 @@ import time
 from ..compat import compat_str
 from ..utils import (
     encodeFilename,
+    decodeArgument,
     format_bytes,
     timeconvert,
 )
@@ -42,6 +43,8 @@ class FileDownloader(object):
     max_filesize:       Skip files larger than this size
     xattr_set_filesize: Set ytdl.filesize user xattribute with expected size.
                         (experimenatal)
+    external_downloader_args:  A list of additional command-line arguments for the
+                        external downloader.
 
     Subclasses of this one must re-define the real_download method.
     """
@@ -202,7 +205,7 @@ class FileDownloader(object):
             return
         try:
             os.utime(filename, (time.time(), filetime))
-        except:
+        except Exception:
             pass
         return filetime
 
@@ -316,7 +319,7 @@ class FileDownloader(object):
         )
 
         continuedl_and_exists = (
-            self.params.get('continuedl', False) and
+            self.params.get('continuedl', True) and
             os.path.isfile(encodeFilename(filename)) and
             not self.params.get('nopart', False)
         )
@@ -351,19 +354,15 @@ class FileDownloader(object):
         # this interface
         self._progress_hooks.append(ph)
 
-    def _debug_cmd(self, args, subprocess_encoding, exe=None):
+    def _debug_cmd(self, args, exe=None):
         if not self.params.get('verbose', False):
             return
 
-        if exe is None:
-            exe = os.path.basename(args[0])
+        str_args = [decodeArgument(a) for a in args]
+
+        if exe is None:
+            exe = os.path.basename(str_args[0])
 
-        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))

youtube_dl/downloader/dash.py

@@ -0,0 +1,66 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import FileDownloader
+from ..compat import compat_urllib_request
+
+
+class DashSegmentsFD(FileDownloader):
+    """
+    Download segments in a DASH manifest
+    """
+    def real_download(self, filename, info_dict):
+        self.report_destination(filename)
+        tmpfilename = self.temp_name(filename)
+        base_url = info_dict['url']
+        segment_urls = info_dict['segment_urls']
+
+        is_test = self.params.get('test', False)
+        remaining_bytes = self._TEST_FILE_SIZE if is_test else None
+        byte_counter = 0
+
+        def append_url_to_file(outf, target_url, target_name, remaining_bytes=None):
+            self.to_screen('[DashSegments] %s: Downloading %s' % (info_dict['id'], target_name))
+            req = compat_urllib_request.Request(target_url)
+            if remaining_bytes is not None:
+                req.add_header('Range', 'bytes=0-%d' % (remaining_bytes - 1))
+
+            data = self.ydl.urlopen(req).read()
+
+            if remaining_bytes is not None:
+                data = data[:remaining_bytes]
+
+            outf.write(data)
+            return len(data)
+
+        def combine_url(base_url, target_url):
+            if re.match(r'^https?://', target_url):
+                return target_url
+            return '%s%s%s' % (base_url, '' if base_url.endswith('/') else '/', target_url)
+
+        with open(tmpfilename, 'wb') as outf:
+            append_url_to_file(
+                outf, combine_url(base_url, info_dict['initialization_url']),
+                'initialization segment')
+            for i, segment_url in enumerate(segment_urls):
+                segment_len = append_url_to_file(
+                    outf, combine_url(base_url, segment_url),
+                    'segment %d / %d' % (i + 1, len(segment_urls)),
+                    remaining_bytes)
+                byte_counter += segment_len
+                if remaining_bytes is not None:
+                    remaining_bytes -= segment_len
+                    if remaining_bytes <= 0:
+                        break
+
+        self.try_rename(tmpfilename, filename)
+
+        self._hook_progress({
+            'downloaded_bytes': byte_counter,
+            'total_bytes': byte_counter,
+            'filename': filename,
+            'status': 'finished',
+        })
+
+        return True

youtube_dl/downloader/external.py

@@ -2,11 +2,11 @@ from __future__ import unicode_literals
 
 import os.path
 import subprocess
-import sys
 
 from .common import FileDownloader
 from ..utils import (
     encodeFilename,
+    encodeArgument,
 )
 
 
@@ -45,25 +45,26 @@ class ExternalFD(FileDownloader):
     def supports(cls, info_dict):
         return info_dict['protocol'] in ('http', 'https', 'ftp', 'ftps')
 
-    def _source_address(self, command_option):
-        source_address = self.params.get('source_address')
-        if source_address is None:
+    def _option(self, command_option, param):
+        param = self.params.get(param)
+        if param is None:
             return []
-        return [command_option, source_address]
+        if isinstance(param, bool):
+            return [command_option]
+        return [command_option, param]
+
+    def _configuration_args(self, default=[]):
+        ex_args = self.params.get('external_downloader_args')
+        if ex_args is None:
+            return default
+        assert isinstance(ex_args, list)
+        return ex_args
 
     def _call_downloader(self, tmpfilename, info_dict):
         """ Either overwrite this or implement _make_cmd """
-        cmd = self._make_cmd(tmpfilename, info_dict)
+        cmd = [encodeArgument(a) for a in self._make_cmd(tmpfilename, info_dict)]
 
-        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()
-            cmd = [a.encode(subprocess_encoding, 'ignore') for a in cmd]
-        else:
-            subprocess_encoding = None
-        self._debug_cmd(cmd, subprocess_encoding)
+        self._debug_cmd(cmd)
 
         p = subprocess.Popen(
             cmd, stderr=subprocess.PIPE)
@@ -78,7 +79,18 @@ class CurlFD(ExternalFD):
         cmd = [self.exe, '--location', '-o', tmpfilename]
         for key, val in info_dict['http_headers'].items():
             cmd += ['--header', '%s: %s' % (key, val)]
-        cmd += self._source_address('--interface')
+        cmd += self._option('--interface', 'source_address')
+        cmd += self._configuration_args()
+        cmd += ['--', info_dict['url']]
+        return cmd
+
+
+class AxelFD(ExternalFD):
+    def _make_cmd(self, tmpfilename, info_dict):
+        cmd = [self.exe, '-o', tmpfilename]
+        for key, val in info_dict['http_headers'].items():
+            cmd += ['-H', '%s: %s' % (key, val)]
+        cmd += self._configuration_args()
         cmd += ['--', info_dict['url']]
         return cmd
 
@@ -88,26 +100,38 @@ class WgetFD(ExternalFD):
         cmd = [self.exe, '-O', tmpfilename, '-nv', '--no-cookies']
         for key, val in info_dict['http_headers'].items():
             cmd += ['--header', '%s: %s' % (key, val)]
-        cmd += self._source_address('--bind-address')
+        cmd += self._option('--bind-address', 'source_address')
+        cmd += self._option('--proxy', 'proxy')
+        cmd += self._option('--no-check-certificate', 'nocheckcertificate')
+        cmd += self._configuration_args()
         cmd += ['--', info_dict['url']]
         return cmd
 
 
 class Aria2cFD(ExternalFD):
     def _make_cmd(self, tmpfilename, info_dict):
-        cmd = [
-            self.exe, '-c',
-            '--min-split-size', '1M', '--max-connection-per-server', '4']
+        cmd = [self.exe, '-c']
+        cmd += self._configuration_args([
+            '--min-split-size', '1M', '--max-connection-per-server', '4'])
         dn = os.path.dirname(tmpfilename)
         if dn:
             cmd += ['--dir', dn]
         cmd += ['--out', os.path.basename(tmpfilename)]
         for key, val in info_dict['http_headers'].items():
             cmd += ['--header', '%s: %s' % (key, val)]
-        cmd += self._source_address('--interface')
+        cmd += self._option('--interface', 'source_address')
+        cmd += self._option('--all-proxy', 'proxy')
         cmd += ['--', info_dict['url']]
         return cmd
 
+
+class HttpieFD(ExternalFD):
+    def _make_cmd(self, tmpfilename, info_dict):
+        cmd = ['http', '--download', '--output', tmpfilename, info_dict['url']]
+        for key, val in info_dict['http_headers'].items():
+            cmd += ['%s:%s' % (key, val)]
+        return cmd
+
 _BY_NAME = dict(
     (klass.get_basename(), klass)
     for name, klass in globals().items()
@@ -122,5 +146,6 @@ def list_external_downloaders():
 def get_external_downloader(external_downloader):
     """ Given the name of the executable, see whether we support the given
         downloader . """
-    bn = os.path.basename(external_downloader)
+    # Drop .exe extension on Windows
+    bn = os.path.splitext(os.path.basename(external_downloader))[0]
     return _BY_NAME[bn]

youtube_dl/downloader/f4m.py

@@ -7,16 +7,14 @@ import os
 import time
 import xml.etree.ElementTree as etree
 
-from .common import FileDownloader
-from .http import HttpFD
+from .fragment import FragmentFD
 from ..compat import (
     compat_urlparse,
+    compat_urllib_error,
 )
 from ..utils import (
     struct_pack,
     struct_unpack,
-    encodeFilename,
-    sanitize_open,
     xpath_text,
 )
 
@@ -121,7 +119,8 @@ class FlvReader(io.BytesIO):
 
         self.read_unsigned_int()  # BootstrapinfoVersion
         # Profile,Live,Update,Reserved
-        self.read(1)
+        flags = self.read_unsigned_char()
+        live = flags & 0x20 != 0
         # time scale
         self.read_unsigned_int()
         # CurrentMediaTime
@@ -160,6 +159,7 @@ class FlvReader(io.BytesIO):
         return {
             'segments': segments,
             'fragments': fragments,
+            'live': live,
         }
 
     def read_bootstrap_info(self):
@@ -182,6 +182,10 @@ def build_fragments_list(boot_info):
     for segment, fragments_count in segment_run_table['segment_run']:
         for _ in range(fragments_count):
             res.append((segment, next(fragments_counter)))
+
+    if boot_info['live']:
+        res = res[-2:]
+
     return res
 
 
@@ -219,16 +223,13 @@ 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):
+class F4mFD(FragmentFD):
     """
     A downloader for f4m manifests or AdobeHDS.
     """
 
+    FD_NAME = 'f4m'
+
     def _get_unencrypted_media(self, doc):
         media = doc.findall(_add_ns('media'))
         if not media:
@@ -246,10 +247,42 @@ class F4mFD(FileDownloader):
             self.report_error('Unsupported DRM')
         return media
 
+    def _get_bootstrap_from_url(self, bootstrap_url):
+        bootstrap = self.ydl.urlopen(bootstrap_url).read()
+        return read_bootstrap_info(bootstrap)
+
+    def _update_live_fragments(self, bootstrap_url, latest_fragment):
+        fragments_list = []
+        retries = 30
+        while (not fragments_list) and (retries > 0):
+            boot_info = self._get_bootstrap_from_url(bootstrap_url)
+            fragments_list = build_fragments_list(boot_info)
+            fragments_list = [f for f in fragments_list if f[1] > latest_fragment]
+            if not fragments_list:
+                # Retry after a while
+                time.sleep(5.0)
+                retries -= 1
+
+        if not fragments_list:
+            self.report_error('Failed to update fragments')
+
+        return fragments_list
+
+    def _parse_bootstrap_node(self, node, base_url):
+        if node.text is None:
+            bootstrap_url = compat_urlparse.urljoin(
+                base_url, node.attrib['url'])
+            boot_info = self._get_bootstrap_from_url(bootstrap_url)
+        else:
+            bootstrap_url = None
+            bootstrap = base64.b64decode(node.text.encode('ascii'))
+            boot_info = read_bootstrap_info(bootstrap)
+        return (boot_info, bootstrap_url)
+
     def real_download(self, filename, info_dict):
         man_url = info_dict['url']
         requested_bitrate = info_dict.get('tbr')
-        self.to_screen('[download] Downloading f4m manifest')
+        self.to_screen('[%s] Downloading f4m manifest' % self.FD_NAME)
         manifest = self.ydl.urlopen(man_url).read()
 
         doc = etree.fromstring(manifest)
@@ -265,18 +298,13 @@ class F4mFD(FileDownloader):
 
         base_url = compat_urlparse.urljoin(man_url, media.attrib['url'])
         bootstrap_node = doc.find(_add_ns('bootstrapInfo'))
-        if bootstrap_node.text is None:
-            bootstrap_url = compat_urlparse.urljoin(
-                base_url, bootstrap_node.attrib['url'])
-            bootstrap = self.ydl.urlopen(bootstrap_url).read()
-        else:
-            bootstrap = base64.b64decode(bootstrap_node.text)
+        boot_info, bootstrap_url = self._parse_bootstrap_node(bootstrap_node, base_url)
+        live = boot_info['live']
         metadata_node = media.find(_add_ns('metadata'))
         if metadata_node is not None:
-            metadata = base64.b64decode(metadata_node.text)
+            metadata = base64.b64decode(metadata_node.text.encode('ascii'))
         else:
             metadata = None
-        boot_info = read_bootstrap_info(bootstrap)
 
         fragments_list = build_fragments_list(boot_info)
         if self.params.get('test', False):
@@ -286,101 +314,67 @@ class F4mFD(FileDownloader):
         # For some akamai manifests we'll need to add a query to the fragment url
         akamai_pv = xpath_text(doc, _add_ns('pv-2.0'))
 
-        self.report_destination(filename)
-        http_dl = HttpQuietDownloader(
-            self.ydl,
-            {
-                'continuedl': True,
-                'quiet': True,
-                'noprogress': True,
-                'ratelimit': self.params.get('ratelimit', None),
-                'test': self.params.get('test', False),
-            }
-        )
-        tmpfilename = self.temp_name(filename)
-        (dest_stream, tmpfilename) = sanitize_open(tmpfilename, 'wb')
+        ctx = {
+            'filename': filename,
+            'total_frags': total_frags,
+        }
+
+        self._prepare_frag_download(ctx)
+
+        dest_stream = ctx['dest_stream']
 
         write_flv_header(dest_stream)
-        write_metadata_tag(dest_stream, metadata)
+        if not live:
+            write_metadata_tag(dest_stream, metadata)
 
-        # This dict stores the download progress, it's updated by the progress
-        # hook
-        state = {
-            'status': 'downloading',
-            'downloaded_bytes': 0,
-            'frag_index': 0,
-            'frag_count': total_frags,
-            'filename': filename,
-            'tmpfilename': tmpfilename,
-        }
-        start = time.time()
-
-        def frag_progress_hook(s):
-            if s['status'] not in ('downloading', 'finished'):
-                return
-
-            frag_total_bytes = s.get('total_bytes', 0)
-            if s['status'] == 'finished':
-                state['downloaded_bytes'] += frag_total_bytes
-                state['frag_index'] += 1
-
-            estimated_size = (
-                (state['downloaded_bytes'] + frag_total_bytes) /
-                (state['frag_index'] + 1) * total_frags)
-            time_now = time.time()
-            state['total_bytes_estimate'] = estimated_size
-            state['elapsed'] = time_now - start
-
-            if s['status'] == 'finished':
-                progress = self.calc_percent(state['frag_index'], total_frags)
-            else:
-                frag_downloaded_bytes = s['downloaded_bytes']
-                frag_progress = self.calc_percent(frag_downloaded_bytes,
-                                                  frag_total_bytes)
-                progress = self.calc_percent(state['frag_index'], total_frags)
-                progress += frag_progress / float(total_frags)
-
-                state['eta'] = self.calc_eta(
-                    start, time_now, estimated_size, state['downloaded_bytes'] + frag_downloaded_bytes)
-                state['speed'] = s.get('speed')
-            self._hook_progress(state)
-
-        http_dl.add_progress_hook(frag_progress_hook)
+        self._start_frag_download(ctx)
 
         frags_filenames = []
-        for (seg_i, frag_i) in fragments_list:
+        while fragments_list:
+            seg_i, frag_i = fragments_list.pop(0)
             name = 'Seg%d-Frag%d' % (seg_i, frag_i)
             url = base_url + name
             if akamai_pv:
                 url += '?' + akamai_pv.strip(';')
-            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)
+            if info_dict.get('extra_param_to_segment_url'):
+                url += info_dict.get('extra_param_to_segment_url')
+            frag_filename = '%s-%s' % (ctx['tmpfilename'], name)
+            try:
+                success = ctx['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
+                if live:
+                    os.remove(frag_filename)
+                else:
+                    frags_filenames.append(frag_filename)
+            except (compat_urllib_error.HTTPError, ) as err:
+                if live and (err.code == 404 or err.code == 410):
+                    # We didn't keep up with the live window. Continue
+                    # with the next available fragment.
+                    msg = 'Fragment %d unavailable' % frag_i
+                    self.report_warning(msg)
+                    fragments_list = []
+                else:
+                    raise
 
-        dest_stream.close()
+            if not fragments_list and live and bootstrap_url:
+                fragments_list = self._update_live_fragments(bootstrap_url, frag_i)
+                total_frags += len(fragments_list)
+                if fragments_list and (fragments_list[0][1] > frag_i + 1):
+                    msg = 'Missed %d fragments' % (fragments_list[0][1] - (frag_i + 1))
+                    self.report_warning(msg)
+
+        self._finish_frag_download(ctx)
 
-        elapsed = 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',
-            'elapsed': elapsed,
-        })
-
         return True

youtube_dl/downloader/fragment.py

@@ -0,0 +1,111 @@
+from __future__ import division, unicode_literals
+
+import os
+import time
+
+from .common import FileDownloader
+from .http import HttpFD
+from ..utils import (
+    encodeFilename,
+    sanitize_open,
+)
+
+
+class HttpQuietDownloader(HttpFD):
+    def to_screen(self, *args, **kargs):
+        pass
+
+
+class FragmentFD(FileDownloader):
+    """
+    A base file downloader class for fragmented media (e.g. f4m/m3u8 manifests).
+    """
+
+    def _prepare_and_start_frag_download(self, ctx):
+        self._prepare_frag_download(ctx)
+        self._start_frag_download(ctx)
+
+    def _prepare_frag_download(self, ctx):
+        self.to_screen('[%s] Total fragments: %d' % (self.FD_NAME, ctx['total_frags']))
+        self.report_destination(ctx['filename'])
+        dl = HttpQuietDownloader(
+            self.ydl,
+            {
+                'continuedl': True,
+                'quiet': True,
+                'noprogress': True,
+                'ratelimit': self.params.get('ratelimit', None),
+                'retries': self.params.get('retries', 0),
+                'test': self.params.get('test', False),
+            }
+        )
+        tmpfilename = self.temp_name(ctx['filename'])
+        dest_stream, tmpfilename = sanitize_open(tmpfilename, 'wb')
+        ctx.update({
+            'dl': dl,
+            'dest_stream': dest_stream,
+            'tmpfilename': tmpfilename,
+        })
+
+    def _start_frag_download(self, ctx):
+        total_frags = ctx['total_frags']
+        # This dict stores the download progress, it's updated by the progress
+        # hook
+        state = {
+            'status': 'downloading',
+            'downloaded_bytes': 0,
+            'frag_index': 0,
+            'frag_count': total_frags,
+            'filename': ctx['filename'],
+            'tmpfilename': ctx['tmpfilename'],
+        }
+        start = time.time()
+        ctx['started'] = start
+
+        def frag_progress_hook(s):
+            if s['status'] not in ('downloading', 'finished'):
+                return
+
+            frag_total_bytes = s.get('total_bytes', 0)
+            if s['status'] == 'finished':
+                state['downloaded_bytes'] += frag_total_bytes
+                state['frag_index'] += 1
+
+            estimated_size = (
+                (state['downloaded_bytes'] + frag_total_bytes) /
+                (state['frag_index'] + 1) * total_frags)
+            time_now = time.time()
+            state['total_bytes_estimate'] = estimated_size
+            state['elapsed'] = time_now - start
+
+            if s['status'] == 'finished':
+                progress = self.calc_percent(state['frag_index'], total_frags)
+            else:
+                frag_downloaded_bytes = s['downloaded_bytes']
+                frag_progress = self.calc_percent(frag_downloaded_bytes,
+                                                  frag_total_bytes)
+                progress = self.calc_percent(state['frag_index'], total_frags)
+                progress += frag_progress / float(total_frags)
+
+                state['eta'] = self.calc_eta(
+                    start, time_now, estimated_size, state['downloaded_bytes'] + frag_downloaded_bytes)
+                state['speed'] = s.get('speed')
+            self._hook_progress(state)
+
+        ctx['dl'].add_progress_hook(frag_progress_hook)
+
+        return start
+
+    def _finish_frag_download(self, ctx):
+        ctx['dest_stream'].close()
+        elapsed = time.time() - ctx['started']
+        self.try_rename(ctx['tmpfilename'], ctx['filename'])
+        fsize = os.path.getsize(encodeFilename(ctx['filename']))
+
+        self._hook_progress({
+            'downloaded_bytes': fsize,
+            'total_bytes': fsize,
+            'filename': ctx['filename'],
+            'status': 'finished',
+            'elapsed': elapsed,
+        })

youtube_dl/downloader/hls.py

@@ -4,12 +4,11 @@ import os
 import re
 import subprocess
 
-from ..postprocessor.ffmpeg import FFmpegPostProcessor
 from .common import FileDownloader
-from ..compat import (
-    compat_urlparse,
-    compat_urllib_request,
-)
+from .fragment import FragmentFD
+
+from ..compat import compat_urlparse
+from ..postprocessor.ffmpeg import FFmpegPostProcessor
 from ..utils import (
     encodeArgument,
     encodeFilename,
@@ -33,6 +32,8 @@ class HlsFD(FileDownloader):
             for opt in (ffpp.executable, '-y', '-i', url, '-f', 'mp4', '-c', 'copy', '-bsf:a', 'aac_adtstoasc')]
         args.append(encodeFilename(tmpfilename, True))
 
+        self._debug_cmd(args)
+
         retval = subprocess.call(args)
         if retval == 0:
             fsize = os.path.getsize(encodeFilename(tmpfilename))
@@ -51,54 +52,50 @@ class HlsFD(FileDownloader):
             return False
 
 
-class NativeHlsFD(FileDownloader):
+class NativeHlsFD(FragmentFD):
     """ A more limited implementation that does not require ffmpeg """
 
-    def real_download(self, filename, info_dict):
-        url = info_dict['url']
-        self.report_destination(filename)
-        tmpfilename = self.temp_name(filename)
+    FD_NAME = 'hlsnative'
 
-        self.to_screen(
-            '[hlsnative] %s: Downloading m3u8 manifest' % info_dict['id'])
-        data = self.ydl.urlopen(url).read()
-        s = data.decode('utf-8', 'ignore')
-        segment_urls = []
+    def real_download(self, filename, info_dict):
+        man_url = info_dict['url']
+        self.to_screen('[%s] Downloading m3u8 manifest' % self.FD_NAME)
+        manifest = self.ydl.urlopen(man_url).read()
+
+        s = manifest.decode('utf-8', 'ignore')
+        fragment_urls = []
         for line in s.splitlines():
             line = line.strip()
             if line and not line.startswith('#'):
                 segment_url = (
                     line
                     if re.match(r'^https?://', line)
-                    else compat_urlparse.urljoin(url, line))
-                segment_urls.append(segment_url)
-
-        is_test = self.params.get('test', False)
-        remaining_bytes = self._TEST_FILE_SIZE if is_test else None
-        byte_counter = 0
-        with open(tmpfilename, 'wb') as outf:
-            for i, segurl in enumerate(segment_urls):
-                self.to_screen(
-                    '[hlsnative] %s: Downloading segment %d / %d' %
-                    (info_dict['id'], i + 1, len(segment_urls)))
-                seg_req = compat_urllib_request.Request(segurl)
-                if remaining_bytes is not None:
-                    seg_req.add_header('Range', 'bytes=0-%d' % (remaining_bytes - 1))
-
-                segment = self.ydl.urlopen(seg_req).read()
-                if remaining_bytes is not None:
-                    segment = segment[:remaining_bytes]
-                    remaining_bytes -= len(segment)
-                outf.write(segment)
-                byte_counter += len(segment)
-                if remaining_bytes is not None and remaining_bytes <= 0:
+                    else compat_urlparse.urljoin(man_url, line))
+                fragment_urls.append(segment_url)
+                # We only download the first fragment during the test
+                if self.params.get('test', False):
                     break
 
-        self._hook_progress({
-            'downloaded_bytes': byte_counter,
-            'total_bytes': byte_counter,
+        ctx = {
             'filename': filename,
-            'status': 'finished',
-        })
-        self.try_rename(tmpfilename, filename)
+            'total_frags': len(fragment_urls),
+        }
+
+        self._prepare_and_start_frag_download(ctx)
+
+        frags_filenames = []
+        for i, frag_url in enumerate(fragment_urls):
+            frag_filename = '%s-Frag%d' % (ctx['tmpfilename'], i)
+            success = ctx['dl'].download(frag_filename, {'url': frag_url})
+            if not success:
+                return False
+            with open(frag_filename, 'rb') as down:
+                ctx['dest_stream'].write(down.read())
+            frags_filenames.append(frag_filename)
+
+        self._finish_frag_download(ctx)
+
+        for frag_file in frags_filenames:
+            os.remove(frag_file)
+
         return True

youtube_dl/downloader/http.py

@@ -4,6 +4,7 @@ import errno
 import os
 import socket
 import time
+import re
 
 from .common import FileDownloader
 from ..compat import (
@@ -28,13 +29,8 @@ class HttpFD(FileDownloader):
         add_headers = info_dict.get('http_headers')
         if add_headers:
             headers.update(add_headers)
-        data = info_dict.get('http_post_data')
-        http_method = info_dict.get('http_method')
-        basic_request = compat_urllib_request.Request(url, data, headers)
-        request = compat_urllib_request.Request(url, data, headers)
-        if http_method is not None:
-            basic_request.get_method = lambda: http_method
-            request.get_method = lambda: http_method
+        basic_request = compat_urllib_request.Request(url, None, headers)
+        request = compat_urllib_request.Request(url, None, headers)
 
         is_test = self.params.get('test', False)
 
@@ -49,7 +45,7 @@ class HttpFD(FileDownloader):
 
         open_mode = 'wb'
         if resume_len != 0:
-            if self.params.get('continuedl', False):
+            if self.params.get('continuedl', True):
                 self.report_resuming_byte(resume_len)
                 request.add_header('Range', 'bytes=%d-' % resume_len)
                 open_mode = 'ab'
@@ -62,6 +58,24 @@ class HttpFD(FileDownloader):
             # Establish connection
             try:
                 data = self.ydl.urlopen(request)
+                # When trying to resume, Content-Range HTTP header of response has to be checked
+                # to match the value of requested Range HTTP header. This is due to a webservers
+                # that don't support resuming and serve a whole file with no Content-Range
+                # set in response despite of requested Range (see
+                # https://github.com/rg3/youtube-dl/issues/6057#issuecomment-126129799)
+                if resume_len > 0:
+                    content_range = data.headers.get('Content-Range')
+                    if content_range:
+                        content_range_m = re.search(r'bytes (\d+)-', content_range)
+                        # Content-Range is present and matches requested Range, resume is possible
+                        if content_range_m and resume_len == int(content_range_m.group(1)):
+                            break
+                    # Content-Range is either not present or invalid. Assuming remote webserver is
+                    # trying to send the whole file, resume is not possible, so wiping the local file
+                    # and performing entire redownload
+                    self.report_unable_to_resume()
+                    resume_len = 0
+                    open_mode = 'wb'
                 break
             except (compat_urllib_error.HTTPError, ) as err:
                 if (err.code < 500 or err.code >= 600) and err.code != 416:
@@ -92,6 +106,8 @@ class HttpFD(FileDownloader):
                             self._hook_progress({
                                 'filename': filename,
                                 'status': 'finished',
+                                'downloaded_bytes': resume_len,
+                                'total_bytes': resume_len,
                             })
                             return True
                         else:
@@ -218,12 +234,6 @@ class HttpFD(FileDownloader):
         if tmpfilename != '-':
             stream.close()
 
-        self._hook_progress({
-            'downloaded_bytes': byte_counter,
-            'total_bytes': data_len,
-            'tmpfilename': tmpfilename,
-            'status': 'error',
-        })
         if data_len is not None and byte_counter != data_len:
             raise ContentTooShortError(byte_counter, int(data_len))
         self.try_rename(tmpfilename, filename)

youtube_dl/downloader/rtmp.py

@@ -3,7 +3,6 @@ from __future__ import unicode_literals
 import os
 import re
 import subprocess
-import sys
 import time
 
 from .common import FileDownloader
@@ -11,6 +10,7 @@ from ..compat import compat_str
 from ..utils import (
     check_executable,
     encodeFilename,
+    encodeArgument,
     get_exe_version,
 )
 
@@ -105,7 +105,7 @@ class RtmpFD(FileDownloader):
         protocol = info_dict.get('rtmp_protocol', None)
         real_time = info_dict.get('rtmp_real_time', False)
         no_resume = info_dict.get('no_resume', False)
-        continue_dl = info_dict.get('continuedl', False)
+        continue_dl = info_dict.get('continuedl', True)
 
         self.report_destination(filename)
         tmpfilename = self.temp_name(filename)
@@ -119,7 +119,9 @@ class RtmpFD(FileDownloader):
         # 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]
+        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:
@@ -129,7 +131,7 @@ class RtmpFD(FileDownloader):
         if play_path is not None:
             basic_args += ['--playpath', play_path]
         if tc_url is not None:
-            basic_args += ['--tcUrl', url]
+            basic_args += ['--tcUrl', tc_url]
         if test:
             basic_args += ['--stop', '1']
         if flash_version is not None:
@@ -152,16 +154,9 @@ class RtmpFD(FileDownloader):
         if not live and continue_dl:
             args += ['--skip', '1']
 
-        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
+        args = [encodeArgument(a) for a in args]
 
-        self._debug_cmd(args, subprocess_encoding, exe='rtmpdump')
+        self._debug_cmd(args, exe='rtmpdump')
 
         RD_SUCCESS = 0
         RD_FAILED = 1
@@ -178,7 +173,11 @@ class RtmpFD(FileDownloader):
             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])
+            args = basic_args + ['--resume']
+            if retval == RD_FAILED:
+                args += ['--skip', '1']
+            args = [encodeArgument(a) for a in args]
+            retval = run_rtmpdump(args)
             cursize = os.path.getsize(encodeFilename(tmpfilename))
             if prevsize == cursize and retval == RD_FAILED:
                 break

youtube_dl/downloader/rtsp.py

@@ -10,21 +10,23 @@ from ..utils import (
 )
 
 
-class MplayerFD(FileDownloader):
+class RtspFD(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
-        if not check_executable('mplayer', ['-h']):
-            self.report_error('MMS or RTSP download detected but "%s" could not be run' % args[0])
+        if check_executable('mplayer', ['-h']):
+            args = [
+                'mplayer', '-really-quiet', '-vo', 'null', '-vc', 'dummy',
+                '-dumpstream', '-dumpfile', tmpfilename, url]
+        elif check_executable('mpv', ['-h']):
+            args = [
+                'mpv', '-really-quiet', '--vo=null', '--stream-dump=' + tmpfilename, url]
+        else:
+            self.report_error('MMS or RTSP download detected but neither "mplayer" nor "mpv" could be run. Please install any.')
             return False
 
-        # Download using mplayer.
         retval = subprocess.call(args)
         if retval == 0:
             fsize = os.path.getsize(encodeFilename(tmpfilename))
@@ -39,5 +41,5 @@ class MplayerFD(FileDownloader):
             return True
         else:
             self.to_stderr('\n')
-            self.report_error('mplayer exited with code %d' % retval)
+            self.report_error('%s exited with code %d' % (args[0], retval))
             return False

youtube_dl/extractor/__init__.py

@@ -4,10 +4,14 @@ from .abc import ABCIE
 from .abc7news import Abc7NewsIE
 from .academicearth import AcademicEarthCourseIE
 from .addanime import AddAnimeIE
-from .adobetv import AdobeTVIE
+from .adobetv import (
+    AdobeTVIE,
+    AdobeTVVideoIE,
+)
 from .adultswim import AdultSwimIE
 from .aftenposten import AftenpostenIE
 from .aftonbladet import AftonbladetIE
+from .airmozilla import AirMozillaIE
 from .aljazeera import AlJazeeraIE
 from .alphaporno import AlphaPornoIE
 from .anitube import AnitubeIE
@@ -15,9 +19,14 @@ from .anysex import AnySexIE
 from .aol import AolIE
 from .allocine import AllocineIE
 from .aparat import AparatIE
+from .appleconnect import AppleConnectIE
 from .appletrailers import AppleTrailersIE
 from .archiveorg import ArchiveOrgIE
-from .ard import ARDIE, ARDMediathekIE
+from .ard import (
+    ARDIE,
+    ARDMediathekIE,
+    SportschauIE,
+)
 from .arte import (
     ArteTvIE,
     ArteTVPlus7IE,
@@ -31,11 +40,16 @@ from .atresplayer import AtresPlayerIE
 from .atttechchannel import ATTTechChannelIE
 from .audiomack import AudiomackIE, AudiomackAlbumIE
 from .azubu import AzubuIE
+from .baidu import BaiduVideoIE
 from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE
-from .bbccouk import BBCCoUkIE
+from .bbc import (
+    BBCCoUkIE,
+    BBCIE,
+)
 from .beeg import BeegIE
 from .behindkink import BehindKinkIE
+from .beatportpro import BeatportProIE
 from .bet import BetIE
 from .bild import BildIE
 from .bilibili import BiliBiliIE
@@ -68,6 +82,7 @@ from .chirbit import (
     ChirbitProfileIE,
 )
 from .cinchcast import CinchcastIE
+from .cinemassacre import CinemassacreIE
 from .clipfish import ClipfishIE
 from .cliphunter import CliphunterIE
 from .clipsyndicate import ClipsyndicateIE
@@ -88,6 +103,7 @@ from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
 from .condenast import CondeNastIE
 from .cracked import CrackedIE
 from .criterion import CriterionIE
+from .crooksandliars import CrooksAndLiarsIE
 from .crunchyroll import (
     CrunchyrollIE,
     CrunchyrollShowPlaylistIE
@@ -98,23 +114,33 @@ from .dailymotion import (
     DailymotionIE,
     DailymotionPlaylistIE,
     DailymotionUserIE,
+    DailymotionCloudIE,
 )
 from .daum import DaumIE
 from .dbtv import DBTVIE
+from .dcn import DCNIE
 from .dctp import DctpTvIE
 from .deezer import DeezerPlaylistIE
 from .dfb import DFBIE
+from .dhm import DHMIE
 from .dotsub import DotsubIE
+from .douyutv import DouyuTVIE
+from .dramafever import (
+    DramaFeverIE,
+    DramaFeverSeriesIE,
+)
 from .dreisat import DreiSatIE
 from .drbonanza import DRBonanzaIE
 from .drtuber import DrTuberIE
 from .drtv import DRTVIE
 from .dvtv import DVTVIE
 from .dump import DumpIE
+from .dumpert import DumpertIE
 from .defense import DefenseGouvFrIE
 from .discovery import DiscoveryIE
 from .divxstage import DivxStageIE
 from .dropbox import DropboxIE
+from .eagleplatform import EaglePlatformIE
 from .ebaumsworld import EbaumsWorldIE
 from .echomsk import EchoMskIE
 from .ehow import EHowIE
@@ -127,11 +153,12 @@ from .ellentv import (
 )
 from .elpais import ElPaisIE
 from .embedly import EmbedlyIE
-from .empflix import EMPFlixIE
 from .engadget import EngadgetIE
 from .eporner import EpornerIE
 from .eroprofile import EroProfileIE
 from .escapist import EscapistIE
+from .espn import ESPNIE
+from .esri import EsriVideoIE
 from .everyonesmixtape import EveryonesMixtapeIE
 from .exfm import ExfmIE
 from .expotv import ExpoTVIE
@@ -139,19 +166,21 @@ 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 .fivetv import FiveTVIE
 from .fktv import (
     FKTVIE,
     FKTVPosteckeIE,
 )
 from .flickr import FlickrIE
 from .folketinget import FolketingetIE
+from .footyroom import FootyRoomIE
 from .fourtube import FourTubeIE
 from .foxgay import FoxgayIE
 from .foxnews import FoxNewsIE
+from .foxsports import FoxSportsIE
 from .franceculture import FranceCultureIE
 from .franceinter import FranceInterIE
 from .francetv import (
@@ -170,11 +199,14 @@ from .gameone import (
     GameOneIE,
     GameOnePlaylistIE,
 )
+from .gamersyde import GamersydeIE
 from .gamespot import GameSpotIE
 from .gamestar import GameStarIE
 from .gametrailers import GametrailersIE
+from .gazeta import GazetaIE
 from .gdcvault import GDCVaultIE
 from .generic import GenericIE
+from .gfycat import GfycatIE
 from .giantbomb import GiantBombIE
 from .giga import GigaIE
 from .glide import GlideIE
@@ -186,7 +218,6 @@ from .googleplus import GooglePlusIE
 from .googlesearch import GoogleSearchIE
 from .gorillavid import GorillaVidIE
 from .goshgay import GoshgayIE
-from .grooveshark import GroovesharkIE
 from .groupon import GrouponIE
 from .hark import HarkIE
 from .hearthisat import HearThisAtIE
@@ -212,10 +243,16 @@ from .imdb import (
 )
 from .imgur import ImgurIE
 from .ina import InaIE
+from .indavideo import (
+    IndavideoIE,
+    IndavideoEmbedIE,
+)
 from .infoq import InfoQIE
 from .instagram import InstagramIE, InstagramUserIE
 from .internetvideoarchive import InternetVideoArchiveIE
 from .iprima import IPrimaIE
+from .iqiyi import IqiyiIE
+from .ir90tv import Ir90TvIE
 from .ivi import (
     IviIE,
     IviCompilationIE
@@ -226,8 +263,11 @@ from .jeuxvideo import JeuxVideoIE
 from .jove import JoveIE
 from .jukebox import JukeboxIE
 from .jpopsukitv import JpopsukiIE
+from .kaltura import KalturaIE
+from .kanalplay import KanalPlayIE
 from .kankan import KankanIE
 from .karaoketv import KaraoketvIE
+from .karrierevideos import KarriereVideosIE
 from .keezmovies import KeezMoviesIE
 from .khanacademy import KhanAcademyIE
 from .kickstarter import KickStarterIE
@@ -235,9 +275,27 @@ from .keek import KeekIE
 from .kontrtube import KontrTubeIE
 from .krasview import KrasViewIE
 from .ku6 import Ku6IE
+from .kuwo import (
+    KuwoIE,
+    KuwoAlbumIE,
+    KuwoChartIE,
+    KuwoSingerIE,
+    KuwoCategoryIE,
+    KuwoMvIE,
+)
 from .la7 import LA7IE
 from .laola1tv import Laola1TvIE
-from .lifenews import LifeNewsIE
+from .lecture2go import Lecture2GoIE
+from .letv import (
+    LetvIE,
+    LetvTvIE,
+    LetvPlaylistIE
+)
+from .libsyn import LibsynIE
+from .lifenews import (
+    LifeNewsIE,
+    LifeEmbedIE,
+)
 from .liveleak import LiveLeakIE
 from .livestream import (
     LivestreamIE,
@@ -255,11 +313,13 @@ from .macgamestore import MacGameStoreIE
 from .mailru import MailRuIE
 from .malemotion import MalemotionIE
 from .mdr import MDRIE
+from .megavideoz import MegaVideozIE
 from .metacafe import MetacafeIE
 from .metacritic import MetacriticIE
 from .mgoon import MgoonIE
 from .minhateca import MinhatecaIE
 from .ministrygrid import MinistryGridIE
+from .miomio import MioMioIE
 from .mit import TechTVMITIE, MITIE, OCWMITIE
 from .mitele import MiTeleIE
 from .mixcloud import MixcloudIE
@@ -285,8 +345,10 @@ from .muenchentv import MuenchenTVIE
 from .musicplayon import MusicPlayOnIE
 from .musicvault import MusicVaultIE
 from .muzu import MuzuTVIE
+from .mwave import MwaveIE
 from .myspace import MySpaceIE, MySpaceAlbumIE
 from .myspass import MySpassIE
+from .myvi import MyviIE
 from .myvideo import MyVideoIE
 from .myvidster import MyVidsterIE
 from .nationalgeographic import NationalGeographicIE
@@ -295,19 +357,33 @@ from .nba import NBAIE
 from .nbc import (
     NBCIE,
     NBCNewsIE,
+    NBCSportsIE,
+    NBCSportsVPlayerIE,
+    MSNBCIE,
+)
+from .ndr import (
+    NDRIE,
+    NJoyIE,
 )
-from .ndr import NDRIE
 from .ndtv import NDTVIE
 from .netzkino import NetzkinoIE
 from .nerdcubed import NerdCubedFeedIE
 from .nerdist import NerdistIE
+from .neteasemusic import (
+    NetEaseMusicIE,
+    NetEaseMusicAlbumIE,
+    NetEaseMusicSingerIE,
+    NetEaseMusicListIE,
+    NetEaseMusicMvIE,
+    NetEaseMusicProgramIE,
+    NetEaseMusicDjRadioIE,
+)
 from .newgrounds import NewgroundsIE
 from .newstube import NewstubeIE
 from .nextmedia import (
     NextMediaIE,
     NextMediaActionNewsIE,
-    AppleDailyRealtimeNewsIE,
-    AppleDailyAnimationNewsIE
+    AppleDailyIE,
 )
 from .nfb import NFBIE
 from .nfl import NFLIE
@@ -321,59 +397,98 @@ from .ninegag import NineGagIE
 from .noco import NocoIE
 from .normalboots import NormalbootsIE
 from .nosvideo import NosVideoIE
+from .nova import NovaIE
 from .novamov import NovaMovIE
 from .nowness import NownessIE
+from .nowtv import NowTVIE
 from .nowvideo import NowVideoIE
 from .npo import (
     NPOIE,
     NPOLiveIE,
     NPORadioIE,
     NPORadioFragmentIE,
-    TegenlichtVproIE,
+    VPROIE,
+    WNLIE
 )
 from .nrk import (
     NRKIE,
+    NRKPlaylistIE,
     NRKTVIE,
 )
 from .ntvde import NTVDeIE
 from .ntvru import NTVRuIE
-from .nytimes import NYTimesIE
+from .nytimes import (
+    NYTimesIE,
+    NYTimesArticleIE,
+)
 from .nuvid import NuvidIE
+from .odnoklassniki import OdnoklassnikiIE
 from .oktoberfesttv import OktoberfestTVIE
-from .ooyala import OoyalaIE
+from .onionstudios import OnionStudiosIE
+from .ooyala import (
+    OoyalaIE,
+    OoyalaExternalIE,
+)
 from .openfilm import OpenFilmIE
 from .orf import (
     ORFTVthekIE,
     ORFOE1IE,
     ORFFM4IE,
+    ORFIPTVIE,
 )
 from .parliamentliveuk import ParliamentLiveUKIE
 from .patreon import PatreonIE
 from .pbs import PBSIE
+from .periscope import (
+    PeriscopeIE,
+    QuickscopeIE,
+)
+from .philharmoniedeparis import PhilharmonieDeParisIE
 from .phoenix import PhoenixIE
 from .photobucket import PhotobucketIE
+from .pinkbike import PinkbikeIE
 from .planetaplay import PlanetaPlayIE
+from .pladform import PladformIE
 from .played import PlayedIE
 from .playfm import PlayFMIE
+from .playtvak import PlaytvakIE
 from .playvid import PlayvidIE
+from .playwire import PlaywireIE
+from .pluralsight import (
+    PluralsightIE,
+    PluralsightCourseIE,
+)
 from .podomatic import PodomaticIE
+from .porn91 import Porn91IE
 from .pornhd import PornHdIE
 from .pornhub import (
     PornHubIE,
     PornHubPlaylistIE,
 )
 from .pornotube import PornotubeIE
+from .pornovoisines import PornoVoisinesIE
 from .pornoxo import PornoXOIE
+from .primesharetv import PrimeShareTVIE
 from .promptfile import PromptFileIE
 from .prosiebensat1 import ProSiebenSat1IE
+from .puls4 import Puls4IE
 from .pyvideo import PyvideoIE
+from .qqmusic import (
+    QQMusicIE,
+    QQMusicSingerIE,
+    QQMusicAlbumIE,
+    QQMusicToplistIE,
+    QQMusicPlaylistIE,
+)
 from .quickvid import QuickVidIE
 from .r7 import R7IE
 from .radiode import RadioDeIE
+from .radiojavan import RadioJavanIE
 from .radiobremen import RadioBremenIE
 from .radiofrance import RadioFranceIE
 from .rai import RaiIE
 from .rbmaradio import RBMARadioIE
+from .rds import RDSIE
 from .redtube import RedTubeIE
 from .restudy import RestudyIE
 from .reverbnation import ReverbNationIE
@@ -384,11 +499,11 @@ from .roxwel import RoxwelIE
 from .rtbf import RTBFIE
 from .rte import RteIE
 from .rtlnl import RtlNlIE
-from .rtlnow import RTLnowIE
 from .rtl2 import RTL2IE
 from .rtp import RTPIE
 from .rts import RTSIE
-from .rtve import RTVEALaCartaIE, RTVELiveIE
+from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE
+from .rtvnh import RTVNHIE
 from .ruhd import RUHDIE
 from .rutube import (
     RutubeIE,
@@ -398,17 +513,24 @@ from .rutube import (
     RutubePersonIE,
 )
 from .rutv import RUTVIE
+from .ruutu import RuutuIE
 from .sandia import SandiaIE
+from .safari import (
+    SafariIE,
+    SafariCourseIE,
+)
 from .sapo import SapoIE
 from .savefrom import SaveFromIE
 from .sbs import SBSIE
 from .scivee import SciVeeIE
 from .screencast import ScreencastIE
 from .screencastomatic import ScreencastOMaticIE
-from .screenwavemedia import CinemassacreIE, ScreenwaveMediaIE, TeamFourIE
+from .screenwavemedia import ScreenwaveMediaIE, TeamFourIE
+from .senateisvp import SenateISVPIE
 from .servingsys import ServingSysIE
 from .sexu import SexuIE
 from .sexykarma import SexyKarmaIE
+from .shahid import ShahidIE
 from .shared import SharedIE
 from .sharesix import ShareSixIE
 from .sina import SinaIE
@@ -420,9 +542,16 @@ from .smotri import (
     SmotriUserIE,
     SmotriBroadcastIE,
 )
+from .snagfilms import (
+    SnagFilmsIE,
+    SnagFilmsEmbedIE,
+)
 from .snotr import SnotrIE
-from .sockshare import SockshareIE
 from .sohu import SohuIE
+from .soompi import (
+    SoompiIE,
+    SoompiShowIE,
+)
 from .soundcloud import (
     SoundcloudIE,
     SoundcloudSetIE,
@@ -435,24 +564,36 @@ from .soundgasm import (
 )
 from .southpark import (
     SouthParkIE,
-    SouthparkDeIE,
+    SouthParkDeIE,
+    SouthParkDkIE,
+    SouthParkEsIE,
+    SouthParkNlIE
 )
 from .space import SpaceIE
+from .spankbang import SpankBangIE
 from .spankwire import SpankwireIE
 from .spiegel import SpiegelIE, SpiegelArticleIE
 from .spiegeltv import SpiegeltvIE
 from .spike import SpikeIE
 from .sport5 import Sport5IE
-from .sportbox import SportBoxIE
+from .sportbox import (
+    SportBoxIE,
+    SportBoxEmbedIE,
+)
 from .sportdeutschland import SportDeutschlandIE
+from .srf import SrfIE
 from .srmediathek import SRMediathekIE
+from .ssa import SSAIE
 from .stanfordoc import StanfordOpenClassroomIE
 from .steam import SteamIE
 from .streamcloud import StreamcloudIE
 from .streamcz import StreamCZIE
 from .streetvoice import StreetVoiceIE
 from .sunporno import SunPornoIE
-from .svtplay import SVTPlayIE
+from .svt import (
+    SVTIE,
+    SVTPlayIE,
+)
 from .swrmediathek import SWRMediathekIE
 from .syfy import SyfyIE
 from .sztvhu import SztvHuIE
@@ -469,6 +610,7 @@ from .techtalks import TechTalksIE
 from .ted import TEDIE
 from .telebruxelles import TeleBruxellesIE
 from .telecinco import TelecincoIE
+from .telegraaf import TelegraafIE
 from .telemb import TeleMBIE
 from .teletask import TeleTaskIE
 from .tenplay import TenPlayIE
@@ -476,13 +618,24 @@ from .testurl import TestURLIE
 from .testtube import TestTubeIE
 from .tf1 import TF1IE
 from .theonion import TheOnionIE
-from .theplatform import ThePlatformIE
+from .theplatform import (
+    ThePlatformIE,
+    ThePlatformFeedIE,
+)
 from .thesixtyone import TheSixtyOneIE
+from .thisamericanlife import ThisAmericanLifeIE
 from .thisav import ThisAVIE
 from .tinypic import TinyPicIE
 from .tlc import TlcIE, TlcDeIE
-from .tmz import TMZIE
-from .tnaflix import TNAFlixIE
+from .tmz import (
+    TMZIE,
+    TMZArticleIE,
+)
+from .tnaflix import (
+    TNAFlixIE,
+    EMPFlixIE,
+    MovieFapIE,
+)
 from .thvideo import (
     THVideoIE,
     THVideoPlaylistIE
@@ -493,17 +646,30 @@ from .traileraddict import TrailerAddictIE
 from .trilulilu import TriluliluIE
 from .trutube import TruTubeIE
 from .tube8 import Tube8IE
+from .tubitv import TubiTvIE
 from .tudou import TudouIE
 from .tumblr import TumblrIE
 from .tunein import TuneInIE
 from .turbo import TurboIE
 from .tutv import TutvIE
+from .tv2 import (
+    TV2IE,
+    TV2ArticleIE,
+)
 from .tv4 import TV4IE
+from .tvc import (
+    TVCIE,
+    TVCArticleIE,
+)
 from .tvigle import TvigleIE
 from .tvp import TvpIE, TvpSeriesIE
 from .tvplay import TVPlayIE
 from .tweakers import TweakersIE
 from .twentyfourvideo import TwentyFourVideoIE
+from .twentytwotracks import (
+    TwentyTwoTracksIE,
+    TwentyTwoTracksGenreIE
+)
 from .twitch import (
     TwitchVideoIE,
     TwitchChapterIE,
@@ -513,24 +679,32 @@ from .twitch import (
     TwitchBookmarksIE,
     TwitchStreamIE,
 )
+from .twitter import TwitterCardIE
 from .ubu import UbuIE
 from .udemy import (
     UdemyIE,
     UdemyCourseIE
 )
+from .udn import UDNEmbedIE
+from .ultimedia import UltimediaIE
 from .unistra import UnistraIE
 from .urort import UrortIE
 from .ustream import UstreamIE, UstreamChannelIE
+from .varzesh3 import Varzesh3IE
 from .vbox7 import Vbox7IE
 from .veehd import VeeHDIE
 from .veoh import VeohIE
+from .vessel import VesselIE
 from .vesti import VestiIE
 from .vevo import VevoIE
-from .vgtv import VGTVIE
+from .vgtv import (
+    BTArticleIE,
+    BTVestlendingenIE,
+    VGTVIE,
+)
 from .vh1 import VH1IE
 from .vice import ViceIE
 from .viddler import ViddlerIE
-from .videobam import VideoBamIE
 from .videodetective import VideoDetectiveIE
 from .videolecturesnet import VideoLecturesNetIE
 from .videofyme import VideofyMeIE
@@ -541,6 +715,7 @@ from .videoweed import VideoWeedIE
 from .vidme import VidmeIE
 from .vidzi import VidziIE
 from .vier import VierIE, VierVideosIE
+from .viewster import ViewsterIE
 from .vimeo import (
     VimeoIE,
     VimeoAlbumIE,
@@ -556,12 +731,16 @@ from .vine import (
     VineIE,
     VineUserIE,
 )
-from .viki import VikiIE
+from .viki import (
+    VikiIE,
+    VikiChannelIE,
+)
 from .vk import (
     VKIE,
     VKUserVideosIE,
 )
 from .vodlocker import VodlockerIE
+from .voicerepublic import VoiceRepublicIE
 from .vporn import VpornIE
 from .vrt import VRTIE
 from .vube import VubeIE
@@ -576,7 +755,10 @@ from .wdr import (
     WDRMobileIE,
     WDRMausIE,
 )
-from .webofstories import WebOfStoriesIE
+from .webofstories import (
+    WebOfStoriesIE,
+    WebOfStoriesPlaylistIE,
+)
 from .weibo import WeiboIE
 from .wimp import WimpIE
 from .wistia import WistiaIE
@@ -585,19 +767,29 @@ from .wrzuta import WrzutaIE
 from .wsj import WSJIE
 from .xbef import XBefIE
 from .xboxclips import XboxClipsIE
-from .xhamster import XHamsterIE
+from .xhamster import (
+    XHamsterIE,
+    XHamsterEmbedIE,
+)
 from .xminus import XMinusIE
 from .xnxx import XNXXIE
-from .xvideos import XVideosIE
+from .xstream import XstreamIE
 from .xtube import XTubeUserIE, XTubeIE
 from .xuite import XuiteIE
+from .xvideos import XVideosIE
 from .xxxymovies import XXXYMoviesIE
 from .yahoo import (
     YahooIE,
     YahooSearchIE,
 )
 from .yam import YamIE
+from .yandexmusic import (
+    YandexMusicTrackIE,
+    YandexMusicAlbumIE,
+    YandexMusicPlaylistIE,
+)
 from .yesjapan import YesJapanIE
+from .yinyuetai import YinYueTaiIE
 from .ynet import YnetIE
 from .youjizz import YouJizzIE
 from .youku import YoukuIE

youtube_dl/extractor/addanime.py

@@ -11,12 +11,13 @@ from ..compat import (
 )
 from ..utils import (
     ExtractorError,
+    qualities,
 )
 
 
 class AddAnimeIE(InfoExtractor):
-    _VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video\.php\?(?:.*?)v=(?P<id>[\w_]+)(?:.*)'
-    _TEST = {
+    _VALID_URL = r'http://(?:\w+\.)?add-anime\.net/(?:watch_video\.php\?(?:.*?)v=|video/)(?P<id>[\w_]+)'
+    _TESTS = [{
         'url': 'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
         'md5': '72954ea10bc979ab5e2eb288b21425a0',
         'info_dict': {
@@ -25,7 +26,10 @@ class AddAnimeIE(InfoExtractor):
             'description': 'One Piece 606',
             'title': 'One Piece 606',
         }
-    }
+    }, {
+        'url': 'http://add-anime.net/video/MDUGWYKNGBD8/One-Piece-687',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -63,8 +67,10 @@ class AddAnimeIE(InfoExtractor):
                 note='Confirming after redirect')
             webpage = self._download_webpage(url, video_id)
 
+        FORMATS = ('normal', 'hq')
+        quality = qualities(FORMATS)
         formats = []
-        for format_id in ('normal', 'hq'):
+        for format_id in FORMATS:
             rex = r"var %s_video_file = '(.*?)';" % re.escape(format_id)
             video_url = self._search_regex(rex, webpage, 'video file URLx',
                                            fatal=False)
@@ -73,6 +79,7 @@ class AddAnimeIE(InfoExtractor):
             formats.append({
                 'format_id': format_id,
                 'url': video_url,
+                'quality': quality(format_id),
             })
         self._sort_formats(formats)
         video_title = self._og_search_title(webpage)

youtube_dl/extractor/adobetv.py

@@ -5,6 +5,8 @@ from ..utils import (
     parse_duration,
     unified_strdate,
     str_to_int,
+    float_or_none,
+    ISO639Utils,
 )
 
 
@@ -69,3 +71,61 @@ class AdobeTVIE(InfoExtractor):
             'view_count': view_count,
             'formats': formats,
         }
+
+
+class AdobeTVVideoIE(InfoExtractor):
+    _VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P<id>\d+)'
+
+    _TEST = {
+        # From https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners
+        'url': 'https://video.tv.adobe.com/v/2456/',
+        'md5': '43662b577c018ad707a63766462b1e87',
+        'info_dict': {
+            'id': '2456',
+            'ext': 'mp4',
+            'title': 'New experience with Acrobat DC',
+            'description': 'New experience with Acrobat DC',
+            'duration': 248.667,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        player_params = self._parse_json(self._search_regex(
+            r'var\s+bridge\s*=\s*([^;]+);', webpage, 'player parameters'),
+            video_id)
+
+        formats = [{
+            'url': source['src'],
+            'width': source.get('width'),
+            'height': source.get('height'),
+            'tbr': source.get('bitrate'),
+        } for source in player_params['sources']]
+
+        # For both metadata and downloaded files the duration varies among
+        # formats. I just pick the max one
+        duration = max(filter(None, [
+            float_or_none(source.get('duration'), scale=1000)
+            for source in player_params['sources']]))
+
+        subtitles = {}
+        for translation in player_params.get('translations', []):
+            lang_id = translation.get('language_w3c') or ISO639Utils.long2short(translation['language_medium'])
+            if lang_id not in subtitles:
+                subtitles[lang_id] = []
+            subtitles[lang_id].append({
+                'url': translation['vttPath'],
+                'ext': 'vtt',
+            })
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': player_params['title'],
+            'description': self._og_search_description(webpage),
+            'duration': duration,
+            'subtitles': subtitles,
+        }

youtube_dl/extractor/adultswim.py

@@ -2,13 +2,12 @@
 from __future__ import unicode_literals
 
 import re
-import json
 
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
-    xpath_text,
     float_or_none,
+    xpath_text,
 )
 
 
@@ -60,6 +59,24 @@ class AdultSwimIE(InfoExtractor):
             'title': 'American Dad - Putting Francine Out of Business',
             'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
         },
+    }, {
+        'url': 'http://www.adultswim.com/videos/tim-and-eric-awesome-show-great-job/dr-steve-brule-for-your-wine/',
+        'playlist': [
+            {
+                'md5': '3e346a2ab0087d687a05e1e7f3b3e529',
+                'info_dict': {
+                    'id': 'sY3cMUR_TbuE4YmdjzbIcQ-0',
+                    'ext': 'flv',
+                    'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
+                    'description': 'Dr. Brule reports live from Wine Country with a special report on wines.  \r\nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.\r\n\r\n',
+                },
+            }
+        ],
+        'info_dict': {
+            'id': 'sY3cMUR_TbuE4YmdjzbIcQ',
+            'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
+            'description': 'Dr. Brule reports live from Wine Country with a special report on wines.  \r\nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.\r\n\r\n',
+        },
     }]
 
     @staticmethod
@@ -80,6 +97,7 @@ class AdultSwimIE(InfoExtractor):
             for video in collection.get('videos'):
                 if video.get('slug') == slug:
                     return collection, video
+        return None, None
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -90,28 +108,30 @@ class AdultSwimIE(InfoExtractor):
         webpage = self._download_webpage(url, episode_path)
 
         # Extract the value of `bootstrappedData` from the Javascript in the page.
-        bootstrappedDataJS = self._search_regex(r'var bootstrappedData = ({.*});', webpage, episode_path)
-
-        try:
-            bootstrappedData = json.loads(bootstrappedDataJS)
-        except ValueError as ve:
-            errmsg = '%s: Failed to parse JSON ' % episode_path
-            raise ExtractorError(errmsg, cause=ve)
+        bootstrapped_data = self._parse_json(self._search_regex(
+            r'var bootstrappedData = ({.*});', webpage, 'bootstraped data'), episode_path)
 
         # Downloading videos from a /videos/playlist/ URL needs to be handled differently.
         # NOTE: We are only downloading one video (the current one) not the playlist
         if is_playlist:
-            collections = bootstrappedData['playlists']['collections']
+            collections = bootstrapped_data['playlists']['collections']
             collection = self.find_collection_by_linkURL(collections, show_path)
             video_info = self.find_video_info(collection, episode_path)
 
             show_title = video_info['showTitle']
             segment_ids = [video_info['videoPlaybackID']]
         else:
-            collections = bootstrappedData['show']['collections']
+            collections = bootstrapped_data['show']['collections']
             collection, video_info = self.find_collection_containing_video(collections, episode_path)
 
-            show = bootstrappedData['show']
+            # Video wasn't found in the collections, let's try `slugged_video`.
+            if video_info is None:
+                if bootstrapped_data.get('slugged_video', {}).get('slug') == episode_path:
+                    video_info = bootstrapped_data['slugged_video']
+                else:
+                    raise ExtractorError('Unable to find video info')
+
+            show = bootstrapped_data['show']
             show_title = show['title']
             segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']]
 

youtube_dl/extractor/aftenposten.py

@@ -1,23 +1,13 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-    parse_iso8601,
-    xpath_with_ns,
-    xpath_text,
-    find_xpath_attr,
-)
 
 
 class AftenpostenIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?aftenposten\.no/webtv/([^/]+/)*(?P<id>[^/]+)-\d+\.html'
-
+    _VALID_URL = r'https?://(?:www\.)?aftenposten\.no/webtv/(?:#!/)?video/(?P<id>\d+)'
     _TEST = {
-        'url': 'http://www.aftenposten.no/webtv/serier-og-programmer/sweatshopenglish/TRAILER-SWEATSHOP---I-cant-take-any-more-7800835.html?paging=&section=webtv_serierogprogrammer_sweatshop_sweatshopenglish',
+        'url': 'http://www.aftenposten.no/webtv/#!/video/21039/trailer-sweatshop-i-can-t-take-any-more',
         'md5': 'fd828cd29774a729bf4d4425fe192972',
         'info_dict': {
             'id': '21039',
@@ -30,74 +20,4 @@ class AftenpostenIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        display_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, display_id)
-
-        video_id = self._html_search_regex(
-            r'data-xs-id="(\d+)"', webpage, 'video id')
-
-        data = self._download_xml(
-            'http://frontend.xstream.dk/ap/feed/video/?platform=web&id=%s' % video_id, video_id)
-
-        NS_MAP = {
-            'atom': 'http://www.w3.org/2005/Atom',
-            'xt': 'http://xstream.dk/',
-            'media': 'http://search.yahoo.com/mrss/',
-        }
-
-        entry = data.find(xpath_with_ns('./atom:entry', NS_MAP))
-
-        title = xpath_text(
-            entry, xpath_with_ns('./atom:title', NS_MAP), 'title')
-        description = xpath_text(
-            entry, xpath_with_ns('./atom:summary', NS_MAP), 'description')
-        timestamp = parse_iso8601(xpath_text(
-            entry, xpath_with_ns('./atom:published', NS_MAP), 'upload date'))
-
-        formats = []
-        media_group = entry.find(xpath_with_ns('./media:group', NS_MAP))
-        for media_content in media_group.findall(xpath_with_ns('./media:content', NS_MAP)):
-            media_url = media_content.get('url')
-            if not media_url:
-                continue
-            tbr = int_or_none(media_content.get('bitrate'))
-            mobj = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', media_url)
-            if mobj:
-                formats.append({
-                    'url': mobj.group('url'),
-                    'play_path': 'mp4:%s' % mobj.group('playpath'),
-                    'app': mobj.group('app'),
-                    'ext': 'flv',
-                    'tbr': tbr,
-                    'format_id': 'rtmp-%d' % tbr,
-                })
-            else:
-                formats.append({
-                    'url': media_url,
-                    'tbr': tbr,
-                })
-        self._sort_formats(formats)
-
-        link = find_xpath_attr(
-            entry, xpath_with_ns('./atom:link', NS_MAP), 'rel', 'original')
-        if link is not None:
-            formats.append({
-                'url': link.get('href'),
-                'format_id': link.get('rel'),
-            })
-
-        thumbnails = [{
-            'url': splash.get('url'),
-            'width': int_or_none(splash.get('width')),
-            'height': int_or_none(splash.get('height')),
-        } for splash in media_group.findall(xpath_with_ns('./xt:splash', NS_MAP))]
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'timestamp': timestamp,
-            'formats': formats,
-            'thumbnails': thumbnails,
-        }
+        return self.url_result('xstream:ap:%s' % self._match_id(url), 'Xstream')

youtube_dl/extractor/aftonbladet.py

@@ -2,14 +2,15 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..utils import int_or_none
 
 
 class AftonbladetIE(InfoExtractor):
-    _VALID_URL = r'^http://tv\.aftonbladet\.se/webbtv.+?(?P<video_id>article[0-9]+)\.ab(?:$|[?#])'
+    _VALID_URL = r'http://tv\.aftonbladet\.se/abtv/articles/(?P<id>[0-9]+)'
     _TEST = {
-        'url': 'http://tv.aftonbladet.se/webbtv/nyheter/vetenskap/rymden/article36015.ab',
+        'url': 'http://tv.aftonbladet.se/abtv/articles/36015',
         'info_dict': {
-            'id': 'article36015',
+            'id': '36015',
             'ext': 'mp4',
             'title': 'Vulkanutbrott i rymden - nu släpper NASA bilderna',
             'description': 'Jupiters måne mest aktiv av alla himlakroppar',
@@ -24,8 +25,9 @@ class AftonbladetIE(InfoExtractor):
 
         # 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')
+        player_config = self._parse_json(self._html_search_regex(
+            r'data-player-config="([^"]+)"', webpage, 'player config'), video_id)
+        internal_meta_id = player_config['videoId']
         internal_meta_url = meta_url % internal_meta_id
         internal_meta_json = self._download_json(
             internal_meta_url, video_id, 'Downloading video meta data')
@@ -43,9 +45,9 @@ class AftonbladetIE(InfoExtractor):
             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'],
+                'width': int_or_none(fmt.get('width')),
+                'height': int_or_none(fmt.get('height')),
+                'tbr': int_or_none(fmt.get('bitrate')),
                 'protocol': 'http',
             })
         self._sort_formats(formats)
@@ -54,9 +56,9 @@ class AftonbladetIE(InfoExtractor):
             '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'],
+            'thumbnail': internal_meta_json.get('imageUrl'),
+            'description': internal_meta_json.get('shortPreamble'),
+            'timestamp': int_or_none(internal_meta_json.get('timePublished')),
+            'duration': int_or_none(internal_meta_json.get('duration')),
+            'view_count': int_or_none(internal_meta_json.get('views')),
         }

youtube_dl/extractor/airmozilla.py

@@ -0,0 +1,74 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_duration,
+    parse_iso8601,
+)
+
+
+class AirMozillaIE(InfoExtractor):
+    _VALID_URL = r'https?://air\.mozilla\.org/(?P<id>[0-9a-z-]+)/?'
+    _TEST = {
+        'url': 'https://air.mozilla.org/privacy-lab-a-meetup-for-privacy-minded-people-in-san-francisco/',
+        'md5': '2e3e7486ba5d180e829d453875b9b8bf',
+        'info_dict': {
+            'id': '6x4q2w',
+            'ext': 'mp4',
+            'title': 'Privacy Lab - a meetup for privacy minded people in San Francisco',
+            'thumbnail': 're:https://\w+\.cloudfront\.net/6x4q2w/poster\.jpg\?t=\d+',
+            'description': 'Brings together privacy professionals and others interested in privacy at for-profits, non-profits, and NGOs in an effort to contribute to the state of the ecosystem...',
+            'timestamp': 1422487800,
+            'upload_date': '20150128',
+            'location': 'SFO Commons',
+            'duration': 3780,
+            'view_count': int,
+            'categories': ['Main'],
+        }
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        video_id = self._html_search_regex(r'//vid.ly/(.*?)/embed', webpage, 'id')
+
+        embed_script = self._download_webpage('https://vid.ly/{0}/embed'.format(video_id), video_id)
+        jwconfig = self._search_regex(r'\svar jwconfig = (\{.*?\});\s', embed_script, 'metadata')
+        metadata = self._parse_json(jwconfig, video_id)
+
+        formats = [{
+            'url': source['file'],
+            'ext': source['type'],
+            'format_id': self._search_regex(r'&format=(.*)$', source['file'], 'video format'),
+            'format': source['label'],
+            'height': int(source['label'].rstrip('p')),
+        } for source in metadata['playlist'][0]['sources']]
+        self._sort_formats(formats)
+
+        view_count = int_or_none(self._html_search_regex(
+            r'Views since archived: ([0-9]+)',
+            webpage, 'view count', fatal=False))
+        timestamp = parse_iso8601(self._html_search_regex(
+            r'<time datetime="(.*?)"', webpage, 'timestamp', fatal=False))
+        duration = parse_duration(self._search_regex(
+            r'Duration:\s*(\d+\s*hours?\s*\d+\s*minutes?)',
+            webpage, 'duration', fatal=False))
+
+        return {
+            'id': video_id,
+            'title': self._og_search_title(webpage),
+            'formats': formats,
+            'url': self._og_search_url(webpage),
+            'display_id': display_id,
+            'thumbnail': metadata['playlist'][0].get('image'),
+            'description': self._og_search_description(webpage),
+            'timestamp': timestamp,
+            'location': self._html_search_regex(r'Location: (.*)', webpage, 'location', default=None),
+            'duration': duration,
+            'view_count': view_count,
+            'categories': re.findall(r'<a href=".*?" class="channel">(.*?)</a>', webpage),
+        }

youtube_dl/extractor/appleconnect.py

@@ -0,0 +1,50 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    str_to_int,
+    ExtractorError
+)
+
+
+class AppleConnectIE(InfoExtractor):
+    _VALID_URL = r'https?://itunes\.apple\.com/\w{0,2}/?post/idsa\.(?P<id>[\w-]+)'
+    _TEST = {
+        'url': 'https://itunes.apple.com/us/post/idsa.4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
+        'md5': '10d0f2799111df4cb1c924520ca78f98',
+        'info_dict': {
+            'id': '4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
+            'ext': 'm4v',
+            'title': 'Energy',
+            'uploader': 'Drake',
+            'thumbnail': 'http://is5.mzstatic.com/image/thumb/Video5/v4/78/61/c5/7861c5fa-ad6d-294b-1464-cf7605b911d6/source/1920x1080sr.jpg',
+            'upload_date': '20150710',
+            'timestamp': 1436545535,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        try:
+            video_json = self._html_search_regex(
+                r'class="auc-video-data">(\{.*?\})', webpage, 'json')
+        except ExtractorError:
+            raise ExtractorError('This post doesn\'t contain a video', expected=True)
+
+        video_data = self._parse_json(video_json, video_id)
+        timestamp = str_to_int(self._html_search_regex(r'data-timestamp="(\d+)"', webpage, 'timestamp'))
+        like_count = str_to_int(self._html_search_regex(r'(\d+) Loves', webpage, 'like count'))
+
+        return {
+            'id': video_id,
+            'url': video_data['sslSrc'],
+            'title': video_data['title'],
+            'description': video_data['description'],
+            'uploader': video_data['artistName'],
+            'thumbnail': video_data['artworkUrl'],
+            'timestamp': timestamp,
+            'like_count': like_count,
+        }

youtube_dl/extractor/archiveorg.py

@@ -33,7 +33,7 @@ class ArchiveOrgIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        json_url = url + ('?' if '?' in url else '&') + 'output=json'
+        json_url = url + ('&' if '?' in url else '?') + 'output=json'
         data = self._download_json(json_url, video_id)
 
         def get_optional(data_dict, field):

youtube_dl/extractor/ard.py

@@ -8,6 +8,7 @@ from .generic import GenericIE
 from ..utils import (
     determine_ext,
     ExtractorError,
+    get_element_by_attribute,
     qualities,
     int_or_none,
     parse_duration,
@@ -22,19 +23,125 @@ class ARDMediathekIE(InfoExtractor):
     _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
 
     _TESTS = [{
+        'url': 'http://www.ardmediathek.de/tv/Dokumentation-und-Reportage/Ich-liebe-das-Leben-trotzdem/rbb-Fernsehen/Video?documentId=29582122&bcastId=3822114',
+        'info_dict': {
+            'id': '29582122',
+            'ext': 'mp4',
+            'title': 'Ich liebe das Leben trotzdem',
+            'description': 'md5:45e4c225c72b27993314b31a84a5261c',
+            'duration': 4557,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://www.ardmediathek.de/tv/Tatort/Tatort-Scheinwelten-H%C3%B6rfassung-Video/Das-Erste/Video?documentId=29522730&bcastId=602916',
+        'md5': 'f4d98b10759ac06c0072bbcd1f0b9e3e',
+        'info_dict': {
+            'id': '29522730',
+            'ext': 'mp4',
+            'title': 'Tatort: Scheinwelten - Hörfassung (Video tgl. ab 20 Uhr)',
+            'description': 'md5:196392e79876d0ac94c94e8cdb2875f1',
+            'duration': 5252,
+        },
+    }, {
+        # audio
+        'url': 'http://www.ardmediathek.de/tv/WDR-H%C3%B6rspiel-Speicher/Tod-eines-Fu%C3%9Fballers/WDR-3/Audio-Podcast?documentId=28488308&bcastId=23074086',
+        'md5': '219d94d8980b4f538c7fcb0865eb7f2c',
+        'info_dict': {
+            'id': '28488308',
+            'ext': 'mp3',
+            'title': 'Tod eines Fußballers',
+            'description': 'md5:f6e39f3461f0e1f54bfa48c8875c86ef',
+            'duration': 3240,
+        },
+    }, {
         'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht',
         'only_matching': True,
-    }, {
-        '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 _extract_media_info(self, media_info_url, webpage, video_id):
+        media_info = self._download_json(
+            media_info_url, video_id, 'Downloading media JSON')
+
+        formats = self._extract_formats(media_info, video_id)
+
+        if not formats:
+            if '"fsk"' in webpage:
+                raise ExtractorError(
+                    'This video is only available after 20:00', expected=True)
+            elif media_info.get('_geoblocked'):
+                raise ExtractorError('This video is not available due to geo restriction', expected=True)
+
+        self._sort_formats(formats)
+
+        duration = int_or_none(media_info.get('_duration'))
+        thumbnail = media_info.get('_previewImage')
+
+        subtitles = {}
+        subtitle_url = media_info.get('_subtitleUrl')
+        if subtitle_url:
+            subtitles['de'] = [{
+                'ext': 'srt',
+                'url': subtitle_url,
+            }]
+
+        return {
+            'id': video_id,
+            'duration': duration,
+            'thumbnail': thumbnail,
+            'formats': formats,
+            'subtitles': subtitles,
+        }
+
+    def _extract_formats(self, media_info, video_id):
+        type_ = media_info.get('_type')
+        media_array = media_info.get('_mediaArray', [])
+        formats = []
+        for num, media in enumerate(media_array):
+            for stream in media.get('_mediaStreamArray', []):
+                stream_urls = stream.get('_stream')
+                if not stream_urls:
+                    continue
+                if not isinstance(stream_urls, list):
+                    stream_urls = [stream_urls]
+                quality = stream.get('_quality')
+                server = stream.get('_server')
+                for stream_url in stream_urls:
+                    ext = determine_ext(stream_url)
+                    if ext == 'f4m':
+                        formats.extend(self._extract_f4m_formats(
+                            stream_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124',
+                            video_id, preference=-1, f4m_id='hds'))
+                    elif ext == 'm3u8':
+                        formats.extend(self._extract_m3u8_formats(
+                            stream_url, video_id, 'mp4', preference=1, m3u8_id='hls'))
+                    else:
+                        if server and server.startswith('rtmp'):
+                            f = {
+                                'url': server,
+                                'play_path': stream_url,
+                                'format_id': 'a%s-rtmp-%s' % (num, quality),
+                            }
+                        elif stream_url.startswith('http'):
+                            f = {
+                                'url': stream_url,
+                                'format_id': 'a%s-%s-%s' % (num, ext, quality)
+                            }
+                        else:
+                            continue
+                        m = re.search(r'_(?P<width>\d+)x(?P<height>\d+)\.mp4$', stream_url)
+                        if m:
+                            f.update({
+                                'width': int(m.group('width')),
+                                'height': int(m.group('height')),
+                            })
+                        if type_ == 'audio':
+                            f['vcodec'] = 'none'
+                        formats.append(f)
+        return formats
+
     def _real_extract(self, url):
         # determine video id from url
         m = re.match(self._VALID_URL, url)
@@ -50,6 +157,9 @@ class ARDMediathekIE(InfoExtractor):
         if '>Der gewünschte Beitrag ist nicht mehr verfügbar.<' in webpage:
             raise ExtractorError('Video %s is no longer available' % video_id, expected=True)
 
+        if 'Diese Sendung ist für Jugendliche unter 12 Jahren nicht geeignet. Der Clip ist deshalb nur von 20 bis 6 Uhr verfügbar.' in webpage:
+            raise ExtractorError('This program is only suitable for those aged 12 and older. Video %s is therefore only available between 20 pm and 6 am.' % video_id, expected=True)
+
         if re.search(r'[\?&]rss($|[=&])', url):
             doc = parse_xml(webpage)
             if doc.tag == 'rss':
@@ -89,46 +199,22 @@ class ARDMediathekIE(InfoExtractor):
                     'format_id': fid,
                     'url': furl,
                 })
+            self._sort_formats(formats)
+            info = {
+                'formats': formats,
+            }
         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')
+            info = self._extract_media_info(
+                'http://www.ardmediathek.de/play/media/%s' % video_id, webpage, video_id)
 
-            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 {
+        info.update({
             'id': video_id,
             'title': title,
             'description': description,
-            'formats': formats,
             'thumbnail': thumbnail,
-        }
+        })
+
+        return info
 
 
 class ARDIE(InfoExtractor):
@@ -186,3 +272,41 @@ class ARDIE(InfoExtractor):
             'upload_date': upload_date,
             'thumbnail': thumbnail,
         }
+
+
+class SportschauIE(ARDMediathekIE):
+    IE_NAME = 'Sportschau'
+    _VALID_URL = r'(?P<baseurl>https?://(?:www\.)?sportschau\.de/(?:[^/]+/)+video(?P<id>[^/#?]+))\.html'
+    _TESTS = [{
+        'url': 'http://www.sportschau.de/tourdefrance/videoseppeltkokainhatnichtsmitklassischemdopingzutun100.html',
+        'info_dict': {
+            'id': 'seppeltkokainhatnichtsmitklassischemdopingzutun100',
+            'ext': 'mp4',
+            'title': 'Seppelt: "Kokain hat nichts mit klassischem Doping zu tun"',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'description': 'Der ARD-Doping Experte Hajo Seppelt gibt seine Einschätzung zum ersten Dopingfall der diesjährigen Tour de France um den Italiener Luca Paolini ab.',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        base_url = mobj.group('baseurl')
+
+        webpage = self._download_webpage(url, video_id)
+        title = get_element_by_attribute('class', 'headline', webpage)
+        description = self._html_search_meta('description', webpage, 'description')
+
+        info = self._extract_media_info(
+            base_url + '-mc_defaultQuality-h.json', webpage, video_id)
+
+        info.update({
+            'title': title,
+            'description': description,
+        })
+
+        return info

youtube_dl/extractor/arte.py

@@ -7,7 +7,6 @@ from .common import InfoExtractor
 from ..utils import (
     find_xpath_attr,
     unified_strdate,
-    get_element_by_id,
     get_element_by_attribute,
     int_or_none,
     qualities,
@@ -146,6 +145,7 @@ class ArteTVPlus7IE(InfoExtractor):
 
             formats.append(format)
 
+        self._check_formats(formats, video_id)
         self._sort_formats(formats)
 
         info_dict['formats'] = formats
@@ -194,7 +194,9 @@ class ArteTVFutureIE(ArteTVPlus7IE):
     def _real_extract(self, url):
         anchor_id, lang = self._extract_url_info(url)
         webpage = self._download_webpage(url, anchor_id)
-        row = get_element_by_id(anchor_id, webpage)
+        row = self._search_regex(
+            r'(?s)id="%s"[^>]*>.+?(<div[^>]*arte_vp_url[^>]*>)' % anchor_id,
+            webpage, 'row')
         return self._extract_from_webpage(row, anchor_id, lang)
 
 

youtube_dl/extractor/atresplayer.py

@@ -19,6 +19,7 @@ from ..utils import (
 
 class AtresPlayerIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?atresplayer\.com/television/[^/]+/[^/]+/[^/]+/(?P<id>.+?)_\d+\.html'
+    _NETRC_MACHINE = 'atresplayer'
     _TESTS = [
         {
             'url': 'http://www.atresplayer.com/television/programas/el-club-de-la-comedia/temporada-4/capitulo-10-especial-solidario-nochebuena_2014122100174.html',

youtube_dl/extractor/baidu.py

@@ -0,0 +1,69 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_urlparse
+
+
+class BaiduVideoIE(InfoExtractor):
+    IE_DESC = '百度视频'
+    _VALID_URL = r'http://v\.baidu\.com/(?P<type>[a-z]+)/(?P<id>\d+)\.htm'
+    _TESTS = [{
+        'url': 'http://v.baidu.com/comic/1069.htm?frp=bdbrand&q=%E4%B8%AD%E5%8D%8E%E5%B0%8F%E5%BD%93%E5%AE%B6',
+        'info_dict': {
+            'id': '1069',
+            'title': '中华小当家 TV版 (全52集)',
+            'description': 'md5:395a419e41215e531c857bb037bbaf80',
+        },
+        'playlist_count': 52,
+    }, {
+        'url': 'http://v.baidu.com/show/11595.htm?frp=bdbrand',
+        'info_dict': {
+            'id': '11595',
+            'title': 're:^奔跑吧兄弟',
+            'description': 'md5:1bf88bad6d850930f542d51547c089b8',
+        },
+        'playlist_mincount': 3,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        playlist_id = mobj.group('id')
+        category = category2 = mobj.group('type')
+        if category == 'show':
+            category2 = 'tvshow'
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        playlist_title = self._html_search_regex(
+            r'title\s*:\s*(["\'])(?P<title>[^\']+)\1', webpage,
+            'playlist title', group='title')
+        playlist_description = self._html_search_regex(
+            r'<input[^>]+class="j-data-intro"[^>]+value="([^"]+)"/>', webpage,
+            playlist_id, 'playlist description')
+
+        site = self._html_search_regex(
+            r'filterSite\s*:\s*["\']([^"]*)["\']', webpage,
+            'primary provider site')
+        api_result = self._download_json(
+            'http://v.baidu.com/%s_intro/?dtype=%sPlayUrl&id=%s&site=%s' % (
+                category, category2, playlist_id, site),
+            playlist_id, 'Get playlist links')
+
+        entries = []
+        for episode in api_result[0]['episodes']:
+            episode_id = '%s_%s' % (playlist_id, episode['episode'])
+
+            redirect_page = self._download_webpage(
+                compat_urlparse.urljoin(url, episode['url']), episode_id,
+                note='Download Baidu redirect page')
+            real_url = self._html_search_regex(
+                r'location\.replace\("([^"]+)"\)', redirect_page, 'real URL')
+
+            entries.append(self.url_result(
+                real_url, video_title=episode['single_title']))
+
+        return self.playlist_result(
+            entries, playlist_id, playlist_title, playlist_description)

youtube_dl/extractor/bambuser.py

@@ -1,12 +1,18 @@
 from __future__ import unicode_literals
 
 import re
-import json
 import itertools
 
 from .common import InfoExtractor
 from ..compat import (
+    compat_urllib_parse,
     compat_urllib_request,
+    compat_str,
+)
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    float_or_none,
 )
 
 
@@ -14,6 +20,8 @@ class BambuserIE(InfoExtractor):
     IE_NAME = 'bambuser'
     _VALID_URL = r'https?://bambuser\.com/v/(?P<id>\d+)'
     _API_KEY = '005f64509e19a868399060af746a00aa'
+    _LOGIN_URL = 'https://bambuser.com/user'
+    _NETRC_MACHINE = 'bambuser'
 
     _TEST = {
         'url': 'http://bambuser.com/v/4050584',
@@ -26,6 +34,9 @@ class BambuserIE(InfoExtractor):
             'duration': 3741,
             'uploader': 'pixelversity',
             'uploader_id': '344706',
+            'timestamp': 1382976692,
+            'upload_date': '20131028',
+            'view_count': int,
         },
         'params': {
             # It doesn't respect the 'Range' header, it would download the whole video
@@ -34,23 +45,60 @@ class BambuserIE(InfoExtractor):
         },
     }
 
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            return
+
+        login_form = {
+            'form_id': 'user_login',
+            'op': 'Log in',
+            'name': username,
+            'pass': password,
+        }
+
+        request = compat_urllib_request.Request(
+            self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
+        request.add_header('Referer', self._LOGIN_URL)
+        response = self._download_webpage(
+            request, None, 'Logging in as %s' % username)
+
+        login_error = self._html_search_regex(
+            r'(?s)<div class="messages error">(.+?)</div>',
+            response, 'login error', default=None)
+        if login_error:
+            raise ExtractorError(
+                'Unable to login: %s' % login_error, expected=True)
+
+    def _real_initialize(self):
+        self._login()
+
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        info_url = ('http://player-c.api.bambuser.com/getVideo.json?'
-                    '&api_key=%s&vid=%s' % (self._API_KEY, video_id))
-        info_json = self._download_webpage(info_url, video_id)
-        info = json.loads(info_json)['result']
+        video_id = self._match_id(url)
+
+        info = self._download_json(
+            'http://player-c.api.bambuser.com/getVideo.json?api_key=%s&vid=%s'
+            % (self._API_KEY, video_id), video_id)
+
+        error = info.get('error')
+        if error:
+            raise ExtractorError(
+                '%s returned error: %s' % (self.IE_NAME, error), expected=True)
+
+        result = info['result']
 
         return {
             'id': video_id,
-            'title': info['title'],
-            'url': info['url'],
-            'thumbnail': info.get('preview'),
-            'duration': int(info['length']),
-            'view_count': int(info['views_total']),
-            'uploader': info['username'],
-            'uploader_id': info['owner']['uid'],
+            'title': result['title'],
+            'url': result['url'],
+            'thumbnail': result.get('preview'),
+            'duration': int_or_none(result.get('length')),
+            'uploader': result.get('username'),
+            'uploader_id': compat_str(result.get('owner', {}).get('uid')),
+            'timestamp': int_or_none(result.get('created')),
+            'fps': float_or_none(result.get('framerate')),
+            'view_count': int_or_none(result.get('views_total')),
+            'comment_count': int_or_none(result.get('comment_count')),
         }
 
 

youtube_dl/extractor/bandcamp.py

@@ -72,7 +72,7 @@ class BandcampIE(InfoExtractor):
 
         download_link = m_download.group(1)
         video_id = self._search_regex(
-            r'(?ms)var TralbumData = {.*?id: (?P<id>\d+),?$',
+            r'(?ms)var TralbumData = .*?[{,]\s*id: (?P<id>\d+),?$',
             webpage, 'video id')
 
         download_webpage = self._download_webpage(download_link, video_id, 'Downloading free downloads page')

youtube_dl/extractor/bbc.py

@@ -0,0 +1,780 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    float_or_none,
+    int_or_none,
+    parse_duration,
+    parse_iso8601,
+)
+from ..compat import compat_HTTPError
+
+
+class BBCCoUkIE(InfoExtractor):
+    IE_NAME = 'bbc.co.uk'
+    IE_DESC = 'BBC iPlayer'
+    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})'
+
+    _MEDIASELECTOR_URLS = [
+        'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s',
+    ]
+
+    _TESTS = [
+        {
+            'url': 'http://www.bbc.co.uk/programmes/b039g8p7',
+            'info_dict': {
+                'id': 'b039d07m',
+                'ext': 'flv',
+                'title': 'Kaleidoscope, Leonard Cohen',
+                'description': 'The Canadian poet and songwriter reflects on his musical career.',
+                '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',
+        },
+        {
+            'url': 'http://www.bbc.co.uk/iplayer/episode/p026c7jt/tomorrows-worlds-the-unearthly-history-of-science-fiction-2-invasion',
+            'info_dict': {
+                'id': 'b03k3pb7',
+                'ext': 'flv',
+                'title': "Tomorrow's Worlds: The Unearthly History of Science Fiction",
+                'description': '2. Invasion',
+                'duration': 3600,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+            'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
+        }, {
+            'url': 'http://www.bbc.co.uk/programmes/b04v20dw',
+            'info_dict': {
+                'id': 'b04v209v',
+                'ext': 'flv',
+                'title': 'Pete Tong, The Essential New Tune Special',
+                'description': "Pete has a very special mix - all of 2014's Essential New Tunes!",
+                'duration': 10800,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            }
+        }, {
+            'url': 'http://www.bbc.co.uk/music/clips/p02frcc3',
+            'note': 'Audio',
+            'info_dict': {
+                'id': 'p02frcch',
+                'ext': 'flv',
+                'title': 'Pete Tong, Past, Present and Future Special, Madeon - After Hours mix',
+                'description': 'French house superstar Madeon takes us out of the club and onto the after party.',
+                'duration': 3507,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            }
+        }, {
+            'url': 'http://www.bbc.co.uk/music/clips/p025c0zz',
+            'note': 'Video',
+            'info_dict': {
+                'id': 'p025c103',
+                'ext': 'flv',
+                'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)',
+                'description': 'Rae Morris performs Closer for BBC Three at Reading 2014',
+                'duration': 226,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            }
+        }, {
+            'url': 'http://www.bbc.co.uk/iplayer/episode/b054fn09/ad/natural-world-20152016-2-super-powered-owls',
+            'info_dict': {
+                'id': 'p02n76xf',
+                'ext': 'flv',
+                'title': 'Natural World, 2015-2016: 2. Super Powered Owls',
+                'description': 'md5:e4db5c937d0e95a7c6b5e654d429183d',
+                'duration': 3540,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+            'skip': 'geolocation',
+        }, {
+            'url': 'http://www.bbc.co.uk/iplayer/episode/b05zmgwn/royal-academy-summer-exhibition',
+            'info_dict': {
+                'id': 'b05zmgw1',
+                'ext': 'flv',
+                'description': 'Kirsty Wark and Morgan Quaintance visit the Royal Academy as it prepares for its annual artistic extravaganza, meeting people who have come together to make the show unique.',
+                'title': 'Royal Academy Summer Exhibition',
+                'duration': 3540,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+            'skip': 'geolocation',
+        }, {
+            'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
+            'only_matching': True,
+        }, {
+            'url': 'http://www.bbc.co.uk/music/clips#p02frcc3',
+            'only_matching': True,
+        }, {
+            'url': 'http://www.bbc.co.uk/iplayer/cbeebies/episode/b0480276/bing-14-atchoo',
+            'only_matching': True,
+        }
+    ]
+
+    class MediaSelectionError(Exception):
+        def __init__(self, id):
+            self.id = id
+
+    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')
+            transfer_format = connection.get('transferFormat')
+            # 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),
+                    })
+            # Skip DASH until supported
+            elif transfer_format == 'dash':
+                pass
+            # 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):
+        error = media_selection.find('./{http://bbc.co.uk/2008/mp/mediaselection}error')
+        if error is not None:
+            raise BBCCoUkIE.MediaSelectionError(error.get('id'))
+        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_or_none(media.get('bitrate'))
+        vcodec = media.get('encoding')
+        service = media.get('service')
+        width = int_or_none(media.get('width'))
+        height = int_or_none(media.get('height'))
+        file_size = int_or_none(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_or_none(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 _get_subtitles(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')
+            subtitles[lang] = [
+                {
+                    'url': connection.get('href'),
+                    'ext': 'ttml',
+                },
+            ]
+        return subtitles
+
+    def _raise_extractor_error(self, media_selection_error):
+        raise ExtractorError(
+            '%s returned error: %s' % (self.IE_NAME, media_selection_error.id),
+            expected=True)
+
+    def _download_media_selector(self, programme_id):
+        last_exception = None
+        for mediaselector_url in self._MEDIASELECTOR_URLS:
+            try:
+                return self._download_media_selector_url(
+                    mediaselector_url % programme_id, programme_id)
+            except BBCCoUkIE.MediaSelectionError as e:
+                if e.id == 'notukerror':
+                    last_exception = e
+                    continue
+                self._raise_extractor_error(e)
+        self._raise_extractor_error(last_exception)
+
+    def _download_media_selector_url(self, url, programme_id=None):
+        try:
+            media_selection = self._download_xml(
+                url, programme_id, 'Downloading media selection XML')
+        except ExtractorError as ee:
+            if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
+                media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().decode('utf-8'))
+            else:
+                raise
+        return self._process_media_selector(media_selection, programme_id)
+
+    def _process_media_selector(self, media_selection, programme_id):
+        formats = []
+        subtitles = None
+
+        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_subtitles(media, programme_id)
+        return formats, subtitles
+
+    def _download_playlist(self, playlist_id):
+        try:
+            playlist = self._download_json(
+                'http://www.bbc.co.uk/programmes/%s/playlist.json' % playlist_id,
+                playlist_id, 'Downloading playlist JSON')
+
+            version = playlist.get('defaultAvailableVersion')
+            if version:
+                smp_config = version['smpConfig']
+                title = smp_config['title']
+                description = smp_config['summary']
+                for item in smp_config['items']:
+                    kind = item['kind']
+                    if kind != 'programme' and kind != 'radioProgramme':
+                        continue
+                    programme_id = item.get('vpid')
+                    duration = int_or_none(item.get('duration'))
+                    formats, subtitles = self._download_media_selector(programme_id)
+                return programme_id, title, description, duration, formats, subtitles
+        except ExtractorError as ee:
+            if not (isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404):
+                raise
+
+        # fallback to legacy playlist
+        return self._process_legacy_playlist(playlist_id)
+
+    def _process_legacy_playlist_url(self, url, display_id):
+        playlist = self._download_legacy_playlist_url(url, display_id)
+        return self._extract_from_legacy_playlist(playlist, display_id)
+
+    def _process_legacy_playlist(self, playlist_id):
+        return self._process_legacy_playlist_url(
+            'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id, playlist_id)
+
+    def _download_legacy_playlist_url(self, url, playlist_id=None):
+        return self._download_xml(
+            url, playlist_id, 'Downloading legacy playlist XML')
+
+    def _extract_from_legacy_playlist(self, playlist, playlist_id):
+        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' % playlist_id
+            elif reason == 'postAvailability':
+                msg = 'Episode %s is no longer available' % playlist_id
+            elif reason == 'noMedia':
+                msg = 'Episode %s is not currently available' % playlist_id
+            else:
+                msg = 'Episode %s is not available: %s' % (playlist_id, reason)
+            raise ExtractorError(msg, expected=True)
+
+        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
+
+            def get_programme_id(item):
+                def get_from_attributes(item):
+                    for p in('identifier', 'group'):
+                        value = item.get(p)
+                        if value and re.match(r'^[pb][\da-z]{7}$', value):
+                            return value
+                get_from_attributes(item)
+                mediator = item.find('./{http://bbc.co.uk/2008/emp/playlist}mediator')
+                if mediator is not None:
+                    return get_from_attributes(mediator)
+
+            programme_id = get_programme_id(item)
+            duration = int_or_none(item.get('duration'))
+            # TODO: programme_id can be None and media items can be incorporated right inside
+            # playlist's item (e.g. http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu)
+            # as f4m and m3u8
+            formats, subtitles = self._download_media_selector(programme_id)
+
+        return programme_id, title, description, duration, formats, subtitles
+
+    def _real_extract(self, url):
+        group_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, group_id, 'Downloading video page')
+
+        programme_id = None
+
+        tviplayer = self._search_regex(
+            r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById',
+            webpage, 'player', default=None)
+
+        if tviplayer:
+            player = self._parse_json(tviplayer, group_id).get('player', {})
+            duration = int_or_none(player.get('duration'))
+            programme_id = player.get('vpid')
+
+        if not programme_id:
+            programme_id = self._search_regex(
+                r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None)
+
+        if programme_id:
+            formats, subtitles = self._download_media_selector(programme_id)
+            title = self._og_search_title(webpage)
+            description = self._search_regex(
+                r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>',
+                webpage, 'description', fatal=False)
+        else:
+            programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
+
+        self._sort_formats(formats)
+
+        return {
+            'id': programme_id,
+            'title': title,
+            'description': description,
+            'thumbnail': self._og_search_thumbnail(webpage, default=None),
+            'duration': duration,
+            'formats': formats,
+            'subtitles': subtitles,
+        }
+
+
+class BBCIE(BBCCoUkIE):
+    IE_NAME = 'bbc'
+    IE_DESC = 'BBC'
+    _VALID_URL = r'https?://(?:www\.)?bbc\.(?:com|co\.uk)/(?:[^/]+/)+(?P<id>[^/#?]+)'
+
+    _MEDIASELECTOR_URLS = [
+        # Provides more formats, namely direct mp4 links, but fails on some videos with
+        # notukerror for non UK (?) users (e.g.
+        # http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
+        'http://open.live.bbc.co.uk/mediaselector/4/mtis/stream/%s',
+        # Provides fewer formats, but works everywhere for everybody (hopefully)
+        'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/journalism-pc/vpid/%s',
+    ]
+
+    _TESTS = [{
+        # article with multiple videos embedded with data-media-meta containing
+        # playlist.sxml, externalId and no direct video links
+        'url': 'http://www.bbc.com/news/world-europe-32668511',
+        'info_dict': {
+            'id': 'world-europe-32668511',
+            'title': 'Russia stages massive WW2 parade despite Western boycott',
+            'description': 'md5:00ff61976f6081841f759a08bf78cc9c',
+        },
+        'playlist_count': 2,
+    }, {
+        # article with multiple videos embedded with data-media-meta (more videos)
+        'url': 'http://www.bbc.com/news/business-28299555',
+        'info_dict': {
+            'id': 'business-28299555',
+            'title': 'Farnborough Airshow: Video highlights',
+            'description': 'BBC reports and video highlights at the Farnborough Airshow.',
+        },
+        'playlist_count': 9,
+        'skip': 'Save time',
+    }, {
+        # article with multiple videos embedded with `new SMP()`
+        'url': 'http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460',
+        'info_dict': {
+            'id': '3662a707-0af9-3149-963f-47bea720b460',
+            'title': 'BBC Blogs - Adam Curtis - BUGGER',
+        },
+        'playlist_count': 18,
+    }, {
+        # single video embedded with mediaAssetPage.init()
+        'url': 'http://www.bbc.com/news/world-europe-32041533',
+        'info_dict': {
+            'id': 'p02mprgb',
+            'ext': 'mp4',
+            'title': 'Aerial footage showed the site of the crash in the Alps - courtesy BFM TV',
+            'duration': 47,
+            'timestamp': 1427219242,
+            'upload_date': '20150324',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }, {
+        # article with single video embedded with data-media-meta containing
+        # direct video links (for now these are extracted) and playlist.xml (with
+        # media items as f4m and m3u8 - currently unsupported)
+        'url': 'http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu',
+        'info_dict': {
+            'id': '150615_telabyad_kentin_cogu',
+            'ext': 'mp4',
+            'title': "YPG: Tel Abyad'ın tamamı kontrolümüzde",
+            'duration': 47,
+            'timestamp': 1434397334,
+            'upload_date': '20150615',
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        # single video embedded with mediaAssetPage.init() (regional section)
+        'url': 'http://www.bbc.com/mundo/video_fotos/2015/06/150619_video_honduras_militares_hospitales_corrupcion_aw',
+        'info_dict': {
+            'id': '150619_video_honduras_militares_hospitales_corrupcion_aw',
+            'ext': 'mp4',
+            'title': 'Honduras militariza sus hospitales por nuevo escándalo de corrupción',
+            'duration': 87,
+            'timestamp': 1434713142,
+            'upload_date': '20150619',
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        # single video from video playlist embedded with vxp-playlist-data JSON
+        'url': 'http://www.bbc.com/news/video_and_audio/must_see/33376376',
+        'info_dict': {
+            'id': 'p02w6qjc',
+            'ext': 'mp4',
+            'title': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''',
+            'duration': 56,
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        # single video story with digitalData
+        'url': 'http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret',
+        'info_dict': {
+            'id': 'p02q6gc4',
+            'ext': 'flv',
+            'title': 'Sri Lanka’s spicy secret',
+            'description': 'As a new train line to Jaffna opens up the country’s north, travellers can experience a truly distinct slice of Tamil culture.',
+            'timestamp': 1437674293,
+            'upload_date': '20150723',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }, {
+        # single video story without digitalData
+        'url': 'http://www.bbc.com/autos/story/20130513-hyundais-rock-star',
+        'info_dict': {
+            'id': 'p018zqqg',
+            'ext': 'mp4',
+            'title': 'Hyundai Santa Fe Sport: Rock star',
+            'description': 'md5:b042a26142c4154a6e472933cf20793d',
+            'timestamp': 1368473503,
+            'upload_date': '20130513',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }, {
+        # single video with playlist.sxml URL
+        'url': 'http://www.bbc.com/sport/0/football/33653409',
+        'info_dict': {
+            'id': 'p02xycnp',
+            'ext': 'mp4',
+            'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?',
+            'description': 'md5:398fca0e2e701c609d726e034fa1fc89',
+            'duration': 140,
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }, {
+        # single video with playlist URL from weather section
+        'url': 'http://www.bbc.com/weather/features/33601775',
+        'only_matching': True,
+    }, {
+        # custom redirection to www.bbc.com
+        'url': 'http://www.bbc.co.uk/news/science-environment-33661876',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return False if BBCCoUkIE.suitable(url) else super(BBCIE, cls).suitable(url)
+
+    def _extract_from_media_meta(self, media_meta, video_id):
+        # Direct links to media in media metadata (e.g.
+        # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu)
+        # TODO: there are also f4m and m3u8 streams incorporated in playlist.sxml
+        source_files = media_meta.get('sourceFiles')
+        if source_files:
+            return [{
+                'url': f['url'],
+                'format_id': format_id,
+                'ext': f.get('encoding'),
+                'tbr': float_or_none(f.get('bitrate'), 1000),
+                'filesize': int_or_none(f.get('filesize')),
+            } for format_id, f in source_files.items() if f.get('url')], []
+
+        programme_id = media_meta.get('externalId')
+        if programme_id:
+            return self._download_media_selector(programme_id)
+
+        # Process playlist.sxml as legacy playlist
+        href = media_meta.get('href')
+        if href:
+            playlist = self._download_legacy_playlist_url(href)
+            _, _, _, _, formats, subtitles = self._extract_from_legacy_playlist(playlist, video_id)
+            return formats, subtitles
+
+        return [], []
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        timestamp = parse_iso8601(self._search_regex(
+            [r'"datePublished":\s*"([^"]+)',
+             r'<meta[^>]+property="article:published_time"[^>]+content="([^"]+)"',
+             r'itemprop="datePublished"[^>]+datetime="([^"]+)"'],
+            webpage, 'date', default=None))
+
+        # single video with playlist.sxml URL (e.g. http://www.bbc.com/sport/0/football/3365340ng)
+        playlist = self._search_regex(
+            r'<param[^>]+name="playlist"[^>]+value="([^"]+)"',
+            webpage, 'playlist', default=None)
+        if playlist:
+            programme_id, title, description, duration, formats, subtitles = \
+                self._process_legacy_playlist_url(playlist, playlist_id)
+            self._sort_formats(formats)
+            return {
+                'id': programme_id,
+                'title': title,
+                'description': description,
+                'duration': duration,
+                'timestamp': timestamp,
+                'formats': formats,
+                'subtitles': subtitles,
+            }
+
+        # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
+        programme_id = self._search_regex(
+            [r'data-video-player-vpid="([\da-z]{8})"',
+             r'<param[^>]+name="externalIdentifier"[^>]+value="([\da-z]{8})"'],
+            webpage, 'vpid', default=None)
+        if programme_id:
+            formats, subtitles = self._download_media_selector(programme_id)
+            self._sort_formats(formats)
+            # digitalData may be missing (e.g. http://www.bbc.com/autos/story/20130513-hyundais-rock-star)
+            digital_data = self._parse_json(
+                self._search_regex(
+                    r'var\s+digitalData\s*=\s*({.+?});?\n', webpage, 'digital data', default='{}'),
+                programme_id, fatal=False)
+            page_info = digital_data.get('page', {}).get('pageInfo', {})
+            title = page_info.get('pageName') or self._og_search_title(webpage)
+            description = page_info.get('description') or self._og_search_description(webpage)
+            timestamp = parse_iso8601(page_info.get('publicationDate')) or timestamp
+            return {
+                'id': programme_id,
+                'title': title,
+                'description': description,
+                'timestamp': timestamp,
+                'formats': formats,
+                'subtitles': subtitles,
+            }
+
+        playlist_title = self._html_search_regex(
+            r'<title>(.*?)(?:\s*-\s*BBC [^ ]+)?</title>', webpage, 'playlist title')
+        playlist_description = self._og_search_description(webpage, default=None)
+
+        def extract_all(pattern):
+            return list(filter(None, map(
+                lambda s: self._parse_json(s, playlist_id, fatal=False),
+                re.findall(pattern, webpage))))
+
+        # Multiple video article (e.g.
+        # http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460)
+        EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+[\da-z]{8}(?:\b[^"]+)?'
+        entries = []
+        for match in extract_all(r'new\s+SMP\(({.+?})\)'):
+            embed_url = match.get('playerSettings', {}).get('externalEmbedUrl')
+            if embed_url and re.match(EMBED_URL, embed_url):
+                entries.append(embed_url)
+        entries.extend(re.findall(
+            r'setPlaylist\("(%s)"\)' % EMBED_URL, webpage))
+        if entries:
+            return self.playlist_result(
+                [self.url_result(entry, 'BBCCoUk') for entry in entries],
+                playlist_id, playlist_title, playlist_description)
+
+        # Multiple video article (e.g. http://www.bbc.com/news/world-europe-32668511)
+        medias = extract_all(r"data-media-meta='({[^']+})'")
+
+        if not medias:
+            # Single video article (e.g. http://www.bbc.com/news/video_and_audio/international)
+            media_asset = self._search_regex(
+                r'mediaAssetPage\.init\(\s*({.+?}), "/',
+                webpage, 'media asset', default=None)
+            if media_asset:
+                media_asset_page = self._parse_json(media_asset, playlist_id, fatal=False)
+                medias = []
+                for video in media_asset_page.get('videos', {}).values():
+                    medias.extend(video.values())
+
+        if not medias:
+            # Multiple video playlist with single `now playing` entry (e.g.
+            # http://www.bbc.com/news/video_and_audio/must_see/33767813)
+            vxp_playlist = self._parse_json(
+                self._search_regex(
+                    r'<script[^>]+class="vxp-playlist-data"[^>]+type="application/json"[^>]*>([^<]+)</script>',
+                    webpage, 'playlist data'),
+                playlist_id)
+            playlist_medias = []
+            for item in vxp_playlist:
+                media = item.get('media')
+                if not media:
+                    continue
+                playlist_medias.append(media)
+                # Download single video if found media with asset id matching the video id from URL
+                if item.get('advert', {}).get('assetId') == playlist_id:
+                    medias = [media]
+                    break
+            # Fallback to the whole playlist
+            if not medias:
+                medias = playlist_medias
+
+        entries = []
+        for num, media_meta in enumerate(medias, start=1):
+            formats, subtitles = self._extract_from_media_meta(media_meta, playlist_id)
+            if not formats:
+                continue
+            self._sort_formats(formats)
+
+            video_id = media_meta.get('externalId')
+            if not video_id:
+                video_id = playlist_id if len(medias) == 1 else '%s-%s' % (playlist_id, num)
+
+            title = media_meta.get('caption')
+            if not title:
+                title = playlist_title if len(medias) == 1 else '%s - Video %s' % (playlist_title, num)
+
+            duration = int_or_none(media_meta.get('durationInSeconds')) or parse_duration(media_meta.get('duration'))
+
+            images = []
+            for image in media_meta.get('images', {}).values():
+                images.extend(image.values())
+            if 'image' in media_meta:
+                images.append(media_meta['image'])
+
+            thumbnails = [{
+                'url': image.get('href'),
+                'width': int_or_none(image.get('width')),
+                'height': int_or_none(image.get('height')),
+            } for image in images]
+
+            entries.append({
+                'id': video_id,
+                'title': title,
+                'thumbnails': thumbnails,
+                'duration': duration,
+                'timestamp': timestamp,
+                'formats': formats,
+                'subtitles': subtitles,
+            })
+
+        return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)

youtube_dl/extractor/bbccouk.py

@@ -1,351 +0,0 @@
-from __future__ import unicode_literals
-
-import xml.etree.ElementTree
-
-from .common import InfoExtractor
-from ..utils import ExtractorError
-from ..compat import compat_HTTPError
-
-
-class BBCCoUkIE(InfoExtractor):
-    IE_NAME = 'bbc.co.uk'
-    IE_DESC = 'BBC iPlayer'
-    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?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': 'The Canadian poet and songwriter reflects on his musical career.',
-                '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',
-        },
-        {
-            'url': 'http://www.bbc.co.uk/iplayer/episode/p026c7jt/tomorrows-worlds-the-unearthly-history-of-science-fiction-2-invasion',
-            'info_dict': {
-                'id': 'b03k3pb7',
-                'ext': 'flv',
-                'title': "Tomorrow's Worlds: The Unearthly History of Science Fiction",
-                'description': '2. Invasion',
-                'duration': 3600,
-            },
-            'params': {
-                # rtmp download
-                'skip_download': True,
-            },
-            'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
-        }, {
-            'url': 'http://www.bbc.co.uk/programmes/b04v20dw',
-            'info_dict': {
-                'id': 'b04v209v',
-                'ext': 'flv',
-                'title': 'Pete Tong, The Essential New Tune Special',
-                'description': "Pete has a very special mix - all of 2014's Essential New Tunes!",
-                'duration': 10800,
-            },
-            'params': {
-                # rtmp download
-                'skip_download': True,
-            }
-        }, {
-            'url': 'http://www.bbc.co.uk/music/clips/p02frcc3',
-            'note': 'Audio',
-            'info_dict': {
-                'id': 'p02frcch',
-                'ext': 'flv',
-                'title': 'Pete Tong, Past, Present and Future Special, Madeon - After Hours mix',
-                'description': 'French house superstar Madeon takes us out of the club and onto the after party.',
-                'duration': 3507,
-            },
-            'params': {
-                # rtmp download
-                'skip_download': True,
-            }
-        }, {
-            'url': 'http://www.bbc.co.uk/music/clips/p025c0zz',
-            'note': 'Video',
-            'info_dict': {
-                'id': 'p025c103',
-                'ext': 'flv',
-                'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)',
-                'description': 'Rae Morris performs Closer for BBC Three at Reading 2014',
-                'duration': 226,
-            },
-            'params': {
-                # rtmp download
-                'skip_download': True,
-            }
-        }, {
-            'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
-            'only_matching': True,
-        }, {
-            'url': 'http://www.bbc.co.uk/music/clips#p02frcc3',
-            'only_matching': True,
-        }, {
-            'url': 'http://www.bbc.co.uk/iplayer/cbeebies/episode/b0480276/bing-14-atchoo',
-            'only_matching': True,
-        }
-    ]
-
-    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):
-        error = media_selection.find('./{http://bbc.co.uk/2008/mp/mediaselection}error')
-        if error is not None:
-            raise ExtractorError(
-                '%s returned error: %s' % (self.IE_NAME, error.get('id')), expected=True)
-        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 _get_subtitles(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 = ''
-
-            def _extract_text(p):
-                if p.text is not None:
-                    stripped_text = p.text.strip()
-                    if stripped_text:
-                        return stripped_text
-                return ' '.join(span.text.strip() for span in p.findall('{http://www.w3.org/2006/10/ttaf1}span'))
-            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'), _extract_text(p))
-            subtitles[lang] = [
-                {
-                    'url': connection.get('href'),
-                    'ext': 'ttml',
-                },
-                {
-                    'data': srt,
-                    'ext': 'srt',
-                },
-            ]
-        return subtitles
-
-    def _download_media_selector(self, programme_id):
-        try:
-            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')
-        except ExtractorError as ee:
-            if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
-                media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().encode('utf-8'))
-            else:
-                raise
-
-        formats = []
-        subtitles = None
-
-        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_subtitles(media, programme_id)
-
-        return formats, subtitles
-
-    def _download_playlist(self, playlist_id):
-        try:
-            playlist = self._download_json(
-                'http://www.bbc.co.uk/programmes/%s/playlist.json' % playlist_id,
-                playlist_id, 'Downloading playlist JSON')
-
-            version = playlist.get('defaultAvailableVersion')
-            if version:
-                smp_config = version['smpConfig']
-                title = smp_config['title']
-                description = smp_config['summary']
-                for item in smp_config['items']:
-                    kind = item['kind']
-                    if kind != 'programme' and kind != 'radioProgramme':
-                        continue
-                    programme_id = item.get('vpid')
-                    duration = int(item.get('duration'))
-                    formats, subtitles = self._download_media_selector(programme_id)
-                return programme_id, title, description, duration, formats, subtitles
-        except ExtractorError as ee:
-            if not (isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404):
-                raise
-
-        # fallback to legacy playlist
-        playlist = self._download_xml(
-            'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id,
-            playlist_id, 'Downloading legacy 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' % playlist_id
-            elif reason == 'postAvailability':
-                msg = 'Episode %s is no longer available' % playlist_id
-            elif reason == 'noMedia':
-                msg = 'Episode %s is not currently available' % playlist_id
-            else:
-                msg = 'Episode %s is not available: %s' % (playlist_id, reason)
-            raise ExtractorError(msg, expected=True)
-
-        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'))
-            formats, subtitles = self._download_media_selector(programme_id)
-
-        return programme_id, title, description, duration, formats, subtitles
-
-    def _real_extract(self, url):
-        group_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, group_id, 'Downloading video page')
-
-        programme_id = self._search_regex(
-            r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None)
-        if programme_id:
-            player = self._download_json(
-                'http://www.bbc.co.uk/iplayer/episode/%s.json' % group_id,
-                group_id)['jsConf']['player']
-            title = player['title']
-            description = player['subtitle']
-            duration = player['duration']
-            formats, subtitles = self._download_media_selector(programme_id)
-        else:
-            programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
-
-        self._sort_formats(formats)
-
-        return {
-            'id': programme_id,
-            'title': title,
-            'description': description,
-            'duration': duration,
-            'formats': formats,
-            'subtitles': subtitles,
-        }

youtube_dl/extractor/beatportpro.py

@@ -0,0 +1,103 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import int_or_none
+
+
+class BeatportProIE(InfoExtractor):
+    _VALID_URL = r'https?://pro\.beatport\.com/track/(?P<display_id>[^/]+)/(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'https://pro.beatport.com/track/synesthesia-original-mix/5379371',
+        'md5': 'b3c34d8639a2f6a7f734382358478887',
+        'info_dict': {
+            'id': '5379371',
+            'display_id': 'synesthesia-original-mix',
+            'ext': 'mp4',
+            'title': 'Froxic - Synesthesia (Original Mix)',
+        },
+    }, {
+        'url': 'https://pro.beatport.com/track/love-and-war-original-mix/3756896',
+        'md5': 'e44c3025dfa38c6577fbaeb43da43514',
+        'info_dict': {
+            'id': '3756896',
+            'display_id': 'love-and-war-original-mix',
+            'ext': 'mp3',
+            'title': 'Wolfgang Gartner - Love & War (Original Mix)',
+        },
+    }, {
+        'url': 'https://pro.beatport.com/track/birds-original-mix/4991738',
+        'md5': 'a1fd8e8046de3950fd039304c186c05f',
+        'info_dict': {
+            'id': '4991738',
+            'display_id': 'birds-original-mix',
+            'ext': 'mp4',
+            'title': "Tos, Middle Milk, Mumblin' Johnsson - Birds (Original Mix)",
+        }
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        track_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        playables = self._parse_json(
+            self._search_regex(
+                r'window\.Playables\s*=\s*({.+?});', webpage,
+                'playables info', flags=re.DOTALL),
+            track_id)
+
+        track = next(t for t in playables['tracks'] if t['id'] == int(track_id))
+
+        title = ', '.join((a['name'] for a in track['artists'])) + ' - ' + track['name']
+        if track['mix']:
+            title += ' (' + track['mix'] + ')'
+
+        formats = []
+        for ext, info in track['preview'].items():
+            if not info['url']:
+                continue
+            fmt = {
+                'url': info['url'],
+                'ext': ext,
+                'format_id': ext,
+                'vcodec': 'none',
+            }
+            if ext == 'mp3':
+                fmt['preference'] = 0
+                fmt['acodec'] = 'mp3'
+                fmt['abr'] = 96
+                fmt['asr'] = 44100
+            elif ext == 'mp4':
+                fmt['preference'] = 1
+                fmt['acodec'] = 'aac'
+                fmt['abr'] = 96
+                fmt['asr'] = 44100
+            formats.append(fmt)
+        self._sort_formats(formats)
+
+        images = []
+        for name, info in track['images'].items():
+            image_url = info.get('url')
+            if name == 'dynamic' or not image_url:
+                continue
+            image = {
+                'id': name,
+                'url': image_url,
+                'height': int_or_none(info.get('height')),
+                'width': int_or_none(info.get('width')),
+            }
+            images.append(image)
+
+        return {
+            'id': compat_str(track.get('id')) or track_id,
+            'display_id': track.get('slug') or display_id,
+            'title': title,
+            'formats': formats,
+            'thumbnails': images,
+        }

youtube_dl/extractor/bet.py

@@ -1,7 +1,7 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse
+from ..compat import compat_urllib_parse_unquote
 from ..utils import (
     xpath_text,
     xpath_with_ns,
@@ -16,11 +16,11 @@ class BetIE(InfoExtractor):
         {
             'url': 'http://www.bet.com/news/politics/2014/12/08/in-bet-exclusive-obama-talks-race-and-racism.html',
             'info_dict': {
-                'id': '740ab250-bb94-4a8a-8787-fe0de7c74471',
+                'id': 'news/national/2014/a-conversation-with-president-obama',
                 'display_id': 'in-bet-exclusive-obama-talks-race-and-racism',
                 'ext': 'flv',
-                'title': 'BET News Presents: A Conversation With President Obama',
-                'description': 'md5:5a88d8ae912c1b33e090290af7ec33c6',
+                'title': 'A Conversation With President Obama',
+                'description': 'md5:699d0652a350cf3e491cd15cc745b5da',
                 'duration': 1534,
                 'timestamp': 1418075340,
                 'upload_date': '20141208',
@@ -35,7 +35,7 @@ class BetIE(InfoExtractor):
         {
             'url': 'http://www.bet.com/video/news/national/2014/justice-for-ferguson-a-community-reacts.html',
             'info_dict': {
-                'id': 'bcd1b1df-673a-42cf-8d01-b282db608f2d',
+                'id': 'news/national/2014/justice-for-ferguson-a-community-reacts',
                 'display_id': 'justice-for-ferguson-a-community-reacts',
                 'ext': 'flv',
                 'title': 'Justice for Ferguson: A Community Reacts',
@@ -57,10 +57,13 @@ class BetIE(InfoExtractor):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
 
-        media_url = compat_urllib_parse.unquote(self._search_regex(
+        media_url = compat_urllib_parse_unquote(self._search_regex(
             [r'mediaURL\s*:\s*"([^"]+)"', r"var\s+mrssMediaUrl\s*=\s*'([^']+)'"],
             webpage, 'media URL'))
 
+        video_id = self._search_regex(
+            r'/video/(.*)/_jcr_content/', media_url, 'video id')
+
         mrss = self._download_xml(media_url, display_id)
 
         item = mrss.find('./channel/item')
@@ -75,8 +78,6 @@ class BetIE(InfoExtractor):
         description = xpath_text(
             item, './description', 'description', fatal=False)
 
-        video_id = xpath_text(item, './guid', 'video id', fatal=False)
-
         timestamp = parse_iso8601(xpath_text(
             item, xpath_with_ns('./dc:date', NS_MAP),
             'upload date', fatal=False))

youtube_dl/extractor/bild.py

@@ -2,7 +2,10 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import int_or_none
+from ..utils import (
+    int_or_none,
+    fix_xml_ampersands,
+)
 
 
 class BildIE(InfoExtractor):
@@ -15,7 +18,7 @@ class BildIE(InfoExtractor):
             'id': '38184146',
             'ext': 'mp4',
             'title': 'BILD hat sie getestet',
-            'thumbnail': 'http://bilder.bild.de/fotos/stand-das-koennen-die-neuen-ipads-38184138/Bild/1.bild.jpg',
+            'thumbnail': 're:^https?://.*\.jpg$',
             'duration': 196,
             'description': 'Mit dem iPad Air 2 und dem iPad Mini 3 hat Apple zwei neue Tablet-Modelle präsentiert. BILD-Reporter Sven Stein durfte die Geräte bereits testen. ',
         }
@@ -25,7 +28,7 @@ class BildIE(InfoExtractor):
         video_id = self._match_id(url)
 
         xml_url = url.split(".bild.html")[0] + ",view=xml.bild.xml"
-        doc = self._download_xml(xml_url, video_id)
+        doc = self._download_xml(xml_url, video_id, transform_source=fix_xml_ampersands)
 
         duration = int_or_none(doc.attrib.get('duration'), scale=1000)
 

youtube_dl/extractor/bilibili.py

@@ -2,34 +2,54 @@
 from __future__ import unicode_literals
 
 import re
+import itertools
+import json
+import xml.etree.ElementTree as ET
 
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
     unified_strdate,
+    ExtractorError,
 )
 
 
 class BiliBiliIE(InfoExtractor):
     _VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>[0-9]+)/'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.bilibili.tv/video/av1074402/',
         'md5': '2c301e4dab317596e837c3e7633e7d86',
         'info_dict': {
-            'id': '1074402',
+            'id': '1074402_part1',
             'ext': 'flv',
             'title': '【金坷垃】金泡沫',
             'duration': 308,
             'upload_date': '20140420',
             'thumbnail': 're:^https?://.+\.jpg',
         },
-    }
+    }, {
+        'url': 'http://www.bilibili.com/video/av1041170/',
+        'info_dict': {
+            'id': '1041170',
+            'title': '【BD1080P】刀语【诸神&异域】',
+        },
+        'playlist_count': 9,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
+        if '(此视频不存在或被删除)' in webpage:
+            raise ExtractorError(
+                'The video does not exist or was deleted', expected=True)
+
+        if '>你没有权限浏览！ 由于版权相关问题 我们不对您所在的地区提供服务<' in webpage:
+            raise ExtractorError(
+                'The video is not available in your region due to copyright reasons',
+                expected=True)
+
         video_code = self._search_regex(
             r'(?s)<div itemprop="video".*?>(.*?)</div>', webpage, 'video code')
 
@@ -54,19 +74,22 @@ class BiliBiliIE(InfoExtractor):
 
         cid = self._search_regex(r'cid=(\d+)', webpage, 'cid')
 
-        lq_doc = self._download_xml(
+        entries = []
+
+        lq_page = self._download_webpage(
             'http://interface.bilibili.com/v_cdn_play?appkey=1&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'),
-        }]
+        try:
+            err_info = json.loads(lq_page)
+            raise ExtractorError(
+                'BiliBili said: ' + err_info['error_text'], expected=True)
+        except ValueError:
+            pass
+
+        lq_doc = ET.fromstring(lq_page)
+        lq_durls = lq_doc.findall('./durl')
 
         hq_doc = self._download_xml(
             'http://interface.bilibili.com/playurl?appkey=1&cid=%s' % cid,
@@ -75,22 +98,45 @@ class BiliBiliIE(InfoExtractor):
             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,
+            hq_durls = hq_doc.findall('./durl')
+            assert len(lq_durls) == len(hq_durls)
+        else:
+            hq_durls = itertools.repeat(None)
+
+        i = 1
+        for lq_durl, hq_durl in zip(lq_durls, hq_durls):
+            formats = [{
+                'format_id': 'lq',
+                'quality': 1,
+                'url': lq_durl.find('./url').text,
                 'filesize': int_or_none(
-                    hq_durl.find('./size'), get_attr='text'),
+                    lq_durl.find('./size'), get_attr='text'),
+            }]
+            if hq_durl is not None:
+                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'),
+                })
+            self._sort_formats(formats)
+
+            entries.append({
+                'id': '%s_part%d' % (video_id, i),
+                'title': title,
+                'formats': formats,
+                'duration': duration,
+                'upload_date': upload_date,
+                'thumbnail': thumbnail,
             })
 
-        self._sort_formats(formats)
+            i += 1
+
         return {
+            '_type': 'multi_video',
+            'entries': entries,
             'id': video_id,
-            'title': title,
-            'formats': formats,
-            'duration': duration,
-            'upload_date': upload_date,
-            'thumbnail': thumbnail,
+            'title': title
         }

youtube_dl/extractor/bliptv.py

@@ -5,7 +5,6 @@ import re
 from .common import InfoExtractor
 
 from ..compat import (
-    compat_str,
     compat_urllib_request,
     compat_urlparse,
 )
@@ -14,6 +13,8 @@ from ..utils import (
     int_or_none,
     parse_iso8601,
     unescapeHTML,
+    xpath_text,
+    xpath_with_ns,
 )
 
 
@@ -23,10 +24,10 @@ class BlipTVIE(InfoExtractor):
     _TESTS = [
         {
             'url': 'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352',
-            'md5': 'c6934ad0b6acf2bd920720ec888eb812',
+            'md5': '80baf1ec5c3d2019037c1c707d676b9f',
             'info_dict': {
                 'id': '5779306',
-                'ext': 'mov',
+                'ext': 'm4v',
                 'title': 'CBR EXCLUSIVE: "Gotham City Imposters" Bats VS Jokerz Short 3',
                 'description': 'md5:9bc31f227219cde65e47eeec8d2dc596',
                 'timestamp': 1323138843,
@@ -100,8 +101,31 @@ class BlipTVIE(InfoExtractor):
                 'vcodec': 'none',
             }
         },
+        {
+            # missing duration
+            'url': 'http://blip.tv/rss/flash/6700880',
+            'info_dict': {
+                'id': '6684191',
+                'ext': 'm4v',
+                'title': 'Cowboy Bebop: Gateway Shuffle Review',
+                'description': 'md5:3acc480c0f9ae157f5fe88547ecaf3f8',
+                'timestamp': 1386639757,
+                'upload_date': '20131210',
+                'uploader': 'sfdebris',
+                'uploader_id': '706520',
+            }
+        }
     ]
 
+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage)
+        if mobj:
+            return 'http://blip.tv/a/a-' + mobj.group(1)
+        mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage)
+        if mobj:
+            return mobj.group(1)
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         lookup_id = mobj.group('lookup_id')
@@ -119,35 +143,34 @@ class BlipTVIE(InfoExtractor):
 
         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
+        def _x(p):
+            return xpath_with_ns(p, {
+                'blip': 'http://blip.tv/dtd/blip/1.0',
+                'media': 'http://search.yahoo.com/mrss/',
+                'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
+            })
 
         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')]
+        video_id = xpath_text(item, _x('blip:item_id'), 'video id') or lookup_id
+        title = xpath_text(item, 'title', 'title', fatal=True)
+        description = clean_html(xpath_text(item, _x('blip:puredescription'), 'description'))
+        timestamp = parse_iso8601(xpath_text(item, _x('blip:datestamp'), 'timestamp'))
+        uploader = xpath_text(item, _x('blip:user'), 'uploader')
+        uploader_id = xpath_text(item, _x('blip:userid'), 'uploader id')
+        duration = int_or_none(xpath_text(item, _x('blip:runtime'), 'duration'))
+        media_thumbnail = item.find(_x('media:thumbnail'))
+        thumbnail = (media_thumbnail.get('url') if media_thumbnail is not None
+                     else xpath_text(item, 'image', 'thumbnail'))
+        categories = [category.text for category in item.findall('category') if category is not None]
 
         formats = []
         subtitles_urls = {}
 
-        media_group = item.find(media('group'))
-        for media_content in media_group.findall(media('content')):
+        media_group = item.find(_x('media:group'))
+        for media_content in media_group.findall(_x('media:content')):
             url = media_content.get('url')
-            role = media_content.get(blip('role'))
+            role = media_content.get(_x('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)
@@ -166,12 +189,13 @@ class BlipTVIE(InfoExtractor):
                     'url': real_url,
                     'format_id': role,
                     'format_note': media_type,
-                    'vcodec': media_content.get(blip('vcodec')) or 'none',
-                    'acodec': media_content.get(blip('acodec')),
+                    'vcodec': media_content.get(_x('blip:vcodec')) or 'none',
+                    'acodec': media_content.get(_x('blip:acodec')),
                     'filesize': media_content.get('filesize'),
                     'width': int_or_none(media_content.get('width')),
                     'height': int_or_none(media_content.get('height')),
                 })
+        self._check_formats(formats, video_id)
         self._sort_formats(formats)
 
         subtitles = self.extract_subtitles(video_id, subtitles_urls)

youtube_dl/extractor/bloomberg.py

@@ -6,32 +6,39 @@ 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/news/videos/[^/]+/(?P<id>[^/?#]+)'
 
     _TEST = {
-        'url': 'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html',
+        'url': 'http://www.bloomberg.com/news/videos/b/aaeae121-5949-481e-a1ce-4562db6f5df2',
         # The md5 checksum changes
         'info_dict': {
             'id': 'qurhIVlJSB6hzkVi229d8g',
             'ext': 'flv',
             'title': 'Shah\'s Presentation on Foreign-Exchange Strategies',
-            'description': 'md5:0681e0d30dcdfc6abf34594961d8ea88',
+            'description': 'md5:a8ba0302912d03d246979735c17d2761',
         },
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        name = mobj.group('name')
+        name = self._match_id(url)
         webpage = self._download_webpage(url, name)
-        f4m_url = self._search_regex(
-            r'<source src="(https?://[^"]+\.f4m.*?)"', webpage,
-            'f4m url')
+        video_id = self._search_regex(r'"bmmrId":"(.+?)"', webpage, 'id')
         title = re.sub(': Video$', '', self._og_search_title(webpage))
 
+        embed_info = self._download_json(
+            'http://www.bloomberg.com/api/embed?id=%s' % video_id, video_id)
+        formats = []
+        for stream in embed_info['streams']:
+            if stream["muxing_format"] == "TS":
+                formats.extend(self._extract_m3u8_formats(stream['url'], video_id))
+            else:
+                formats.extend(self._extract_f4m_formats(stream['url'], video_id))
+        self._sort_formats(formats)
+
         return {
-            'id': name.split('-')[-1],
+            'id': video_id,
             'title': title,
-            'formats': self._extract_f4m_formats(f4m_url, name),
+            'formats': formats,
             'description': self._og_search_description(webpage),
             'thumbnail': self._og_search_thumbnail(webpage),
         }

youtube_dl/extractor/br.py

@@ -16,27 +16,38 @@ class BRIE(InfoExtractor):
 
     _TESTS = [
         {
-            'url': 'http://www.br.de/mediathek/video/sendungen/heimatsound/heimatsound-festival-2014-trailer-100.html',
-            'md5': '93556dd2bcb2948d9259f8670c516d59',
+            'url': 'http://www.br.de/mediathek/video/sendungen/abendschau/betriebliche-altersvorsorge-104.html',
+            'md5': '83a0477cf0b8451027eb566d88b51106',
             'info_dict': {
-                'id': '25e279aa-1ffd-40fd-9955-5325bd48a53a',
+                'id': '48f656ef-287e-486f-be86-459122db22cc',
                 'ext': 'mp4',
-                'title': 'Wenn das Traditions-Theater wackelt',
-                'description': 'Heimatsound-Festival 2014: Wenn das Traditions-Theater wackelt',
-                'duration': 34,
-                'uploader': 'BR',
-                'upload_date': '20140802',
+                'title': 'Die böse Überraschung',
+                'description': 'Betriebliche Altersvorsorge: Die böse Überraschung',
+                'duration': 180,
+                'uploader': 'Reinhard Weber',
+                'upload_date': '20150422',
             }
         },
         {
-            'url': 'http://www.br.de/nachrichten/schaeuble-haushaltsentwurf-bundestag-100.html',
-            'md5': '3db0df1a9a9cd9fa0c70e6ea8aa8e820',
+            'url': 'http://www.br.de/nachrichten/oberbayern/inhalt/muenchner-polizeipraesident-schreiber-gestorben-100.html',
+            'md5': 'a44396d73ab6a68a69a568fae10705bb',
             'info_dict': {
-                'id': 'c6aae3de-2cf9-43f2-957f-f17fef9afaab',
+                'id': 'a4b83e34-123d-4b81-9f4e-c0d3121a4e05',
+                'ext': 'mp4',
+                'title': 'Manfred Schreiber ist tot',
+                'description': 'Abendschau kompakt: Manfred Schreiber ist tot',
+                'duration': 26,
+            }
+        },
+        {
+            'url': 'http://www.br.de/radio/br-klassik/sendungen/allegro/premiere-urauffuehrung-the-land-2015-dance-festival-muenchen-100.html',
+            'md5': '8b5b27c0b090f3b35eac4ab3f7a73d3d',
+            'info_dict': {
+                'id': '74c603c9-26d3-48bb-b85b-079aeed66e0b',
                 'ext': 'aac',
-                'title': '"Keine neuen Schulden im nächsten Jahr"',
-                'description': 'Haushaltsentwurf: "Keine neuen Schulden im nächsten Jahr"',
-                'duration': 64,
+                'title': 'Kurzweilig und sehr bewegend',
+                'description': '"The Land" von Peeping Tom: Kurzweilig und sehr bewegend',
+                'duration': 296,
             }
         },
         {

youtube_dl/extractor/breakcom.py

@@ -18,6 +18,7 @@ class BreakIE(InfoExtractor):
             'id': '2468056',
             'ext': 'mp4',
             'title': 'When Girls Act Like D-Bags',
+            'age_limit': 13,
         }
     }, {
         'url': 'http://www.break.com/video/ugc/baby-flex-2773063',
@@ -41,7 +42,7 @@ class BreakIE(InfoExtractor):
             'tbr': media['bitRate'],
             'width': media['width'],
             'height': media['height'],
-        } for media in info['media']]
+        } for media in info['media'] if media.get('mediaPurpose') == 'play']
 
         if not formats:
             formats.append({

youtube_dl/extractor/brightcove.py

@@ -13,6 +13,7 @@ from ..compat import (
     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urlparse,
+    compat_xml_parse_error,
 )
 from ..utils import (
     determine_ext,
@@ -117,7 +118,10 @@ class BrightcoveIE(InfoExtractor):
         object_str = re.sub(r'(<object[^>]*)(xmlns=".*?")', r'\1', object_str)
         object_str = fix_xml_ampersands(object_str)
 
-        object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8'))
+        try:
+            object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8'))
+        except compat_xml_parse_error:
+            return
 
         fv_el = find_xpath_attr(object_doc, './param', 'name', 'flashVars')
         if fv_el is not None:
@@ -153,6 +157,28 @@ class BrightcoveIE(InfoExtractor):
         linkBase = find_param('linkBaseURL')
         if linkBase is not None:
             params['linkBaseURL'] = linkBase
+        return cls._make_brightcove_url(params)
+
+    @classmethod
+    def _build_brighcove_url_from_js(cls, object_js):
+        # The layout of JS is as follows:
+        # customBC.createVideo = function (width, height, playerID, playerKey, videoPlayer, VideoRandomID) {
+        #   // build Brightcove <object /> XML
+        # }
+        m = re.search(
+            r'''(?x)customBC.\createVideo\(
+                .*?                                                  # skipping width and height
+                ["\'](?P<playerID>\d+)["\']\s*,\s*                   # playerID
+                ["\'](?P<playerKey>AQ[^"\']{48})[^"\']*["\']\s*,\s*  # playerKey begins with AQ and is 50 characters
+                                                                     # in length, however it's appended to itself
+                                                                     # in places, so truncate
+                ["\'](?P<videoID>\d+)["\']                           # @videoPlayer
+            ''', object_js)
+        if m:
+            return cls._make_brightcove_url(m.groupdict())
+
+    @classmethod
+    def _make_brightcove_url(cls, params):
         data = compat_urllib_parse.urlencode(params)
         return cls._FEDERATED_URL_TEMPLATE % data
 
@@ -169,7 +195,7 @@ class BrightcoveIE(InfoExtractor):
         """Return a list of all Brightcove URLs from the webpage """
 
         url_m = re.search(
-            r'<meta\s+property="og:video"\s+content="(https?://(?:secure|c)\.brightcove.com/[^"]+)"',
+            r'<meta\s+property=[\'"]og:video[\'"]\s+content=[\'"](https?://(?:secure|c)\.brightcove.com/[^\'"]+)[\'"]',
             webpage)
         if url_m:
             url = unescapeHTML(url_m.group(1))
@@ -183,9 +209,14 @@ class BrightcoveIE(InfoExtractor):
             (?:
                 [^>]+?class=[\'"][^>]*?BrightcoveExperience.*?[\'"] |
                 [^>]*?>\s*<param\s+name="movie"\s+value="https?://[^/]*brightcove\.com/
-            ).+?</object>''',
+            ).+?>\s*</object>''',
             webpage)
-        return [cls._build_brighcove_url(m) for m in matches]
+        if matches:
+            return list(filter(None, [cls._build_brighcove_url(m) for m in matches]))
+
+        return list(filter(None, [
+            cls._build_brighcove_url_from_js(custom_bc)
+            for custom_bc in re.findall(r'(customBC\.createVideo\(.+?\);)', webpage)]))
 
     def _real_extract(self, url):
         url, smuggled_data = unsmuggle_url(url, {})

youtube_dl/extractor/byutv.py

@@ -16,7 +16,7 @@ class BYUtvIE(InfoExtractor):
             'ext': 'mp4',
             'description': 'md5:5438d33774b6bdc662f9485a340401cc',
             'title': 'Season 5 Episode 5',
-            'thumbnail': 're:^https?://.*promo.*'
+            'thumbnail': 're:^https?://.*\.jpg$'
         },
         'params': {
             'skip_download': True,

youtube_dl/extractor/canalplus.py

@@ -25,14 +25,14 @@ class CanalplusIE(InfoExtractor):
     }
 
     _TESTS = [{
-        'url': 'http://www.canalplus.fr/c-infos-documentaires/pid1830-c-zapping.html?vid=922470',
-        'md5': '3db39fb48b9685438ecf33a1078023e4',
+        'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1263092',
+        'md5': 'b3481d7ca972f61e37420798d0a9d934',
         'info_dict': {
-            'id': '922470',
+            'id': '1263092',
             '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',
+            'title': 'Le Zapping - 13/05/15',
+            'description': 'md5:09738c0d06be4b5d06a0940edb0da73f',
+            'upload_date': '20150513',
         },
     }, {
         'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190',
@@ -56,7 +56,7 @@ class CanalplusIE(InfoExtractor):
         'skip': 'videos get deleted after a while',
     }, {
         'url': 'http://www.itele.fr/france/video/aubervilliers-un-lycee-en-colere-111559',
-        'md5': '65aa83ad62fe107ce29e564bb8712580',
+        'md5': 'f3a46edcdf28006598ffaf5b30e6a2d4',
         'info_dict': {
             'id': '1213714',
             'ext': 'flv',
@@ -106,15 +106,11 @@ class CanalplusIE(InfoExtractor):
                 continue
             format_id = fmt.tag
             if format_id == 'HLS':
-                hls_formats = self._extract_m3u8_formats(format_url, video_id, 'flv')
-                for fmt in hls_formats:
-                    fmt['preference'] = preference(format_id)
-                formats.extend(hls_formats)
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, video_id, 'mp4', preference=preference(format_id)))
             elif format_id == 'HDS':
-                hds_formats = self._extract_f4m_formats(format_url + '?hdcore=2.11.3', video_id)
-                for fmt in hds_formats:
-                    fmt['preference'] = preference(format_id)
-                formats.extend(hds_formats)
+                formats.extend(self._extract_f4m_formats(
+                    format_url + '?hdcore=2.11.3', video_id, preference=preference(format_id)))
             else:
                 formats.append({
                     'url': format_url,

youtube_dl/extractor/cbs.py

@@ -4,12 +4,13 @@ from .common import InfoExtractor
 
 
 class CBSIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?cbs\.com/shows/[^/]+/(?:video|artist)/(?P<id>[^/]+)/.*'
+    _VALID_URL = r'https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/(?:video|artist)|colbertlateshow\.com/(?:video|podcasts))/[^/]+/(?P<id>[^/]+)'
 
     _TESTS = [{
         'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
         'info_dict': {
             'id': '4JUVEwq3wUT7',
+            'display_id': 'connect-chat-feat-garth-brooks',
             '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!',
@@ -24,6 +25,7 @@ class CBSIE(InfoExtractor):
         'url': 'http://www.cbs.com/shows/liveonletterman/artist/221752/st-vincent/',
         'info_dict': {
             'id': 'WWF_5KqY3PK1',
+            'display_id': 'st-vincent',
             '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.',
@@ -34,12 +36,23 @@ class CBSIE(InfoExtractor):
             'skip_download': True,
         },
         '_skip': 'Blocked outside the US',
+    }, {
+        'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
         real_id = self._search_regex(
-            r"video\.settings\.pid\s*=\s*'([^']+)';",
+            [r"video\.settings\.pid\s*=\s*'([^']+)';", r"cbsplayer\.pid\s*=\s*'([^']+)';"],
             webpage, 'real video ID')
-        return self.url_result('theplatform:%s' % real_id)
+        return {
+            '_type': 'url_transparent',
+            'ie_key': 'ThePlatform',
+            'url': 'theplatform:%s' % real_id,
+            'display_id': display_id,
+        }

youtube_dl/extractor/cbsnews.py

@@ -32,7 +32,7 @@ class CBSNewsIE(InfoExtractor):
                 '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',
+                'thumbnail': 're:^https?://.*\.jpg$',
                 'duration': 205,
             },
             'params': {

youtube_dl/extractor/ccc.py

@@ -16,7 +16,7 @@ class CCCIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://media.ccc.de/browse/congress/2013/30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor.html#video',
-        'md5': '205a365d0d57c0b1e43a12c9ffe8f9be',
+        'md5': '3a1eda8f3a29515d27f5adb967d7e740',
         'info_dict': {
             'id': '20131228183',
             'ext': 'mp4',
@@ -51,7 +51,7 @@ class CCCIE(InfoExtractor):
 
         matches = re.finditer(r'''(?xs)
             <(?:span|div)\s+class='label\s+filetype'>(?P<format>.*?)</(?:span|div)>\s*
-            <a\s+href='(?P<http_url>[^']+)'>\s*
+            <a\s+download\s+href='(?P<http_url>[^']+)'>\s*
             (?:
                 .*?
                 <a\s+href='(?P<torrent_url>[^']+\.torrent)'

youtube_dl/extractor/ceskatelevize.py

@@ -7,6 +7,7 @@ from .common import InfoExtractor
 from ..compat import (
     compat_urllib_request,
     compat_urllib_parse,
+    compat_urllib_parse_unquote,
     compat_urllib_parse_urlparse,
 )
 from ..utils import (
@@ -88,7 +89,7 @@ class CeskaTelevizeIE(InfoExtractor):
         if playlist_url == 'error_region':
             raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
 
-        req = compat_urllib_request.Request(compat_urllib_parse.unquote(playlist_url))
+        req = compat_urllib_request.Request(compat_urllib_parse_unquote(playlist_url))
         req.add_header('Referer', url)
 
         playlist = self._download_json(req, video_id)

youtube_dl/extractor/chilloutzone.py

@@ -57,7 +57,7 @@ class ChilloutzoneIE(InfoExtractor):
 
         base64_video_info = self._html_search_regex(
             r'var cozVidData = "(.+?)";', webpage, 'video data')
-        decoded_video_info = base64.b64decode(base64_video_info).decode("utf-8")
+        decoded_video_info = base64.b64decode(base64_video_info.encode('utf-8')).decode('utf-8')
         video_info_dict = json.loads(decoded_video_info)
 
         # get video information from dict

youtube_dl/extractor/cinemassacre.py

@@ -0,0 +1,110 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+from .bliptv import BlipTVIE
+
+
+class CinemassacreIE(InfoExtractor):
+    _VALID_URL = 'https?://(?: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': 'Cinemassacre-19911',
+                'ext': 'mp4',
+                'upload_date': '20121110',
+                'title': '“Angry Video Game Nerd: The Movie” – Trailer',
+                'description': 'md5:fb87405fcb42a331742a0dce2708560b',
+            },
+        },
+        {
+            'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
+            'md5': 'd72f10cd39eac4215048f62ab477a511',
+            'info_dict': {
+                'id': 'Cinemassacre-521be8ef82b16',
+                'ext': 'mp4',
+                'upload_date': '20131002',
+                'title': 'The Mummy’s Hand (1940)',
+            },
+        },
+        {
+            # blip.tv embedded video
+            'url': 'http://cinemassacre.com/2006/12/07/chronologically-confused-about-bad-movie-and-video-game-sequel-titles/',
+            'md5': 'ca9b3c8dd5a66f9375daeb5135f5a3de',
+            'info_dict': {
+                'id': '4065369',
+                'ext': 'flv',
+                'title': 'AVGN: Chronologically Confused about Bad Movie and Video Game Sequel Titles',
+                'upload_date': '20061207',
+                'uploader': 'cinemassacre',
+                'uploader_id': '250778',
+                'timestamp': 1283233867,
+                'description': 'md5:0a108c78d130676b207d0f6d029ecffd',
+            }
+        },
+        {
+            # Youtube embedded video
+            'url': 'http://cinemassacre.com/2006/09/01/mckids/',
+            'md5': '6eb30961fa795fedc750eac4881ad2e1',
+            'info_dict': {
+                'id': 'FnxsNhuikpo',
+                'ext': 'mp4',
+                'upload_date': '20060901',
+                'uploader': 'Cinemassacre Extras',
+                'description': 'md5:de9b751efa9e45fbaafd9c8a1123ed53',
+                'uploader_id': 'Cinemassacre',
+                'title': 'AVGN: McKids',
+            }
+        },
+        {
+            'url': 'http://cinemassacre.com/2015/05/25/mario-kart-64-nintendo-64-james-mike-mondays/',
+            'md5': '1376908e49572389e7b06251a53cdd08',
+            'info_dict': {
+                'id': 'Cinemassacre-555779690c440',
+                'ext': 'mp4',
+                'description': 'Let’s Play Mario Kart 64 !! Mario Kart 64 is a classic go-kart racing game released for the Nintendo 64 (N64). Today James & Mike do 4 player Battle Mode with Kyle and Bootsy!',
+                'title': 'Mario Kart 64 (Nintendo 64) James & Mike Mondays',
+                'upload_date': '20150525',
+            }
+        }
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('display_id')
+        video_date = mobj.group('date_y') + mobj.group('date_m') + mobj.group('date_d')
+
+        webpage = self._download_webpage(url, display_id)
+
+        playerdata_url = self._search_regex(
+            [
+                r'src="(http://(?:player2\.screenwavemedia\.com|player\.screenwavemedia\.com/play)/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
+                r'<iframe[^>]+src="((?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"',
+            ],
+            webpage, 'player data URL', default=None)
+        if not playerdata_url:
+            playerdata_url = BlipTVIE._extract_url(webpage)
+        if not playerdata_url:
+            raise ExtractorError('Unable to find player data')
+
+        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)
+        video_thumbnail = self._og_search_thumbnail(webpage)
+
+        return {
+            '_type': 'url_transparent',
+            'display_id': display_id,
+            'title': video_title,
+            'description': video_description,
+            'upload_date': video_date,
+            'thumbnail': video_thumbnail,
+            'url': playerdata_url,
+        }

youtube_dl/extractor/clipfish.py

@@ -1,53 +1,68 @@
 from __future__ import unicode_literals
 
 import re
-import time
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
-    ExtractorError,
-    parse_duration,
+    determine_ext,
+    int_or_none,
+    js_to_json,
+    parse_iso8601,
+    remove_end,
 )
 
 
 class ClipfishIE(InfoExtractor):
-    IE_NAME = 'clipfish'
-
-    _VALID_URL = r'^https?://(?:www\.)?clipfish\.de/.*?/video/(?P<id>[0-9]+)/'
+    _VALID_URL = r'https?://(?:www\.)?clipfish\.de/(?:[^/]+/)+video/(?P<id>[0-9]+)'
     _TEST = {
         'url': 'http://www.clipfish.de/special/game-trailer/video/3966754/fifa-14-e3-2013-trailer/',
-        'md5': '2521cd644e862936cf2e698206e47385',
+        'md5': '79bc922f3e8a9097b3d68a93780fd475',
         'info_dict': {
             'id': '3966754',
             'ext': 'mp4',
             'title': 'FIFA 14 - E3 2013 Trailer',
+            'timestamp': 1370938118,
+            'upload_date': '20130611',
             'duration': 82,
-        },
-        'skip': 'Blocked in the US'
+        }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
+        video_id = self._match_id(url)
 
-        info_url = ('http://www.clipfish.de/devxml/videoinfo/%s?ts=%d' %
-                    (video_id, int(time.time())))
-        doc = self._download_xml(
-            info_url, video_id, note='Downloading info page')
-        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 = parse_duration(doc.find('duration').text)
+        webpage = self._download_webpage(url, video_id)
+
+        video_info = self._parse_json(
+            js_to_json(self._html_search_regex(
+                '(?s)videoObject\s*=\s*({.+?});', webpage, 'video object')),
+            video_id)
+
+        formats = []
+        for video_url in re.findall(r'var\s+videourl\s*=\s*"([^"]+)"', webpage):
+            ext = determine_ext(video_url)
+            if ext == 'm3u8':
+                formats.append({
+                    'url': video_url.replace('de.hls.fra.clipfish.de', 'hls.fra.clipfish.de'),
+                    'ext': 'mp4',
+                    'format_id': 'hls',
+                })
+            else:
+                formats.append({
+                    'url': video_url,
+                    'format_id': ext,
+                })
+        self._sort_formats(formats)
+
+        title = remove_end(self._og_search_title(webpage), ' - Video')
+        thumbnail = self._og_search_thumbnail(webpage)
+        duration = int_or_none(video_info.get('length'))
+        timestamp = parse_iso8601(self._html_search_meta('uploadDate', webpage, 'upload date'))
 
         return {
             'id': video_id,
             'title': title,
-            'url': video_url,
+            'formats': formats,
             'thumbnail': thumbnail,
             'duration': duration,
+            'timestamp': timestamp,
         }

youtube_dl/extractor/clipsyndicate.py

@@ -1,7 +1,5 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     find_xpath_attr,
@@ -10,9 +8,9 @@ from ..utils import (
 
 
 class ClipsyndicateIE(InfoExtractor):
-    _VALID_URL = r'http://www\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)'
+    _VALID_URL = r'http://(?:chic|www)\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.clipsyndicate.com/video/play/4629301/brick_briscoe',
         'md5': '4d7d549451bad625e0ff3d7bd56d776c',
         'info_dict': {
@@ -22,11 +20,13 @@ class ClipsyndicateIE(InfoExtractor):
             'duration': 612,
             'thumbnail': 're:^https?://.+\.jpg',
         },
-    }
+    }, {
+        'url': 'http://chic.clipsyndicate.com/video/play/5844117/shark_attack',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         js_player = self._download_webpage(
             'http://eplayer.clipsyndicate.com/embed/player.js?va_id=%s' % video_id,
             video_id, 'Downlaoding player')

youtube_dl/extractor/cloudy.py

@@ -105,6 +105,7 @@ class CloudyIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         file_key = self._search_regex(
-            r'filekey\s*=\s*"([^"]+)"', webpage, 'file_key')
+            [r'key\s*:\s*"([^"]+)"', r'filekey\s*=\s*"([^"]+)"'],
+            webpage, 'file_key')
 
         return self._extract_video(video_host, video_id, file_key)

youtube_dl/extractor/cnet.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 class CNETIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/',
         'info_dict': {
             'id': '56f4ea68-bd21-4852-b08c-4de5b8354c60',
@@ -25,7 +25,20 @@ class CNETIE(InfoExtractor):
         'params': {
             'skip_download': 'requires rtmpdump',
         }
-    }
+    }, {
+        'url': 'http://www.cnet.com/videos/whiny-pothole-tweets-at-local-government-when-hit-by-cars-tomorrow-daily-187/',
+        'info_dict': {
+            'id': '56527b93-d25d-44e3-b738-f989ce2e49ba',
+            'ext': 'flv',
+            'description': 'Khail and Ashley wonder what other civic woes can be solved by self-tweeting objects, investigate a new kind of VR camera and watch an origami robot self-assemble, walk, climb, dig and dissolve. #TDPothole',
+            'uploader_id': 'b163284d-6b73-44fc-b3e6-3da66c392d40',
+            'uploader': 'Ashley Esqueda',
+            'title': 'Whiny potholes tweet at local government when hit by cars (Tomorrow Daily 187)',
+        },
+        'params': {
+            'skip_download': True,  # requires rtmpdump
+        },
+    }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
@@ -42,7 +55,7 @@ class CNETIE(InfoExtractor):
             raise ExtractorError('Cannot find video data')
 
         mpx_account = data['config']['players']['default']['mpx_account']
-        vid = vdata['files']['rtmp']
+        vid = vdata['files'].get('rtmp', vdata['files']['hds'])
         tp_link = 'http://link.theplatform.com/s/%s/%s' % (mpx_account, vid)
 
         video_id = vdata['id']

youtube_dl/extractor/cnn.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 class CNNIE(InfoExtractor):
     _VALID_URL = r'''(?x)https?://(?:(?:edition|www)\.)?cnn\.com/video/(?:data/.+?|\?)/
-        (?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:cnn|hln)(?:-ap)?|(?=&)))'''
+        (?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:[a-z\-]+)|(?=&)))'''
 
     _TESTS = [{
         'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',
@@ -45,6 +45,12 @@ class CNNIE(InfoExtractor):
             'description': 'md5:e7223a503315c9f150acac52e76de086',
             'upload_date': '20141222',
         }
+    }, {
+        'url': 'http://cnn.com/video/?/video/politics/2015/03/27/pkg-arizona-senator-church-attendance-mandatory.ktvk',
+        'only_matching': True,
+    }, {
+        'url': 'http://cnn.com/video/?/video/us/2015/04/06/dnt-baker-refuses-anti-gay-order.wkmg',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/comcarcoff.py

@@ -36,7 +36,7 @@ class ComCarCoffIE(InfoExtractor):
             webpage, 'full data json'))
 
         video_id = full_data['activeVideo']['video']
-        video_data = full_data['videos'][video_id]
+        video_data = full_data.get('videos', {}).get(video_id) or full_data['singleshots'][video_id]
         thumbnails = [{
             'url': video_data['images']['thumb'],
         }, {

youtube_dl/extractor/comedycentral.py

@@ -201,7 +201,7 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
 
         uri = mMovieParams[0][1]
         # Correct cc.com in uri
-        uri = re.sub(r'(episode:[^.]+)(\.cc)?\.com', r'\1.cc.com', uri)
+        uri = re.sub(r'(episode:[^.]+)(\.cc)?\.com', r'\1.com', uri)
 
         index_url = 'http://%s.cc.com/feeds/mrss?%s' % (show_name, compat_urllib_parse.urlencode({'uri': uri}))
         idoc = self._download_xml(
@@ -250,6 +250,8 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
                 })
                 self._sort_formats(formats)
 
+            subtitles = self._extract_subtitles(cdoc, guid)
+
             virtual_id = show_name + ' ' + epTitle + ' part ' + compat_str(part_num + 1)
             entries.append({
                 'id': guid,
@@ -260,6 +262,7 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
                 'duration': duration,
                 'thumbnail': thumbnail,
                 'description': description,
+                'subtitles': subtitles,
             })
 
         return {

youtube_dl/extractor/common.py

@@ -14,25 +14,35 @@ import xml.etree.ElementTree
 
 from ..compat import (
     compat_cookiejar,
+    compat_cookies,
+    compat_getpass,
     compat_HTTPError,
     compat_http_client,
     compat_urllib_error,
+    compat_urllib_parse,
     compat_urllib_parse_urlparse,
+    compat_urllib_request,
     compat_urlparse,
     compat_str,
 )
 from ..utils import (
+    NO_DEFAULT,
     age_restricted,
+    bug_reports_message,
     clean_html,
     compiled_regex_type,
+    determine_ext,
     ExtractorError,
+    fix_xml_ampersands,
     float_or_none,
     int_or_none,
     RegexNotFoundError,
     sanitize_filename,
     unescapeHTML,
+    url_basename,
+    xpath_text,
+    xpath_with_ns,
 )
-_NO_DEFAULT = object()
 
 
 class InfoExtractor(object):
@@ -46,7 +56,7 @@ class InfoExtractor(object):
     information possibly downloading the video to the file system, among
     other possible outcomes.
 
-    The type field determines the the type of the result.
+    The type field determines the type of the result.
     By far the most common value (and the default if _type is missing) is
     "video", which indicates a single video.
 
@@ -62,7 +72,7 @@ class InfoExtractor(object):
 
                     Potential fields:
                     * url        Mandatory. The URL of the video file
-                    * ext        Will be calculated from url if missing
+                    * 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.
@@ -110,11 +120,8 @@ class InfoExtractor(object):
                                   (quality takes higher priority)
                                  -1 for default (order by other properties),
                                  -2 or smaller for less than default.
-                    * http_method  HTTP method to use for the download.
                     * http_headers  A dictionary of additional HTTP headers
                                  to add to the request.
-                    * http_post_data  Additional data to send with a POST
-                                 request.
                     * stretched_ratio  If given and not 1, indicates that the
                                  video's pixels are not square.
                                  width : height ratio as float.
@@ -155,7 +162,7 @@ class InfoExtractor(object):
                     lower to higher preference, each element is a dictionary
                     with the "ext" entry and one of:
                         * "data": The subtitles file contents
-                        * "url": A url pointing to the subtitles file
+                        * "url": A URL pointing to the subtitles file
     automatic_captions: Like 'subtitles', used by the YoutubeIE for
                     automatically generated captions
     duration:       Length of the video in seconds, as an integer.
@@ -176,13 +183,18 @@ class InfoExtractor(object):
                                      Set to "root" to indicate that this is a
                                      comment to the original video.
     age_limit:      Age restriction for the video, as an integer (years)
-    webpage_url:    The url to the video webpage, if given to youtube-dl it
+    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"]
+    tags:           A list of tags assigned to the video, e.g. ["sweden", "pop music"]
     is_live:        True, False, or None (=unknown). Whether this video is a
                     live stream that goes on instead of a fixed-length video.
+    start_time:     Time in seconds where the reproduction should start, as
+                    specified in the URL.
+    end_time:       Time in seconds where the reproduction should end, as
+                    specified in the URL.
 
     Unless mentioned otherwise, the fields should be Unicode strings.
 
@@ -193,8 +205,8 @@ class InfoExtractor(object):
     There must be a key "entries", which is a list, an iterable, or a PagedList
     object, each element of which is a valid dictionary by this specification.
 
-    Additionally, playlists can have "title" and "id" attributes with the same
-    semantics as videos (see above).
+    Additionally, playlists can have "title", "description" and "id" attributes
+    with the same semantics as videos (see above).
 
 
     _type "multi_video" indicates that there are multiple videos that
@@ -324,7 +336,7 @@ class InfoExtractor(object):
                 self._downloader.report_warning(errmsg)
                 return False
 
-    def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
+    def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None):
         """ Returns a tuple (page content as string, URL handle) """
         # Strip hashes from the URL (#1038)
         if isinstance(url_or_request, (compat_str, str)):
@@ -334,14 +346,11 @@ class InfoExtractor(object):
         if urlh is False:
             assert not fatal
             return False
-        content = self._webpage_read_content(urlh, url_or_request, video_id, note, errnote, fatal)
+        content = self._webpage_read_content(urlh, url_or_request, video_id, note, errnote, fatal, encoding=encoding)
         return (content, urlh)
 
-    def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None):
-        content_type = urlh.headers.get('Content-Type', '')
-        webpage_bytes = urlh.read()
-        if prefix is not None:
-            webpage_bytes = prefix + webpage_bytes
+    @staticmethod
+    def _guess_encoding_from_content(content_type, webpage_bytes):
         m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
         if m:
             encoding = m.group(1)
@@ -354,6 +363,16 @@ class InfoExtractor(object):
                 encoding = 'utf-16'
             else:
                 encoding = 'utf-8'
+
+        return encoding
+
+    def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None, encoding=None):
+        content_type = urlh.headers.get('Content-Type', '')
+        webpage_bytes = urlh.read()
+        if prefix is not None:
+            webpage_bytes = prefix + webpage_bytes
+        if not encoding:
+            encoding = self._guess_encoding_from_content(content_type, webpage_bytes)
         if self._downloader.params.get('dump_intermediate_pages', False):
             try:
                 url = url_or_request.get_full_url()
@@ -410,13 +429,13 @@ class InfoExtractor(object):
 
         return content
 
-    def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5):
+    def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None):
         """ Returns the data of the page as a string """
         success = False
         try_count = 0
         while success is False:
             try:
-                res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal)
+                res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal, encoding=encoding)
                 success = True
             except compat_http_client.IncompleteRead as e:
                 try_count += 1
@@ -431,10 +450,10 @@ class InfoExtractor(object):
 
     def _download_xml(self, url_or_request, video_id,
                       note='Downloading XML', errnote='Unable to download XML',
-                      transform_source=None, fatal=True):
+                      transform_source=None, fatal=True, encoding=None):
         """Return the xml as an xml.etree.ElementTree.Element"""
         xml_string = self._download_webpage(
-            url_or_request, video_id, note, errnote, fatal=fatal)
+            url_or_request, video_id, note, errnote, fatal=fatal, encoding=encoding)
         if xml_string is False:
             return xml_string
         if transform_source:
@@ -445,9 +464,10 @@ class InfoExtractor(object):
                        note='Downloading JSON metadata',
                        errnote='Unable to download JSON metadata',
                        transform_source=None,
-                       fatal=True):
+                       fatal=True, encoding=None):
         json_string = self._download_webpage(
-            url_or_request, video_id, note, errnote, fatal=fatal)
+            url_or_request, video_id, note, errnote, fatal=fatal,
+            encoding=encoding)
         if (not fatal) and json_string is False:
             return None
         return self._parse_json(
@@ -492,14 +512,16 @@ class InfoExtractor(object):
 
     # Methods for following #608
     @staticmethod
-    def url_result(url, ie=None, video_id=None):
-        """Returns a url that points to a page that should be processed"""
+    def url_result(url, ie=None, video_id=None, video_title=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',
                       'url': url,
                       'ie_key': ie}
         if video_id is not None:
             video_info['id'] = video_id
+        if video_title is not None:
+            video_info['title'] = video_title
         return video_info
 
     @staticmethod
@@ -515,7 +537,7 @@ class InfoExtractor(object):
             video_info['description'] = playlist_description
         return video_info
 
-    def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None):
+    def _search_regex(self, pattern, string, name, default=NO_DEFAULT, fatal=True, flags=0, group=None):
         """
         Perform a regex search on the given string, using a single or a list of
         patterns returning the first matching group.
@@ -541,16 +563,15 @@ class InfoExtractor(object):
                 return next(g for g in mobj.groups() if g is not None)
             else:
                 return mobj.group(group)
-        elif default is not _NO_DEFAULT:
+        elif default is not NO_DEFAULT:
             return default
         elif fatal:
             raise RegexNotFoundError('Unable to extract %s' % _name)
         else:
-            self._downloader.report_warning('unable to extract %s; '
-                                            'please report this issue on http://yt-dl.org/bug' % _name)
+            self._downloader.report_warning('unable to extract %s' % _name + bug_reports_message())
             return None
 
-    def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None):
+    def _html_search_regex(self, pattern, string, name, default=NO_DEFAULT, fatal=True, flags=0, group=None):
         """
         Like _search_regex, but strips HTML tags and unescapes entities.
         """
@@ -562,7 +583,7 @@ class InfoExtractor(object):
 
     def _get_login_info(self):
         """
-        Get the the login info as (username, password)
+        Get the login info as (username, password)
         It will look in the netrc file using the _NETRC_MACHINE value
         If there's no info available, return (None, None)
         """
@@ -590,7 +611,7 @@ class InfoExtractor(object):
 
         return (username, password)
 
-    def _get_tfa_info(self):
+    def _get_tfa_info(self, note='two-factor verification code'):
         """
         Get the two-factor authentication info
         TODO - asking the user will be required for sms/phone verify
@@ -604,7 +625,7 @@ class InfoExtractor(object):
         if downloader_params.get('twofactor', None) is not None:
             return downloader_params['twofactor']
 
-        return None
+        return compat_getpass('Type %s and press [Return]: ' % note)
 
     # Helper functions for extracting OpenGraph info
     @staticmethod
@@ -617,6 +638,12 @@ class InfoExtractor(object):
             template % (content_re, property_re),
         ]
 
+    @staticmethod
+    def _meta_regex(prop):
+        return r'''(?isx)<meta
+                    (?=[^>]+(?:itemprop|name|property|id|http-equiv)=(["\']?)%s\1)
+                    [^>]+?content=(["\'])(?P<content>.*?)\2''' % re.escape(prop)
+
     def _og_search_property(self, prop, html, name=None, **kargs):
         if name is None:
             name = 'OpenGraph %s' % prop
@@ -626,7 +653,7 @@ class InfoExtractor(object):
         return unescapeHTML(escaped)
 
     def _og_search_thumbnail(self, html, **kargs):
-        return self._og_search_property('image', html, 'thumbnail url', fatal=False, **kargs)
+        return self._og_search_property('image', html, 'thumbnail URL', fatal=False, **kargs)
 
     def _og_search_description(self, html, **kargs):
         return self._og_search_property('description', html, fatal=False, **kargs)
@@ -647,9 +674,7 @@ class InfoExtractor(object):
         if display_name is None:
             display_name = name
         return self._html_search_regex(
-            r'''(?isx)<meta
-                    (?=[^>]+(?:itemprop|name|property)=(["\']?)%s\1)
-                    [^>]+?content=(["\'])(?P<content>.*?)\2''' % re.escape(name),
+            self._meta_regex(name),
             html, display_name, fatal=fatal, group='content', **kwargs)
 
     def _dc_search_uploader(self, html):
@@ -698,7 +723,28 @@ class InfoExtractor(object):
         return self._html_search_meta('twitter:player', html,
                                       'twitter card player')
 
-    def _sort_formats(self, formats):
+    @staticmethod
+    def _hidden_inputs(html):
+        hidden_inputs = {}
+        for input in re.findall(r'<input([^>]+)>', html):
+            if not re.search(r'type=(["\'])hidden\1', input):
+                continue
+            name = re.search(r'name=(["\'])(?P<value>.+?)\1', input)
+            if not name:
+                continue
+            value = re.search(r'value=(["\'])(?P<value>.*?)\1', input)
+            if not value:
+                continue
+            hidden_inputs[name.group('value')] = value.group('value')
+        return hidden_inputs
+
+    def _form_hidden_inputs(self, form_id, html):
+        form = self._search_regex(
+            r'(?s)<form[^>]+?id=(["\'])%s\1[^>]*>(?P<form>.+?)</form>' % form_id,
+            html, '%s form' % form_id, group='form')
+        return self._hidden_inputs(form)
+
+    def _sort_formats(self, formats, field_preference=None):
         if not formats:
             raise ExtractorError('No video formats found')
 
@@ -708,6 +754,9 @@ class InfoExtractor(object):
             if not f.get('ext') and 'url' in f:
                 f['ext'] = determine_ext(f['url'])
 
+            if isinstance(field_preference, (list, tuple)):
+                return tuple(f.get(field) if f.get(field) is not None else -1 for field in field_preference)
+
             preference = f.get('preference')
             if preference is None:
                 proto = f.get('protocol')
@@ -754,7 +803,7 @@ class InfoExtractor(object):
                 f.get('fps') if f.get('fps') is not None else -1,
                 f.get('filesize_approx') if f.get('filesize_approx') is not None else -1,
                 f.get('source_preference') if f.get('source_preference') is not None else -1,
-                f.get('format_id'),
+                f.get('format_id') if f.get('format_id') is not None else '',
             )
         formats.sort(key=_formats_key)
 
@@ -767,13 +816,17 @@ class InfoExtractor(object):
                 formats)
 
     def _is_valid_url(self, url, video_id, item='video'):
+        url = self._proto_relative_url(url, scheme='http:')
+        # For now assume non HTTP(S) URLs always valid
+        if not (url.startswith('http://') or url.startswith('https://')):
+            return True
         try:
             self._request_webpage(url, video_id, 'Checking %s URL' % item)
             return True
         except ExtractorError as e:
             if isinstance(e.cause, compat_HTTPError):
-                self.report_warning(
-                    '%s URL is invalid, skipping' % item, video_id)
+                self.to_screen(
+                    '%s: %s URL is invalid, skipping' % (video_id, item))
                 return False
             raise
 
@@ -801,10 +854,14 @@ class InfoExtractor(object):
         self.to_screen(msg)
         time.sleep(timeout)
 
-    def _extract_f4m_formats(self, manifest_url, video_id, preference=None, f4m_id=None):
+    def _extract_f4m_formats(self, manifest_url, video_id, preference=None, f4m_id=None,
+                             transform_source=lambda s: fix_xml_ampersands(s).strip()):
         manifest = self._download_xml(
             manifest_url, video_id, 'Downloading f4m manifest',
-            'Unable to download f4m manifest')
+            'Unable to download f4m manifest',
+            # Some manifests may be malformed, e.g. prosiebensat1 generated manifests
+            # (see https://github.com/rg3/youtube-dl/issues/6215#issuecomment-121704244)
+            transform_source=transform_source)
 
         formats = []
         manifest_version = '1.0'
@@ -814,11 +871,22 @@ class InfoExtractor(object):
             media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media')
         for i, media_el in enumerate(media_nodes):
             if manifest_version == '2.0':
-                manifest_url = ('/'.join(manifest_url.split('/')[:-1]) + '/' +
-                                (media_el.attrib.get('href') or media_el.attrib.get('url')))
+                media_url = media_el.attrib.get('href') or media_el.attrib.get('url')
+                if not media_url:
+                    continue
+                manifest_url = (
+                    media_url if media_url.startswith('http://') or media_url.startswith('https://')
+                    else ('/'.join(manifest_url.split('/')[:-1]) + '/' + media_url))
+                # If media_url is itself a f4m manifest do the recursive extraction
+                # since bitrates in parent manifest (this one) and media_url manifest
+                # may differ leading to inability to resolve the format by requested
+                # bitrate in f4m downloader
+                if determine_ext(manifest_url) == 'f4m':
+                    formats.extend(self._extract_f4m_formats(manifest_url, video_id, preference, f4m_id))
+                    continue
             tbr = int_or_none(media_el.attrib.get('bitrate'))
             formats.append({
-                'format_id': '-'.join(filter(None, [f4m_id, 'f4m-%d' % (i if tbr is None else tbr)])),
+                'format_id': '-'.join(filter(None, [f4m_id, compat_str(i if tbr is None else tbr)])),
                 'url': manifest_url,
                 'ext': 'flv',
                 'tbr': tbr,
@@ -832,10 +900,11 @@ class InfoExtractor(object):
 
     def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None,
                               entry_protocol='m3u8', preference=None,
-                              m3u8_id=None):
+                              m3u8_id=None, note=None, errnote=None,
+                              fatal=True):
 
         formats = [{
-            'format_id': '-'.join(filter(None, [m3u8_id, 'm3u8-meta'])),
+            'format_id': '-'.join(filter(None, [m3u8_id, 'meta'])),
             'url': m3u8_url,
             'ext': ext,
             'protocol': 'm3u8',
@@ -851,8 +920,11 @@ class InfoExtractor(object):
 
         m3u8_doc = self._download_webpage(
             m3u8_url, video_id,
-            note='Downloading m3u8 information',
-            errnote='Failed to download m3u8 information')
+            note=note or 'Downloading m3u8 information',
+            errnote=errnote or 'Failed to download m3u8 information',
+            fatal=fatal)
+        if m3u8_doc is False:
+            return m3u8_doc
         last_info = None
         last_media = None
         kv_rex = re.compile(
@@ -879,8 +951,13 @@ class InfoExtractor(object):
                     formats.append({'url': format_url(line)})
                     continue
                 tbr = int_or_none(last_info.get('BANDWIDTH'), scale=1000)
+                format_id = []
+                if m3u8_id:
+                    format_id.append(m3u8_id)
+                last_media_name = last_media.get('NAME') if last_media and last_media.get('TYPE') != 'SUBTITLES' else None
+                format_id.append(last_media_name if last_media_name else '%d' % (tbr if tbr else len(formats)))
                 f = {
-                    'format_id': '-'.join(filter(None, [m3u8_id, 'm3u8-%d' % (tbr if tbr else len(formats))])),
+                    'format_id': '-'.join(format_id),
                     'url': format_url(line.strip()),
                     'tbr': tbr,
                     'ext': ext,
@@ -908,52 +985,222 @@ class InfoExtractor(object):
         self._sort_formats(formats)
         return formats
 
-    # TODO: improve extraction
-    def _extract_smil_formats(self, smil_url, video_id, fatal=True):
-        smil = self._download_xml(
-            smil_url, video_id, 'Downloading SMIL file',
-            'Unable to download SMIL file', fatal=fatal)
+    @staticmethod
+    def _xpath_ns(path, namespace=None):
+        if not namespace:
+            return path
+        out = []
+        for c in path.split('/'):
+            if not c or c == '.':
+                out.append(c)
+            else:
+                out.append('{%s}%s' % (namespace, c))
+        return '/'.join(out)
+
+    def _extract_smil_formats(self, smil_url, video_id, fatal=True, f4m_params=None):
+        smil = self._download_smil(smil_url, video_id, fatal=fatal)
+
         if smil is False:
             assert not fatal
             return []
 
-        base = smil.find('./head/meta').get('base')
+        namespace = self._parse_smil_namespace(smil)
+
+        return self._parse_smil_formats(
+            smil, smil_url, video_id, namespace=namespace, f4m_params=f4m_params)
+
+    def _extract_smil_info(self, smil_url, video_id, fatal=True, f4m_params=None):
+        smil = self._download_smil(smil_url, video_id, fatal=fatal)
+        if smil is False:
+            return {}
+        return self._parse_smil(smil, smil_url, video_id, f4m_params=f4m_params)
+
+    def _download_smil(self, smil_url, video_id, fatal=True):
+        return self._download_xml(
+            smil_url, video_id, 'Downloading SMIL file',
+            'Unable to download SMIL file', fatal=fatal)
+
+    def _parse_smil(self, smil, smil_url, video_id, f4m_params=None):
+        namespace = self._parse_smil_namespace(smil)
+
+        formats = self._parse_smil_formats(
+            smil, smil_url, video_id, namespace=namespace, f4m_params=f4m_params)
+        subtitles = self._parse_smil_subtitles(smil, namespace=namespace)
+
+        video_id = os.path.splitext(url_basename(smil_url))[0]
+        title = None
+        description = None
+        for meta in smil.findall(self._xpath_ns('./head/meta', namespace)):
+            name = meta.attrib.get('name')
+            content = meta.attrib.get('content')
+            if not name or not content:
+                continue
+            if not title and name == 'title':
+                title = content
+            elif not description and name in ('description', 'abstract'):
+                description = content
+
+        return {
+            'id': video_id,
+            'title': title or video_id,
+            'description': description,
+            'formats': formats,
+            'subtitles': subtitles,
+        }
+
+    def _parse_smil_namespace(self, smil):
+        return self._search_regex(
+            r'(?i)^{([^}]+)?}smil$', smil.tag, 'namespace', default=None)
+
+    def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None):
+        base = smil_url
+        for meta in smil.findall(self._xpath_ns('./head/meta', namespace)):
+            b = meta.get('base') or meta.get('httpBase')
+            if b:
+                base = b
+                break
 
         formats = []
         rtmp_count = 0
-        for video in smil.findall('./body/switch/video'):
+        http_count = 0
+
+        videos = smil.findall(self._xpath_ns('.//video', namespace))
+        for video in videos:
             src = video.get('src')
             if not src:
                 continue
+
             bitrate = int_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000)
+            filesize = int_or_none(video.get('size') or video.get('fileSize'))
             width = int_or_none(video.get('width'))
             height = int_or_none(video.get('height'))
             proto = video.get('proto')
-            if not proto:
-                if base:
-                    if base.startswith('rtmp'):
-                        proto = 'rtmp'
-                    elif base.startswith('http'):
-                        proto = 'http'
             ext = video.get('ext')
-            if proto == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(src, video_id, ext))
-            elif proto == 'rtmp':
+            src_ext = determine_ext(src)
+            streamer = video.get('streamer') or base
+
+            if proto == 'rtmp' or streamer.startswith('rtmp'):
                 rtmp_count += 1
-                streamer = video.get('streamer') or base
                 formats.append({
                     'url': streamer,
                     'play_path': src,
                     'ext': 'flv',
                     'format_id': 'rtmp-%d' % (rtmp_count if bitrate is None else bitrate),
                     'tbr': bitrate,
+                    'filesize': filesize,
                     'width': width,
                     'height': height,
                 })
+                if transform_rtmp_url:
+                    streamer, src = transform_rtmp_url(streamer, src)
+                    formats[-1].update({
+                        'url': streamer,
+                        'play_path': src,
+                    })
+                continue
+
+            src_url = src if src.startswith('http') else compat_urlparse.urljoin(base, src)
+
+            if proto == 'm3u8' or src_ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    src_url, video_id, ext or 'mp4', m3u8_id='hls'))
+                continue
+
+            if src_ext == 'f4m':
+                f4m_url = src_url
+                if not f4m_params:
+                    f4m_params = {
+                        'hdcore': '3.2.0',
+                        'plugin': 'flowplayer-3.2.0.1',
+                    }
+                f4m_url += '&' if '?' in f4m_url else '?'
+                f4m_url += compat_urllib_parse.urlencode(f4m_params)
+                formats.extend(self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds'))
+                continue
+
+            if src_url.startswith('http'):
+                http_count += 1
+                formats.append({
+                    'url': src_url,
+                    'ext': ext or src_ext or 'flv',
+                    'format_id': 'http-%d' % (bitrate or http_count),
+                    'tbr': bitrate,
+                    'filesize': filesize,
+                    'width': width,
+                    'height': height,
+                })
+                continue
+
         self._sort_formats(formats)
 
         return formats
 
+    def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'):
+        subtitles = {}
+        for num, textstream in enumerate(smil.findall(self._xpath_ns('.//textstream', namespace))):
+            src = textstream.get('src')
+            if not src:
+                continue
+            ext = textstream.get('ext') or determine_ext(src)
+            if not ext:
+                type_ = textstream.get('type')
+                SUBTITLES_TYPES = {
+                    'text/vtt': 'vtt',
+                    'text/srt': 'srt',
+                    'application/smptett+xml': 'tt',
+                }
+                if type_ in SUBTITLES_TYPES:
+                    ext = SUBTITLES_TYPES[type_]
+            lang = textstream.get('systemLanguage') or textstream.get('systemLanguageName') or textstream.get('lang') or subtitles_lang
+            subtitles.setdefault(lang, []).append({
+                'url': src,
+                'ext': ext,
+            })
+        return subtitles
+
+    def _extract_xspf_playlist(self, playlist_url, playlist_id, fatal=True):
+        xspf = self._download_xml(
+            playlist_url, playlist_id, 'Downloading xpsf playlist',
+            'Unable to download xspf manifest', fatal=fatal)
+        if xspf is False:
+            return []
+        return self._parse_xspf(xspf, playlist_id)
+
+    def _parse_xspf(self, playlist, playlist_id):
+        NS_MAP = {
+            'xspf': 'http://xspf.org/ns/0/',
+            's1': 'http://static.streamone.nl/player/ns/0',
+        }
+
+        entries = []
+        for track in playlist.findall(xpath_with_ns('./xspf:trackList/xspf:track', NS_MAP)):
+            title = xpath_text(
+                track, xpath_with_ns('./xspf:title', NS_MAP), 'title', default=playlist_id)
+            description = xpath_text(
+                track, xpath_with_ns('./xspf:annotation', NS_MAP), 'description')
+            thumbnail = xpath_text(
+                track, xpath_with_ns('./xspf:image', NS_MAP), 'thumbnail')
+            duration = float_or_none(
+                xpath_text(track, xpath_with_ns('./xspf:duration', NS_MAP), 'duration'), 1000)
+
+            formats = [{
+                'url': location.text,
+                'format_id': location.get(xpath_with_ns('s1:label', NS_MAP)),
+                'width': int_or_none(location.get(xpath_with_ns('s1:width', NS_MAP))),
+                'height': int_or_none(location.get(xpath_with_ns('s1:height', NS_MAP))),
+            } for location in track.findall(xpath_with_ns('./xspf:location', NS_MAP))]
+            self._sort_formats(formats)
+
+            entries.append({
+                'id': playlist_id,
+                'title': title,
+                'description': description,
+                'thumbnail': thumbnail,
+                'duration': duration,
+                'formats': formats,
+            })
+        return entries
+
     def _live_title(self, name):
         """ Generate the title for a live video """
         now = datetime.datetime.now()
@@ -988,6 +1235,12 @@ class InfoExtractor(object):
             None, '/', True, False, expire_time, '', None, None, None)
         self._downloader.cookiejar.set_cookie(cookie)
 
+    def _get_cookies(self, url):
+        """ Return a compat_cookies.SimpleCookie with the cookies for the url """
+        req = compat_urllib_request.Request(url)
+        self._downloader.cookiejar.add_cookie_header(req)
+        return compat_cookies.SimpleCookie(req.get_header('Cookie'))
+
     def get_testcases(self, include_onlymatching=False):
         t = getattr(self, '_TEST', None)
         if t:
@@ -1026,6 +1279,23 @@ class InfoExtractor(object):
     def _get_subtitles(self, *args, **kwargs):
         raise NotImplementedError("This method must be implemented by subclasses")
 
+    @staticmethod
+    def _merge_subtitle_items(subtitle_list1, subtitle_list2):
+        """ Merge subtitle items for one language. Items with duplicated URLs
+        will be dropped. """
+        list1_urls = set([item['url'] for item in subtitle_list1])
+        ret = list(subtitle_list1)
+        ret.extend([item for item in subtitle_list2 if item['url'] not in list1_urls])
+        return ret
+
+    @classmethod
+    def _merge_subtitles(cls, subtitle_dict1, subtitle_dict2):
+        """ Merge two subtitle dictionaries, language by language. """
+        ret = dict(subtitle_dict1)
+        for lang in subtitle_dict2:
+            ret[lang] = cls._merge_subtitle_items(subtitle_dict1.get(lang, []), subtitle_dict2[lang])
+        return ret
+
     def extract_automatic_captions(self, *args, **kwargs):
         if (self._downloader.params.get('writeautomaticsub', False) or
                 self._downloader.params.get('listsubtitles')):
@@ -1039,7 +1309,7 @@ class InfoExtractor(object):
 class SearchInfoExtractor(InfoExtractor):
     """
     Base class for paged search queries extractors.
-    They accept urls in the format _SEARCH_KEY(|all|[0-9]):{query}
+    They accept URLs in the format _SEARCH_KEY(|all|[0-9]):{query}
     Instances should define _SEARCH_KEY and _MAX_RESULTS.
     """
 

youtube_dl/extractor/cracked.py

@@ -11,39 +11,65 @@ from ..utils import (
 
 class CrackedIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?cracked\.com/video_(?P<id>\d+)_[\da-z-]+\.html'
-    _TEST = {
-        'url': 'http://www.cracked.com/video_19006_4-plot-holes-you-didnt-notice-in-your-favorite-movies.html',
-        'md5': '4b29a5eeec292cd5eca6388c7558db9e',
+    _TESTS = [{
+        'url': 'http://www.cracked.com/video_19070_if-animal-actors-got-e21-true-hollywood-stories.html',
+        'md5': '89b90b9824e3806ca95072c4d78f13f7',
         'info_dict': {
-            'id': '19006',
+            'id': '19070',
             'ext': 'mp4',
-            'title': '4 Plot Holes You Didn\'t Notice in Your Favorite Movies',
-            'description': 'md5:3b909e752661db86007d10e5ec2df769',
-            'timestamp': 1405659600,
-            'upload_date': '20140718',
+            'title': 'If Animal Actors Got E! True Hollywood Stories',
+            'timestamp': 1404954000,
+            'upload_date': '20140710',
         }
-    }
+    }, {
+        # youtube embed
+        'url': 'http://www.cracked.com/video_19006_4-plot-holes-you-didnt-notice-in-your-favorite-movies.html',
+        'md5': 'ccd52866b50bde63a6ef3b35016ba8c7',
+        'info_dict': {
+            'id': 'EjI00A3rZD0',
+            'ext': 'mp4',
+            'title': "4 Plot Holes You Didn't Notice in Your Favorite Movies - The Spit Take",
+            'description': 'md5:c603708c718b796fe6079e2b3351ffc7',
+            'upload_date': '20140725',
+            'uploader_id': 'Cracked',
+            'uploader': 'Cracked',
+        }
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
 
+        youtube_url = self._search_regex(
+            r'<iframe[^>]+src="((?:https?:)?//www\.youtube\.com/embed/[^"]+)"',
+            webpage, 'youtube url', default=None)
+        if youtube_url:
+            return self.url_result(youtube_url, 'Youtube')
+
         video_url = self._html_search_regex(
-            [r'var\s+CK_vidSrc\s*=\s*"([^"]+)"', r'<video\s+src="([^"]+)"'], webpage, 'video URL')
+            [r'var\s+CK_vidSrc\s*=\s*"([^"]+)"', r'<video\s+src="([^"]+)"'],
+            webpage, 'video URL')
 
-        title = self._og_search_title(webpage)
-        description = self._og_search_description(webpage)
+        title = self._search_regex(
+            [r'property="?og:title"?\s+content="([^"]+)"', r'class="?title"?>([^<]+)'],
+            webpage, 'title')
 
-        timestamp = self._html_search_regex(r'<time datetime="([^"]+)"', webpage, 'upload date', fatal=False)
+        description = self._search_regex(
+            r'name="?(?:og:)?description"?\s+content="([^"]+)"',
+            webpage, 'description', default=None)
+
+        timestamp = self._html_search_regex(
+            r'"date"\s*:\s*"([^"]+)"', webpage, 'upload date', fatal=False)
         if timestamp:
             timestamp = parse_iso8601(timestamp[:-6])
 
         view_count = str_to_int(self._html_search_regex(
-            r'<span class="views" id="viewCounts">([\d,\.]+) Views</span>', webpage, 'view count', fatal=False))
+            r'<span\s+class="?views"? id="?viewCounts"?>([\d,\.]+) Views</span>',
+            webpage, 'view count', fatal=False))
         comment_count = str_to_int(self._html_search_regex(
-            r'<span id="commentCounts">([\d,\.]+)</span>', webpage, 'comment count', fatal=False))
+            r'<span\s+id="?commentCounts"?>([\d,\.]+)</span>',
+            webpage, 'comment count', fatal=False))
 
         m = re.search(r'_(?P<width>\d+)X(?P<height>\d+)\.mp4$', video_url)
         if m:

youtube_dl/extractor/crooksandliars.py

@@ -0,0 +1,60 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    qualities,
+)
+
+
+class CrooksAndLiarsIE(InfoExtractor):
+    _VALID_URL = r'https?://embed\.crooksandliars\.com/(?:embed|v)/(?P<id>[A-Za-z0-9]+)'
+    _TESTS = [{
+        'url': 'https://embed.crooksandliars.com/embed/8RUoRhRi',
+        'info_dict': {
+            'id': '8RUoRhRi',
+            'ext': 'mp4',
+            'title': 'Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!',
+            'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'timestamp': 1428207000,
+            'upload_date': '20150405',
+            'uploader': 'Heather',
+            'duration': 236,
+        }
+    }, {
+        'url': 'http://embed.crooksandliars.com/v/MTE3MjUtMzQ2MzA',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            'http://embed.crooksandliars.com/embed/%s' % video_id, video_id)
+
+        manifest = self._parse_json(
+            self._search_regex(
+                r'var\s+manifest\s*=\s*({.+?})\n', webpage, 'manifest JSON'),
+            video_id)
+
+        quality = qualities(('webm_low', 'mp4_low', 'webm_high', 'mp4_high'))
+
+        formats = [{
+            'url': item['url'],
+            'format_id': item['type'],
+            'quality': quality(item['type']),
+        } for item in manifest['flavors'] if item['mime'].startswith('video/')]
+        self._sort_formats(formats)
+
+        return {
+            'url': url,
+            'id': video_id,
+            'title': manifest['title'],
+            'description': manifest.get('description'),
+            'thumbnail': self._proto_relative_url(manifest.get('poster')),
+            'timestamp': int_or_none(manifest.get('created')),
+            'uploader': manifest.get('author'),
+            'duration': int_or_none(manifest.get('duration')),
+            'formats': formats,
+        }

youtube_dl/extractor/crunchyroll.py

@@ -12,23 +12,26 @@ from math import pow, sqrt, floor
 from .common import InfoExtractor
 from ..compat import (
     compat_urllib_parse,
+    compat_urllib_parse_unquote,
     compat_urllib_request,
+    compat_urlparse,
 )
 from ..utils import (
     ExtractorError,
     bytes_to_intlist,
     intlist_to_bytes,
+    remove_end,
     unified_strdate,
     urlencode_postdata,
 )
 from ..aes import (
     aes_cbc_decrypt,
-    inc,
 )
 
 
 class CrunchyrollIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
+    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)'
+    _NETRC_MACHINE = 'crunchyroll'
     _TESTS = [{
         'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
         'info_dict': {
@@ -45,6 +48,22 @@ class CrunchyrollIE(InfoExtractor):
             # rtmp
             'skip_download': True,
         },
+    }, {
+        'url': 'http://www.crunchyroll.com/media-589804/culture-japan-1',
+        'info_dict': {
+            'id': '589804',
+            'ext': 'flv',
+            'title': 'Culture Japan Episode 1 – Rebuilding Japan after the 3.11',
+            'description': 'md5:fe2743efedb49d279552926d0bd0cd9e',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': 'Danny Choo Network',
+            'upload_date': '20120213',
+        },
+        'params': {
+            # rtmp
+            'skip_download': True,
+        },
+
     }, {
         'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
         'only_matching': True,
@@ -76,8 +95,8 @@ class CrunchyrollIE(InfoExtractor):
         self._login()
 
     def _decrypt_subtitles(self, data, iv, id):
-        data = bytes_to_intlist(data)
-        iv = bytes_to_intlist(iv)
+        data = bytes_to_intlist(base64.b64decode(data.encode('utf-8')))
+        iv = bytes_to_intlist(base64.b64decode(iv.encode('utf-8')))
         id = int(id)
 
         def obfuscate_key_aux(count, modulo, start):
@@ -101,13 +120,6 @@ class CrunchyrollIE(InfoExtractor):
 
         key = obfuscate_key(id)
 
-        class Counter:
-            __value = iv
-
-            def next_value(self):
-                temp = self.__value
-                self.__value = inc(self.__value)
-                return temp
         decrypted_data = intlist_to_bytes(aes_cbc_decrypt(data, key, iv))
         return zlib.decompress(decrypted_data)
 
@@ -186,6 +198,16 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
 
         return output
 
+    def _extract_subtitles(self, subtitle):
+        sub_root = xml.etree.ElementTree.fromstring(subtitle)
+        return [{
+            'ext': 'srt',
+            'data': self._convert_subtitles_to_srt(sub_root),
+        }, {
+            'ext': 'ass',
+            'data': self._convert_subtitles_to_ass(sub_root),
+        }]
+
     def _get_subtitles(self, video_id, webpage):
         subtitles = {}
         for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage):
@@ -197,25 +219,11 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             data = self._search_regex(r'<data>([^<]+)', sub_page, 'subtitle_data', fatal=False)
             if not id or not iv or not data:
                 continue
-            id = int(id)
-            iv = base64.b64decode(iv)
-            data = base64.b64decode(data)
-
             subtitle = self._decrypt_subtitles(data, iv, id).decode('utf-8')
             lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False)
             if not lang_code:
                 continue
-            sub_root = xml.etree.ElementTree.fromstring(subtitle)
-            subtitles[lang_code] = [
-                {
-                    'ext': 'srt',
-                    'data': self._convert_subtitles_to_srt(sub_root),
-                },
-                {
-                    'ext': 'ass',
-                    'data': self._convert_subtitles_to_ass(sub_root),
-                },
-            ]
+            subtitles[lang_code] = self._extract_subtitles(subtitle)
         return subtitles
 
     def _real_extract(self, url):
@@ -249,7 +257,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             video_upload_date = unified_strdate(video_upload_date)
         video_uploader = self._html_search_regex(r'<div>\s*Publisher:(.+?)</div>', webpage, 'video_uploader', fatal=False, flags=re.DOTALL)
 
-        playerdata_url = compat_urllib_parse.unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, 'playerdata_url'))
+        playerdata_url = compat_urllib_parse_unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, 'playerdata_url'))
         playerdata_req = compat_urllib_request.Request(playerdata_url)
         playerdata_req.data = compat_urllib_parse.urlencode({'current_page': webpage_url})
         playerdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
@@ -262,16 +270,31 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
         for fmt in re.findall(r'showmedia\.([0-9]{3,4})p', webpage):
             stream_quality, stream_format = self._FORMAT_IDS[fmt]
             video_format = fmt + 'p'
-            streamdata_req = compat_urllib_request.Request('http://www.crunchyroll.com/xml/')
-            # urlencode doesn't work!
-            streamdata_req.data = 'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality=' + stream_quality + '&media%5Fid=' + stream_id + '&video%5Fformat=' + stream_format
+            streamdata_req = compat_urllib_request.Request(
+                'http://www.crunchyroll.com/xml/?req=RpcApiVideoPlayer_GetStandardConfig&media_id=%s&video_format=%s&video_quality=%s'
+                % (stream_id, stream_format, stream_quality),
+                compat_urllib_parse.urlencode({'current_page': url}).encode('utf-8'))
             streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
-            streamdata_req.add_header('Content-Length', str(len(streamdata_req.data)))
             streamdata = self._download_xml(
                 streamdata_req, video_id,
                 note='Downloading media info for %s' % video_format)
-            video_url = streamdata.find('.//host').text
-            video_play_path = streamdata.find('.//file').text
+            stream_info = streamdata.find('./{default}preload/stream_info')
+            video_url = stream_info.find('./host').text
+            video_play_path = stream_info.find('./file').text
+
+            if '.fplive.net/' in video_url:
+                video_url = re.sub(r'^rtmpe?://', 'http://', video_url.strip())
+                parsed_video_url = compat_urlparse.urlparse(video_url)
+                direct_video_url = compat_urlparse.urlunparse(parsed_video_url._replace(
+                    netloc='v.lvlt.crcdn.net',
+                    path='%s/%s' % (remove_end(parsed_video_url.path, '/'), video_play_path.split(':')[-1])))
+                if self._is_valid_url(direct_video_url, video_id, video_format):
+                    formats.append({
+                        'url': direct_video_url,
+                        'format_id': video_format,
+                    })
+                    continue
+
             formats.append({
                 'url': video_url,
                 'play_path': video_play_path,

youtube_dl/extractor/cspan.py

@@ -7,7 +7,10 @@ from ..utils import (
     int_or_none,
     unescapeHTML,
     find_xpath_attr,
+    smuggle_url,
+    determine_ext,
 )
+from .senateisvp import SenateISVPIE
 
 
 class CSpanIE(InfoExtractor):
@@ -35,11 +38,22 @@ class CSpanIE(InfoExtractor):
         }
     }, {
         'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall',
+        'md5': '446562a736c6bf97118e389433ed88d4',
         'info_dict': {
             'id': '342759',
+            'ext': 'mp4',
             'title': 'General Motors Ignition Switch Recall',
+            'duration': 14848,
+            'description': 'md5:70c7c3b8fa63fa60d42772440596034c'
         },
-        'playlist_duration_sum': 14855,
+    }, {
+        # Video from senate.gov
+        'url': 'http://www.c-span.org/video/?104517-1/immigration-reforms-needed-protect-skilled-american-workers',
+        'info_dict': {
+            'id': 'judiciary031715',
+            'ext': 'flv',
+            'title': 'Immigration Reforms Needed to Protect Skilled American Workers',
+        }
     }]
 
     def _real_extract(self, url):
@@ -56,7 +70,7 @@ class CSpanIE(InfoExtractor):
                 # present, otherwise this is a stripped version
                 r'<p class=\'initial\'>(.*?)</p>'
             ],
-            webpage, 'description', flags=re.DOTALL)
+            webpage, 'description', flags=re.DOTALL, default=None)
 
         info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id
         data = self._download_json(info_url, video_id)
@@ -68,7 +82,16 @@ class CSpanIE(InfoExtractor):
         title = find_xpath_attr(doc, './/string', 'name', 'title').text
         thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text
 
+        senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
+        if senate_isvp_url:
+            surl = smuggle_url(senate_isvp_url, {'force_title': title})
+            return self.url_result(surl, 'SenateISVP', video_id, title)
+
         files = data['video']['files']
+        try:
+            capfile = data['video']['capfile']['#text']
+        except KeyError:
+            capfile = None
 
         entries = [{
             'id': '%s_%d' % (video_id, partnum + 1),
@@ -79,11 +102,22 @@ class CSpanIE(InfoExtractor):
             'description': description,
             'thumbnail': thumbnail,
             'duration': int_or_none(f.get('length', {}).get('#text')),
+            'subtitles': {
+                'en': [{
+                    'url': capfile,
+                    'ext': determine_ext(capfile, 'dfxp')
+                }],
+            } if capfile else None,
         } for partnum, f in enumerate(files)]
 
-        return {
-            '_type': 'playlist',
-            'entries': entries,
-            'title': title,
-            'id': video_id,
-        }
+        if len(entries) == 1:
+            entry = dict(entries[0])
+            entry['id'] = video_id
+            return entry
+        else:
+            return {
+                '_type': 'playlist',
+                'entries': entries,
+                'title': title,
+                'id': video_id,
+            }

youtube_dl/extractor/ctsnews.py

@@ -6,6 +6,7 @@ from ..utils import parse_iso8601, ExtractorError
 
 
 class CtsNewsIE(InfoExtractor):
+    IE_DESC = '華視新聞'
     # https connection failed (Connection reset)
     _VALID_URL = r'http://news\.cts\.com\.tw/[a-z]+/[a-z]+/\d+/(?P<id>\d+)\.html'
     _TESTS = [{

youtube_dl/extractor/dailymotion.py

@@ -13,8 +13,9 @@ from ..compat import (
 )
 from ..utils import (
     ExtractorError,
+    determine_ext,
     int_or_none,
-    orderedSet,
+    parse_iso8601,
     str_to_int,
     unescapeHTML,
 )
@@ -25,14 +26,19 @@ class DailymotionBaseInfoExtractor(InfoExtractor):
     def _build_request(url):
         """Build a request with the family filter disabled"""
         request = compat_urllib_request.Request(url)
-        request.add_header('Cookie', 'family_filter=off')
-        request.add_header('Cookie', 'ff=off')
+        request.add_header('Cookie', 'family_filter=off; ff=off')
         return request
 
+    def _download_webpage_handle_no_ff(self, url, *args, **kwargs):
+        request = self._build_request(url)
+        return self._download_webpage_handle(request, *args, **kwargs)
+
+    def _download_webpage_no_ff(self, url, *args, **kwargs):
+        request = self._build_request(url)
+        return self._download_webpage(request, *args, **kwargs)
+
 
 class DailymotionIE(DailymotionBaseInfoExtractor):
-    """Information Extractor for Dailymotion"""
-
     _VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(embed|#)/)?video/(?P<id>[^/?_]+)'
     IE_NAME = 'dailymotion'
 
@@ -46,13 +52,22 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
 
     _TESTS = [
         {
-            'url': 'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech',
-            'md5': '392c4b85a60a90dc4792da41ce3144eb',
+            'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames',
+            'md5': '2137c41a8e78554bb09225b8eb322406',
             'info_dict': {
-                'id': 'x33vw9',
+                'id': 'x2iuewm',
                 'ext': 'mp4',
-                'uploader': 'Amphora Alex and Van .',
-                'title': 'Tutoriel de Youtubeur"DL DES VIDEO DE YOUTUBE"',
+                'title': 'Steam Machine Models, Pricing Listed on Steam Store - IGN News',
+                'description': 'Several come bundled with the Steam Controller.',
+                'thumbnail': 're:^https?:.*\.(?:jpg|png)$',
+                'duration': 74,
+                'timestamp': 1425657362,
+                'upload_date': '20150306',
+                'uploader': 'IGN',
+                'uploader_id': 'xijv66',
+                'age_limit': 0,
+                'view_count': int,
+                'comment_count': int,
             }
         },
         # Vevo video
@@ -86,37 +101,106 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        url = 'http://www.dailymotion.com/video/%s' % video_id
 
-        # Retrieve video webpage to extract further information
-        request = self._build_request(url)
-        webpage = self._download_webpage(request, video_id)
-
-        # Extract URL, uploader and title from webpage
-        self.report_extraction(video_id)
-
-        # It may just embed a vevo video:
-        m_vevo = re.search(
-            r'<link rel="video_src" href="[^"]*?vevo.com[^"]*?video=(?P<id>[\w]*)',
-            webpage)
-        if m_vevo is not None:
-            vevo_id = m_vevo.group('id')
-            self.to_screen('Vevo video detected: %s' % vevo_id)
-            return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
+        webpage = self._download_webpage_no_ff(
+            'https://www.dailymotion.com/video/%s' % video_id, video_id)
 
         age_limit = self._rta_search(webpage)
 
-        video_upload_date = None
-        mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage)
-        if mobj is not None:
-            video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
+        description = self._og_search_description(webpage) or self._html_search_meta(
+            'description', webpage, 'description')
+
+        view_count = str_to_int(self._search_regex(
+            [r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserPlays:(\d+)"',
+             r'video_views_count[^>]+>\s+([\d\.,]+)'],
+            webpage, 'view count', fatal=False))
+        comment_count = int_or_none(self._search_regex(
+            r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserComments:(\d+)"',
+            webpage, 'comment count', fatal=False))
+
+        player_v5 = self._search_regex(
+            r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);',
+            webpage, 'player v5', default=None)
+        if player_v5:
+            player = self._parse_json(player_v5, video_id)
+            metadata = player['metadata']
+            formats = []
+            for quality, media_list in metadata['qualities'].items():
+                for media in media_list:
+                    media_url = media.get('url')
+                    if not media_url:
+                        continue
+                    type_ = media.get('type')
+                    if type_ == 'application/vnd.lumberjack.manifest':
+                        continue
+                    if type_ == 'application/x-mpegURL' or determine_ext(media_url) == 'm3u8':
+                        formats.extend(self._extract_m3u8_formats(
+                            media_url, video_id, 'mp4', m3u8_id='hls'))
+                    else:
+                        f = {
+                            'url': media_url,
+                            'format_id': quality,
+                        }
+                        m = re.search(r'H264-(?P<width>\d+)x(?P<height>\d+)', media_url)
+                        if m:
+                            f.update({
+                                'width': int(m.group('width')),
+                                'height': int(m.group('height')),
+                            })
+                        formats.append(f)
+            self._sort_formats(formats)
+
+            title = metadata['title']
+            duration = int_or_none(metadata.get('duration'))
+            timestamp = int_or_none(metadata.get('created_time'))
+            thumbnail = metadata.get('poster_url')
+            uploader = metadata.get('owner', {}).get('screenname')
+            uploader_id = metadata.get('owner', {}).get('id')
+
+            subtitles = {}
+            for subtitle_lang, subtitle in metadata.get('subtitles', {}).get('data', {}).items():
+                subtitles[subtitle_lang] = [{
+                    'ext': determine_ext(subtitle_url),
+                    'url': subtitle_url,
+                } for subtitle_url in subtitle.get('urls', [])]
+
+            return {
+                'id': video_id,
+                'title': title,
+                'description': description,
+                'thumbnail': thumbnail,
+                'duration': duration,
+                'timestamp': timestamp,
+                'uploader': uploader,
+                'uploader_id': uploader_id,
+                'age_limit': age_limit,
+                'view_count': view_count,
+                'comment_count': comment_count,
+                'formats': formats,
+                'subtitles': subtitles,
+            }
+
+        # vevo embed
+        vevo_id = self._search_regex(
+            r'<link rel="video_src" href="[^"]*?vevo.com[^"]*?video=(?P<id>[\w]*)',
+            webpage, 'vevo embed', default=None)
+        if vevo_id:
+            return self.url_result('vevo:%s' % vevo_id, 'Vevo')
+
+        # fallback old player
+        embed_page = self._download_webpage_no_ff(
+            'https://www.dailymotion.com/embed/video/%s' % video_id,
+            video_id, 'Downloading embed page')
+
+        timestamp = parse_iso8601(self._html_search_meta(
+            'video:release_date', webpage, 'upload date'))
+
+        info = self._parse_json(
+            self._search_regex(
+                r'var info = ({.*?}),$', embed_page,
+                'video info', flags=re.MULTILINE),
+            video_id)
 
-        embed_url = 'http://www.dailymotion.com/embed/video/%s' % video_id
-        embed_page = self._download_webpage(embed_url, video_id,
-                                            'Downloading embed page')
-        info = self._search_regex(r'var info = ({.*?}),$', embed_page,
-                                  'video info', flags=re.MULTILINE)
-        info = json.loads(info)
         if info.get('error') is not None:
             msg = 'Couldn\'t get video, Dailymotion says: %s' % info['error']['title']
             raise ExtractorError(msg, expected=True)
@@ -137,16 +221,11 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
                     'width': width,
                     'height': height,
                 })
-        if not formats:
-            raise ExtractorError('Unable to extract video URL')
+        self._sort_formats(formats)
 
         # subtitles
         video_subtitles = self.extract_subtitles(video_id, webpage)
 
-        view_count = str_to_int(self._search_regex(
-            r'video_views_count[^>]+>\s+([\d\.,]+)',
-            webpage, 'view count', fatal=False))
-
         title = self._og_search_title(webpage, default=None)
         if title is None:
             title = self._html_search_regex(
@@ -157,12 +236,14 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
             'id': video_id,
             'formats': formats,
             'uploader': info['owner.screenname'],
-            'upload_date': video_upload_date,
+            'timestamp': timestamp,
             'title': title,
+            'description': description,
             'subtitles': video_subtitles,
             'thumbnail': info['thumbnail_url'],
             'age_limit': age_limit,
             'view_count': view_count,
+            'duration': info['duration']
         }
 
     def _get_subtitles(self, video_id, webpage):
@@ -196,18 +277,26 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
     }]
 
     def _extract_entries(self, id):
-        video_ids = []
+        video_ids = set()
+        processed_urls = set()
         for pagenum in itertools.count(1):
-            request = self._build_request(self._PAGE_TEMPLATE % (id, pagenum))
-            webpage = self._download_webpage(request,
-                                             id, 'Downloading page %s' % pagenum)
+            page_url = self._PAGE_TEMPLATE % (id, pagenum)
+            webpage, urlh = self._download_webpage_handle_no_ff(
+                page_url, id, 'Downloading page %s' % pagenum)
+            if urlh.geturl() in processed_urls:
+                self.report_warning('Stopped at duplicated page %s, which is the same as %s' % (
+                    page_url, urlh.geturl()), id)
+                break
 
-            video_ids.extend(re.findall(r'data-xid="(.+?)"', webpage))
+            processed_urls.add(urlh.geturl())
+
+            for video_id in re.findall(r'data-xid="(.+?)"', webpage):
+                if video_id not in video_ids:
+                    yield self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
+                    video_ids.add(video_id)
 
             if re.search(self._MORE_PAGES_INDICATOR, webpage) is None:
                 break
-        return [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
-                for video_id in orderedSet(video_ids)]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -224,7 +313,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
 
 class DailymotionUserIE(DailymotionPlaylistIE):
     IE_NAME = 'dailymotion:user'
-    _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|#|video|playlist)/)(?:(?:old/)?user/)?(?P<user>[^/]+)'
     _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
     _TESTS = [{
         'url': 'https://www.dailymotion.com/user/nqtv',
@@ -233,12 +322,24 @@ class DailymotionUserIE(DailymotionPlaylistIE):
             'title': 'Rémi Gaillard',
         },
         'playlist_mincount': 100,
+    }, {
+        'url': 'http://www.dailymotion.com/user/UnderProject',
+        'info_dict': {
+            'id': 'UnderProject',
+            'title': 'UnderProject',
+        },
+        'playlist_mincount': 1800,
+        'expected_warnings': [
+            'Stopped at duplicated page',
+        ],
+        'skip': 'Takes too long time',
     }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         user = mobj.group('user')
-        webpage = self._download_webpage(url, user)
+        webpage = self._download_webpage(
+            'https://www.dailymotion.com/user/%s' % user, user)
         full_user = unescapeHTML(self._html_search_regex(
             r'<a class="nav-image" title="([^"]+)" href="/%s">' % re.escape(user),
             webpage, 'user'))
@@ -249,3 +350,52 @@ class DailymotionUserIE(DailymotionPlaylistIE):
             'title': full_user,
             'entries': self._extract_entries(user),
         }
+
+
+class DailymotionCloudIE(DailymotionBaseInfoExtractor):
+    _VALID_URL_PREFIX = r'http://api\.dmcloud\.net/(?:player/)?embed/'
+    _VALID_URL = r'%s[^/]+/(?P<id>[^/?]+)' % _VALID_URL_PREFIX
+    _VALID_EMBED_URL = r'%s[^/]+/[^\'"]+' % _VALID_URL_PREFIX
+
+    _TESTS = [{
+        # From http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html
+        # Tested at FranceTvInfo_2
+        'url': 'http://api.dmcloud.net/embed/4e7343f894a6f677b10006b4/556e03339473995ee145930c?auth=1464865870-0-jyhsm84b-ead4c701fb750cf9367bf4447167a3db&autoplay=1',
+        'only_matching': True,
+    }, {
+        # http://www.francetvinfo.fr/societe/larguez-les-amarres-le-cobaturage-se-developpe_980101.html
+        'url': 'http://api.dmcloud.net/player/embed/4e7343f894a6f677b10006b4/559545469473996d31429f06?auth=1467430263-0-90tglw2l-a3a4b64ed41efe48d7fccad85b8b8fda&autoplay=1',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def _extract_dmcloud_url(self, webpage):
+        mobj = re.search(r'<iframe[^>]+src=[\'"](%s)[\'"]' % self._VALID_EMBED_URL, webpage)
+        if mobj:
+            return mobj.group(1)
+
+        mobj = re.search(
+            r'<input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=[\'"](%s)[\'"]' % self._VALID_EMBED_URL,
+            webpage)
+        if mobj:
+            return mobj.group(1)
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage_no_ff(url, video_id)
+
+        title = self._html_search_regex(r'<title>([^>]+)</title>', webpage, 'title')
+
+        video_info = self._parse_json(self._search_regex(
+            r'var\s+info\s*=\s*([^;]+);', webpage, 'video info'), video_id)
+
+        # TODO: parse ios_url, which is in fact a manifest
+        video_url = video_info['mp4_url']
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'thumbnail': video_info.get('thumbnail_url'),
+        }

youtube_dl/extractor/dcn.py

@@ -0,0 +1,84 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_parse,
+    compat_urllib_request,
+)
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+)
+
+
+class DCNIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/.+|show/\d+/.+?)/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.dcndigital.ae/#/show/199074/%D8%B1%D8%AD%D9%84%D8%A9-%D8%A7%D9%84%D8%B9%D9%85%D8%B1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/17375/6887',
+        'info_dict':
+        {
+            'id': '17375',
+            'ext': 'mp4',
+            'title': 'رحلة العمر : الحلقة 1',
+            'description': 'md5:0156e935d870acb8ef0a66d24070c6d6',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 2041,
+            'timestamp': 1227504126,
+            'upload_date': '20081124',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        request = compat_urllib_request.Request(
+            'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
+            headers={'Origin': 'http://www.dcndigital.ae'})
+
+        video = self._download_json(request, video_id)
+        title = video.get('title_en') or video['title_ar']
+
+        webpage = self._download_webpage(
+            'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?'
+            + compat_urllib_parse.urlencode({
+                'id': video['id'],
+                'user_id': video['user_id'],
+                'signature': video['signature'],
+                'countries': 'Q0M=',
+                'filter': 'DENY',
+            }), video_id)
+
+        m3u8_url = self._html_search_regex(r'file:\s*"([^"]+)', webpage, 'm3u8 url')
+        formats = self._extract_m3u8_formats(
+            m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
+
+        rtsp_url = self._search_regex(
+            r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False)
+        if rtsp_url:
+            formats.append({
+                'url': rtsp_url,
+                'format_id': 'rtsp',
+            })
+
+        self._sort_formats(formats)
+
+        img = video.get('img')
+        thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None
+        duration = int_or_none(video.get('duration'))
+        description = video.get('description_en') or video.get('description_ar')
+        timestamp = parse_iso8601(video.get('create_time') or video.get('update_time'), ' ')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'timestamp': timestamp,
+            'formats': formats,
+        }

youtube_dl/extractor/dfb.py

@@ -3,42 +3,47 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import unified_strdate
 
 
 class DFBIE(InfoExtractor):
     IE_NAME = 'tv.dfb.de'
-    _VALID_URL = r'https?://tv\.dfb\.de/video/[^/]+/(?P<id>\d+)'
+    _VALID_URL = r'https?://tv\.dfb\.de/video/(?P<display_id>[^/]+)/(?P<id>\d+)'
 
     _TEST = {
-        'url': 'http://tv.dfb.de/video/highlights-des-empfangs-in-berlin/9070/',
+        'url': 'http://tv.dfb.de/video/u-19-em-stimmen-zum-spiel-gegen-russland/11633/',
         # The md5 is different each time
         'info_dict': {
-            'id': '9070',
+            'id': '11633',
+            'display_id': 'u-19-em-stimmen-zum-spiel-gegen-russland',
             'ext': 'flv',
-            'title': 'Highlights des Empfangs in Berlin',
-            'upload_date': '20140716',
+            'title': 'U 19-EM: Stimmen zum Spiel gegen Russland',
+            'upload_date': '20150714',
         },
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
 
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(url, display_id)
         player_info = self._download_xml(
             'http://tv.dfb.de/server/hd_video.php?play=%s' % video_id,
-            video_id)
+            display_id)
         video_info = player_info.find('video')
 
-        f4m_info = self._download_xml(self._proto_relative_url(video_info.find('url').text.strip()), video_id)
+        f4m_info = self._download_xml(
+            self._proto_relative_url(video_info.find('url').text.strip()), display_id)
         token_el = f4m_info.find('token')
         manifest_url = token_el.attrib['url'] + '?' + 'hdnea=' + token_el.attrib['auth'] + '&hdcore=3.2.0'
+        formats = self._extract_f4m_formats(manifest_url, display_id)
 
         return {
             'id': video_id,
+            'display_id': display_id,
             'title': video_info.find('title').text,
-            'url': manifest_url,
-            'ext': 'flv',
             'thumbnail': self._og_search_thumbnail(webpage),
-            'upload_date': ''.join(video_info.find('time_date').text.split('.')[::-1]),
+            'upload_date': unified_strdate(video_info.find('time_date').text),
+            'formats': formats,
         }

youtube_dl/extractor/dhm.py

@@ -0,0 +1,59 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import parse_duration
+
+
+class DHMIE(InfoExtractor):
+    IE_DESC = 'Filmarchiv - Deutsches Historisches Museum'
+    _VALID_URL = r'https?://(?:www\.)?dhm\.de/filmarchiv/(?:[^/]+/)+(?P<id>[^/]+)'
+
+    _TESTS = [{
+        'url': 'http://www.dhm.de/filmarchiv/die-filme/the-marshallplan-at-work-in-west-germany/',
+        'md5': '11c475f670209bf6acca0b2b7ef51827',
+        'info_dict': {
+            'id': 'the-marshallplan-at-work-in-west-germany',
+            'ext': 'flv',
+            'title': 'MARSHALL PLAN AT WORK IN WESTERN GERMANY, THE',
+            'description': 'md5:1fabd480c153f97b07add61c44407c82',
+            'duration': 660,
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+    }, {
+        'url': 'http://www.dhm.de/filmarchiv/02-mapping-the-wall/peter-g/rolle-1/',
+        'md5': '09890226332476a3e3f6f2cb74734aa5',
+        'info_dict': {
+            'id': 'rolle-1',
+            'ext': 'flv',
+            'title': 'ROLLE 1',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        playlist_url = self._search_regex(
+            r"file\s*:\s*'([^']+)'", webpage, 'playlist url')
+
+        entries = self._extract_xspf_playlist(playlist_url, playlist_id)
+
+        title = self._search_regex(
+            [r'dc:title="([^"]+)"', r'<title> &raquo;([^<]+)</title>'],
+            webpage, 'title').strip()
+        description = self._html_search_regex(
+            r'<p><strong>Description:</strong>(.+?)</p>',
+            webpage, 'description', default=None)
+        duration = parse_duration(self._search_regex(
+            r'<em>Length\s*</em>\s*:\s*</strong>([^<]+)',
+            webpage, 'duration', default=None))
+
+        entries[0].update({
+            'title': title,
+            'description': description,
+            'duration': duration,
+        })
+
+        return self.playlist_result(entries, playlist_id)

youtube_dl/extractor/discovery.py

@@ -2,19 +2,19 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
+    parse_duration,
     parse_iso8601,
-    int_or_none,
 )
+from ..compat import compat_str
 
 
 class DiscoveryIE(InfoExtractor):
     _VALID_URL = r'http://www\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9_\-]*)(?:\.htm)?'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm',
-        'md5': '3c69d77d9b0d82bfd5e5932a60f26504',
         'info_dict': {
-            'id': 'mission-impossible-outtakes',
-            'ext': 'flv',
+            'id': '20769',
+            'ext': 'mp4',
             'title': 'Mission Impossible Outtakes',
             'description': ('Watch Jamie Hyneman and Adam Savage practice being'
                             ' each other -- to the point of confusing Jamie\'s dog -- and '
@@ -24,22 +24,36 @@ class DiscoveryIE(InfoExtractor):
             'timestamp': 1303099200,
             'upload_date': '20110418',
         },
-    }
+        'params': {
+            'skip_download': True,  # requires ffmpeg
+        }
+    }, {
+        'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mythbusters-the-simpsons',
+        'info_dict': {
+            'id': 'mythbusters-the-simpsons',
+            'title': 'MythBusters: The Simpsons',
+        },
+        'playlist_count': 9,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        info = self._download_json(url + '?flat=1', video_id)
 
-        info = self._parse_json(self._search_regex(
-            r'(?s)<script type="application/ld\+json">(.*?)</script>',
-            webpage, 'video info'), video_id)
+        video_title = info.get('playlist_title') or info.get('video_title')
 
-        return {
-            'id': video_id,
-            'title': info['name'],
-            'url': info['contentURL'],
-            'description': info.get('description'),
-            'thumbnail': info.get('thumbnailUrl'),
-            'timestamp': parse_iso8601(info.get('uploadDate')),
-            'duration': int_or_none(info.get('duration')),
-        }
+        entries = [{
+            'id': compat_str(video_info['id']),
+            'formats': self._extract_m3u8_formats(
+                video_info['src'], video_id, ext='mp4',
+                note='Download m3u8 information for video %d' % (idx + 1)),
+            'title': video_info['title'],
+            'description': video_info.get('description'),
+            'duration': parse_duration(video_info.get('video_length')),
+            'webpage_url': video_info.get('href'),
+            'thumbnail': video_info.get('thumbnailURL'),
+            'alt_title': video_info.get('secondary_title'),
+            'timestamp': parse_iso8601(video_info.get('publishedDate')),
+        } for idx, video_info in enumerate(info['playlist'])]
+
+        return self.playlist_result(entries, video_id, video_title)

youtube_dl/extractor/dotsub.py

@@ -36,7 +36,8 @@ class DotsubIE(InfoExtractor):
         if not video_url:
             webpage = self._download_webpage(url, video_id)
             video_url = self._search_regex(
-                r'"file"\s*:\s*\'([^\']+)', webpage, 'video url')
+                [r'<source[^>]+src="([^"]+)"', r'"file"\s*:\s*\'([^\']+)'],
+                webpage, 'video url')
 
         return {
             'id': video_id,

youtube_dl/extractor/douyutv.py

@@ -0,0 +1,113 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import hashlib
+import time
+from .common import InfoExtractor
+from ..utils import (ExtractorError, unescapeHTML)
+from ..compat import (compat_str, compat_basestring)
+
+
+class DouyuTVIE(InfoExtractor):
+    IE_DESC = '斗鱼'
+    _VALID_URL = r'http://(?:www\.)?douyutv\.com/(?P<id>[A-Za-z0-9]+)'
+    _TESTS = [{
+        'url': 'http://www.douyutv.com/iseven',
+        'info_dict': {
+            'id': '17732',
+            'display_id': 'iseven',
+            'ext': 'flv',
+            'title': 're:^清晨醒脑！T-ara根本停不下来！ [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'description': 'md5:c93d6692dde6fe33809a46edcbecca44',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': '7师傅',
+            'uploader_id': '431925',
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        'url': 'http://www.douyutv.com/85982',
+        'info_dict': {
+            'id': '85982',
+            'display_id': '85982',
+            'ext': 'flv',
+            'title': 're:^小漠从零单排记！——CSOL2躲猫猫 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'description': 'md5:746a2f7a253966a06755a912f0acc0d2',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': 'douyu小漠',
+            'uploader_id': '3769985',
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        if video_id.isdigit():
+            room_id = video_id
+        else:
+            page = self._download_webpage(url, video_id)
+            room_id = self._html_search_regex(
+                r'"room_id"\s*:\s*(\d+),', page, 'room id')
+
+        prefix = 'room/%s?aid=android&client_sys=android&time=%d' % (
+            room_id, int(time.time()))
+
+        auth = hashlib.md5((prefix + '1231').encode('ascii')).hexdigest()
+        config = self._download_json(
+            'http://www.douyutv.com/api/v1/%s&auth=%s' % (prefix, auth),
+            video_id)
+
+        data = config['data']
+
+        error_code = config.get('error', 0)
+        if error_code is not 0:
+            error_desc = 'Server reported error %i' % error_code
+            if isinstance(data, (compat_str, compat_basestring)):
+                error_desc += ': ' + data
+            raise ExtractorError(error_desc, expected=True)
+
+        show_status = data.get('show_status')
+        # 1 = live, 2 = offline
+        if show_status == '2':
+            raise ExtractorError(
+                'Live stream is offline', expected=True)
+
+        base_url = data['rtmp_url']
+        live_path = data['rtmp_live']
+
+        title = self._live_title(unescapeHTML(data['room_name']))
+        description = data.get('show_details')
+        thumbnail = data.get('room_src')
+
+        uploader = data.get('nickname')
+        uploader_id = data.get('owner_uid')
+
+        multi_formats = data.get('rtmp_multi_bitrate')
+        if not isinstance(multi_formats, dict):
+            multi_formats = {}
+        multi_formats['live'] = live_path
+
+        formats = [{
+            'url': '%s/%s' % (base_url, format_path),
+            'format_id': format_id,
+            'preference': 1 if format_id == 'live' else 0,
+        } for format_id, format_path in multi_formats.items()]
+        self._sort_formats(formats)
+
+        return {
+            'id': room_id,
+            'display_id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'formats': formats,
+            'is_live': True,
+        }

youtube_dl/extractor/dramafever.py

@@ -0,0 +1,216 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import itertools
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_HTTPError,
+    compat_urllib_parse,
+    compat_urllib_request,
+    compat_urlparse,
+)
+from ..utils import (
+    ExtractorError,
+    clean_html,
+    determine_ext,
+    int_or_none,
+    parse_iso8601,
+)
+
+
+class DramaFeverBaseIE(InfoExtractor):
+    _LOGIN_URL = 'https://www.dramafever.com/accounts/login/'
+    _NETRC_MACHINE = 'dramafever'
+
+    _CONSUMER_SECRET = 'DA59dtVXYLxajktV'
+
+    _consumer_secret = None
+
+    def _get_consumer_secret(self):
+        mainjs = self._download_webpage(
+            'http://www.dramafever.com/static/51afe95/df2014/scripts/main.js',
+            None, 'Downloading main.js', fatal=False)
+        if not mainjs:
+            return self._CONSUMER_SECRET
+        return self._search_regex(
+            r"var\s+cs\s*=\s*'([^']+)'", mainjs,
+            'consumer secret', default=self._CONSUMER_SECRET)
+
+    def _real_initialize(self):
+        self._login()
+        self._consumer_secret = self._get_consumer_secret()
+
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            return
+
+        login_form = {
+            'username': username,
+            'password': password,
+        }
+
+        request = compat_urllib_request.Request(
+            self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
+        response = self._download_webpage(
+            request, None, 'Logging in as %s' % username)
+
+        if all(logout_pattern not in response
+               for logout_pattern in ['href="/accounts/logout/"', '>Log out<']):
+            error = self._html_search_regex(
+                r'(?s)class="hidden-xs prompt"[^>]*>(.+?)<',
+                response, 'error message', default=None)
+            if error:
+                raise ExtractorError('Unable to login: %s' % error, expected=True)
+            raise ExtractorError('Unable to log in')
+
+
+class DramaFeverIE(DramaFeverBaseIE):
+    IE_NAME = 'dramafever'
+    _VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+/[0-9]+)(?:/|$)'
+    _TEST = {
+        'url': 'http://www.dramafever.com/drama/4512/1/Cooking_with_Shin/',
+        'info_dict': {
+            'id': '4512.1',
+            'ext': 'flv',
+            'title': 'Cooking with Shin 4512.1',
+            'description': 'md5:a8eec7942e1664a6896fcd5e1287bfd0',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'timestamp': 1404336058,
+            'upload_date': '20140702',
+            'duration': 343,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url).replace('/', '.')
+
+        try:
+            feed = self._download_json(
+                'http://www.dramafever.com/amp/episode/feed.json?guid=%s' % video_id,
+                video_id, 'Downloading episode JSON')['channel']['item']
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError):
+                raise ExtractorError(
+                    'Currently unavailable in your country.', expected=True)
+            raise
+
+        media_group = feed.get('media-group', {})
+
+        formats = []
+        for media_content in media_group['media-content']:
+            src = media_content.get('@attributes', {}).get('url')
+            if not src:
+                continue
+            ext = determine_ext(src)
+            if ext == 'f4m':
+                formats.extend(self._extract_f4m_formats(
+                    src, video_id, f4m_id='hds'))
+            elif ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    src, video_id, 'mp4', m3u8_id='hls'))
+            else:
+                formats.append({
+                    'url': src,
+                })
+        self._sort_formats(formats)
+
+        title = media_group.get('media-title')
+        description = media_group.get('media-description')
+        duration = int_or_none(media_group['media-content'][0].get('@attributes', {}).get('duration'))
+        thumbnail = self._proto_relative_url(
+            media_group.get('media-thumbnail', {}).get('@attributes', {}).get('url'))
+        timestamp = parse_iso8601(feed.get('pubDate'), ' ')
+
+        subtitles = {}
+        for media_subtitle in media_group.get('media-subTitle', []):
+            lang = media_subtitle.get('@attributes', {}).get('lang')
+            href = media_subtitle.get('@attributes', {}).get('href')
+            if not lang or not href:
+                continue
+            subtitles[lang] = [{
+                'ext': 'ttml',
+                'url': href,
+            }]
+
+        series_id, episode_number = video_id.split('.')
+        episode_info = self._download_json(
+            # We only need a single episode info, so restricting page size to one episode
+            # and dealing with page number as with episode number
+            r'http://www.dramafever.com/api/4/episode/series/?cs=%s&series_id=%s&page_number=%s&page_size=1'
+            % (self._consumer_secret, series_id, episode_number),
+            video_id, 'Downloading episode info JSON', fatal=False)
+        if episode_info:
+            value = episode_info.get('value')
+            if value:
+                subfile = value[0].get('subfile') or value[0].get('new_subfile')
+                if subfile and subfile != 'http://www.dramafever.com/st/':
+                    subtitles.setdefault('English', []).append({
+                        'ext': 'srt',
+                        'url': subfile,
+                    })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+            'duration': duration,
+            'formats': formats,
+            'subtitles': subtitles,
+        }
+
+
+class DramaFeverSeriesIE(DramaFeverBaseIE):
+    IE_NAME = 'dramafever:series'
+    _VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+)(?:/(?:(?!\d+(?:/|$)).+)?)?$'
+    _TESTS = [{
+        'url': 'http://www.dramafever.com/drama/4512/Cooking_with_Shin/',
+        'info_dict': {
+            'id': '4512',
+            'title': 'Cooking with Shin',
+            'description': 'md5:84a3f26e3cdc3fb7f500211b3593b5c1',
+        },
+        'playlist_count': 4,
+    }, {
+        'url': 'http://www.dramafever.com/drama/124/IRIS/',
+        'info_dict': {
+            'id': '124',
+            'title': 'IRIS',
+            'description': 'md5:b3a30e587cf20c59bd1c01ec0ee1b862',
+        },
+        'playlist_count': 20,
+    }]
+
+    _PAGE_SIZE = 60  # max is 60 (see http://api.drama9.com/#get--api-4-episode-series-)
+
+    def _real_extract(self, url):
+        series_id = self._match_id(url)
+
+        series = self._download_json(
+            'http://www.dramafever.com/api/4/series/query/?cs=%s&series_id=%s'
+            % (self._consumer_secret, series_id),
+            series_id, 'Downloading series JSON')['series'][series_id]
+
+        title = clean_html(series['name'])
+        description = clean_html(series.get('description') or series.get('description_short'))
+
+        entries = []
+        for page_num in itertools.count(1):
+            episodes = self._download_json(
+                'http://www.dramafever.com/api/4/episode/series/?cs=%s&series_id=%s&page_size=%d&page_number=%d'
+                % (self._consumer_secret, series_id, self._PAGE_SIZE, page_num),
+                series_id, 'Downloading episodes JSON page #%d' % page_num)
+            for episode in episodes.get('value', []):
+                episode_url = episode.get('episode_url')
+                if not episode_url:
+                    continue
+                entries.append(self.url_result(
+                    compat_urlparse.urljoin(url, episode_url),
+                    'DramaFever', episode.get('guid')))
+            if page_num == episodes['num_pages']:
+                break
+
+        return self.playlist_result(entries, series_id, title, description)

youtube_dl/extractor/drbonanza.py

@@ -15,7 +15,6 @@ class DRBonanzaIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.dr.dk/bonanza/serie/portraetter/Talkshowet.htm?assetId=65517',
-        'md5': 'fe330252ddea607635cf2eb2c99a0af3',
         'info_dict': {
             'id': '65517',
             'ext': 'mp4',
@@ -26,6 +25,9 @@ class DRBonanzaIE(InfoExtractor):
             'upload_date': '20110120',
             'duration': 3664,
         },
+        'params': {
+            'skip_download': True,  # requires rtmp
+        },
     }, {
         'url': 'http://www.dr.dk/bonanza/radio/serie/sport/fodbold.htm?assetId=59410',
         'md5': '6dfe039417e76795fb783c52da3de11d',
@@ -93,6 +95,11 @@ class DRBonanzaIE(InfoExtractor):
                         'format_id': file['Type'].replace('Video', ''),
                         'preference': preferencemap.get(file['Type'], -10),
                     })
+                    if format['url'].startswith('rtmp'):
+                        rtmp_url = format['url']
+                        format['rtmp_live'] = True  # --resume does not work
+                        if '/bonanza/' in rtmp_url:
+                            format['play_path'] = rtmp_url.split('/bonanza/')[1]
                     formats.append(format)
                 elif file['Type'] == "Thumb":
                     thumbnail = file['Location']
@@ -111,9 +118,6 @@ class DRBonanzaIE(InfoExtractor):
         description = '%s\n%s\n%s\n' % (
             info['Description'], info['Actors'], info['Colophon'])
 
-        for f in formats:
-            f['url'] = f['url'].replace('rtmp://vod-bonanza.gss.dr.dk/bonanza/', 'http://vodfiles.dr.dk/')
-            f['url'] = f['url'].replace('mp4:bonanza', 'bonanza')
         self._sort_formats(formats)
 
         display_id = re.sub(r'[^\w\d-]', '', re.sub(r' ', '-', title.lower())) + '-' + asset_id

youtube_dl/extractor/dreisat.py

@@ -3,24 +3,33 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import unified_strdate
+from ..utils import (
+    ExtractorError,
+    unified_strdate,
+)
 
 
 class DreiSatIE(InfoExtractor):
     IE_NAME = '3sat'
-    _VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/(?:index\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
-    _TEST = {
-        'url': 'http://www.3sat.de/mediathek/index.php?obj=36983',
-        'md5': '9dcfe344732808dbfcc901537973c922',
-        'info_dict': {
-            'id': '36983',
-            'ext': 'mp4',
-            'title': 'Kaffeeland Schweiz',
-            'description': 'md5:cc4424b18b75ae9948b13929a0814033',
-            'uploader': '3sat',
-            'upload_date': '20130622'
-        }
-    }
+    _VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/(?:index\.php|mediathek\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
+    _TESTS = [
+        {
+            'url': 'http://www.3sat.de/mediathek/index.php?mode=play&obj=45918',
+            'md5': 'be37228896d30a88f315b638900a026e',
+            'info_dict': {
+                'id': '45918',
+                'ext': 'mp4',
+                'title': 'Waidmannsheil',
+                'description': 'md5:cce00ca1d70e21425e72c86a98a56817',
+                'uploader': '3sat',
+                'upload_date': '20140913'
+            }
+        },
+        {
+            'url': 'http://www.3sat.de/mediathek/mediathek.php?mode=play&obj=51066',
+            'only_matching': True,
+        },
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -28,6 +37,15 @@ class DreiSatIE(InfoExtractor):
         details_url = 'http://www.3sat.de/mediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
         details_doc = self._download_xml(details_url, video_id, 'Downloading video details')
 
+        status_code = details_doc.find('./status/statuscode')
+        if status_code is not None and status_code.text != 'ok':
+            code = status_code.text
+            if code == 'notVisibleAnymore':
+                message = 'Video %s is not available' % video_id
+            else:
+                message = '%s returned error: %s' % (self.IE_NAME, code)
+            raise ExtractorError(message, expected=True)
+
         thumbnail_els = details_doc.findall('.//teaserimage')
         thumbnails = [{
             'width': int(te.attrib['key'].partition('x')[0]),

youtube_dl/extractor/drtuber.py

@@ -36,25 +36,24 @@ class DrTuberIE(InfoExtractor):
             r'<source src="([^"]+)"', webpage, 'video URL')
 
         title = self._html_search_regex(
-            [r'class="hd_title" style="[^"]+">([^<]+)</h1>', r'<title>([^<]+) - \d+'],
+            [r'<p[^>]+class="title_substrate">([^<]+)</p>', r'<title>([^<]+) - \d+'],
             webpage, 'title')
 
         thumbnail = self._html_search_regex(
             r'poster="([^"]+)"',
             webpage, 'thumbnail', fatal=False)
 
-        like_count = str_to_int(self._html_search_regex(
-            r'<span id="rate_likes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
-            webpage, 'like count', fatal=False))
-        dislike_count = str_to_int(self._html_search_regex(
-            r'<span id="rate_dislikes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
-            webpage, 'like count', fatal=False))
-        comment_count = str_to_int(self._html_search_regex(
-            r'<span class="comments_count">([\d,\.]+)</span>',
-            webpage, 'comment count', fatal=False))
+        def extract_count(id_, name):
+            return str_to_int(self._html_search_regex(
+                r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_,
+                webpage, '%s count' % name, fatal=False))
+
+        like_count = extract_count('rate_likes', 'like')
+        dislike_count = extract_count('rate_dislikes', 'dislike')
+        comment_count = extract_count('comments_count', 'comment')
 
         cats_str = self._search_regex(
-            r'<span>Categories:</span><div>(.+?)</div>', webpage, 'categories', fatal=False)
+            r'<div[^>]+class="categories_list">(.+?)</div>', webpage, 'categories', fatal=False)
         categories = [] if not cats_str else re.findall(r'<a title="([^"]+)"', cats_str)
 
         return {

youtube_dl/extractor/drtv.py

@@ -1,23 +1,27 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
-from .common import InfoExtractor, ExtractorError
-from ..utils import parse_iso8601
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    parse_iso8601,
+)
 
 
 class DRTVIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
 
     _TEST = {
-        'url': 'http://www.dr.dk/tv/se/partiets-mand/partiets-mand-7-8',
-        'md5': '4a7e1dd65cdb2643500a3f753c942f25',
+        'url': 'https://www.dr.dk/tv/se/boern/ultra/panisk-paske/panisk-paske-5',
+        'md5': 'dc515a9ab50577fa14cc4e4b0265168f',
         'info_dict': {
-            'id': 'partiets-mand-7-8',
+            'id': 'panisk-paske-5',
             'ext': 'mp4',
-            'title': 'Partiets mand (7:8)',
-            'description': 'md5:a684b90a8f9336cd4aab94b7647d7862',
-            'timestamp': 1403047940,
-            'upload_date': '20140617',
-            'duration': 1299.040,
+            'title': 'Panisk Påske (5)',
+            'description': 'md5:ca14173c5ab24cd26b0fcc074dff391c',
+            'timestamp': 1426984612,
+            'upload_date': '20150322',
+            'duration': 1455,
         },
     }
 
@@ -26,6 +30,10 @@ class DRTVIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
+        if '>Programmet er ikke længere tilgængeligt' in webpage:
+            raise ExtractorError(
+                'Video %s is not available' % video_id, expected=True)
+
         video_id = self._search_regex(
             r'data-(?:material-identifier|episode-slug)="([^"]+)"',
             webpage, 'video id')
@@ -55,19 +63,31 @@ class DRTVIE(InfoExtractor):
                 restricted_to_denmark = asset['RestrictedToDenmark']
                 spoken_subtitles = asset['Target'] == 'SpokenSubtitles'
                 for link in asset['Links']:
-                    target = link['Target']
                     uri = link['Uri']
+                    target = link['Target']
                     format_id = target
-                    preference = -1 if target == 'HDS' else -2
+                    preference = None
                     if spoken_subtitles:
-                        preference -= 2
+                        preference = -1
                         format_id += '-spoken-subtitles'
-                    formats.append({
-                        'url': uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43' if target == 'HDS' else uri,
-                        'format_id': format_id,
-                        'ext': link['FileFormat'],
-                        'preference': preference,
-                    })
+                    if target == 'HDS':
+                        formats.extend(self._extract_f4m_formats(
+                            uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43',
+                            video_id, preference, f4m_id=format_id))
+                    elif target == 'HLS':
+                        formats.extend(self._extract_m3u8_formats(
+                            uri, video_id, 'mp4', preference=preference,
+                            m3u8_id=format_id))
+                    else:
+                        bitrate = link.get('Bitrate')
+                        if bitrate:
+                            format_id += '-%s' % bitrate
+                        formats.append({
+                            'url': uri,
+                            'format_id': format_id,
+                            'tbr': bitrate,
+                            'ext': link.get('FileFormat'),
+                        })
                 subtitles_list = asset.get('SubtitlesList')
                 if isinstance(subtitles_list, list):
                     LANGS = {

youtube_dl/extractor/dump.py

@@ -28,12 +28,12 @@ class DumpIE(InfoExtractor):
         video_url = self._search_regex(
             r's1.addVariable\("file",\s*"([^"]+)"', webpage, 'video URL')
 
-        thumb = self._og_search_thumbnail(webpage)
-        title = self._search_regex(r'<b>([^"]+)</b>', webpage, 'title')
+        title = self._og_search_title(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
 
         return {
             'id': video_id,
             'title': title,
             'url': video_url,
-            'thumbnail': thumb,
+            'thumbnail': thumbnail,
         }

youtube_dl/extractor/dumpert.py

@@ -0,0 +1,60 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import base64
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_request
+from ..utils import qualities
+
+
+class DumpertIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?dumpert\.nl/mediabase/(?P<id>[0-9]+/[0-9a-zA-Z]+)'
+    _TEST = {
+        'url': 'http://www.dumpert.nl/mediabase/6646981/951bc60f/',
+        'md5': '1b9318d7d5054e7dcb9dc7654f21d643',
+        'info_dict': {
+            'id': '6646981/951bc60f',
+            'ext': 'mp4',
+            'title': 'Ik heb nieuws voor je',
+            'description': 'Niet schrikken hoor',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        req = compat_urllib_request.Request(url)
+        req.add_header('Cookie', 'nsfw=1; cpc=10')
+        webpage = self._download_webpage(req, video_id)
+
+        files_base64 = self._search_regex(
+            r'data-files="([^"]+)"', webpage, 'data files')
+
+        files = self._parse_json(
+            base64.b64decode(files_base64.encode('utf-8')).decode('utf-8'),
+            video_id)
+
+        quality = qualities(['flv', 'mobile', 'tablet', '720p'])
+
+        formats = [{
+            'url': video_url,
+            'format_id': format_id,
+            'quality': quality(format_id),
+        } for format_id, video_url in files.items() if format_id != 'still']
+        self._sort_formats(formats)
+
+        title = self._html_search_meta(
+            'title', webpage) or self._og_search_title(webpage)
+        description = self._html_search_meta(
+            'description', webpage) or self._og_search_description(webpage)
+        thumbnail = files.get('still') or self._og_search_thumbnail(webpage)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'formats': formats
+        }

youtube_dl/extractor/eagleplatform.py

@@ -0,0 +1,99 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+)
+
+
+class EaglePlatformIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                    (?:
+                        eagleplatform:(?P<custom_host>[^/]+):|
+                        https?://(?P<host>.+?\.media\.eagleplatform\.com)/index/player\?.*\brecord_id=
+                    )
+                    (?P<id>\d+)
+                '''
+    _TESTS = [{
+        # http://lenta.ru/news/2015/03/06/navalny/
+        'url': 'http://lentaru.media.eagleplatform.com/index/player?player=new&record_id=227304&player_template_id=5201',
+        'md5': '0b7994faa2bd5c0f69a3db6db28d078d',
+        'info_dict': {
+            'id': '227304',
+            'ext': 'mp4',
+            'title': 'Навальный вышел на свободу',
+            'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 87,
+            'view_count': int,
+            'age_limit': 0,
+        },
+    }, {
+        # http://muz-tv.ru/play/7129/
+        # http://media.clipyou.ru/index/player?record_id=12820&width=730&height=415&autoplay=true
+        'url': 'eagleplatform:media.clipyou.ru:12820',
+        'md5': '6c2ebeab03b739597ce8d86339d5a905',
+        'info_dict': {
+            'id': '12820',
+            'ext': 'mp4',
+            'title': "'O Sole Mio",
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 216,
+            'view_count': int,
+        },
+        'skip': 'Georestricted',
+    }]
+
+    def _handle_error(self, response):
+        status = int_or_none(response.get('status', 200))
+        if status != 200:
+            raise ExtractorError(' '.join(response['errors']), expected=True)
+
+    def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata'):
+        response = super(EaglePlatformIE, self)._download_json(url_or_request, video_id, note)
+        self._handle_error(response)
+        return response
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        host, video_id = mobj.group('custom_host') or mobj.group('host'), mobj.group('id')
+
+        player_data = self._download_json(
+            'http://%s/api/player_data?id=%s' % (host, video_id), video_id)
+
+        media = player_data['data']['playlist']['viewports'][0]['medialist'][0]
+
+        title = media['title']
+        description = media.get('description')
+        thumbnail = media.get('snapshot')
+        duration = int_or_none(media.get('duration'))
+        view_count = int_or_none(media.get('views'))
+
+        age_restriction = media.get('age_restriction')
+        age_limit = None
+        if age_restriction:
+            age_limit = 0 if age_restriction == 'allow_all' else 18
+
+        m3u8_data = self._download_json(
+            media['sources']['secure_m3u8']['auto'],
+            video_id, 'Downloading m3u8 JSON')
+
+        formats = self._extract_m3u8_formats(
+            m3u8_data['data'][0], video_id,
+            'mp4', entry_protocol='m3u8_native')
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'view_count': view_count,
+            'age_limit': age_limit,
+            'formats': formats,
+        }

youtube_dl/extractor/ehow.py

@@ -1,9 +1,7 @@
 from __future__ import unicode_literals
 
-from ..compat import (
-    compat_urllib_parse,
-)
 from .common import InfoExtractor
+from ..compat import compat_urllib_parse_unquote
 
 
 class EHowIE(InfoExtractor):
@@ -26,7 +24,7 @@ class EHowIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
         video_url = self._search_regex(
             r'(?:file|source)=(http[^\'"&]*)', webpage, 'video URL')
-        final_url = compat_urllib_parse.unquote(video_url)
+        final_url = compat_urllib_parse_unquote(video_url)
         uploader = self._html_search_meta('uploader', webpage)
         title = self._og_search_title(webpage).replace(' | eHow', '')