release 2014.02.22

We are at the point that testing takes waay too long for a release cycle, and fails way too often.
Tests through travis are a better indicator than testing just before release.

README.md

@@ -14,198 +14,239 @@ your Unix box, on Windows or on Mac OS X. It is released to the public domain,
 which means you can modify it, redistribute it or use it however you like.
 
 # OPTIONS
-    -h, --help                 print this help text and exit
-    --version                  print program version and exit
-    -U, --update               update this program to latest version. Make sure
-                               that you have sufficient permissions (run with
-                               sudo if needed)
-    -i, --ignore-errors        continue on download errors, for example to to
-                               skip unavailable videos in a playlist
-    --abort-on-error           Abort downloading of further videos (in the
-                               playlist or the command line) if an error occurs
-    --dump-user-agent          display the current browser identification
-    --user-agent UA            specify a custom user agent
-    --referer REF              specify a custom referer, use if the video access
-                               is restricted to one domain
-    --list-extractors          List all supported extractors and the URLs they
-                               would handle
-    --extractor-descriptions   Output descriptions of all supported extractors
-    --proxy URL                Use the specified HTTP/HTTPS proxy. Pass in an
-                               empty string (--proxy "") for direct connection
-    --no-check-certificate     Suppress HTTPS certificate validation.
-    --cache-dir DIR            Location in the filesystem where youtube-dl can
-                               store some downloaded information permanently. By
-                               default $XDG_CACHE_HOME/youtube-dl or ~/.cache
-                               /youtube-dl . At the moment, only YouTube player
-                               files (for videos with obfuscated signatures) are
-                               cached, but that may change.
-    --no-cache-dir             Disable filesystem caching
-    --socket-timeout None      Time to wait before giving up, in seconds
-    --bidi-workaround          Work around terminals that lack bidirectional
-                               text support. Requires bidiv or fribidi
-                               executable in PATH
+    -h, --help                       print this help text and exit
+    --version                        print program version and exit
+    -U, --update                     update this program to latest version. Make
+                                     sure that you have sufficient permissions
+                                     (run with sudo if needed)
+    -i, --ignore-errors              continue on download errors, for example to
+                                     skip unavailable videos in a playlist
+    --abort-on-error                 Abort downloading of further videos (in the
+                                     playlist or the command line) if an error
+                                     occurs
+    --dump-user-agent                display the current browser identification
+    --user-agent UA                  specify a custom user agent
+    --referer REF                    specify a custom referer, use if the video
+                                     access is restricted to one domain
+    --list-extractors                List all supported extractors and the URLs
+                                     they would handle
+    --extractor-descriptions         Output descriptions of all supported
+                                     extractors
+    --proxy URL                      Use the specified HTTP/HTTPS proxy. Pass in
+                                     an empty string (--proxy "") for direct
+                                     connection
+    --no-check-certificate           Suppress HTTPS certificate validation.
+    --cache-dir DIR                  Location in the filesystem where youtube-dl
+                                     can store some downloaded information
+                                     permanently. By default $XDG_CACHE_HOME
+                                     /youtube-dl or ~/.cache/youtube-dl . At the
+                                     moment, only YouTube player files (for
+                                     videos with obfuscated signatures) are
+                                     cached, but that may change.
+    --no-cache-dir                   Disable filesystem caching
+    --socket-timeout None            Time to wait before giving up, in seconds
+    --bidi-workaround                Work around terminals that lack
+                                     bidirectional text support. Requires bidiv
+                                     or fribidi executable in PATH
+    --default-search PREFIX          Use this prefix for unqualified URLs. For
+                                     example "gvsearch2:" downloads two videos
+                                     from google videos for  youtube-dl "large
+                                     apple". By default (with value "auto")
+                                     youtube-dl guesses.
+    --ignore-config                  Do not read configuration files. When given
+                                     in the global configuration file /etc
+                                     /youtube-dl.conf: do not read the user
+                                     configuration in ~/.config/youtube-dl.conf
+                                     (%APPDATA%/youtube-dl/config.txt on
+                                     Windows)
 
 ## Video Selection:
-    --playlist-start NUMBER    playlist video to start at (default is 1)
-    --playlist-end NUMBER      playlist video to end at (default is last)
-    --match-title REGEX        download only matching titles (regex or caseless
-                               sub-string)
-    --reject-title REGEX       skip download for matching titles (regex or
-                               caseless sub-string)
-    --max-downloads NUMBER     Abort after downloading NUMBER files
-    --min-filesize SIZE        Do not download any videos smaller than SIZE
-                               (e.g. 50k or 44.6m)
-    --max-filesize SIZE        Do not download any videos larger than SIZE (e.g.
-                               50k or 44.6m)
-    --date DATE                download only videos uploaded in this date
-    --datebefore DATE          download only videos uploaded on or before this
-                               date (i.e. inclusive)
-    --dateafter DATE           download only videos uploaded on or after this
-                               date (i.e. inclusive)
-    --min-views COUNT          Do not download any videos with less than COUNT
-                               views
-    --max-views COUNT          Do not download any videos with more than COUNT
-                               views
-    --no-playlist              download only the currently playing video
-    --age-limit YEARS          download only videos suitable for the given age
-    --download-archive FILE    Download only videos not listed in the archive
-                               file. Record the IDs of all downloaded videos in
-                               it.
-    --include-ads              Download advertisements as well (experimental)
+    --playlist-start NUMBER          playlist video to start at (default is 1)
+    --playlist-end NUMBER            playlist video to end at (default is last)
+    --match-title REGEX              download only matching titles (regex or
+                                     caseless sub-string)
+    --reject-title REGEX             skip download for matching titles (regex or
+                                     caseless sub-string)
+    --max-downloads NUMBER           Abort after downloading NUMBER files
+    --min-filesize SIZE              Do not download any videos smaller than
+                                     SIZE (e.g. 50k or 44.6m)
+    --max-filesize SIZE              Do not download any videos larger than SIZE
+                                     (e.g. 50k or 44.6m)
+    --date DATE                      download only videos uploaded in this date
+    --datebefore DATE                download only videos uploaded on or before
+                                     this date (i.e. inclusive)
+    --dateafter DATE                 download only videos uploaded on or after
+                                     this date (i.e. inclusive)
+    --min-views COUNT                Do not download any videos with less than
+                                     COUNT views
+    --max-views COUNT                Do not download any videos with more than
+                                     COUNT views
+    --no-playlist                    download only the currently playing video
+    --age-limit YEARS                download only videos suitable for the given
+                                     age
+    --download-archive FILE          Download only videos not listed in the
+                                     archive file. Record the IDs of all
+                                     downloaded videos in it.
+    --include-ads                    Download advertisements as well
+                                     (experimental)
+    --youtube-include-dash-manifest  Try to download the DASH manifest on
+                                     YouTube videos (experimental)
 
 ## Download Options:
-    -r, --rate-limit LIMIT     maximum download rate in bytes per second (e.g.
-                               50K or 4.2M)
-    -R, --retries RETRIES      number of retries (default is 10)
-    --buffer-size SIZE         size of download buffer (e.g. 1024 or 16K)
-                               (default is 1024)
-    --no-resize-buffer         do not automatically adjust the buffer size. By
-                               default, the buffer size is automatically resized
-                               from an initial value of SIZE.
+    -r, --rate-limit LIMIT           maximum download rate in bytes per second
+                                     (e.g. 50K or 4.2M)
+    -R, --retries RETRIES            number of retries (default is 10)
+    --buffer-size SIZE               size of download buffer (e.g. 1024 or 16K)
+                                     (default is 1024)
+    --no-resize-buffer               do not automatically adjust the buffer
+                                     size. By default, the buffer size is
+                                     automatically resized from an initial value
+                                     of SIZE.
 
 ## Filesystem Options:
-    -t, --title                use title in file name (default)
-    --id                       use only video ID in file name
-    -l, --literal              [deprecated] alias of --title
-    -A, --auto-number          number downloaded files starting from 00000
-    -o, --output TEMPLATE      output filename template. Use %(title)s to get
-                               the title, %(uploader)s for the uploader name,
-                               %(uploader_id)s for the uploader nickname if
-                               different, %(autonumber)s to get an automatically
-                               incremented number, %(ext)s for the filename
-                               extension, %(format)s for the format description
-                               (like "22 - 1280x720" or "HD"), %(format_id)s for
-                               the unique id of the format (like Youtube's
-                               itags: "137"), %(upload_date)s for the upload
-                               date (YYYYMMDD), %(extractor)s for the provider
-                               (youtube, metacafe, etc), %(id)s for the video
-                               id, %(playlist)s for the playlist the video is
-                               in, %(playlist_index)s for the position in the
-                               playlist and %% for a literal percent. Use - to
-                               output to stdout. Can also be used to download to
-                               a different directory, for example with -o '/my/d
-                               ownloads/%(uploader)s/%(title)s-%(id)s.%(ext)s' .
-    --autonumber-size NUMBER   Specifies the number of digits in %(autonumber)s
-                               when it is present in output filename template or
-                               --auto-number option is given
-    --restrict-filenames       Restrict filenames to only ASCII characters, and
-                               avoid "&" and spaces in filenames
-    -a, --batch-file FILE      file containing URLs to download ('-' for stdin)
-    --load-info FILE           json file containing the video information
-                               (created with the "--write-json" option)
-    -w, --no-overwrites        do not overwrite files
-    -c, --continue             force resume of partially downloaded files. By
-                               default, youtube-dl will resume downloads if
-                               possible.
-    --no-continue              do not resume partially downloaded files (restart
-                               from beginning)
-    --cookies FILE             file to read cookies from and dump cookie jar in
-    --no-part                  do not use .part files
-    --no-mtime                 do not use the Last-modified header to set the
-                               file modification time
-    --write-description        write video description to a .description file
-    --write-info-json          write video metadata to a .info.json file
-    --write-annotations        write video annotations to a .annotation file
-    --write-thumbnail          write thumbnail image to disk
+    -t, --title                      use title in file name (default)
+    --id                             use only video ID in file name
+    -l, --literal                    [deprecated] alias of --title
+    -A, --auto-number                number downloaded files starting from 00000
+    -o, --output TEMPLATE            output filename template. Use %(title)s to
+                                     get the title, %(uploader)s for the
+                                     uploader name, %(uploader_id)s for the
+                                     uploader nickname if different,
+                                     %(autonumber)s to get an automatically
+                                     incremented number, %(ext)s for the
+                                     filename extension, %(format)s for the
+                                     format description (like "22 - 1280x720" or
+                                     "HD"), %(format_id)s for the unique id of
+                                     the format (like Youtube's itags: "137"),
+                                     %(upload_date)s for the upload date
+                                     (YYYYMMDD), %(extractor)s for the provider
+                                     (youtube, metacafe, etc), %(id)s for the
+                                     video id, %(playlist)s for the playlist the
+                                     video is in, %(playlist_index)s for the
+                                     position in the playlist and %% for a
+                                     literal percent. Use - to output to stdout.
+                                     Can also be used to download to a different
+                                     directory, for example with -o '/my/downloa
+                                     ds/%(uploader)s/%(title)s-%(id)s.%(ext)s' .
+    --autonumber-size NUMBER         Specifies the number of digits in
+                                     %(autonumber)s when it is present in output
+                                     filename template or --auto-number option
+                                     is given
+    --restrict-filenames             Restrict filenames to only ASCII
+                                     characters, and avoid "&" and spaces in
+                                     filenames
+    -a, --batch-file FILE            file containing URLs to download ('-' for
+                                     stdin)
+    --load-info FILE                 json file containing the video information
+                                     (created with the "--write-json" option)
+    -w, --no-overwrites              do not overwrite files
+    -c, --continue                   force resume of partially downloaded files.
+                                     By default, youtube-dl will resume
+                                     downloads if possible.
+    --no-continue                    do not resume partially downloaded files
+                                     (restart from beginning)
+    --cookies FILE                   file to read cookies from and dump cookie
+                                     jar in
+    --no-part                        do not use .part files
+    --no-mtime                       do not use the Last-modified header to set
+                                     the file modification time
+    --write-description              write video description to a .description
+                                     file
+    --write-info-json                write video metadata to a .info.json file
+    --write-annotations              write video annotations to a .annotation
+                                     file
+    --write-thumbnail                write thumbnail image to disk
 
 ## Verbosity / Simulation Options:
-    -q, --quiet                activates quiet mode
-    -s, --simulate             do not download the video and do not write
-                               anything to disk
-    --skip-download            do not download the video
-    -g, --get-url              simulate, quiet but print URL
-    -e, --get-title            simulate, quiet but print title
-    --get-id                   simulate, quiet but print id
-    --get-thumbnail            simulate, quiet but print thumbnail URL
-    --get-description          simulate, quiet but print video description
-    --get-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
-    --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
+    -q, --quiet                      activates quiet mode
+    -s, --simulate                   do not download the video and do not write
+                                     anything to disk
+    --skip-download                  do not download the video
+    -g, --get-url                    simulate, quiet but print URL
+    -e, --get-title                  simulate, quiet but print title
+    --get-id                         simulate, quiet but print id
+    --get-thumbnail                  simulate, quiet but print thumbnail URL
+    --get-description                simulate, quiet but print video description
+    --get-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
+    --newline                        output progress bar as new lines
+    --no-progress                    do not print progress bar
+    --console-title                  display progress in console titlebar
+    -v, --verbose                    print various debugging information
+    --dump-intermediate-pages        print downloaded pages to debug problems
+                                     (very verbose)
+    --write-pages                    Write downloaded intermediary pages to
+                                     files in the current directory to debug
+                                     problems
+    --print-traffic                  Display sent and read HTTP traffic
 
 ## Video Format Options:
-    -f, --format FORMAT        video format code, specify the order of
-                               preference using slashes: "-f 22/17/18". "-f mp4"
-                               and "-f flv" are also supported
-    --all-formats              download all available video formats
-    --prefer-free-formats      prefer free video formats unless a specific one
-                               is requested
-    --max-quality FORMAT       highest quality format to download
-    -F, --list-formats         list all available formats
+    -f, --format FORMAT              video format code, specify the order of
+                                     preference using slashes: "-f 22/17/18".
+                                     "-f mp4" and "-f flv" are also supported.
+                                     You can also use the special names "best",
+                                     "bestaudio", "worst", and "worstaudio". By
+                                     default, youtube-dl will pick the best
+                                     quality.
+    --all-formats                    download all available video formats
+    --prefer-free-formats            prefer free video formats unless a specific
+                                     one is requested
+    --max-quality FORMAT             highest quality format to download
+    -F, --list-formats               list all available formats
 
 ## Subtitle Options:
-    --write-sub                write subtitle file
-    --write-auto-sub           write automatic subtitle file (youtube only)
-    --all-subs                 downloads all the available subtitles of the
-                               video
-    --list-subs                lists all available subtitles for the video
-    --sub-format FORMAT        subtitle format (default=srt) ([sbv/vtt] youtube
-                               only)
-    --sub-lang LANGS           languages of the subtitles to download (optional)
-                               separated by commas, use IETF language tags like
-                               'en,pt'
+    --write-sub                      write subtitle file
+    --write-auto-sub                 write automatic subtitle file (youtube
+                                     only)
+    --all-subs                       downloads all the available subtitles of
+                                     the video
+    --list-subs                      lists all available subtitles for the video
+    --sub-format FORMAT              subtitle format (default=srt) ([sbv/vtt]
+                                     youtube only)
+    --sub-lang LANGS                 languages of the subtitles to download
+                                     (optional) separated by commas, use IETF
+                                     language tags like 'en,pt'
 
 ## Authentication Options:
-    -u, --username USERNAME    account username
-    -p, --password PASSWORD    account password
-    -n, --netrc                use .netrc authentication data
-    --video-password PASSWORD  video password (vimeo, smotri)
+    -u, --username USERNAME          account username
+    -p, --password PASSWORD          account password
+    -n, --netrc                      use .netrc authentication data
+    --video-password PASSWORD        video password (vimeo, smotri)
 
 ## Post-processing Options:
-    -x, --extract-audio        convert video files to audio-only files (requires
-                               ffmpeg or avconv and ffprobe or avprobe)
-    --audio-format FORMAT      "best", "aac", "vorbis", "mp3", "m4a", "opus", or
-                               "wav"; best by default
-    --audio-quality QUALITY    ffmpeg/avconv audio quality specification, insert
-                               a value between 0 (better) and 9 (worse) for VBR
-                               or a specific bitrate like 128K (default 5)
-    --recode-video FORMAT      Encode the video to another format if necessary
-                               (currently supported: mp4|flv|ogg|webm)
-    -k, --keep-video           keeps the video file on disk after the post-
-                               processing; the video is erased by default
-    --no-post-overwrites       do not overwrite post-processed files; the post-
-                               processed files are overwritten by default
-    --embed-subs               embed subtitles in the video (only for mp4
-                               videos)
-    --add-metadata             write metadata to the video file
-    --xattrs                   write metadata to the video file's xattrs (using
-                               dublin core and xdg standards)
-    --prefer-avconv            Prefer avconv over ffmpeg for running the
-                               postprocessors (default)
-    --prefer-ffmpeg            Prefer ffmpeg over avconv for running the
-                               postprocessors
+    -x, --extract-audio              convert video files to audio-only files
+                                     (requires ffmpeg or avconv and ffprobe or
+                                     avprobe)
+    --audio-format FORMAT            "best", "aac", "vorbis", "mp3", "m4a",
+                                     "opus", or "wav"; best by default
+    --audio-quality QUALITY          ffmpeg/avconv audio quality specification,
+                                     insert a value between 0 (better) and 9
+                                     (worse) for VBR or a specific bitrate like
+                                     128K (default 5)
+    --recode-video FORMAT            Encode the video to another format if
+                                     necessary (currently supported:
+                                     mp4|flv|ogg|webm)
+    -k, --keep-video                 keeps the video file on disk after the
+                                     post-processing; the video is erased by
+                                     default
+    --no-post-overwrites             do not overwrite post-processed files; the
+                                     post-processed files are overwritten by
+                                     default
+    --embed-subs                     embed subtitles in the video (only for mp4
+                                     videos)
+    --add-metadata                   write metadata to the video file
+    --xattrs                         write metadata to the video file's xattrs
+                                     (using dublin core and xdg standards)
+    --prefer-avconv                  Prefer avconv over ffmpeg for running the
+                                     postprocessors (default)
+    --prefer-ffmpeg                  Prefer ffmpeg over avconv for running the
+                                     postprocessors
 
 # CONFIGURATION
 
-You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl.conf`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<Yourname>\youtube-dl.conf`.
+You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl/config`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<Yourname>\youtube-dl.conf`.
 
 # OUTPUT TEMPLATE
 
@@ -240,12 +281,14 @@ Videos can be filtered by their upload date using the options `--date`, `--dateb
  
 Examples:
 
-  $ # Download only the videos uploaded in the last 6 months
-	$ youtube-dl --dateafter now-6months
-  $ # Download only the videos uploaded on January 1, 1970
-	$ youtube-dl --date 19700101
-  $ # will only download the videos uploaded in the 200x decade
-	$ youtube-dl --dateafter 20000101 --datebefore 20091231
+    # Download only the videos uploaded in the last 6 months
+    $ youtube-dl --dateafter now-6months
+
+    # Download only the videos uploaded on January 1, 1970
+    $ youtube-dl --date 19700101
+
+    $ # will only download the videos uploaded in the 200x decade
+    $ youtube-dl --dateafter 20000101 --datebefore 20091231
 
 # FAQ
 
@@ -290,11 +333,31 @@ Since June 2012 (#342) youtube-dl is packed as an executable zipfile, simply unz
 
 To run the exe you need to install first the [Microsoft Visual C++ 2008 Redistributable Package](http://www.microsoft.com/en-us/download/details.aspx?id=29).
 
-# COPYRIGHT
+# DEVELOPER INSTRUCTIONS
 
-youtube-dl is released into the public domain by the copyright holders.
+Most users do not need to build youtube-dl and can [download the builds](http://rg3.github.io/youtube-dl/download.html) or get them from their distribution.
 
-This README file was originally written by Daniel Bolton (<https://github.com/dbbolton>) and is likewise released into the public domain.
+To run youtube-dl as a developer, you don't need to build anything either. Simply execute
+
+    python -m youtube_dl
+
+To run the test, simply invoke your favorite test runner, or execute a test file directly; any of the following work:
+
+    python -m unittest discover
+    python test/test_download.py
+    nosetests
+
+If you want to create a build of youtube-dl yourself, you'll need
+
+* python
+* make
+* pandoc
+* zip
+* nosetests
+
+### Adding support for a new site
+
+If you want to add support for a new site, copy *any* [recently modified](https://github.com/rg3/youtube-dl/commits/master/youtube_dl/extractor) file in `youtube_dl/extractor`, add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py). 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). Don't forget to run the tests with `python test/test_download.py TestDownload.test_YourExtractor`! For a detailed tutorial, refer to [this blog post](http://filippo.io/add-support-for-a-new-video-site-to-youtube-dl/).
 
 # BUGS
 
@@ -353,3 +416,9 @@ Only post features that you (or an incapicated friend you can personally talk to
 ###  Is your question about youtube-dl?
 
 It may sound strange, but some bug reports we receive are completely unrelated to youtube-dl and relate to a different or even the reporter's own application. Please make sure that you are actually using youtube-dl. If you are using a UI for youtube-dl, report the bug to the maintainer of the actual application providing the UI. On the other hand, if your UI for youtube-dl fails in some way you believe is related to youtube-dl, by all means, go ahead and report the bug.
+
+# COPYRIGHT
+
+youtube-dl is released into the public domain by the copyright holders.
+
+This README file was originally written by Daniel Bolton (<https://github.com/dbbolton>) and is likewise released into the public domain.

devscripts/release.sh

@@ -14,9 +14,9 @@
 
 set -e
 
-skip_tests=false
-if [ "$1" = '--skip-test' ]; then
-    skip_tests=true
+skip_tests=true
+if [ "$1" = '--run-tests' ]; then
+    skip_tests=false
     shift
 fi
 

setup.py

@@ -3,7 +3,9 @@
 
 from __future__ import print_function
 
+import os.path
 import pkg_resources
+import warnings
 import sys
 
 try:
@@ -44,12 +46,24 @@ py2exe_params = {
 if len(sys.argv) >= 2 and sys.argv[1] == 'py2exe':
     params = py2exe_params
 else:
+    files_spec = [
+        ('etc/bash_completion.d', ['youtube-dl.bash-completion']),
+        ('share/doc/youtube_dl', ['README.txt']),
+        ('share/man/man1', ['youtube-dl.1'])
+    ]
+    root = os.path.dirname(os.path.abspath(__file__))
+    data_files = []
+    for dirname, files in files_spec:
+        resfiles = []
+        for fn in files:
+            if not os.path.exists(fn):
+                warnings.warn('Skipping file %s since it is not present. Type  make  to build all automatically generated files.' % fn)
+            else:
+                resfiles.append(fn)
+        data_files.append((dirname, resfiles))
+
     params = {
-        'data_files': [  # Installing system-wide would require sudo...
-            ('etc/bash_completion.d', ['youtube-dl.bash-completion']),
-            ('share/doc/youtube_dl', ['README.txt']),
-            ('share/man/man1', ['youtube-dl.1'])
-        ]
+        'data_files': data_files,
     }
     if setuptools_available:
         params['entry_points'] = {'console_scripts': ['youtube-dl = youtube_dl:main']}

test/test_YoutubeDL.py

@@ -1,5 +1,7 @@
 #!/usr/bin/env python
 
+from __future__ import unicode_literals
+
 # Allow direct execution
 import os
 import sys
@@ -30,125 +32,155 @@ class TestFormatSelection(unittest.TestCase):
         ydl = YDL()
         ydl.params['prefer_free_formats'] = True
         formats = [
-            {u'ext': u'webm', u'height': 460},
-            {u'ext': u'mp4',  u'height': 460},
+            {'ext': 'webm', 'height': 460},
+            {'ext': 'mp4',  'height': 460},
         ]
-        info_dict = {u'formats': formats, u'extractor': u'test'}
+        info_dict = {'formats': formats, 'extractor': 'test'}
         yie = YoutubeIE(ydl)
         yie._sort_formats(info_dict['formats'])
         ydl.process_ie_result(info_dict)
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded[u'ext'], u'webm')
+        self.assertEqual(downloaded['ext'], 'webm')
 
         # Different resolution => download best quality (mp4)
         ydl = YDL()
         ydl.params['prefer_free_formats'] = True
         formats = [
-            {u'ext': u'webm', u'height': 720},
-            {u'ext': u'mp4', u'height': 1080},
+            {'ext': 'webm', 'height': 720},
+            {'ext': 'mp4', 'height': 1080},
         ]
-        info_dict[u'formats'] = formats
+        info_dict['formats'] = formats
         yie = YoutubeIE(ydl)
         yie._sort_formats(info_dict['formats'])
         ydl.process_ie_result(info_dict)
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded[u'ext'], u'mp4')
+        self.assertEqual(downloaded['ext'], 'mp4')
 
         # No prefer_free_formats => prefer mp4 and flv for greater compatibilty
         ydl = YDL()
         ydl.params['prefer_free_formats'] = False
         formats = [
-            {u'ext': u'webm', u'height': 720},
-            {u'ext': u'mp4', u'height': 720},
-            {u'ext': u'flv', u'height': 720},
+            {'ext': 'webm', 'height': 720},
+            {'ext': 'mp4', 'height': 720},
+            {'ext': 'flv', 'height': 720},
         ]
-        info_dict[u'formats'] = formats
+        info_dict['formats'] = formats
         yie = YoutubeIE(ydl)
         yie._sort_formats(info_dict['formats'])
         ydl.process_ie_result(info_dict)
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded[u'ext'], u'mp4')
+        self.assertEqual(downloaded['ext'], 'mp4')
 
         ydl = YDL()
         ydl.params['prefer_free_formats'] = False
         formats = [
-            {u'ext': u'flv', u'height': 720},
-            {u'ext': u'webm', u'height': 720},
+            {'ext': 'flv', 'height': 720},
+            {'ext': 'webm', 'height': 720},
         ]
-        info_dict[u'formats'] = formats
+        info_dict['formats'] = formats
         yie = YoutubeIE(ydl)
         yie._sort_formats(info_dict['formats'])
         ydl.process_ie_result(info_dict)
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded[u'ext'], u'flv')
+        self.assertEqual(downloaded['ext'], 'flv')
 
     def test_format_limit(self):
         formats = [
-            {u'format_id': u'meh', u'url': u'http://example.com/meh', 'preference': 1},
-            {u'format_id': u'good', u'url': u'http://example.com/good', 'preference': 2},
-            {u'format_id': u'great', u'url': u'http://example.com/great', 'preference': 3},
-            {u'format_id': u'excellent', u'url': u'http://example.com/exc', 'preference': 4},
+            {'format_id': 'meh', 'url': 'http://example.com/meh', 'preference': 1},
+            {'format_id': 'good', 'url': 'http://example.com/good', 'preference': 2},
+            {'format_id': 'great', 'url': 'http://example.com/great', 'preference': 3},
+            {'format_id': 'excellent', 'url': 'http://example.com/exc', 'preference': 4},
         ]
         info_dict = {
-            u'formats': formats, u'extractor': u'test', 'id': 'testvid'}
+            'formats': formats, 'extractor': 'test', 'id': 'testvid'}
 
         ydl = YDL()
         ydl.process_ie_result(info_dict)
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded[u'format_id'], u'excellent')
+        self.assertEqual(downloaded['format_id'], 'excellent')
 
         ydl = YDL({'format_limit': 'good'})
         assert ydl.params['format_limit'] == 'good'
         ydl.process_ie_result(info_dict.copy())
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded[u'format_id'], u'good')
+        self.assertEqual(downloaded['format_id'], 'good')
 
         ydl = YDL({'format_limit': 'great', 'format': 'all'})
         ydl.process_ie_result(info_dict.copy())
-        self.assertEqual(ydl.downloaded_info_dicts[0][u'format_id'], u'meh')
-        self.assertEqual(ydl.downloaded_info_dicts[1][u'format_id'], u'good')
-        self.assertEqual(ydl.downloaded_info_dicts[2][u'format_id'], u'great')
+        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[u'format_id'], u'excellent')
+        self.assertEqual(downloaded['format_id'], 'excellent')
 
     def test_format_selection(self):
         formats = [
-            {u'format_id': u'35', u'ext': u'mp4', 'preference': 1},
-            {u'format_id': u'45', u'ext': u'webm', 'preference': 2},
-            {u'format_id': u'47', u'ext': u'webm', 'preference': 3},
-            {u'format_id': u'2', u'ext': u'flv', 'preference': 4},
+            {'format_id': '35', 'ext': 'mp4', 'preference': 1},
+            {'format_id': '45', 'ext': 'webm', 'preference': 2},
+            {'format_id': '47', 'ext': 'webm', 'preference': 3},
+            {'format_id': '2', 'ext': 'flv', 'preference': 4},
         ]
-        info_dict = {u'formats': formats, u'extractor': u'test'}
+        info_dict = {'formats': formats, 'extractor': 'test'}
 
-        ydl = YDL({'format': u'20/47'})
+        ydl = YDL({'format': '20/47'})
         ydl.process_ie_result(info_dict.copy())
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], u'47')
+        self.assertEqual(downloaded['format_id'], '47')
 
-        ydl = YDL({'format': u'20/71/worst'})
+        ydl = YDL({'format': '20/71/worst'})
         ydl.process_ie_result(info_dict.copy())
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], u'35')
+        self.assertEqual(downloaded['format_id'], '35')
 
         ydl = YDL()
         ydl.process_ie_result(info_dict.copy())
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], u'2')
+        self.assertEqual(downloaded['format_id'], '2')
 
-        ydl = YDL({'format': u'webm/mp4'})
+        ydl = YDL({'format': 'webm/mp4'})
         ydl.process_ie_result(info_dict.copy())
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], u'47')
+        self.assertEqual(downloaded['format_id'], '47')
 
-        ydl = YDL({'format': u'3gp/40/mp4'})
+        ydl = YDL({'format': '3gp/40/mp4'})
         ydl.process_ie_result(info_dict.copy())
         downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], u'35')
+        self.assertEqual(downloaded['format_id'], '35')
+
+    def test_format_selection_audio(self):
+        formats = [
+            {'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none'},
+            {'format_id': 'audio-mid', 'ext': 'webm', 'preference': 2, 'vcodec': 'none'},
+            {'format_id': 'audio-high', 'ext': 'flv', 'preference': 3, 'vcodec': 'none'},
+            {'format_id': 'vid', 'ext': 'mp4', 'preference': 4},
+        ]
+        info_dict = {'formats': formats, 'extractor': 'test'}
+
+        ydl = YDL({'format': 'bestaudio'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'audio-high')
+
+        ydl = YDL({'format': 'worstaudio'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'audio-low')
+
+        formats = [
+            {'format_id': 'vid-low', 'ext': 'mp4', 'preference': 1},
+            {'format_id': 'vid-high', 'ext': 'mp4', 'preference': 2},
+        ]
+        info_dict = {'formats': formats, 'extractor': 'test'}
+
+        ydl = YDL({'format': 'bestaudio/worstaudio/best'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'vid-high')
 
     def test_youtube_format_selection(self):
         order = [
@@ -200,17 +232,17 @@ class TestFormatSelection(unittest.TestCase):
 
     def test_prepare_filename(self):
         info = {
-            u'id': u'1234',
-            u'ext': u'mp4',
-            u'width': None,
+            'id': '1234',
+            'ext': 'mp4',
+            'width': None,
         }
         def fname(templ):
             ydl = YoutubeDL({'outtmpl': templ})
             return ydl.prepare_filename(info)
-        self.assertEqual(fname(u'%(id)s.%(ext)s'), u'1234.mp4')
-        self.assertEqual(fname(u'%(id)s-%(width)s.%(ext)s'), u'1234-NA.mp4')
+        self.assertEqual(fname('%(id)s.%(ext)s'), '1234.mp4')
+        self.assertEqual(fname('%(id)s-%(width)s.%(ext)s'), '1234-NA.mp4')
         # Replace missing fields with 'NA'
-        self.assertEqual(fname(u'%(uploader_date)s-%(id)s.%(ext)s'), u'NA-1234.mp4')
+        self.assertEqual(fname('%(uploader_date)s-%(id)s.%(ext)s'), 'NA-1234.mp4')
 
 
 if __name__ == '__main__':

test/test_all_urls.py

@@ -1,5 +1,7 @@
 #!/usr/bin/env python
 
+from __future__ import unicode_literals
+
 # Allow direct execution
 import os
 import sys
@@ -13,6 +15,7 @@ from youtube_dl.extractor import (
     FacebookIE,
     gen_extractors,
     JustinTVIE,
+    PBSIE,
     YoutubeIE,
 )
 
@@ -29,18 +32,20 @@ class TestAllURLsMatching(unittest.TestCase):
 
     def test_youtube_playlist_matching(self):
         assertPlaylist = lambda url: self.assertMatch(url, ['youtube:playlist'])
-        assertPlaylist(u'ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
-        assertPlaylist(u'UUBABnxM4Ar9ten8Mdjj1j0Q') #585
-        assertPlaylist(u'PL63F0C78739B09958')
-        assertPlaylist(u'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
-        assertPlaylist(u'https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
-        assertPlaylist(u'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
-        assertPlaylist(u'https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') #668
-        self.assertFalse('youtube:playlist' in self.matching_ies(u'PLtS2H6bU1M'))
+        assertPlaylist('ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
+        assertPlaylist('UUBABnxM4Ar9ten8Mdjj1j0Q') #585
+        assertPlaylist('PL63F0C78739B09958')
+        assertPlaylist('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
+        assertPlaylist('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
+        assertPlaylist('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
+        assertPlaylist('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') #668
+        self.assertFalse('youtube:playlist' in self.matching_ies('PLtS2H6bU1M'))
+        # Top tracks
+        assertPlaylist('https://www.youtube.com/playlist?list=MCUS.20142101')
 
     def test_youtube_matching(self):
-        self.assertTrue(YoutubeIE.suitable(u'PLtS2H6bU1M'))
-        self.assertFalse(YoutubeIE.suitable(u'https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')) #668
+        self.assertTrue(YoutubeIE.suitable('PLtS2H6bU1M'))
+        self.assertFalse(YoutubeIE.suitable('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')) #668
         self.assertMatch('http://youtu.be/BaW_jenozKc', ['youtube'])
         self.assertMatch('http://www.youtube.com/v/BaW_jenozKc', ['youtube'])
         self.assertMatch('https://youtube.googleapis.com/v/BaW_jenozKc', ['youtube'])
@@ -63,6 +68,9 @@ class TestAllURLsMatching(unittest.TestCase):
     def test_youtube_show_matching(self):
         self.assertMatch('http://www.youtube.com/show/airdisasters', ['youtube:show'])
 
+    def test_youtube_truncated(self):
+        self.assertMatch('http://www.youtube.com/watch?', ['youtube:truncated_url'])
+
     def test_justin_tv_channelid_matching(self):
         self.assertTrue(JustinTVIE.suitable(u"justin.tv/vanillatv"))
         self.assertTrue(JustinTVIE.suitable(u"twitch.tv/vanillatv"))
@@ -80,7 +88,7 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/tsm_theoddone/c/2349361"))
 
     def test_youtube_extract(self):
-        assertExtractId = lambda url, id: self.assertEqual(YoutubeIE()._extract_id(url), id)
+        assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
         assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
         assertExtractId('https://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
         assertExtractId('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc', 'BaW_jenozKc')
@@ -89,7 +97,7 @@ class TestAllURLsMatching(unittest.TestCase):
         assertExtractId('BaW_jenozKc', 'BaW_jenozKc')
 
     def test_facebook_matching(self):
-        self.assertTrue(FacebookIE.suitable(u'https://www.facebook.com/Shiniknoh#!/photo.php?v=10153317450565268'))
+        self.assertTrue(FacebookIE.suitable('https://www.facebook.com/Shiniknoh#!/photo.php?v=10153317450565268'))
 
     def test_no_duplicates(self):
         ies = gen_extractors()
@@ -120,5 +128,13 @@ class TestAllURLsMatching(unittest.TestCase):
     def test_soundcloud_not_matching_sets(self):
         self.assertMatch('http://soundcloud.com/floex/sets/gone-ep', ['soundcloud:set'])
 
+    def test_tumblr(self):
+        self.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes', ['Tumblr'])
+        self.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430', ['Tumblr'])
+
+    def test_pbs(self):
+        # https://github.com/rg3/youtube-dl/issues/2350
+        self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['PBS'])
+
 if __name__ == '__main__':
     unittest.main()

test/test_download.py

@@ -18,10 +18,12 @@ from test.helper import (
 import hashlib
 import io
 import json
+import re
 import socket
 
 import youtube_dl.YoutubeDL
 from youtube_dl.utils import (
+    compat_http_client,
     compat_str,
     compat_urllib_error,
     compat_HTTPError,
@@ -110,7 +112,7 @@ def generator(test_case):
                     ydl.download([test_case['url']])
                 except (DownloadError, ExtractorError) as err:
                     # Check if the exception is not a network related one
-                    if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError) or (err.exc_info[0] == compat_HTTPError and err.exc_info[1].code == 503):
+                    if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError, compat_http_client.BadStatusLine) or (err.exc_info[0] == compat_HTTPError and err.exc_info[1].code == 503):
                         raise
 
                     if try_num == RETRIES:
@@ -136,12 +138,21 @@ def generator(test_case):
                 with io.open(info_json_fn, encoding='utf-8') as infof:
                     info_dict = json.load(infof)
                 for (info_field, expected) in tc.get('info_dict', {}).items():
-                    if isinstance(expected, compat_str) and expected.startswith('md5:'):
-                        got = 'md5:' + md5(info_dict.get(info_field))
-                    else:
+                    if isinstance(expected, compat_str) and expected.startswith('re:'):
                         got = info_dict.get(info_field)
-                    self.assertEqual(expected, got,
-                        u'invalid value for field %s, expected %r, got %r' % (info_field, expected, got))
+                        match_str = expected[len('re:'):]
+                        match_rex = re.compile(match_str)
+
+                        self.assertTrue(
+                            isinstance(got, compat_str) and match_rex.match(got),
+                            u'field %s (value: %r) should match %r' % (info_field, got, match_str))
+                    else:
+                        if isinstance(expected, compat_str) and expected.startswith('md5:'):
+                            got = 'md5:' + md5(info_dict.get(info_field))
+                        else:
+                            got = info_dict.get(info_field)
+                        self.assertEqual(expected, got,
+                            u'invalid value for field %s, expected %r, got %r' % (info_field, expected, got))
 
                 # If checkable fields are missing from the test case, print the info_dict
                 test_info_dict = dict((key, value if not isinstance(value, compat_str) or len(value) < 250 else 'md5:' + md5(value))

test/test_playlists.py

@@ -33,6 +33,9 @@ from youtube_dl.extractor import (
     ImdbListIE,
     KhanAcademyIE,
     EveryonesMixtapeIE,
+    RutubeChannelIE,
+    GoogleSearchIE,
+    GenericIE,
 )
 
 
@@ -52,10 +55,10 @@ class TestPlaylists(unittest.TestCase):
     def test_dailymotion_user(self):
         dl = FakeYDL()
         ie = DailymotionUserIE(dl)
-        result = ie.extract('http://www.dailymotion.com/user/generation-quoi/')
+        result = ie.extract('https://www.dailymotion.com/user/nqtv')
         self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], 'Génération Quoi')
-        self.assertTrue(len(result['entries']) >= 26)
+        self.assertEqual(result['title'], 'Rémi Gaillard')
+        self.assertTrue(len(result['entries']) >= 100)
 
     def test_vimeo_channel(self):
         dl = FakeYDL()
@@ -195,11 +198,11 @@ class TestPlaylists(unittest.TestCase):
     def test_imdb_list(self):
         dl = FakeYDL()
         ie = ImdbListIE(dl)
-        result = ie.extract('http://www.imdb.com/list/sMjedvGDd8U')
+        result = ie.extract('http://www.imdb.com/list/JFs9NWw6XI0')
         self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'sMjedvGDd8U')
-        self.assertEqual(result['title'], 'Animated and Family Films')
-        self.assertTrue(len(result['entries']) >= 48)
+        self.assertEqual(result['id'], 'JFs9NWw6XI0')
+        self.assertEqual(result['title'], 'March 23, 2012 Releases')
+        self.assertEqual(len(result['entries']), 7)
 
     def test_khanacademy_topic(self):
         dl = FakeYDL()
@@ -219,7 +222,42 @@ class TestPlaylists(unittest.TestCase):
         self.assertEqual(result['id'], 'm7m0jJAbMQi')
         self.assertEqual(result['title'], 'Driving')
         self.assertEqual(len(result['entries']), 24)
+        
+    def test_rutube_channel(self):
+        dl = FakeYDL()
+        ie = RutubeChannelIE(dl)
+        result = ie.extract('http://rutube.ru/tags/video/1409')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], '1409')
+        self.assertTrue(len(result['entries']) >= 34)
 
+    def test_multiple_brightcove_videos(self):
+        # https://github.com/rg3/youtube-dl/issues/2283
+        dl = FakeYDL()
+        ie = GenericIE(dl)
+        result = ie.extract('http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'always-never-nuclear-command-and-control')
+        self.assertEqual(result['title'], 'Always/Never: A Little-Seen Movie About Nuclear Command and Control : The New Yorker')
+        self.assertEqual(len(result['entries']), 3)
+
+    def test_GoogleSearch(self):
+        dl = FakeYDL()
+        ie = GoogleSearchIE(dl)
+        result = ie.extract('gvsearch15:python language')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'python language')
+        self.assertEqual(result['title'], 'python language')
+        self.assertTrue(len(result['entries']) == 15)
+
+    def test_generic_rss_feed(self):
+        dl = FakeYDL()
+        ie = GenericIE(dl)
+        result = ie.extract('http://www.escapistmagazine.com/rss/videos/list/1.xml')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'http://www.escapistmagazine.com/rss/videos/list/1.xml')
+        self.assertEqual(result['title'], 'Zero Punctuation')
+        self.assertTrue(len(result['entries']) > 10)
 
 if __name__ == '__main__':
     unittest.main()

test/test_subtitles.py

@@ -10,9 +10,11 @@ from test.helper import FakeYDL, md5
 
 
 from youtube_dl.extractor import (
+    BlipTVIE,
     YoutubeIE,
     DailymotionIE,
     TEDIE,
+    VimeoIE,
 )
 
 
@@ -202,5 +204,80 @@ class TestTedSubtitles(BaseTestSubtitles):
         for lang in langs:
             self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
 
+
+class TestBlipTVSubtitles(BaseTestSubtitles):
+    url = 'http://blip.tv/a/a-6603250'
+    IE = BlipTVIE
+
+    def test_list_subtitles(self):
+        self.DL.expect_warning(u'Automatic Captions not supported by this server')
+        self.DL.params['listsubtitles'] = True
+        info_dict = self.getInfoDict()
+        self.assertEqual(info_dict, None)
+
+    def test_allsubtitles(self):
+        self.DL.expect_warning(u'Automatic Captions not supported by this server')
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(set(subtitles.keys()), set(['en']))
+        self.assertEqual(md5(subtitles['en']), '5b75c300af65fe4476dff79478bb93e4')
+
+
+class TestVimeoSubtitles(BaseTestSubtitles):
+    url = 'http://vimeo.com/76979871'
+    IE = VimeoIE
+
+    def test_no_writesubtitles(self):
+        subtitles = self.getSubtitles()
+        self.assertEqual(subtitles, None)
+
+    def test_subtitles(self):
+        self.DL.params['writesubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(md5(subtitles['en']), '8062383cf4dec168fc40a088aa6d5888')
+
+    def test_subtitles_lang(self):
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['subtitleslangs'] = ['fr']
+        subtitles = self.getSubtitles()
+        self.assertEqual(md5(subtitles['fr']), 'b6191146a6c5d3a452244d853fde6dc8')
+
+    def test_allsubtitles(self):
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(set(subtitles.keys()), set(['de', 'en', 'es', 'fr']))
+
+    def test_list_subtitles(self):
+        self.DL.expect_warning(u'Automatic Captions not supported by this server')
+        self.DL.params['listsubtitles'] = True
+        info_dict = self.getInfoDict()
+        self.assertEqual(info_dict, None)
+
+    def test_automatic_captions(self):
+        self.DL.expect_warning(u'Automatic Captions not supported by this server')
+        self.DL.params['writeautomaticsub'] = True
+        self.DL.params['subtitleslang'] = ['en']
+        subtitles = self.getSubtitles()
+        self.assertTrue(len(subtitles.keys()) == 0)
+
+    def test_nosubtitles(self):
+        self.DL.expect_warning(u'video doesn\'t have subtitles')
+        self.url = 'http://vimeo.com/56015672'
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(len(subtitles), 0)
+
+    def test_multiple_langs(self):
+        self.DL.params['writesubtitles'] = True
+        langs = ['es', 'fr', 'de']
+        self.DL.params['subtitleslangs'] = langs
+        subtitles = self.getSubtitles()
+        for lang in langs:
+            self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
+
+
 if __name__ == '__main__':
     unittest.main()

test/test_utils.py

@@ -19,11 +19,13 @@ from youtube_dl.utils import (
     fix_xml_ampersands,
     get_meta_content,
     orderedSet,
+    PagedList,
     parse_duration,
     sanitize_filename,
     shell_quote,
     smuggle_url,
     str_to_int,
+    struct_unpack,
     timeconvert,
     unescapeHTML,
     unified_strdate,
@@ -126,6 +128,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unified_strdate('8/7/2009'), '20090708')
         self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
         self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
+        self.assertEqual(unified_strdate('1968-12-10'), '19681210')
 
     def test_find_xpath_attr(self):
         testxml = u'''<root>
@@ -199,7 +202,16 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(parse_duration('1'), 1)
         self.assertEqual(parse_duration('1337:12'), 80232)
         self.assertEqual(parse_duration('9:12:43'), 33163)
+        self.assertEqual(parse_duration('12:00'), 720)
+        self.assertEqual(parse_duration('00:01:01'), 61)
         self.assertEqual(parse_duration('x:y'), None)
+        self.assertEqual(parse_duration('3h11m53s'), 11513)
+        self.assertEqual(parse_duration('62m45s'), 3765)
+        self.assertEqual(parse_duration('6m59s'), 419)
+        self.assertEqual(parse_duration('49s'), 49)
+        self.assertEqual(parse_duration('0h0m0s'), 0)
+        self.assertEqual(parse_duration('0m0s'), 0)
+        self.assertEqual(parse_duration('0s'), 0)
 
     def test_fix_xml_ampersands(self):
         self.assertEqual(
@@ -214,5 +226,29 @@ class TestUtil(unittest.TestCase):
             fix_xml_ampersands('&#1234;&#x1abC;'), '&#1234;&#x1abC;')
         self.assertEqual(fix_xml_ampersands('&#&#'), '&amp;#&amp;#')
 
+    def test_paged_list(self):
+        def testPL(size, pagesize, sliceargs, expected):
+            def get_page(pagenum):
+                firstid = pagenum * pagesize
+                upto = min(size, pagenum * pagesize + pagesize)
+                for i in range(firstid, upto):
+                    yield i
+
+            pl = PagedList(get_page, pagesize)
+            got = pl.getslice(*sliceargs)
+            self.assertEqual(got, expected)
+
+        testPL(5, 2, (), [0, 1, 2, 3, 4])
+        testPL(5, 2, (1,), [1, 2, 3, 4])
+        testPL(5, 2, (2,), [2, 3, 4])
+        testPL(5, 2, (4,), [4])
+        testPL(5, 2, (0, 3), [0, 1, 2])
+        testPL(5, 2, (1, 4), [1, 2, 3])
+        testPL(5, 2, (2, 99), [2, 3, 4])
+        testPL(5, 2, (20, 99), [])
+
+    def test_struct_unpack(self):
+        self.assertEqual(struct_unpack(u'!B', b'\x00'), (0,))
+
 if __name__ == '__main__':
     unittest.main()

test/test_youtube_lists.py

@@ -30,7 +30,7 @@ class TestYoutubeLists(unittest.TestCase):
         result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
         self.assertIsPlaylist(result)
         self.assertEqual(result['title'], 'ytdl test PL')
-        ytie_results = [YoutubeIE()._extract_id(url['url']) for url in result['entries']]
+        ytie_results = [YoutubeIE().extract_id(url['url']) for url in result['entries']]
         self.assertEqual(ytie_results, [ 'bV9L5Ht9LgY', 'FXxLjLQi3Fg', 'tU3Bgo5qJZE'])
 
     def test_youtube_playlist_noplaylist(self):
@@ -39,7 +39,7 @@ class TestYoutubeLists(unittest.TestCase):
         ie = YoutubePlaylistIE(dl)
         result = ie.extract('https://www.youtube.com/watch?v=FXxLjLQi3Fg&list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
         self.assertEqual(result['_type'], 'url')
-        self.assertEqual(YoutubeIE()._extract_id(result['url']), 'FXxLjLQi3Fg')
+        self.assertEqual(YoutubeIE().extract_id(result['url']), 'FXxLjLQi3Fg')
 
     def test_issue_673(self):
         dl = FakeYDL()
@@ -59,7 +59,7 @@ class TestYoutubeLists(unittest.TestCase):
         dl = FakeYDL()
         ie = YoutubePlaylistIE(dl)
         result = ie.extract('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
-        ytie_results = [YoutubeIE()._extract_id(url['url']) for url in result['entries']]
+        ytie_results = [YoutubeIE().extract_id(url['url']) for url in result['entries']]
         self.assertFalse('pElCt5oNDuI' in ytie_results)
         self.assertFalse('KdPEApIVdWM' in ytie_results)
         
@@ -76,9 +76,9 @@ class TestYoutubeLists(unittest.TestCase):
         # TODO find a > 100 (paginating?) videos course
         result = ie.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
         entries = result['entries']
-        self.assertEqual(YoutubeIE()._extract_id(entries[0]['url']), 'j9WZyLZCBzs')
+        self.assertEqual(YoutubeIE().extract_id(entries[0]['url']), 'j9WZyLZCBzs')
         self.assertEqual(len(entries), 25)
-        self.assertEqual(YoutubeIE()._extract_id(entries[-1]['url']), 'rYefUsYuEp0')
+        self.assertEqual(YoutubeIE().extract_id(entries[-1]['url']), 'rYefUsYuEp0')
 
     def test_youtube_channel(self):
         dl = FakeYDL()
@@ -117,10 +117,17 @@ class TestYoutubeLists(unittest.TestCase):
         original_video = entries[0]
         self.assertEqual(original_video['id'], 'rjFaenf1T-Y')
 
+    def test_youtube_toptracks(self):
+        dl = FakeYDL()
+        ie = YoutubePlaylistIE(dl)
+        result = ie.extract('https://www.youtube.com/playlist?list=MCUS')
+        entries = result['entries']
+        self.assertEqual(len(entries), 100)
+
     def test_youtube_toplist(self):
         dl = FakeYDL()
         ie = YoutubeTopListIE(dl)
-        result = ie.extract('yttoplist:music:Top Tracks')
+        result = ie.extract('yttoplist:music:Trending')
         entries = result['entries']
         self.assertTrue(len(entries) >= 5)
 

test/test_youtube_signature.py

@@ -27,6 +27,12 @@ _TESTS = [
         85,
         u'3456789a0cdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRS[UVWXYZ!"#$%&\'()*+,-./:;<=>?@',
     ),
+    (
+        u'https://s.ytimg.com/yts/jsbin/html5player-vfle-mVwz.js',
+        u'js',
+        90,
+        u']\\[@?>=<;:/.-,+*)(\'&%$#"hZYXWVUTSRQPONMLKJIHGFEDCBAzyxwvutsrqponmlkjiagfedcb39876',
+    ),
 ]
 
 

youtube-dl.plugin.zsh

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

youtube_dl/YoutubeDL.py

@@ -39,6 +39,7 @@ from .utils import (
     locked_file,
     make_HTTPS_handler,
     MaxDownloadsReached,
+    PagedList,
     PostProcessingError,
     platform_name,
     preferredencoding,
@@ -152,6 +153,8 @@ class YoutubeDL(object):
                        support, using fridibi
     debug_printtraffic:Print out sent and received HTTP traffic
     include_ads:       Download ads as well
+    default_search:    Prepend this string if an input url is not valid.
+                       'auto' for elaborate guessing
 
     The following parameters are not used by YoutubeDL itself, they are used by
     the FileDownloader:
@@ -328,7 +331,7 @@ class YoutubeDL(object):
 
     def __exit__(self, *args):
         self.restore_console_title()
-    
+
         if self.params.get('cookiefile') is not None:
             self.cookiejar.save()
 
@@ -393,10 +396,6 @@ class YoutubeDL(object):
         except UnicodeEncodeError:
             self.to_screen('[download] The file has already been downloaded')
 
-    def increment_downloads(self):
-        """Increment the ordinal that assigns a number to each file."""
-        self._num_downloads += 1
-
     def prepare_filename(self, info_dict):
         """Generate the output filename."""
         try:
@@ -514,6 +513,8 @@ class YoutubeDL(object):
             except ExtractorError as de: # An error we somewhat expected
                 self.report_error(compat_str(de), de.format_traceback())
                 break
+            except MaxDownloadsReached:
+                raise
             except Exception as e:
                 if self.params.get('ignoreerrors', False):
                     self.report_error(compat_str(e), tb=compat_str(traceback.format_exc()))
@@ -576,19 +577,27 @@ class YoutubeDL(object):
 
             playlist_results = []
 
-            n_all_entries = len(ie_result['entries'])
             playliststart = self.params.get('playliststart', 1) - 1
             playlistend = self.params.get('playlistend', None)
             # For backwards compatibility, interpret -1 as whole list
             if playlistend == -1:
                 playlistend = None
 
-            entries = ie_result['entries'][playliststart:playlistend]
-            n_entries = len(entries)
-
-            self.to_screen(
-                "[%s] playlist '%s': Collected %d video ids (downloading %d of them)" %
-                (ie_result['extractor'], playlist, n_all_entries, n_entries))
+            if isinstance(ie_result['entries'], list):
+                n_all_entries = len(ie_result['entries'])
+                entries = ie_result['entries'][playliststart:playlistend]
+                n_entries = len(entries)
+                self.to_screen(
+                    "[%s] playlist %s: Collected %d video ids (downloading %d of them)" %
+                    (ie_result['extractor'], playlist, n_all_entries, n_entries))
+            else:
+                assert isinstance(ie_result['entries'], PagedList)
+                entries = ie_result['entries'].getslice(
+                    playliststart, playlistend)
+                n_entries = len(entries)
+                self.to_screen(
+                    "[%s] playlist %s: Downloading %d videos" %
+                    (ie_result['extractor'], playlist, n_entries))
 
             for i, entry in enumerate(entries, 1):
                 self.to_screen('[download] Downloading video #%s of %s' % (i, n_entries))
@@ -635,6 +644,18 @@ class YoutubeDL(object):
             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]
         else:
             extensions = ['mp4', 'flv', 'webm', '3gp']
             if format_spec in extensions:
@@ -689,17 +710,17 @@ class YoutubeDL(object):
 
         # TODO Central sorting goes here
 
-        if formats[0] is not info_dict: 
+        if formats[0] is not info_dict:
             # only set the 'formats' fields if the original info_dict list them
             # otherwise we end up with a circular reference, the first (and unique)
-            # element in the 'formats' field in info_dict is info_dict itself, 
+            # element in the 'formats' field in info_dict is info_dict itself,
             # wich can't be exported to json
             info_dict['formats'] = formats
         if self.params.get('listformats', None):
             self.list_formats(info_dict)
             return
 
-        req_format = self.params.get('format', 'best')
+        req_format = self.params.get('format')
         if req_format is None:
             req_format = 'best'
         formats_to_download = []
@@ -748,8 +769,11 @@ class YoutubeDL(object):
         """Process a single resolved IE result."""
 
         assert info_dict.get('_type', 'video') == 'video'
-        #We increment the download the download count here to match the previous behaviour.
-        self.increment_downloads()
+
+        max_downloads = self.params.get('max_downloads')
+        if max_downloads is not None:
+            if self._num_downloads >= int(max_downloads):
+                raise MaxDownloadsReached()
 
         info_dict['fulltitle'] = info_dict['title']
         if len(info_dict['title']) > 200:
@@ -766,10 +790,7 @@ class YoutubeDL(object):
             self.to_screen('[download] ' + reason)
             return
 
-        max_downloads = self.params.get('max_downloads')
-        if max_downloads is not None:
-            if self._num_downloads > int(max_downloads):
-                raise MaxDownloadsReached()
+        self._num_downloads += 1
 
         filename = self.prepare_filename(info_dict)
 
@@ -1073,9 +1094,15 @@ class YoutubeDL(object):
                 res += fdict['format_note'] + ' '
             if fdict.get('tbr') is not None:
                 res += '%4dk ' % fdict['tbr']
+            if fdict.get('container') is not None:
+                if res:
+                    res += ', '
+                res += '%s container' % fdict['container']
             if (fdict.get('vcodec') is not None and
                     fdict.get('vcodec') != 'none'):
-                res += '%-5s' % fdict['vcodec']
+                if res:
+                    res += ', '
+                res += fdict['vcodec']
                 if fdict.get('vbr') is not None:
                     res += '@'
             elif fdict.get('vbr') is not None and fdict.get('abr') is not None:
@@ -1085,13 +1112,18 @@ class YoutubeDL(object):
             if fdict.get('acodec') is not None:
                 if res:
                     res += ', '
-                res += '%-5s' % fdict['acodec']
+                if fdict['acodec'] == 'none':
+                    res += 'video only'
+                else:
+                    res += '%-5s' % fdict['acodec']
             elif fdict.get('abr') is not None:
                 if res:
                     res += ', '
                 res += 'audio'
             if fdict.get('abr') is not None:
                 res += '@%3dk' % fdict['abr']
+            if fdict.get('asr') is not None:
+                res += ' (%5dHz)' % fdict['asr']
             if fdict.get('filesize') is not None:
                 if res:
                     res += ', '

youtube_dl/__init__.py

@@ -40,6 +40,12 @@ __authors__  = (
     'Michael Orlitzky',
     'Chris Gahan',
     'Saimadhav Heblikar',
+    'Mike Col',
+    'Oleg Prutz',
+    'pulpe',
+    'Andreas Schmitz',
+    'Michael Kaiser',
+    'Niklas Laxström',
 )
 
 __license__ = 'Public Domain'
@@ -99,6 +105,43 @@ def parseOpts(overrideArguments=None):
             optionf.close()
         return res
 
+    def _readUserConf():
+        xdg_config_home = os.environ.get('XDG_CONFIG_HOME')
+        if xdg_config_home:
+            userConfFile = os.path.join(xdg_config_home, 'youtube-dl', 'config')
+            if not os.path.isfile(userConfFile):
+                userConfFile = os.path.join(xdg_config_home, 'youtube-dl.conf')
+        else:
+            userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl', 'config')
+            if not os.path.isfile(userConfFile):
+                userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf')
+        userConf = _readOptions(userConfFile, None)
+
+        if userConf is None:
+            appdata_dir = os.environ.get('appdata')
+            if appdata_dir:
+                userConf = _readOptions(
+                    os.path.join(appdata_dir, 'youtube-dl', 'config'),
+                    default=None)
+                if userConf is None:
+                    userConf = _readOptions(
+                        os.path.join(appdata_dir, 'youtube-dl', 'config.txt'),
+                        default=None)
+
+        if userConf is None:
+            userConf = _readOptions(
+                os.path.join(os.path.expanduser('~'), 'youtube-dl.conf'),
+                default=None)
+        if userConf is None:
+            userConf = _readOptions(
+                os.path.join(os.path.expanduser('~'), 'youtube-dl.conf.txt'),
+                default=None)
+
+        if userConf is None:
+            userConf = []
+
+        return userConf
+
     def _format_option_string(option):
         ''' ('-o', '--option') -> -o, --format METAVAR'''
 
@@ -165,7 +208,7 @@ def parseOpts(overrideArguments=None):
     general.add_option('-U', '--update',
             action='store_true', dest='update_self', help='update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed)')
     general.add_option('-i', '--ignore-errors',
-            action='store_true', dest='ignoreerrors', help='continue on download errors, for example to to skip unavailable videos in a playlist', default=False)
+            action='store_true', dest='ignoreerrors', help='continue on download errors, for example to skip unavailable videos in a playlist', default=False)
     general.add_option('--abort-on-error',
             action='store_false', dest='ignoreerrors',
             help='Abort downloading of further videos (in the playlist or the command line) if an error occurs')
@@ -199,6 +242,13 @@ def parseOpts(overrideArguments=None):
     general.add_option(
         '--bidi-workaround', dest='bidi_workaround', action='store_true',
         help=u'Work around terminals that lack bidirectional text support. Requires bidiv or fribidi executable in PATH')
+    general.add_option('--default-search',
+            dest='default_search', metavar='PREFIX',
+            help='Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for  youtube-dl "large apple". By default (with value "auto") youtube-dl guesses.')
+    general.add_option(
+        '--ignore-config',
+        action='store_true',
+        help='Do not read configuration files. When given in the global configuration file /etc/youtube-dl.conf: do not read the user configuration in ~/.config/youtube-dl.conf (%APPDATA%/youtube-dl/config.txt on Windows)')
 
 
     selection.add_option(
@@ -242,6 +292,10 @@ def parseOpts(overrideArguments=None):
         '--include-ads', dest='include_ads',
         action='store_true',
         help='Download advertisements as well (experimental)')
+    selection.add_option(
+        '--youtube-include-dash-manifest', action='store_true',
+        dest='youtube_include_dash_manifest', default=False,
+        help='Try to download the DASH manifest on YouTube videos (experimental)')
 
     authentication.add_option('-u', '--username',
             dest='username', metavar='USERNAME', help='account username')
@@ -254,8 +308,8 @@ def parseOpts(overrideArguments=None):
 
 
     video_format.add_option('-f', '--format',
-            action='store', dest='format', metavar='FORMAT', default='best',
-            help='video format code, specify the order of preference using slashes: "-f 22/17/18". "-f mp4" and "-f flv" are also supported')
+            action='store', dest='format', metavar='FORMAT', default=None,
+            help='video format code, specify the order of preference using slashes: "-f 22/17/18". "-f mp4" and "-f flv" are also supported. You can also use the special names "best", "bestaudio", "worst", and "worstaudio". By default, youtube-dl will pick the best quality.')
     video_format.add_option('--all-formats',
             action='store_const', dest='format', help='download all available video formats', const='all')
     video_format.add_option('--prefer-free-formats',
@@ -346,7 +400,8 @@ def parseOpts(overrideArguments=None):
             help=optparse.SUPPRESS_HELP)
     verbosity.add_option('--print-traffic',
             dest='debug_printtraffic', action='store_true', default=False,
-            help=optparse.SUPPRESS_HELP)
+            help='Display sent and read HTTP traffic')
+
 
     filesystem.add_option('-t', '--title',
             action='store_true', dest='usetitle', help='use title in file name (default)', default=False)
@@ -449,44 +504,18 @@ def parseOpts(overrideArguments=None):
         if opts.verbose:
             write_string(u'[debug] Override config: ' + repr(overrideArguments) + '\n')
     else:
-        systemConf = _readOptions('/etc/youtube-dl.conf')
-
-        xdg_config_home = os.environ.get('XDG_CONFIG_HOME')
-        if xdg_config_home:
-            userConfFile = os.path.join(xdg_config_home, 'youtube-dl', 'config')
-            if not os.path.isfile(userConfFile):
-                userConfFile = os.path.join(xdg_config_home, 'youtube-dl.conf')
-        else:
-            userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl', 'config')
-            if not os.path.isfile(userConfFile):
-                userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf')
-        userConf = _readOptions(userConfFile, None)
-
-        if userConf is None:
-            appdata_dir = os.environ.get('appdata')
-            if appdata_dir:
-                userConf = _readOptions(
-                    os.path.join(appdata_dir, 'youtube-dl', 'config'),
-                    default=None)
-                if userConf is None:
-                    userConf = _readOptions(
-                        os.path.join(appdata_dir, 'youtube-dl', 'config.txt'),
-                        default=None)
-
-        if userConf is None:
-            userConf = _readOptions(
-                os.path.join(os.path.expanduser('~'), 'youtube-dl.conf'),
-                default=None)
-        if userConf is None:
-            userConf = _readOptions(
-                os.path.join(os.path.expanduser('~'), 'youtube-dl.conf.txt'),
-                default=None)
-
-        if userConf is None:
-            userConf = []
-
         commandLineConf = sys.argv[1:]
+        if '--ignore-config' in commandLineConf:
+            systemConf = []
+            userConf = []
+        else:
+            systemConf = _readOptions('/etc/youtube-dl.conf')
+            if '--ignore-config' in systemConf:
+                userConf = []
+            else:
+                userConf = _readUserConf()
         argv = systemConf + userConf + commandLineConf
+
         opts, args = parser.parse_args(argv)
         if opts.verbose:
             write_string(u'[debug] System config: ' + repr(_hide_login_info(systemConf)) + '\n')
@@ -619,6 +648,12 @@ def _real_main(argv=None):
         date = DateRange.day(opts.date)
     else:
         date = DateRange(opts.dateafter, opts.datebefore)
+    if opts.default_search not in ('auto', None) and ':' not in opts.default_search:
+        parser.error(u'--default-search invalid; did you forget a colon (:) at the end?')
+
+    # Do not download videos when there are audio-only formats
+    if opts.extractaudio and not opts.keepvideo and opts.format is None:
+        opts.format = 'bestaudio/best'
 
     # --all-sub automatically sets --write-sub if --write-auto-sub is not given
     # this was the old behaviour if only --all-sub was given.
@@ -720,6 +755,8 @@ def _real_main(argv=None):
         'debug_printtraffic': opts.debug_printtraffic,
         'prefer_ffmpeg': opts.prefer_ffmpeg,
         'include_ads': opts.include_ads,
+        'default_search': opts.default_search,
+        'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
     }
 
     with YoutubeDL(ydl_opts) as ydl:

youtube_dl/downloader/__init__.py

@@ -1,23 +1,29 @@
+from __future__ import unicode_literals
+
 from .common import FileDownloader
 from .hls import HlsFD
 from .http import HttpFD
 from .mplayer import MplayerFD
 from .rtmp import RtmpFD
+from .f4m import F4mFD
 
 from ..utils import (
     determine_ext,
 )
 
+
 def get_suitable_downloader(info_dict):
     """Get the downloader class that can handle the info dict."""
     url = info_dict['url']
+    protocol = info_dict.get('protocol')
 
     if url.startswith('rtmp'):
         return RtmpFD
-    if determine_ext(url) == u'm3u8':
+    if (protocol == 'm3u8') or (protocol is None and determine_ext(url) == 'm3u8'):
         return HlsFD
     if url.startswith('mms') or url.startswith('rtsp'):
         return MplayerFD
+    if determine_ext(url) == 'f4m':
+        return F4mFD
     else:
         return HttpFD
-

youtube_dl/downloader/common.py

@@ -314,4 +314,3 @@ class FileDownloader(object):
         if the download is successful.
         """
         self._progress_hooks.append(ph)
-

youtube_dl/downloader/f4m.py

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

youtube_dl/downloader/http.py

@@ -27,7 +27,7 @@ class HttpFD(FileDownloader):
         request = compat_urllib_request.Request(url, None, headers)
 
         if self.params.get('test', False):
-            request.add_header('Range','bytes=0-10240')
+            request.add_header('Range', 'bytes=0-10240')
 
         # Establish possible resume length
         if os.path.isfile(encodeFilename(tmpfilename)):
@@ -39,7 +39,7 @@ class HttpFD(FileDownloader):
         if resume_len != 0:
             if self.params.get('continuedl', False):
                 self.report_resuming_byte(resume_len)
-                request.add_header('Range','bytes=%d-' % resume_len)
+                request.add_header('Range', 'bytes=%d-' % resume_len)
                 open_mode = 'ab'
             else:
                 resume_len = 0
@@ -100,7 +100,7 @@ class HttpFD(FileDownloader):
         if data_len is not None:
             data_len = int(data_len) + resume_len
             min_data_len = self.params.get("min_filesize", None)
-            max_data_len =  self.params.get("max_filesize", None)
+            max_data_len = self.params.get("max_filesize", None)
             if min_data_len is not None and data_len < min_data_len:
                 self.to_screen(u'\r[download] File is smaller than min-filesize (%s bytes < %s bytes). Aborting.' % (data_len, min_data_len))
                 return False

youtube_dl/downloader/mplayer.py

@@ -18,10 +18,10 @@ class MplayerFD(FileDownloader):
         try:
             subprocess.call(['mplayer', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
         except (OSError, IOError):
-            self.report_error(u'MMS or RTSP download detected but "%s" could not be run' % args[0] )
+            self.report_error(u'MMS or RTSP download detected but "%s" could not be run' % args[0])
             return False
 
-        # Download using mplayer. 
+        # Download using mplayer.
         retval = subprocess.call(args)
         if retval == 0:
             fsize = os.path.getsize(encodeFilename(tmpfilename))

youtube_dl/downloader/rtmp.py

@@ -87,8 +87,10 @@ class RtmpFD(FileDownloader):
         url = info_dict['url']
         player_url = info_dict.get('player_url', None)
         page_url = info_dict.get('page_url', None)
+        app = info_dict.get('app', None)
         play_path = info_dict.get('play_path', None)
         tc_url = info_dict.get('tc_url', None)
+        flash_version = info_dict.get('flash_version', None)
         live = info_dict.get('rtmp_live', False)
         conn = info_dict.get('rtmp_conn', None)
 
@@ -111,12 +113,16 @@ class RtmpFD(FileDownloader):
             basic_args += ['--swfVfy', player_url]
         if page_url is not None:
             basic_args += ['--pageUrl', page_url]
+        if app is not None:
+            basic_args += ['--app', app]
         if play_path is not None:
             basic_args += ['--playpath', play_path]
         if tc_url is not None:
             basic_args += ['--tcUrl', url]
         if test:
             basic_args += ['--stop', '1']
+        if flash_version is not None:
+            basic_args += ['--flashVer', flash_version]
         if live:
             basic_args += ['--live']
         if conn:

youtube_dl/extractor/__init__.py

@@ -15,6 +15,7 @@ from .arte import (
 from .auengine import AUEngineIE
 from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE
+from .bbccouk import BBCCoUkIE
 from .blinkx import BlinkxIE
 from .bliptv import BlipTVIE, BlipTVUserIE
 from .bloomberg import BloombergIE
@@ -25,11 +26,16 @@ from .canalplus import CanalplusIE
 from .canalc2 import Canalc2IE
 from .cbs import CBSIE
 from .channel9 import Channel9IE
+from .chilloutzone import ChilloutzoneIE
 from .cinemassacre import CinemassacreIE
 from .clipfish import ClipfishIE
+from .cliphunter import CliphunterIE
 from .clipsyndicate import ClipsyndicateIE
 from .cmt import CMTIE
-from .cnn import CNNIE
+from .cnn import (
+    CNNIE,
+    CNNBlogsIE,
+)
 from .collegehumor import CollegeHumorIE
 from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
 from .condenast import CondeNastIE
@@ -47,22 +53,27 @@ from .depositfiles import DepositFilesIE
 from .dotsub import DotsubIE
 from .dreisat import DreiSatIE
 from .defense import DefenseGouvFrIE
+from .discovery import DiscoveryIE
 from .dropbox import DropboxIE
 from .ebaumsworld import EbaumsWorldIE
 from .ehow import EHowIE
 from .eighttracks import EightTracksIE
 from .eitb import EitbIE
+from .elpais import ElPaisIE
 from .escapist import EscapistIE
 from .everyonesmixtape import EveryonesMixtapeIE
 from .exfm import ExfmIE
 from .extremetube import ExtremeTubeIE
 from .facebook import FacebookIE
 from .faz import FazIE
+from .firstpost import FirstpostIE
+from .firsttv import FirstTVIE
 from .fktv import (
     FKTVIE,
     FKTVPosteckeIE,
 )
 from .flickr import FlickrIE
+from .fourtube import FourTubeIE
 from .franceinter import FranceInterIE
 from .francetv import (
     PluzzIE,
@@ -72,6 +83,7 @@ from .francetv import (
     CultureboxIE,
 )
 from .freesound import FreesoundIE
+from .freespeech import FreespeechIE
 from .funnyordie import FunnyOrDieIE
 from .gamekings import GamekingsIE
 from .gamespot import GameSpotIE
@@ -80,8 +92,10 @@ from .generic import GenericIE
 from .googleplus import GooglePlusIE
 from .googlesearch import GoogleSearchIE
 from .hark import HarkIE
+from .helsinki import HelsinkiIE
 from .hotnewhiphop import HotNewHipHopIE
 from .howcast import HowcastIE
+from .huffpost import HuffPostIE
 from .hypem import HypemIE
 from .ign import IGNIE, OneUPIE
 from .imdb import (
@@ -92,10 +106,12 @@ from .ina import InaIE
 from .infoq import InfoQIE
 from .instagram import InstagramIE
 from .internetvideoarchive import InternetVideoArchiveIE
+from .iprima import IPrimaIE
 from .ivi import (
     IviIE,
     IviCompilationIE
 )
+from .jadorecettepub import JadoreCettePubIE
 from .jeuxvideo import JeuxVideoIE
 from .jukebox import JukeboxIE
 from .justintv import JustinTVIE
@@ -105,13 +121,18 @@ from .keezmovies import KeezMoviesIE
 from .khanacademy import KhanAcademyIE
 from .kickstarter import KickStarterIE
 from .keek import KeekIE
+from .kontrtube import KontrTubeIE
+from .la7 import LA7IE
+from .lifenews import LifeNewsIE
 from .liveleak import LiveLeakIE
 from .livestream import LivestreamIE, LivestreamOriginalIE
 from .lynda import (
     LyndaIE,
     LyndaCourseIE
 )
+from .m6 import M6IE
 from .macgamestore import MacGameStoreIE
+from .malemotion import MalemotionIE
 from .mdr import MDRIE
 from .metacafe import MetacafeIE
 from .metacritic import MetacriticIE
@@ -119,6 +140,7 @@ from .mit import TechTVMITIE, MITIE
 from .mixcloud import MixcloudIE
 from .mpora import MporaIE
 from .mofosex import MofosexIE
+from .mooshare import MooshareIE
 from .mtv import (
     MTVIE,
     MTVIggyIE,
@@ -130,12 +152,16 @@ from .myvideo import MyVideoIE
 from .naver import NaverIE
 from .nba import NBAIE
 from .nbc import NBCNewsIE
+from .ndr import NDRIE
 from .ndtv import NDTVIE
 from .newgrounds import NewgroundsIE
+from .nfb import NFBIE
 from .nhl import NHLIE, NHLVideocenterIE
 from .niconico import NiconicoIE
 from .ninegag import NineGagIE
+from .normalboots import NormalbootsIE
 from .novamov import NovamovIE
+from .nowness import NownessIE
 from .nowvideo import NowVideoIE
 from .ooyala import OoyalaIE
 from .orf import ORFIE
@@ -154,7 +180,13 @@ from .ro220 import Ro220IE
 from .rottentomatoes import RottenTomatoesIE
 from .roxwel import RoxwelIE
 from .rtlnow import RTLnowIE
-from .rutube import RutubeIE
+from .rutube import (
+    RutubeIE,
+    RutubeChannelIE,
+    RutubeMovieIE,
+    RutubePersonIE,
+)
+from .savefrom import SaveFromIE
 from .servingsys import ServingSysIE
 from .sina import SinaIE
 from .slashdot import SlashdotIE
@@ -179,16 +211,21 @@ from .stanfordoc import StanfordOpenClassroomIE
 from .statigram import StatigramIE
 from .steam import SteamIE
 from .streamcloud import StreamcloudIE
+from .streamcz import StreamCZIE
+from .syfy import SyfyIE
 from .sztvhu import SztvHuIE
 from .teamcoco import TeamcocoIE
 from .techtalks import TechTalksIE
 from .ted import TEDIE
+from .testurl import TestURLIE
 from .tf1 import TF1IE
 from .theplatform import ThePlatformIE
 from .thisav import ThisAVIE
+from .tinypic import TinyPicIE
 from .toutv import TouTvIE
 from .traileraddict import TrailerAddictIE
 from .trilulilu import TriluliluIE
+from .trutube import TruTubeIE
 from .tube8 import Tube8IE
 from .tudou import TudouIE
 from .tumblr import TumblrIE
@@ -199,6 +236,7 @@ from .ustream import UstreamIE, UstreamChannelIE
 from .vbox7 import Vbox7IE
 from .veehd import VeeHDIE
 from .veoh import VeohIE
+from .vesti import VestiIE
 from .vevo import VevoIE
 from .vice import ViceIE
 from .viddler import ViddlerIE
@@ -216,8 +254,8 @@ from .vimeo import (
 from .vine import VineIE
 from .viki import VikiIE
 from .vk import VKIE
+from .vube import VubeIE
 from .wat import WatIE
-from .websurg import WeBSurgIE
 from .weibo import WeiboIE
 from .wimp import WimpIE
 from .wistia import WistiaIE

youtube_dl/extractor/ard.py

@@ -1,22 +1,28 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 from ..utils import (
+    determine_ext,
     ExtractorError,
 )
 
+
 class ARDIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[^/\?]+)(?:\?.*)?'
-    _TITLE = r'<h1(?: class="boxTopHeadline")?>(?P<title>.*)</h1>'
-    _MEDIA_STREAM = r'mediaCollection\.addMediaStream\((?P<media_type>\d+), (?P<quality>\d+), "(?P<rtmp_url>[^"]*)", "(?P<video_url>[^"]*)", "[^"]*"\)'
+    _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[^/\?]+)(?:\?.*)?'
+
     _TEST = {
-        u'url': u'http://www.ardmediathek.de/das-erste/tagesschau-in-100-sek?documentId=14077640',
-        u'file': u'14077640.mp4',
-        u'md5': u'6ca8824255460c787376353f9e20bbd8',
-        u'info_dict': {
-            u"title": u"11.04.2013 09:23 Uhr - Tagesschau in 100 Sekunden"
+        'url': 'http://www.ardmediathek.de/das-erste/guenther-jauch/edward-snowden-im-interview-held-oder-verraeter?documentId=19288786',
+        'file': '19288786.mp4',
+        'md5': '515bf47ce209fb3f5a61b7aad364634c',
+        'info_dict': {
+            'title': 'Edward Snowden im Interview - Held oder Verräter?',
+            'description': 'Edward Snowden hat alles aufs Spiel gesetzt, um die weltweite \xdcberwachung durch die Geheimdienste zu enttarnen. Nun stellt sich der ehemalige NSA-Mitarbeiter erstmals weltweit in einem TV-Interview den Fragen eines NDR-Journalisten. Die Sendung vom Sonntagabend.',
+            'thumbnail': 'http://www.ardmediathek.de/ard/servlet/contentblob/19/28/87/90/19288790/bild/2250037',
         },
-        u'skip': u'Requires rtmpdump'
+        'skip': 'Blocked outside of Germany',
     }
 
     def _real_extract(self, url):
@@ -29,26 +35,49 @@ class ARDIE(InfoExtractor):
         else:
             video_id = m.group('video_id')
 
-        # determine title and media streams from webpage
-        html = self._download_webpage(url, video_id)
-        title = re.search(self._TITLE, html).group('title')
-        streams = [mo.groupdict() for mo in re.finditer(self._MEDIA_STREAM, html)]
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(
+            r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>', webpage, 'title')
+        description = self._html_search_meta(
+            'dcterms.abstract', webpage, 'description')
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        streams = [
+            mo.groupdict()
+            for mo in re.finditer(
+                r'mediaCollection\.addMediaStream\((?P<media_type>\d+), (?P<quality>\d+), "(?P<rtmp_url>[^"]*)", "(?P<video_url>[^"]*)", "[^"]*"\)', webpage)]
         if not streams:
-            assert '"fsk"' in html
-            raise ExtractorError(u'This video is only available after 8:00 pm')
+            if '"fsk"' in webpage:
+                raise ExtractorError('This video is only available after 20:00')
 
-        # choose default media type and highest quality for now
-        stream = max([s for s in streams if int(s["media_type"]) == 0],
-                     key=lambda s: int(s["quality"]))
+        formats = []
+        for s in streams:
+            format = {
+                'quality': int(s['quality']),
+            }
+            if s.get('rtmp_url'):
+                format['protocol'] = 'rtmp'
+                format['url'] = s['rtmp_url']
+                format['playpath'] = s['video_url']
+            else:
+                format['url'] = s['video_url']
 
-        # there's two possibilities: RTMP stream or HTTP download
-        info = {'id': video_id, 'title': title, 'ext': 'mp4'}
-        if stream['rtmp_url']:
-            self.to_screen(u'RTMP download detected')
-            assert stream['video_url'].startswith('mp4:')
-            info["url"] = stream["rtmp_url"]
-            info["play_path"] = stream['video_url']
-        else:
-            assert stream["video_url"].endswith('.mp4')
-            info["url"] = stream["video_url"]
-        return [info]
+            quality_name = self._search_regex(
+                r'[,.]([a-zA-Z0-9_-]+),?\.mp4', format['url'],
+                'quality name', default='NA')
+            format['format_id'] = '%s-%s-%s-%s' % (
+                determine_ext(format['url']), quality_name, s['media_type'],
+                s['quality'])
+
+            formats.append(format)
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'formats': formats,
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/bbccouk.py

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

youtube_dl/extractor/bliptv.py

@@ -1,128 +1,137 @@
 from __future__ import unicode_literals
 
 import datetime
-import json
 import re
-import socket
 
 from .common import InfoExtractor
+from .subtitles import SubtitlesInfoExtractor
 from ..utils import (
-    compat_http_client,
     compat_str,
-    compat_urllib_error,
     compat_urllib_request,
 
-    ExtractorError,
     unescapeHTML,
 )
 
 
-class BlipTVIE(InfoExtractor):
+class BlipTVIE(SubtitlesInfoExtractor):
     """Information extractor for blip.tv"""
 
-    _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv/((.+/)|(play/)|(api\.swf#))(.+)$'
+    _VALID_URL = r'https?://(?:\w+\.)?blip\.tv/((.+/)|(play/)|(api\.swf#))(?P<presumptive_id>.+)$'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352',
-        'file': '5779306.mov',
         'md5': 'c6934ad0b6acf2bd920720ec888eb812',
         'info_dict': {
+            'id': '5779306',
+            'ext': 'mov',
             'upload_date': '20111205',
             'description': 'md5:9bc31f227219cde65e47eeec8d2dc596',
             'uploader': 'Comic Book Resources - CBR TV',
             'title': 'CBR EXCLUSIVE: "Gotham City Imposters" Bats VS Jokerz Short 3',
         }
-    }
-
-    def report_direct_download(self, title):
-        """Report information extraction."""
-        self.to_screen('%s: Direct download detected' % title)
+    }, {
+        # https://github.com/rg3/youtube-dl/pull/2274
+        'note': 'Video with subtitles',
+        'url': 'http://blip.tv/play/h6Uag5OEVgI.html',
+        'md5': '309f9d25b820b086ca163ffac8031806',
+        'info_dict': {
+            'id': '6586561',
+            'ext': 'mp4',
+            'uploader': 'Red vs. Blue',
+            'description': 'One-Zero-One',
+            'upload_date': '20130614',
+            'title': 'Red vs. Blue Season 11 Episode 1',
+        }
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError('Invalid URL: %s' % url)
+        presumptive_id = mobj.group('presumptive_id')
 
         # See https://github.com/rg3/youtube-dl/issues/857
-        embed_mobj = re.search(r'^(?:https?://)?(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)([a-zA-Z0-9]+)', url)
+        embed_mobj = re.match(r'https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)([a-zA-Z0-9]+)', url)
         if embed_mobj:
             info_url = 'http://blip.tv/play/%s.x?p=1' % embed_mobj.group(1)
             info_page = self._download_webpage(info_url, embed_mobj.group(1))
-            video_id = self._search_regex(r'data-episode-id="(\d+)', info_page,  'video_id')
+            video_id = self._search_regex(
+                r'data-episode-id="([0-9]+)', info_page, 'video_id')
             return self.url_result('http://blip.tv/a/a-' + video_id, 'BlipTV')
-
-        if '?' in url:
-            cchar = '&'
-        else:
-            cchar = '?'
+        
+        cchar = '&' if '?' in url else '?'
         json_url = url + cchar + 'skin=json&version=2&no_wrap=1'
         request = compat_urllib_request.Request(json_url)
         request.add_header('User-Agent', 'iTunes/10.6.1')
-        self.report_extraction(mobj.group(1))
-        urlh = self._request_webpage(request, None, False,
-            'unable to download video info webpage')
 
-        try:
-            json_code_bytes = urlh.read()
-            json_code = json_code_bytes.decode('utf-8')
-        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-            raise ExtractorError('Unable to read video info webpage: %s' % compat_str(err))
+        json_data = self._download_json(request, video_id=presumptive_id)
 
-        try:
-            json_data = json.loads(json_code)
-            if 'Post' in json_data:
-                data = json_data['Post']
-            else:
-                data = json_data
+        if 'Post' in json_data:
+            data = json_data['Post']
+        else:
+            data = json_data
 
-            upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
-            formats = []
-            if 'additionalMedia' in data:
-                for f in sorted(data['additionalMedia'], key=lambda f: int(f['media_height'])):
-                    if not int(f['media_width']): # filter m3u8
-                        continue
-                    formats.append({
-                        'url': f['url'],
-                        'format_id': f['role'],
-                        'width': int(f['media_width']),
-                        'height': int(f['media_height']),
-                    })
-            else:
+        video_id = compat_str(data['item_id'])
+        upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
+        subtitles = {}
+        formats = []
+        if 'additionalMedia' in data:
+            for f in data['additionalMedia']:
+                if f.get('file_type_srt') == 1:
+                    LANGS = {
+                        'english': 'en',
+                    }
+                    lang = f['role'].rpartition('-')[-1].strip().lower()
+                    langcode = LANGS.get(lang, lang)
+                    subtitles[langcode] = f['url']
+                    continue
+                if not int(f['media_width']):  # filter m3u8
+                    continue
                 formats.append({
-                    'url': data['media']['url'],
-                    'width': int(data['media']['width']),
-                    'height': int(data['media']['height']),
+                    'url': f['url'],
+                    'format_id': f['role'],
+                    'width': int(f['media_width']),
+                    'height': int(f['media_height']),
                 })
+        else:
+            formats.append({
+                'url': data['media']['url'],
+                'width': int(data['media']['width']),
+                'height': int(data['media']['height']),
+            })
+        self._sort_formats(formats)
 
-            self._sort_formats(formats)
+        # subtitles
+        video_subtitles = self.extract_subtitles(video_id, subtitles)
+        if self._downloader.params.get('listsubtitles', False):
+            self._list_available_subtitles(video_id, subtitles)
+            return
 
-            return {
-                'id': compat_str(data['item_id']),
-                'uploader': data['display_name'],
-                'upload_date': upload_date,
-                'title': data['title'],
-                'thumbnail': data['thumbnailUrl'],
-                'description': data['description'],
-                'user_agent': 'iTunes/10.6.1',
-                'formats': formats,
-            }
-        except (ValueError, KeyError) as err:
-            raise ExtractorError('Unable to parse video information: %s' % repr(err))
+        return {
+            'id': video_id,
+            'uploader': data['display_name'],
+            'upload_date': upload_date,
+            'title': data['title'],
+            'thumbnail': data['thumbnailUrl'],
+            'description': data['description'],
+            'user_agent': 'iTunes/10.6.1',
+            'formats': formats,
+            'subtitles': video_subtitles,
+        }
+
+    def _download_subtitle_url(self, sub_lang, url):
+        # For some weird reason, blip.tv serves a video instead of subtitles
+        # when we request with a common UA
+        req = compat_urllib_request.Request(url)
+        req.add_header('Youtubedl-user-agent', 'youtube-dl')
+        return self._download_webpage(req, None, note=False)
 
 
 class BlipTVUserIE(InfoExtractor):
-    """Information Extractor for blip.tv users."""
-
     _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$'
     _PAGE_SIZE = 12
     IE_NAME = 'blip.tv:user'
 
     def _real_extract(self, url):
-        # Extract username
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError('Invalid URL: %s' % url)
-
         username = mobj.group(1)
 
         page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1'
@@ -131,7 +140,6 @@ class BlipTVUserIE(InfoExtractor):
         mobj = re.search(r'data-users-id="([^"]+)"', page)
         page_base = page_base % mobj.group(1)
 
-
         # Download video ids using BlipTV Ajax calls. Result size per
         # query is limited (currently to 12 videos) so we need to query
         # page by page until there are no video ids - it means we got
@@ -142,8 +150,8 @@ class BlipTVUserIE(InfoExtractor):
 
         while True:
             url = page_base + "&page=" + str(pagenum)
-            page = self._download_webpage(url, username,
-                                          'Downloading video ids from page %d' % pagenum)
+            page = self._download_webpage(
+                url, username, 'Downloading video ids from page %d' % pagenum)
 
             # Extract video identifiers
             ids_in_page = []
@@ -167,4 +175,4 @@ class BlipTVUserIE(InfoExtractor):
 
         urls = ['http://blip.tv/%s' % video_id for video_id in video_ids]
         url_entries = [self.url_result(vurl, 'BlipTV') for vurl in urls]
-        return [self.playlist_result(url_entries, playlist_title = username)]
+        return [self.playlist_result(url_entries, playlist_title=username)]

youtube_dl/extractor/bloomberg.py

@@ -24,5 +24,7 @@ class BloombergIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         name = mobj.group('name')
         webpage = self._download_webpage(url, name)
-        ooyala_code = self._search_regex(r'<source src="http://player.ooyala.com/player/[^/]+/([^".]+)', webpage, u'ooyala url')
-        return OoyalaIE._build_url_result(ooyala_code)
+        embed_code = self._search_regex(
+            r'<source src="https?://[^/]+/[^/]+/[^/]+/([^/]+)', webpage,
+            'embed code')
+        return OoyalaIE._build_url_result(embed_code)

youtube_dl/extractor/breakcom.py

@@ -1,18 +1,20 @@
+from __future__ import unicode_literals
+
 import re
 import json
 
 from .common import InfoExtractor
-from ..utils import determine_ext
 
 
 class BreakIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?break\.com/video/([^/]+)'
+    _VALID_URL = r'http://(?:www\.)?break\.com/video/([^/]+)'
     _TEST = {
-        u'url': u'http://www.break.com/video/when-girls-act-like-guys-2468056',
-        u'file': u'2468056.mp4',
-        u'md5': u'a3513fb1547fba4fb6cfac1bffc6c46b',
-        u'info_dict': {
-            u"title": u"When Girls Act Like D-Bags"
+        'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056',
+        'md5': 'a3513fb1547fba4fb6cfac1bffc6c46b',
+        'info_dict': {
+            'id': '2468056',
+            'ext': 'mp4',
+            'title': 'When Girls Act Like D-Bags',
         }
     }
 
@@ -22,17 +24,16 @@ class BreakIE(InfoExtractor):
         embed_url = 'http://www.break.com/embed/%s' % video_id
         webpage = self._download_webpage(embed_url, video_id)
         info_json = self._search_regex(r'var embedVars = ({.*?});', webpage,
-                                       u'info json', flags=re.DOTALL)
+                                       'info json', flags=re.DOTALL)
         info = json.loads(info_json)
         video_url = info['videoUri']
         m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', video_url)
         if m_youtube is not None:
             return self.url_result(m_youtube.group(1), 'Youtube')
         final_url = video_url + '?' + info['AuthToken']
-        return [{
-            'id':        video_id,
-            'url':       final_url,
-            'ext':       determine_ext(final_url),
-            'title':     info['contentName'],
+        return {
+            'id': video_id,
+            'url': final_url,
+            'title': info['contentName'],
             'thumbnail': info['thumbUri'],
-        }]
+        }

youtube_dl/extractor/brightcove.py

@@ -17,13 +17,13 @@ from ..utils import (
 
     ExtractorError,
     unsmuggle_url,
+    unescapeHTML,
 )
 
 
 class BrightcoveIE(InfoExtractor):
     _VALID_URL = r'https?://.*brightcove\.com/(services|viewer).*\?(?P<query>.*)'
     _FEDERATED_URL_TEMPLATE = 'http://c.brightcove.com/services/viewer/htmlFederated?%s'
-    _PLAYLIST_URL_TEMPLATE = 'http://c.brightcove.com/services/json/experience/runtime/?command=get_programming_for_experience&playerKey=%s'
 
     _TESTS = [
         {
@@ -70,7 +70,7 @@ class BrightcoveIE(InfoExtractor):
                 'description': 'md5:363109c02998fee92ec02211bd8000df',
                 'uploader': 'National Ballet of Canada',
             },
-        },
+        }
     ]
 
     @classmethod
@@ -128,20 +128,28 @@ class BrightcoveIE(InfoExtractor):
 
     @classmethod
     def _extract_brightcove_url(cls, webpage):
-        """Try to extract the brightcove url from the wepbage, returns None
+        """Try to extract the brightcove url from the webpage, returns None
         if it can't be found
         """
-        m_brightcove = re.search(
+        urls = cls._extract_brightcove_urls(webpage)
+        return urls[0] if urls else None
+
+    @classmethod
+    def _extract_brightcove_urls(cls, webpage):
+        """Return a list of all Brightcove URLs from the webpage """
+
+        url_m = re.search(r'<meta\s+property="og:video"\s+content="(http://c.brightcove.com/[^"]+)"', webpage)
+        if url_m:
+            return [unescapeHTML(url_m.group(1))]
+
+        matches = re.findall(
             r'''(?sx)<object
             (?:
-                [^>]+?class=([\'"])[^>]*?BrightcoveExperience.*?\1 |
+                [^>]+?class=[\'"][^>]*?BrightcoveExperience.*?[\'"] |
                 [^>]*?>\s*<param\s+name="movie"\s+value="https?://[^/]*brightcove\.com/
             ).+?</object>''',
             webpage)
-        if m_brightcove is not None:
-            return cls._build_brighcove_url(m_brightcove.group())
-        else:
-            return None
+        return [cls._build_brighcove_url(m) for m in matches]
 
     def _real_extract(self, url):
         url, smuggled_data = unsmuggle_url(url, {})
@@ -183,8 +191,9 @@ class BrightcoveIE(InfoExtractor):
         return self._extract_video_info(video_info)
 
     def _get_playlist_info(self, player_key):
-        playlist_info = self._download_webpage(self._PLAYLIST_URL_TEMPLATE % player_key,
-                                               player_key, 'Downloading playlist information')
+        info_url = 'http://c.brightcove.com/services/json/experience/runtime/?command=get_programming_for_experience&playerKey=%s' % player_key
+        playlist_info = self._download_webpage(
+            info_url, player_key, 'Downloading playlist information')
 
         json_data = json.loads(playlist_info)
         if 'videoList' not in json_data:
@@ -198,7 +207,7 @@ class BrightcoveIE(InfoExtractor):
     def _extract_video_info(self, video_info):
         info = {
             'id': compat_str(video_info['id']),
-            'title': video_info['displayName'],
+            'title': video_info['displayName'].strip(),
             'description': video_info.get('shortDescription'),
             'thumbnail': video_info.get('videoStillURL') or video_info.get('thumbnailURL'),
             'uploader': video_info.get('publisherName'),

youtube_dl/extractor/canalc2.py

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

youtube_dl/extractor/channel9.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+from __future__ import unicode_literals
 
 import re
 
@@ -11,38 +11,40 @@ class Channel9IE(InfoExtractor):
 
     The type of provided URL (video or playlist) is determined according to
     meta Search.PageType from web page HTML rather than URL itself, as it is
-    not always possible to do.    
+    not always possible to do.
     '''
-    IE_DESC = u'Channel 9'
-    IE_NAME = u'channel9'
-    _VALID_URL = r'^https?://(?:www\.)?channel9\.msdn\.com/(?P<contentpath>.+)/?'
+    IE_DESC = 'Channel 9'
+    IE_NAME = 'channel9'
+    _VALID_URL = r'https?://(?:www\.)?channel9\.msdn\.com/(?P<contentpath>.+)/?'
 
     _TESTS = [
         {
-            u'url': u'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002',
-            u'file': u'Events_TechEd_Australia_2013_KOS002.mp4',
-            u'md5': u'bbd75296ba47916b754e73c3a4bbdf10',
-            u'info_dict': {
-                u'title': u'Developer Kick-Off Session: Stuff We Love',
-                u'description': u'md5:c08d72240b7c87fcecafe2692f80e35f',
-                u'duration': 4576,
-                u'thumbnail': u'http://media.ch9.ms/ch9/9d51/03902f2d-fc97-4d3c-b195-0bfe15a19d51/KOS002_220.jpg',
-                u'session_code': u'KOS002',
-                u'session_day': u'Day 1',
-                u'session_room': u'Arena 1A',
-                u'session_speakers': [ u'Ed Blankenship', u'Andrew Coates', u'Brady Gaster', u'Patrick Klug', u'Mads Kristensen' ],
+            'url': 'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002',
+            'md5': 'bbd75296ba47916b754e73c3a4bbdf10',
+            'info_dict': {
+                'id': 'Events/TechEd/Australia/2013/KOS002',
+                'ext': 'mp4',
+                'title': 'Developer Kick-Off Session: Stuff We Love',
+                'description': 'md5:c08d72240b7c87fcecafe2692f80e35f',
+                'duration': 4576,
+                'thumbnail': 'http://media.ch9.ms/ch9/9d51/03902f2d-fc97-4d3c-b195-0bfe15a19d51/KOS002_220.jpg',
+                'session_code': 'KOS002',
+                'session_day': 'Day 1',
+                'session_room': 'Arena 1A',
+                'session_speakers': [ 'Ed Blankenship', 'Andrew Coates', 'Brady Gaster', 'Patrick Klug', 'Mads Kristensen' ],
             },
         },
         {
-            u'url': u'http://channel9.msdn.com/posts/Self-service-BI-with-Power-BI-nuclear-testing',
-            u'file': u'posts_Self-service-BI-with-Power-BI-nuclear-testing.mp4',
-            u'md5': u'b43ee4529d111bc37ba7ee4f34813e68',
-            u'info_dict': {
-                u'title': u'Self-service BI with Power BI - nuclear testing',
-                u'description': u'md5:d1e6ecaafa7fb52a2cacdf9599829f5b',
-                u'duration': 1540,
-                u'thumbnail': u'http://media.ch9.ms/ch9/87e1/0300391f-a455-4c72-bec3-4422f19287e1/selfservicenuk_512.jpg',
-                u'authors': [ u'Mike Wilmot' ],
+            'url': 'http://channel9.msdn.com/posts/Self-service-BI-with-Power-BI-nuclear-testing',
+            'md5': 'b43ee4529d111bc37ba7ee4f34813e68',
+            'info_dict': {
+                'id': 'posts/Self-service-BI-with-Power-BI-nuclear-testing',
+                'ext': 'mp4',
+                'title': 'Self-service BI with Power BI - nuclear testing',
+                'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b',
+                'duration': 1540,
+                'thumbnail': 'http://media.ch9.ms/ch9/87e1/0300391f-a455-4c72-bec3-4422f19287e1/selfservicenuk_512.jpg',
+                'authors': [ 'Mike Wilmot' ],
             },
         }
     ]
@@ -60,7 +62,7 @@ class Channel9IE(InfoExtractor):
             return 0
         units = m.group('units')
         try:
-            exponent = [u'B', u'KB', u'MB', u'GB', u'TB', u'PB', u'EB', u'ZB', u'YB'].index(units.upper())
+            exponent = ['B', 'KB', 'MB', 'GB', 'TB', 'PB', 'EB', 'ZB', 'YB'].index(units.upper())
         except ValueError:
             return 0
         size = float(m.group('size'))
@@ -80,7 +82,7 @@ class Channel9IE(InfoExtractor):
             'url': x.group('url'),
             'format_id': x.group('quality'),
             'format_note': x.group('note'),
-            'format': u'%s (%s)' % (x.group('quality'), x.group('note')),
+            'format': '%s (%s)' % (x.group('quality'), x.group('note')),
             'filesize': self._restore_bytes(x.group('filesize')), # File size is approximate
             'preference': self._known_formats.index(x.group('quality')),
             'vcodec': 'none' if x.group('note') == 'Audio only' else None,
@@ -91,10 +93,10 @@ class Channel9IE(InfoExtractor):
         return formats
 
     def _extract_title(self, html):
-        title = self._html_search_meta(u'title', html, u'title')
+        title = self._html_search_meta('title', html, 'title')
         if title is None:           
             title = self._og_search_title(html)
-            TITLE_SUFFIX = u' (Channel 9)'
+            TITLE_SUFFIX = ' (Channel 9)'
             if title is not None and title.endswith(TITLE_SUFFIX):
                 title = title[:-len(TITLE_SUFFIX)]
         return title
@@ -110,7 +112,7 @@ class Channel9IE(InfoExtractor):
         m = re.search(DESCRIPTION_REGEX, html)
         if m is not None:
             return m.group('description')
-        return self._html_search_meta(u'description', html, u'description')
+        return self._html_search_meta('description', html, 'description')
 
     def _extract_duration(self, html):
         m = re.search(r'data-video_duration="(?P<hours>\d{2}):(?P<minutes>\d{2}):(?P<seconds>\d{2})"', html)
@@ -172,7 +174,7 @@ class Channel9IE(InfoExtractor):
 
         # Nothing to download
         if len(formats) == 0 and slides is None and zip_ is None:
-            self._downloader.report_warning(u'None of recording, slides or zip are available for %s' % content_path)
+            self._downloader.report_warning('None of recording, slides or zip are available for %s' % content_path)
             return
 
         # Extract meta
@@ -244,7 +246,7 @@ class Channel9IE(InfoExtractor):
         return contents
 
     def _extract_list(self, content_path):
-        rss = self._download_xml(self._RSS_URL % content_path, content_path, u'Downloading RSS')
+        rss = self._download_xml(self._RSS_URL % content_path, content_path, 'Downloading RSS')
         entries = [self.url_result(session_url.text, 'Channel9')
                    for session_url in rss.findall('./channel/item/link')]
         title_text = rss.find('./channel/title').text
@@ -254,11 +256,11 @@ class Channel9IE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         content_path = mobj.group('contentpath')
 
-        webpage = self._download_webpage(url, content_path, u'Downloading web page')
+        webpage = self._download_webpage(url, content_path, 'Downloading web page')
 
         page_type_m = re.search(r'<meta name="Search.PageType" content="(?P<pagetype>[^"]+)"/>', webpage)
         if page_type_m is None:
-            raise ExtractorError(u'Search.PageType not found, don\'t know how to process this page', expected=True)
+            raise ExtractorError('Search.PageType not found, don\'t know how to process this page', expected=True)
 
         page_type = page_type_m.group('pagetype')
         if page_type == 'List':         # List page, may contain list of 'item'-like objects
@@ -268,4 +270,4 @@ class Channel9IE(InfoExtractor):
         elif page_type == 'Session':    # Event session page, may contain downloadable content
             return self._extract_session(webpage, content_path)
         else:
-            raise ExtractorError(u'Unexpected Search.PageType %s' % page_type, expected=True)
+            raise ExtractorError('Unexpected Search.PageType %s' % page_type, expected=True)

youtube_dl/extractor/chilloutzone.py

@@ -0,0 +1,97 @@
+from __future__ import unicode_literals
+
+import re
+import base64
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    ExtractorError
+)
+
+
+class ChilloutzoneIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?chilloutzone\.net/video/(?P<id>[\w|-]+)\.html'
+    _TESTS = [{
+        'url': 'http://www.chilloutzone.net/video/enemene-meck-alle-katzen-weg.html',
+        'md5': 'a76f3457e813ea0037e5244f509e66d1',
+        'info_dict': {
+            'id': 'enemene-meck-alle-katzen-weg',
+            'ext': 'mp4',
+            'title': 'Enemene Meck - Alle Katzen weg',
+            'description': 'Ist das der Umkehrschluss des Niesenden Panda-Babys?',
+        },
+    }, {
+        'note': 'Video hosted at YouTube',
+        'url': 'http://www.chilloutzone.net/video/eine-sekunde-bevor.html',
+        'info_dict': {
+            'id': '1YVQaAgHyRU',
+            'ext': 'mp4',
+            'title': '16 Photos Taken 1 Second Before Disaster',
+            'description': 'md5:58a8fcf6a459fe0a08f54140f0ad1814',
+            'uploader': 'BuzzFeedVideo',
+            'uploader_id': 'BuzzFeedVideo',
+            'upload_date': '20131105',
+        },
+    }, {
+        'note': 'Video hosted at Vimeo',
+        'url': 'http://www.chilloutzone.net/video/icon-blending.html',
+        'md5': '2645c678b8dc4fefcc0e1b60db18dac1',
+        'info_dict': {
+            'id': '85523671',
+            'ext': 'mp4',
+            'title': 'The Sunday Times - Icons',
+            'description': 'md5:3e1c0dc6047498d6728dcdaad0891762',
+            'uploader': 'Us',
+            'uploader_id': 'usfilms',
+            'upload_date': '20140131'
+        },
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        base64_video_info = self._html_search_regex(
+            r'var cozVidData = "(.+?)";', webpage, 'video data')
+        decoded_video_info = base64.b64decode(base64_video_info).decode("utf-8")
+        video_info_dict = json.loads(decoded_video_info)
+
+        # get video information from dict
+        video_url = video_info_dict['mediaUrl']
+        description = clean_html(video_info_dict.get('description'))
+        title = video_info_dict['title']
+        native_platform = video_info_dict['nativePlatform']
+        native_video_id = video_info_dict['nativeVideoId']
+        source_priority = video_info_dict['sourcePriority']
+
+        # If nativePlatform is None a fallback mechanism is used (i.e. youtube embed)
+        if native_platform is None:
+            youtube_url = self._html_search_regex(
+                r'<iframe.* src="((?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"',
+                webpage, 'fallback video URL', default=None)
+            if youtube_url is not None:
+                return self.url_result(youtube_url, ie='Youtube')
+
+        # Non Fallback: Decide to use native source (e.g. youtube or vimeo) or
+        # the own CDN
+        if source_priority == 'native':
+            if native_platform == 'youtube':
+                return self.url_result(native_video_id, ie='Youtube')
+            if native_platform == 'vimeo':
+                return self.url_result(
+                    'http://vimeo.com/' + native_video_id, ie='Vimeo')
+
+        if not video_url:
+            raise ExtractorError('No video found')
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'title': title,
+            'description': description,
+        }

youtube_dl/extractor/cliphunter.py

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

youtube_dl/extractor/cnn.py

@@ -6,6 +6,7 @@ from .common import InfoExtractor
 from ..utils import (
     int_or_none,
     parse_duration,
+    url_basename,
 )
 
 
@@ -98,3 +99,28 @@ class CNNIE(InfoExtractor):
             'duration': duration,
             'upload_date': upload_date,
         }
+
+
+class CNNBlogsIE(InfoExtractor):
+    _VALID_URL = r'https?://[^\.]+\.blogs\.cnn\.com/.+'
+    _TEST = {
+        'url': 'http://reliablesources.blogs.cnn.com/2014/02/09/criminalizing-journalism/',
+        'md5': '3e56f97b0b6ffb4b79f4ea0749551084',
+        'info_dict': {
+            'id': 'bestoftv/2014/02/09/criminalizing-journalism.cnn',
+            'ext': 'mp4',
+            'title': 'Criminalizing journalism?',
+            'description': 'Glenn Greenwald responds to comments made this week on Capitol Hill that journalists could be criminal accessories.',
+            'upload_date': '20140209',
+        },
+        'add_ie': ['CNN'],
+    }
+
+    def _real_extract(self, url):
+        webpage = self._download_webpage(url, url_basename(url))
+        cnn_url = self._html_search_regex(r'data-url="(.+?)"', webpage, 'cnn url')
+        return {
+            '_type': 'url',
+            'url': cnn_url,
+            'ie_key': CNNIE.ie_key(),
+        }

youtube_dl/extractor/collegehumor.py

@@ -4,6 +4,7 @@ import json
 import re
 
 from .common import InfoExtractor
+from ..utils import int_or_none
 
 
 class CollegeHumorIE(InfoExtractor):
@@ -11,24 +12,45 @@ class CollegeHumorIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe',
-        'file': '6902724.mp4',
         'md5': 'dcc0f5c1c8be98dc33889a191f4c26bd',
         'info_dict': {
+            'id': '6902724',
+            'ext': 'mp4',
             'title': 'Comic-Con Cosplay Catastrophe',
-            'description': 'Fans get creative this year at San Diego.  Too',
+            'description': 'Fans get creative this year',
             'age_limit': 13,
         },
     },
     {
         'url': 'http://www.collegehumor.com/video/3505939/font-conference',
-        'file': '3505939.mp4',
         'md5': '72fa701d8ef38664a4dbb9e2ab721816',
         'info_dict': {
+            'id': '3505939',
+            'ext': 'mp4',
             'title': 'Font Conference',
-            'description': 'This video wasn\'t long enough, so we made it double-spaced.',
+            'description': 'This video wasn\'t long enough,',
             'age_limit': 10,
+            'duration': 179,
         },
-    }]
+    },
+    # embedded youtube video
+    {
+        'url': 'http://www.collegehumor.com/embed/6950457',
+        'info_dict': {
+            'id': 'W5gMp3ZjYg4',
+            'ext': 'mp4',
+            'title': 'Funny Dogs Protecting Babies Compilation 2014 [NEW HD]',
+            'uploader': 'Funnyplox TV',
+            'uploader_id': 'funnyploxtv',
+            'description': 'md5:7ded37421526d54afdf005e25bc2b7a3',
+            'upload_date': '20140128',
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'add_ie': ['Youtube'],
+    },
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -38,6 +60,12 @@ class CollegeHumorIE(InfoExtractor):
         data = json.loads(self._download_webpage(
             jsonUrl, video_id, 'Downloading info JSON'))
         vdata = data['video']
+        if vdata.get('youtubeId') is not None:
+            return {
+                '_type': 'url',
+                'url': vdata['youtubeId'],
+                'ie_key': 'Youtube',
+            }
 
         AGE_LIMITS = {'nc17': 18, 'r': 18, 'pg13': 13, 'pg': 10, 'g': 0}
         rating = vdata.get('rating')
@@ -49,7 +77,7 @@ class CollegeHumorIE(InfoExtractor):
         PREFS = {'high_quality': 2, 'low_quality': 0}
         formats = []
         for format_key in ('mp4', 'webm'):
-            for qname, qurl in vdata[format_key].items():
+            for qname, qurl in vdata.get(format_key, {}).items():
                 formats.append({
                     'format_id': format_key + '_' + qname,
                     'url': qurl,
@@ -58,6 +86,8 @@ class CollegeHumorIE(InfoExtractor):
                 })
         self._sort_formats(formats)
 
+        duration = int_or_none(vdata.get('duration'), 1000)
+
         return {
             'id': video_id,
             'title': vdata['title'],
@@ -65,4 +95,5 @@ class CollegeHumorIE(InfoExtractor):
             'thumbnail': vdata.get('thumbnail'),
             'formats': formats,
             'age_limit': age_limit,
+            'duration': duration,
         }

youtube_dl/extractor/comedycentral.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -12,33 +14,25 @@ from ..utils import (
 
 
 class ComedyCentralIE(MTVServicesInfoExtractor):
-    _VALID_URL = r'''(?x)https?://(?:www.)?comedycentral.com/
+    _VALID_URL = r'''(?x)https?://(?:www\.)?comedycentral\.com/
         (video-clips|episodes|cc-studios|video-collections)
         /(?P<title>.*)'''
-    _FEED_URL = u'http://comedycentral.com/feeds/mrss/'
+    _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
 
     _TEST = {
-        u'url': u'http://www.comedycentral.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
-        u'md5': u'4167875aae411f903b751a21f357f1ee',
-        u'info_dict': {
-            u'id': u'cef0cbb3-e776-4bc9-b62e-8016deccb354',
-            u'ext': u'mp4',
-            u'title': u'Uncensored - Greg Fitzsimmons - Too Good of a Mother',
-            u'description': u'After a certain point, breastfeeding becomes c**kblocking.',
+        'url': 'http://www.comedycentral.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
+        'md5': '4167875aae411f903b751a21f357f1ee',
+        'info_dict': {
+            'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354',
+            'ext': 'mp4',
+            'title': 'CC:Stand-Up|Greg Fitzsimmons: Life on Stage|Uncensored - Too Good of a Mother',
+            'description': 'After a certain point, breastfeeding becomes c**kblocking.',
         },
     }
 
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        title = mobj.group('title')
-        webpage = self._download_webpage(url, title)
-        mgid = self._search_regex(r'data-mgid="(?P<mgid>mgid:.*?)"',
-                                  webpage, u'mgid')
-        return self._get_videos_info(mgid)
-
 
 class ComedyCentralShowsIE(InfoExtractor):
-    IE_DESC = u'The Daily Show / Colbert Report'
+    IE_DESC = 'The Daily Show / Colbert Report'
     # urls can be abbreviations like :thedailyshow or :colbert
     # urls for episodes like:
     # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day
@@ -55,14 +49,14 @@ class ComedyCentralShowsIE(InfoExtractor):
                               extended-interviews/(?P<interID>[0-9]+)/playlist_tds_extended_(?P<interview_title>.*?)/.*?)))
                      $"""
     _TEST = {
-        u'url': u'http://www.thedailyshow.com/watch/thu-december-13-2012/kristen-stewart',
-        u'file': u'422212.mp4',
-        u'md5': u'4e2f5cb088a83cd8cdb7756132f9739d',
-        u'info_dict': {
-            u"upload_date": u"20121214", 
-            u"description": u"Kristen Stewart", 
-            u"uploader": u"thedailyshow", 
-            u"title": u"thedailyshow-kristen-stewart part 1"
+        'url': 'http://www.thedailyshow.com/watch/thu-december-13-2012/kristen-stewart',
+        'file': '422212.mp4',
+        'md5': '4e2f5cb088a83cd8cdb7756132f9739d',
+        'info_dict': {
+            "upload_date": "20121214",
+            "description": "Kristen Stewart",
+            "uploader": "thedailyshow",
+            "title": "thedailyshow-kristen-stewart part 1"
         }
     }
 
@@ -92,22 +86,22 @@ class ComedyCentralShowsIE(InfoExtractor):
 
     @staticmethod
     def _transform_rtmp_url(rtmp_video_url):
-        m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp.comedystor/.*)$', rtmp_video_url)
+        m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\.comedystor/.*)$', rtmp_video_url)
         if not m:
-            raise ExtractorError(u'Cannot transform RTMP url')
+            raise ExtractorError('Cannot transform RTMP url')
         base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
         return base + m.group('finalid')
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url, re.VERBOSE)
         if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
+            raise ExtractorError('Invalid URL: %s' % url)
 
         if mobj.group('shortname'):
             if mobj.group('shortname') in ('tds', 'thedailyshow'):
-                url = u'http://www.thedailyshow.com/full-episodes/'
+                url = 'http://www.thedailyshow.com/full-episodes/'
             else:
-                url = u'http://www.colbertnation.com/full-episodes/'
+                url = 'http://www.colbertnation.com/full-episodes/'
             mobj = re.match(self._VALID_URL, url, re.VERBOSE)
             assert mobj is not None
 
@@ -133,9 +127,9 @@ class ComedyCentralShowsIE(InfoExtractor):
             url = htmlHandle.geturl()
             mobj = re.match(self._VALID_URL, url, re.VERBOSE)
             if mobj is None:
-                raise ExtractorError(u'Invalid redirected URL: ' + url)
+                raise ExtractorError('Invalid redirected URL: ' + url)
             if mobj.group('episode') == '':
-                raise ExtractorError(u'Redirected URL is still not specific: ' + url)
+                raise ExtractorError('Redirected URL is still not specific: ' + url)
             epTitle = mobj.group('episode')
 
         mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage)
@@ -147,15 +141,15 @@ class ComedyCentralShowsIE(InfoExtractor):
 
             altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage)
             if len(altMovieParams) == 0:
-                raise ExtractorError(u'unable to find Flash URL in webpage ' + url)
+                raise ExtractorError('unable to find Flash URL in webpage ' + url)
             else:
                 mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
 
         uri = mMovieParams[0][1]
         indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri})
         idoc = self._download_xml(indexUrl, epTitle,
-                                          u'Downloading show index',
-                                          u'unable to download episode index')
+                                          'Downloading show index',
+                                          'unable to download episode index')
 
         results = []
 
@@ -170,7 +164,7 @@ class ComedyCentralShowsIE(InfoExtractor):
             configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
                         compat_urllib_parse.urlencode({'uri': mediaId}))
             cdoc = self._download_xml(configUrl, epTitle,
-                                               u'Downloading configuration for %s' % shortMediaId)
+                                               'Downloading configuration for %s' % shortMediaId)
 
             turls = []
             for rendition in cdoc.findall('.//rendition'):
@@ -178,7 +172,7 @@ class ComedyCentralShowsIE(InfoExtractor):
                 turls.append(finfo)
 
             if len(turls) == 0:
-                self._downloader.report_error(u'unable to download ' + mediaId + ': No videos found')
+                self._downloader.report_error('unable to download ' + mediaId + ': No videos found')
                 continue
 
             formats = []
@@ -192,7 +186,7 @@ class ComedyCentralShowsIE(InfoExtractor):
                     'width': w,
                 })
 
-            effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1)
+            effTitle = showId + '-' + epTitle + ' part ' + compat_str(partNum+1)
             results.append({
                 'id': shortMediaId,
                 'formats': formats,

youtube_dl/extractor/common.py

@@ -63,13 +63,15 @@ class InfoExtractor(object):
                     * tbr        Average bitrate of audio and video in KBit/s
                     * abr        Average audio bitrate in KBit/s
                     * acodec     Name of the audio codec in use
+                    * asr        Audio sampling rate in Hertz
                     * vbr        Average video bitrate in KBit/s
                     * vcodec     Name of the video codec in use
+                    * container  Name of the container format
                     * filesize   The number of bytes, if known in advance
                     * player_url SWF Player URL (used for rtmpdump).
                     * protocol   The protocol that will be used for the actual
                                  download, lower-case.
-                                 "http", "https", "rtsp", "rtmp" or so.
+                                 "http", "https", "rtsp", "rtmp", "m3u8" or so.
                     * preference Order number of this format. If this field is
                                  present and not None, the formats get sorted
                                  by this field.
@@ -238,7 +240,7 @@ class InfoExtractor(object):
             except AttributeError:
                 url = url_or_request
             if len(url) > 200:
-                h = u'___' + hashlib.md5(url).hexdigest()
+                h = u'___' + hashlib.md5(url.encode('utf-8')).hexdigest()
                 url = url[:200 - len(h)] + h
             raw_filename = ('%s_%s.dump' % (video_id, url))
             filename = sanitize_filename(raw_filename, restricted=True)
@@ -269,8 +271,11 @@ class InfoExtractor(object):
 
     def _download_json(self, url_or_request, video_id,
                        note=u'Downloading JSON metadata',
-                       errnote=u'Unable to download JSON metadata'):
+                       errnote=u'Unable to download JSON metadata',
+                       transform_source=None):
         json_string = self._download_webpage(url_or_request, video_id, note, errnote)
+        if transform_source:
+            json_string = transform_source(json_string)
         try:
             return json.loads(json_string)
         except ValueError as ve:
@@ -397,7 +402,7 @@ class InfoExtractor(object):
     # Helper functions for extracting OpenGraph info
     @staticmethod
     def _og_regexes(prop):
-        content_re = r'content=(?:"([^>]+?)"|\'(.+?)\')'
+        content_re = r'content=(?:"([^>]+?)"|\'([^>]+?)\')'
         property_re = r'(?:name|property)=[\'"]og:%s[\'"]' % re.escape(prop)
         template = r'<meta[^>]+?%s[^>]+?%s'
         return [
@@ -463,7 +468,14 @@ class InfoExtractor(object):
         }
         return RATING_TABLE.get(rating.lower(), None)
 
+    def _twitter_search_player(self, html):
+        return self._html_search_meta('twitter:player', html,
+            'twitter card player')
+
     def _sort_formats(self, formats):
+        if not formats:
+            raise ExtractorError(u'No video formats found')
+
         def _formats_key(f):
             # TODO remove the following workaround
             from ..utils import determine_ext

youtube_dl/extractor/condenast.py

@@ -30,7 +30,7 @@ class CondeNastIE(InfoExtractor):
         'vanityfair': 'Vanity Fair',
     }
 
-    _VALID_URL = r'http://(video|www).(?P<site>%s).com/(?P<type>watch|series|video)/(?P<id>.+)' % '|'.join(_SITES.keys())
+    _VALID_URL = r'http://(video|www)\.(?P<site>%s)\.com/(?P<type>watch|series|video)/(?P<id>.+)' % '|'.join(_SITES.keys())
     IE_DESC = 'Condé Nast media group: %s' % ', '.join(sorted(_SITES.values()))
 
     _TEST = {

youtube_dl/extractor/crunchyroll.py

@@ -1,4 +1,6 @@
 # encoding: utf-8
+from __future__ import unicode_literals
+
 import re, base64, zlib
 from hashlib import sha1
 from math import pow, sqrt, floor
@@ -18,29 +20,29 @@ from ..aes import (
 )
 
 class CrunchyrollIE(InfoExtractor):
-    _VALID_URL = r'(?:https?://)?(?:www\.)?(?P<url>crunchyroll\.com/[^/]*/[^/?&]*?(?P<video_id>[0-9]+))(?:[/?&]|$)'
+    _VALID_URL = r'(?:https?://)?(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
     _TESTS = [{
-        u'url': u'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
-        u'file': u'645513.flv',
-        #u'md5': u'b1639fd6ddfaa43788c85f6d1dddd412',
-        u'info_dict': {
-            u'title': u'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!',
-            u'description': u'md5:2d17137920c64f2f49981a7797d275ef',
-            u'thumbnail': u'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
-            u'uploader': u'Yomiuri Telecasting Corporation (YTV)',
-            u'upload_date': u'20131013',
+        'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
+        'file': '645513.flv',
+        #'md5': 'b1639fd6ddfaa43788c85f6d1dddd412',
+        'info_dict': {
+            'title': 'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!',
+            'description': 'md5:2d17137920c64f2f49981a7797d275ef',
+            'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
+            'uploader': 'Yomiuri Telecasting Corporation (YTV)',
+            'upload_date': '20131013',
         },
-        u'params': {
+        'params': {
             # rtmp
-            u'skip_download': True,
+            'skip_download': True,
         },
     }]
 
     _FORMAT_IDS = {
-        u'360': (u'60', u'106'),
-        u'480': (u'61', u'106'),
-        u'720': (u'62', u'106'),
-        u'1080': (u'80', u'108'),
+        '360': ('60', '106'),
+        '480': ('61', '106'),
+        '720': ('62', '106'),
+        '1080': ('80', '108'),
     }
 
     def _decrypt_subtitles(self, data, iv, id):
@@ -63,7 +65,7 @@ class CrunchyrollIE(InfoExtractor):
             num3 = key ^ num1
             num4 = num3 ^ (num3 >> 3) ^ num2
             prefix = intlist_to_bytes(obfuscate_key_aux(20, 97, (1, 2)))
-            shaHash = bytes_to_intlist(sha1(prefix + str(num4).encode(u'ascii')).digest())
+            shaHash = bytes_to_intlist(sha1(prefix + str(num4).encode('ascii')).digest())
             # Extend 160 Bit hash to 256 Bit
             return shaHash + [0] * 12
         
@@ -79,93 +81,98 @@ class CrunchyrollIE(InfoExtractor):
 
     def _convert_subtitles_to_srt(self, subtitles):
         i=1
-        output = u''
+        output = ''
         for start, end, text in re.findall(r'<event [^>]*?start="([^"]+)" [^>]*?end="([^"]+)" [^>]*?text="([^"]+)"[^>]*?>', subtitles):
-            start = start.replace(u'.', u',')
-            end = end.replace(u'.', u',')
+            start = start.replace('.', ',')
+            end = end.replace('.', ',')
             text = clean_html(text)
-            text = text.replace(u'\\N', u'\n')
+            text = text.replace('\\N', '\n')
             if not text:
                 continue
-            output += u'%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
+            output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
             i+=1
         return output
 
     def _real_extract(self,url):
         mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('video_id')
 
-        webpage_url = u'http://www.' + mobj.group('url')
-        video_id = mobj.group(u'video_id')
-        webpage = self._download_webpage(webpage_url, video_id)
-        note_m = self._html_search_regex(r'<div class="showmedia-trailer-notice">(.+?)</div>', webpage, u'trailer-notice', default=u'')
+        if mobj.group('prefix') == 'm':
+            mobile_webpage = self._download_webpage(url, video_id, 'Downloading mobile webpage')
+            webpage_url = self._search_regex(r'<link rel="canonical" href="([^"]+)" />', mobile_webpage, 'webpage_url')
+        else:
+            webpage_url = 'http://www.' + mobj.group('url')
+
+        webpage = self._download_webpage(webpage_url, video_id, 'Downloading webpage')
+        note_m = self._html_search_regex(r'<div class="showmedia-trailer-notice">(.+?)</div>', webpage, 'trailer-notice', default='')
         if note_m:
             raise ExtractorError(note_m)
 
-        video_title = self._html_search_regex(r'<h1[^>]*>(.+?)</h1>', webpage, u'video_title', flags=re.DOTALL)
-        video_title = re.sub(r' {2,}', u' ', video_title)
-        video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, u'video_description', default=u'')
+        video_title = self._html_search_regex(r'<h1[^>]*>(.+?)</h1>', webpage, 'video_title', flags=re.DOTALL)
+        video_title = re.sub(r' {2,}', ' ', video_title)
+        video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, 'video_description', default='')
         if not video_description:
             video_description = None
-        video_upload_date = self._html_search_regex(r'<div>Availability for free users:(.+?)</div>', webpage, u'video_upload_date', fatal=False, flags=re.DOTALL)
+        video_upload_date = self._html_search_regex(r'<div>Availability for free users:(.+?)</div>', webpage, 'video_upload_date', fatal=False, flags=re.DOTALL)
         if video_upload_date:
             video_upload_date = unified_strdate(video_upload_date)
-        video_uploader = self._html_search_regex(r'<div>\s*Publisher:(.+?)</div>', webpage, u'video_uploader', fatal=False, flags=re.DOTALL)
+        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, u'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({u'current_page': webpage_url})
-        playerdata_req.add_header(u'Content-Type', u'application/x-www-form-urlencoded')
-        playerdata = self._download_webpage(playerdata_req, video_id, note=u'Downloading media info')
+        playerdata_req.data = compat_urllib_parse.urlencode({'current_page': webpage_url})
+        playerdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
+        playerdata = self._download_webpage(playerdata_req, video_id, note='Downloading media info')
         
-        stream_id = self._search_regex(r'<media_id>([^<]+)', playerdata, u'stream_id')
-        video_thumbnail = self._search_regex(r'<episode_image_url>([^<]+)', playerdata, u'thumbnail', fatal=False)
+        stream_id = self._search_regex(r'<media_id>([^<]+)', playerdata, 'stream_id')
+        video_thumbnail = self._search_regex(r'<episode_image_url>([^<]+)', playerdata, 'thumbnail', fatal=False)
 
         formats = []
         for fmt in re.findall(r'\?p([0-9]{3,4})=1', webpage):
             stream_quality, stream_format = self._FORMAT_IDS[fmt]
-            video_format = fmt+u'p'
-            streamdata_req = compat_urllib_request.Request(u'http://www.crunchyroll.com/xml/')
+            video_format = fmt+'p'
+            streamdata_req = compat_urllib_request.Request('http://www.crunchyroll.com/xml/')
             # urlencode doesn't work!
-            streamdata_req.data = u'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality='+stream_quality+u'&media%5Fid='+stream_id+u'&video%5Fformat='+stream_format
-            streamdata_req.add_header(u'Content-Type', u'application/x-www-form-urlencoded')
-            streamdata_req.add_header(u'Content-Length', str(len(streamdata_req.data)))
-            streamdata = self._download_webpage(streamdata_req, video_id, note=u'Downloading media info for '+video_format)
-            video_url = self._search_regex(r'<host>([^<]+)', streamdata, u'video_url')
-            video_play_path = self._search_regex(r'<file>([^<]+)', streamdata, u'video_play_path')
+            streamdata_req.data = 'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality='+stream_quality+'&media%5Fid='+stream_id+'&video%5Fformat='+stream_format
+            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_webpage(streamdata_req, video_id, note='Downloading media info for '+video_format)
+            video_url = self._search_regex(r'<host>([^<]+)', streamdata, 'video_url')
+            video_play_path = self._search_regex(r'<file>([^<]+)', streamdata, 'video_play_path')
             formats.append({
-                u'url': video_url,
-                u'play_path':   video_play_path,
-                u'ext': 'flv',
-                u'format': video_format,
-                u'format_id': video_format,
+                'url': video_url,
+                'play_path':   video_play_path,
+                'ext': 'flv',
+                'format': video_format,
+                'format_id': video_format,
             })
 
         subtitles = {}
         for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage):
-            sub_page = self._download_webpage(u'http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id='+sub_id,\
-                                              video_id, note=u'Downloading subtitles for '+sub_name)
-            id = self._search_regex(r'id=\'([0-9]+)', sub_page, u'subtitle_id', fatal=False)
-            iv = self._search_regex(r'<iv>([^<]+)', sub_page, u'subtitle_iv', fatal=False)
-            data = self._search_regex(r'<data>([^<]+)', sub_page, u'subtitle_data', fatal=False)
+            sub_page = self._download_webpage('http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id='+sub_id,\
+                                              video_id, note='Downloading subtitles for '+sub_name)
+            id = self._search_regex(r'id=\'([0-9]+)', sub_page, 'subtitle_id', fatal=False)
+            iv = self._search_regex(r'<iv>([^<]+)', sub_page, 'subtitle_iv', fatal=False)
+            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(u'utf-8')
-            lang_code = self._search_regex(r'lang_code=\'([^\']+)', subtitle, u'subtitle_lang_code', fatal=False)
+            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
             subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle)
 
         return {
-            u'id':          video_id,
-            u'title':       video_title,
-            u'description': video_description,
-            u'thumbnail':   video_thumbnail,
-            u'uploader':    video_uploader,
-            u'upload_date': video_upload_date,
-            u'subtitles':   subtitles,
-            u'formats':     formats,
+            'id':          video_id,
+            'title':       video_title,
+            'description': video_description,
+            'thumbnail':   video_thumbnail,
+            'uploader':    video_uploader,
+            'upload_date': video_upload_date,
+            'subtitles':   subtitles,
+            'formats':     formats,
         }

youtube_dl/extractor/cspan.py

@@ -1,48 +1,60 @@
 from __future__ import unicode_literals
 
-import json
 import re
 
 from .common import InfoExtractor
 from ..utils import (
     unescapeHTML,
+    find_xpath_attr,
 )
 
 
 class CSpanIE(InfoExtractor):
-    _VALID_URL = r'http://www\.c-spanvideo\.org/program/(.*)'
+    _VALID_URL = r'http://(?:www\.)?c-span\.org/video/\?(?P<id>\d+)'
     IE_DESC = 'C-SPAN'
     _TEST = {
-        'url': 'http://www.c-spanvideo.org/program/HolderonV',
-        'file': '315139.mp4',
+        'url': 'http://www.c-span.org/video/?313572-1/HolderonV',
         'md5': '8e44ce11f0f725527daccc453f553eb0',
         'info_dict': {
+            'id': '315139',
+            'ext': 'mp4',
             'title': 'Attorney General Eric Holder on Voting Rights Act Decision',
-            'description': 'Attorney General Eric Holder spoke to reporters following the Supreme Court decision in [Shelby County v. Holder] in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced until Congress established new guidelines for review.',
+            'description': 'Attorney General Eric Holder spoke to reporters following the Supreme Court decision in Shelby County v. Holder in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced until Congress established new guidelines for review.',
         },
+        'skip': 'Regularly fails on travis, for unknown reasons',
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        prog_name = mobj.group(1)
-        webpage = self._download_webpage(url, prog_name)
-        video_id = self._search_regex(r'programid=(.*?)&', webpage, 'video id')
+        page_id = mobj.group('id')
+        webpage = self._download_webpage(url, page_id)
+        video_id = self._search_regex(r'data-progid=\'(\d+)\'>', webpage, 'video id')
 
-        title = self._html_search_regex(
-            r'<!-- title -->\n\s*<h1[^>]*>(.*?)</h1>', webpage, 'title')
-        description = self._og_search_description(webpage)
+        description = self._html_search_regex(
+            [
+                # The full description
+                r'<div class=\'expandable\'>(.*?)<a href=\'#\'',
+                # If the description is small enough the other div is not
+                # present, otherwise this is a stripped version
+                r'<p class=\'initial\'>(.*?)</p>'
+            ],
+            webpage, 'description', flags=re.DOTALL)
 
         info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id
-        data_json = self._download_webpage(
-            info_url, video_id, 'Downloading video info')
-        data = json.loads(data_json)
+        data = self._download_json(info_url, video_id)
 
         url = unescapeHTML(data['video']['files'][0]['path']['#text'])
 
+        doc = self._download_xml('http://www.c-span.org/common/services/flashXml.php?programid=' + video_id,
+            video_id)
+
+        def find_string(s):
+            return find_xpath_attr(doc, './/string', 'name', s).text
+
         return {
             'id': video_id,
-            'title': title,
+            'title': find_string('title'),
             'url': url,
             'description': description,
-            'thumbnail': self._og_search_thumbnail(webpage),
+            'thumbnail': find_string('poster'),
         }

youtube_dl/extractor/d8.py

@@ -1,22 +1,25 @@
 # encoding: utf-8
+from __future__ import unicode_literals
+
 from .canalplus import CanalplusIE
 
 
 class D8IE(CanalplusIE):
     _VALID_URL = r'https?://www\.d8\.tv/.*?/(?P<path>.*)'
     _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/d8/%s'
-    IE_NAME = u'd8.tv'
+    IE_NAME = 'd8.tv'
 
     _TEST = {
-        u'url': u'http://www.d8.tv/d8-docs-mags/pid6589-d8-campagne-intime.html',
-        u'file': u'966289.flv',
-        u'info_dict': {
-            u'title': u'Campagne intime - Documentaire exceptionnel',
-            u'description': u'md5:d2643b799fb190846ae09c61e59a859f',
-            u'upload_date': u'20131108',
+        'url': 'http://www.d8.tv/d8-docs-mags/pid6589-d8-campagne-intime.html',
+        'file': '966289.flv',
+        'info_dict': {
+            'title': 'Campagne intime - Documentaire exceptionnel',
+            'description': 'md5:d2643b799fb190846ae09c61e59a859f',
+            'upload_date': '20131108',
         },
-        u'params': {
+        'params': {
             # rtmp
-            u'skip_download': True,
+            'skip_download': True,
         },
+        'skip': 'videos get deleted after a while',
     }

youtube_dl/extractor/discovery.py

@@ -0,0 +1,46 @@
+from __future__ import unicode_literals
+
+import re
+import json
+
+from .common import InfoExtractor
+
+
+class DiscoveryIE(InfoExtractor):
+    _VALID_URL = r'http://dsc\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9\-]*)(.htm)?'
+    _TEST = {
+        'url': 'http://dsc.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm',
+        'file': '614784.mp4',
+        'md5': 'e12614f9ee303a6ccef415cb0793eba2',
+        'info_dict': {
+            'title': 'MythBusters: Mission Impossible Outtakes',
+            'description': ('Watch Jamie Hyneman and Adam Savage practice being'
+                ' each other -- to the point of confusing Jamie\'s dog -- and '
+                'don\'t miss Adam moon-walking as Jamie ... behind Jamie\'s'
+                ' back.'),
+            'duration': 156,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id)
+
+        video_list_json = self._search_regex(r'var videoListJSON = ({.*?});',
+            webpage, 'video list', flags=re.DOTALL)
+        video_list = json.loads(video_list_json)
+        info = video_list['clips'][0]
+        formats = []
+        for f in info['mp4']:
+            formats.append(
+                {'url': f['src'], r'ext': r'mp4', 'tbr': int(f['bitrate'][:-1])})
+
+        return {
+            'id': info['contentId'],
+            'title': video_list['name'],
+            'formats': formats,
+            'description': info['videoCaption'],
+            'thumbnail': info.get('videoStillURL') or info.get('thumbnailURL'),
+            'duration': info['duration'],
+        }

youtube_dl/extractor/dotsub.py

@@ -1,41 +1,42 @@
+from __future__ import unicode_literals
+
 import re
-import json
 import time
 
 from .common import InfoExtractor
 
 
 class DotsubIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?dotsub\.com/view/([^/]+)'
+    _VALID_URL = r'http://(?:www\.)?dotsub\.com/view/(?P<id>[^/]+)'
     _TEST = {
-        u'url': u'http://dotsub.com/view/aed3b8b2-1889-4df5-ae63-ad85f5572f27',
-        u'file': u'aed3b8b2-1889-4df5-ae63-ad85f5572f27.flv',
-        u'md5': u'0914d4d69605090f623b7ac329fea66e',
-        u'info_dict': {
-            u"title": u"Pyramids of Waste (2010), AKA The Lightbulb Conspiracy - Planned obsolescence documentary",
-            u"uploader": u"4v4l0n42",
-            u'description': u'Pyramids of Waste (2010) also known as "The lightbulb conspiracy" is a documentary about how our economic system based on consumerism  and planned obsolescence is breaking our planet down.\r\n\r\nSolutions to this can be found at:\r\nhttp://robotswillstealyourjob.com\r\nhttp://www.federicopistono.org\r\n\r\nhttp://opensourceecology.org\r\nhttp://thezeitgeistmovement.com',
-            u'thumbnail': u'http://dotsub.com/media/aed3b8b2-1889-4df5-ae63-ad85f5572f27/p',
-            u'upload_date': u'20101213',
+        'url': 'http://dotsub.com/view/aed3b8b2-1889-4df5-ae63-ad85f5572f27',
+        'md5': '0914d4d69605090f623b7ac329fea66e',
+        'info_dict': {
+            'id': 'aed3b8b2-1889-4df5-ae63-ad85f5572f27',
+            'ext': 'flv',
+            'title': 'Pyramids of Waste (2010), AKA The Lightbulb Conspiracy - Planned obsolescence documentary',
+            'uploader': '4v4l0n42',
+            'description': 'Pyramids of Waste (2010) also known as "The lightbulb conspiracy" is a documentary about how our economic system based on consumerism  and planned obsolescence is breaking our planet down.\r\n\r\nSolutions to this can be found at:\r\nhttp://robotswillstealyourjob.com\r\nhttp://www.federicopistono.org\r\n\r\nhttp://opensourceecology.org\r\nhttp://thezeitgeistmovement.com',
+            'thumbnail': 'http://dotsub.com/media/aed3b8b2-1889-4df5-ae63-ad85f5572f27/p',
+            'upload_date': '20101213',
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
-        info_url = "https://dotsub.com/api/media/%s/metadata" %(video_id)
-        webpage = self._download_webpage(info_url, video_id)
-        info = json.loads(webpage)
+        video_id = mobj.group('id')
+        info_url = "https://dotsub.com/api/media/%s/metadata" % video_id
+        info = self._download_json(info_url, video_id)
         date = time.gmtime(info['dateCreated']/1000) # The timestamp is in miliseconds
 
-        return [{
-            'id':          video_id,
-            'url':         info['mediaURI'],
-            'ext':         'flv',
-            'title':       info['title'],
-            'thumbnail':   info['screenshotURI'],
+        return {
+            'id': video_id,
+            'url': info['mediaURI'],
+            'ext': 'flv',
+            'title': info['title'],
+            'thumbnail': info['screenshotURI'],
             'description': info['description'],
-            'uploader':    info['user'],
-            'view_count':  info['numberOfViews'],
-            'upload_date': u'%04i%02i%02i' % (date.tm_year, date.tm_mon, date.tm_mday),
-        }]
+            'uploader': info['user'],
+            'view_count': info['numberOfViews'],
+            'upload_date': '%04i%02i%02i' % (date.tm_year, date.tm_mon, date.tm_mday),
+        }

youtube_dl/extractor/dropbox.py

@@ -10,11 +10,12 @@ from .common import InfoExtractor
 class DropboxIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?dropbox[.]com/s/(?P<id>[a-zA-Z0-9]{15})/(?P<title>[^?#]*)'
     _TEST = {
-        'url': 'https://www.dropbox.com/s/mcnzehi9wo55th4/20131219_085616.mp4',
-        'file': 'mcnzehi9wo55th4.mp4',
-        'md5': 'f6d65b1b326e82fd7ab7720bea3dacae',
+        'url': 'https://www.dropbox.com/s/0qr9sai2veej4f8/THE_DOCTOR_GAMES.mp4',
+        'md5': '8ae17c51172fb7f93bdd6a214cc8c896',
         'info_dict': {
-            'title': '20131219_085616'
+            'id': '0qr9sai2veej4f8',
+            'ext': 'mp4',
+            'title': 'THE_DOCTOR_GAMES'
         }
     }
 

youtube_dl/extractor/elpais.py

@@ -0,0 +1,58 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import unified_strdate
+
+
+class ElPaisIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:[^.]+\.)?elpais\.com/.*/(?P<id>[^/#?]+)\.html(?:$|[?#])'
+    IE_DESC = 'El País'
+
+    _TEST = {
+        'url': 'http://blogs.elpais.com/la-voz-de-inaki/2014/02/tiempo-nuevo-recetas-viejas.html',
+        'md5': '98406f301f19562170ec071b83433d55',
+        'info_dict': {
+            'id': 'tiempo-nuevo-recetas-viejas',
+            'ext': 'mp4',
+            'title': 'Tiempo nuevo, recetas viejas',
+            'description': 'De lunes a viernes, a partir de las ocho de la mañana, Iñaki Gabilondo nos cuenta su visión de la actualidad nacional e internacional.',
+            'upload_date': '20140206',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        prefix = self._html_search_regex(
+            r'var url_cache = "([^"]+)";', webpage, 'URL prefix')
+        video_suffix = self._search_regex(
+            r"URLMediaFile = url_cache \+ '([^']+)'", webpage, 'video URL')
+        video_url = prefix + video_suffix
+        thumbnail_suffix = self._search_regex(
+            r"URLMediaStill = url_cache \+ '([^']+)'", webpage, 'thumbnail URL',
+            fatal=False)
+        thumbnail = (
+            None if thumbnail_suffix is None
+            else prefix + thumbnail_suffix)
+        title = self._html_search_regex(
+            '<h2 class="entry-header entry-title.*?>(.*?)</h2>',
+            webpage, 'title')
+        date_str = self._search_regex(
+            r'<p class="date-header date-int updated"\s+title="([^"]+)">',
+            webpage, 'upload date', fatal=False)
+        upload_date = (None if date_str is None else unified_strdate(date_str))
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'description': self._og_search_description(webpage),
+            'thumbnail': thumbnail,
+            'upload_date': upload_date,
+        }

youtube_dl/extractor/escapist.py

@@ -1,9 +1,9 @@
-import json
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_str,
     compat_urllib_parse,
 
     ExtractorError,
@@ -11,70 +11,68 @@ from ..utils import (
 
 
 class EscapistIE(InfoExtractor):
-    _VALID_URL = r'^https?://?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
+    _VALID_URL = r'^https?://?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<id>[0-9]+)-'
     _TEST = {
-        u'url': u'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
-        u'file': u'6618-Breaking-Down-Baldurs-Gate.mp4',
-        u'md5': u'ab3a706c681efca53f0a35f1415cf0d1',
-        u'info_dict': {
-            u"description": u"Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.", 
-            u"uploader": u"the-escapist-presents", 
-            u"title": u"Breaking Down Baldur's Gate"
+        'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
+        'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
+        'info_dict': {
+            'id': '6618',
+            'ext': 'mp4',
+            'description': "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
+            'uploader': 'the-escapist-presents',
+            'title': "Breaking Down Baldur's Gate",
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         showName = mobj.group('showname')
-        videoId = mobj.group('episode')
+        video_id = mobj.group('id')
 
-        self.report_extraction(videoId)
-        webpage = self._download_webpage(url, videoId)
+        self.report_extraction(video_id)
+        webpage = self._download_webpage(url, video_id)
 
         videoDesc = self._html_search_regex(
             r'<meta name="description" content="([^"]*)"',
-            webpage, u'description', fatal=False)
+            webpage, 'description', fatal=False)
 
         playerUrl = self._og_search_video_url(webpage, name=u'player URL')
 
         title = self._html_search_regex(
             r'<meta name="title" content="([^"]*)"',
-            webpage, u'title').split(' : ')[-1]
+            webpage, 'title').split(' : ')[-1]
 
-        configUrl = self._search_regex('config=(.*)$', playerUrl, u'config URL')
+        configUrl = self._search_regex('config=(.*)$', playerUrl, 'config URL')
         configUrl = compat_urllib_parse.unquote(configUrl)
 
         formats = []
 
-        def _add_format(name, cfgurl):
-            configJSON = self._download_webpage(
-                cfgurl, videoId,
-                u'Downloading ' + name + ' configuration',
-                u'Unable to download ' + name + ' configuration')
+        def _add_format(name, cfgurl, quality):
+            config = self._download_json(
+                cfgurl, video_id,
+                'Downloading ' + name + ' configuration',
+                'Unable to download ' + name + ' configuration',
+                transform_source=lambda s: s.replace("'", '"'))
 
-            # Technically, it's JavaScript, not JSON
-            configJSON = configJSON.replace("'", '"')
-
-            try:
-                config = json.loads(configJSON)
-            except (ValueError,) as err:
-                raise ExtractorError(u'Invalid JSON in configuration file: ' + compat_str(err))
             playlist = config['playlist']
             formats.append({
                 'url': playlist[1]['url'],
                 'format_id': name,
+                'quality': quality,
             })
 
-        _add_format(u'normal', configUrl)
+        _add_format('normal', configUrl, quality=0)
         hq_url = (configUrl +
                   ('&hq=1' if '?' in configUrl else configUrl + '?hq=1'))
         try:
-            _add_format(u'hq', hq_url)
+            _add_format('hq', hq_url, quality=1)
         except ExtractorError:
             pass  # That's fine, we'll just use normal quality
 
+        self._sort_formats(formats)
+
         return {
-            'id': videoId,
+            'id': video_id,
             'formats': formats,
             'uploader': showName,
             'title': title,

youtube_dl/extractor/exfm.py

@@ -1,56 +1,58 @@
+from __future__ import unicode_literals
+
 import re
-import json
 
 from .common import InfoExtractor
 
 
 class ExfmIE(InfoExtractor):
-    IE_NAME = u'exfm'
-    IE_DESC = u'ex.fm'
-    _VALID_URL = r'(?:http://)?(?:www\.)?ex\.fm/song/([^/]+)'
-    _SOUNDCLOUD_URL = r'(?:http://)?(?:www\.)?api\.soundcloud\.com/tracks/([^/]+)/stream'
+    IE_NAME = 'exfm'
+    IE_DESC = 'ex.fm'
+    _VALID_URL = r'http://(?:www\.)?ex\.fm/song/(?P<id>[^/]+)'
+    _SOUNDCLOUD_URL = r'http://(?:www\.)?api\.soundcloud\.com/tracks/([^/]+)/stream'
     _TESTS = [
         {
-            u'url': u'http://ex.fm/song/eh359',
-            u'file': u'44216187.mp3',
-            u'md5': u'e45513df5631e6d760970b14cc0c11e7',
-            u'info_dict': {
-                u"title": u"Test House \"Love Is Not Enough\" (Extended Mix) DeadJournalist Exclusive",
-                u"uploader": u"deadjournalist",
-                u'upload_date': u'20120424',
-                u'description': u'Test House \"Love Is Not Enough\" (Extended Mix) DeadJournalist Exclusive',
+            'url': 'http://ex.fm/song/eh359',
+            'md5': 'e45513df5631e6d760970b14cc0c11e7',
+            'info_dict': {
+                'id': '44216187',
+                'ext': 'mp3',
+                'title': 'Test House "Love Is Not Enough" (Extended Mix) DeadJournalist Exclusive',
+                'uploader': 'deadjournalist',
+                'upload_date': '20120424',
+                'description': 'Test House \"Love Is Not Enough\" (Extended Mix) DeadJournalist Exclusive',
             },
-            u'note': u'Soundcloud song',
-            u'skip': u'The site is down too often',
+            'note': 'Soundcloud song',
+            'skip': 'The site is down too often',
         },
         {
-            u'url': u'http://ex.fm/song/wddt8',
-            u'file': u'wddt8.mp3',
-            u'md5': u'966bd70741ac5b8570d8e45bfaed3643',
-            u'info_dict': {
-                u'title': u'Safe and Sound',
-                u'uploader': u'Capital Cities',
+            'url': 'http://ex.fm/song/wddt8',
+            'md5': '966bd70741ac5b8570d8e45bfaed3643',
+            'info_dict': {
+                'id': 'wddt8',
+                'ext': 'mp3',
+                'title': 'Safe and Sound',
+                'uploader': 'Capital Cities',
             },
-            u'skip': u'The site is down too often',
+            'skip': 'The site is down too often',
         },
     ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        song_id = mobj.group(1)
-        info_url = "http://ex.fm/api/v3/song/%s" %(song_id)
-        webpage = self._download_webpage(info_url, song_id)
-        info = json.loads(webpage)
-        song_url = info['song']['url']
+        song_id = mobj.group('id')
+        info_url = "http://ex.fm/api/v3/song/%s" % song_id
+        info = self._download_json(info_url, song_id)['song']
+        song_url = info['url']
         if re.match(self._SOUNDCLOUD_URL, song_url) is not None:
             self.to_screen('Soundcloud song detected')
-            return self.url_result(song_url.replace('/stream',''), 'Soundcloud')
-        return [{
-            'id':          song_id,
-            'url':         song_url,
-            'ext':         'mp3',
-            'title':       info['song']['title'],
-            'thumbnail':   info['song']['image']['large'],
-            'uploader':    info['song']['artist'],
-            'view_count':  info['song']['loved_count'],
-        }]
+            return self.url_result(song_url.replace('/stream', ''), 'Soundcloud')
+        return {
+            'id': song_id,
+            'url': song_url,
+            'ext': 'mp3',
+            'title': info['title'],
+            'thumbnail': info['image']['large'],
+            'uploader': info['artist'],
+            'view_count': info['loved_count'],
+        }

youtube_dl/extractor/firstpost.py

@@ -0,0 +1,38 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class FirstpostIE(InfoExtractor):
+    IE_NAME = 'Firstpost.com'
+    _VALID_URL = r'http://(?:www\.)?firstpost\.com/[^/]+/.*-(?P<id>[0-9]+)\.html'
+
+    _TEST = {
+        'url': 'http://www.firstpost.com/india/india-to-launch-indigenous-aircraft-carrier-monday-1025403.html',
+        'md5': 'ee9114957692f01fb1263ed87039112a',
+        'info_dict': {
+            'id': '1025403',
+            'ext': 'mp4',
+            'title': 'India to launch indigenous aircraft carrier INS Vikrant today',
+            'description': 'Its flight deck is over twice the size of a football field, its power unit can light up the entire Kochi city and the cabling is enough to cover the distance between here to Delhi.',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        video_url = self._html_search_regex(
+            r'<div.*?name="div_video".*?flashvars="([^"]+)">',
+            webpage, 'video URL')
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }

youtube_dl/extractor/firsttv.py

@@ -0,0 +1,60 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class FirstTVIE(InfoExtractor):
+    IE_NAME = 'firsttv'
+    IE_DESC = 'Видеоархив - Первый канал'
+    _VALID_URL = r'http://(?:www\.)?1tv\.ru/videoarchive/(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://www.1tv.ru/videoarchive/73390',
+        'md5': '3de6390cf0cca4a5eae1d1d83895e5ad',
+        'info_dict': {
+            'id': '73390',
+            'ext': 'mp4',
+            'title': 'Олимпийские канатные дороги',
+            'description': 'md5:cc730d2bf4215463e37fff6a1e277b13',
+            'thumbnail': 'http://img1.1tv.ru/imgsize640x360/PR20140210114657.JPG',
+            'duration': 149,
+        },
+        'skip': 'Only works from Russia',
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id, 'Downloading page')
+
+        video_url = self._html_search_regex(
+            r'''(?s)jwplayer\('flashvideoportal_1'\)\.setup\({.*?'file': '([^']+)'.*?}\);''', webpage, 'video URL')
+
+        title = self._html_search_regex(
+            r'<div class="tv_translation">\s*<h1><a href="[^"]+">([^<]*)</a>', webpage, 'title')
+        description = self._html_search_regex(
+            r'<div class="descr">\s*<div>&nbsp;</div>\s*<p>([^<]*)</p></div>', webpage, 'description', fatal=False)
+
+        thumbnail = self._og_search_thumbnail(webpage)
+        duration = self._og_search_property('video:duration', webpage, 'video duration', fatal=False)
+
+        like_count = self._html_search_regex(r'title="Понравилось".*?/></label> \[(\d+)\]',
+            webpage, 'like count', fatal=False)
+        dislike_count = self._html_search_regex(r'title="Не понравилось".*?/></label> \[(\d+)\]',
+            webpage, 'dislike count', fatal=False)
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'thumbnail': thumbnail,
+            'title': title,
+            'description': description,
+            'duration': int_or_none(duration),
+            'like_count': int_or_none(like_count),
+            'dislike_count': int_or_none(dislike_count),
+        }

youtube_dl/extractor/fourtube.py

@@ -0,0 +1,95 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_request,
+    unified_strdate,
+    str_to_int,
+    parse_duration,
+)
+from youtube_dl.utils import clean_html
+
+
+class FourTubeIE(InfoExtractor):
+    IE_NAME = '4tube'
+    _VALID_URL = r'https?://(?:www\.)?4tube\.com/videos/(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://www.4tube.com/videos/209733/hot-babe-holly-michaels-gets-her-ass-stuffed-by-black',
+        'md5': '6516c8ac63b03de06bc8eac14362db4f',
+        'info_dict': {
+            'id': '209733',
+            'ext': 'mp4',
+            'title': 'Hot Babe Holly Michaels gets her ass stuffed by black',
+            'uploader': 'WCP Club',
+            'uploader_id': 'wcp-club',
+            'upload_date': '20131031',
+            'duration': 583,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+
+        video_id = mobj.group('id')
+        webpage_url = 'http://www.4tube.com/videos/' + video_id
+        webpage = self._download_webpage(webpage_url, video_id)
+
+        self.report_extraction(video_id)
+
+        playlist_json = self._html_search_regex(r'var playerConfigPlaylist\s+=\s+([^;]+)', webpage, 'Playlist')
+        media_id = self._search_regex(r'idMedia:\s*(\d+)', playlist_json, 'Media Id')
+        sources = self._search_regex(r'sources:\s*\[([^\]]*)\]', playlist_json, 'Sources').split(',')
+        title = self._search_regex(r'title:\s*"([^"]*)', playlist_json, 'Title')
+        thumbnail_url = self._search_regex(r'image:\s*"([^"]*)', playlist_json, 'Thumbnail', fatal=False)
+
+        uploader_str = self._search_regex(r'<span>Uploaded by</span>(.*?)<span>', webpage, 'uploader', fatal=False)
+        mobj = re.search(r'<a href="/sites/(?P<id>[^"]+)"><strong>(?P<name>[^<]+)</strong></a>', uploader_str)
+        (uploader, uploader_id) = (mobj.group('name'), mobj.group('id')) if mobj else (clean_html(uploader_str), None)
+
+        upload_date = None
+        view_count = None
+        duration = None
+        description = self._html_search_meta('description', webpage, 'description')
+        if description:
+            upload_date = self._search_regex(r'Published Date: (\d{2} [a-zA-Z]{3} \d{4})', description, 'upload date',
+                fatal=False)
+            if upload_date:
+                upload_date = unified_strdate(upload_date)
+            view_count = self._search_regex(r'Views: ([\d,\.]+)', description, 'view count', fatal=False)
+            if view_count:
+                view_count = str_to_int(view_count)
+            duration = parse_duration(self._search_regex(r'Length: (\d+m\d+s)', description, 'duration', fatal=False))
+
+        token_url = "http://tkn.4tube.com/{0}/desktop/{1}".format(media_id, "+".join(sources))
+        headers = {
+                b'Content-Type': b'application/x-www-form-urlencoded',
+                b'Origin': b'http://www.4tube.com',
+                }
+        token_req = compat_urllib_request.Request(token_url, b'{}', headers)
+        tokens = self._download_json(token_req, video_id)
+
+        formats = [{
+            'url': tokens[format]['token'],
+            'format_id': format + 'p',
+            'resolution': format + 'p',
+            'quality': int(format),
+            } for format in sources]
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': thumbnail_url,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'upload_date': upload_date,
+            'view_count': view_count,
+            'duration': duration,
+            'age_limit': 18,
+            'webpage_url': webpage_url,
+        }

youtube_dl/extractor/francetv.py

@@ -1,4 +1,7 @@
 # encoding: utf-8
+
+from __future__ import unicode_literals
+
 import re
 import json
 
@@ -30,7 +33,7 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
 
 
 class PluzzIE(FranceTVBaseInfoExtractor):
-    IE_NAME = u'pluzz.francetv.fr'
+    IE_NAME = 'pluzz.francetv.fr'
     _VALID_URL = r'https?://pluzz\.francetv\.fr/videos/(.*?)\.html'
 
     # Can't use tests, videos expire in 7 days
@@ -44,17 +47,17 @@ class PluzzIE(FranceTVBaseInfoExtractor):
 
 
 class FranceTvInfoIE(FranceTVBaseInfoExtractor):
-    IE_NAME = u'francetvinfo.fr'
+    IE_NAME = 'francetvinfo.fr'
     _VALID_URL = r'https?://www\.francetvinfo\.fr/replay.*/(?P<title>.+)\.html'
 
     _TEST = {
-        u'url': u'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
-        u'file': u'84981923.mp4',
-        u'info_dict': {
-            u'title': u'Soir 3',
+        'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
+        'file': '84981923.mp4',
+        'info_dict': {
+            'title': 'Soir 3',
         },
-        u'params': {
-            u'skip_download': True,
+        'params': {
+            'skip_download': True,
         },
     }
 
@@ -62,13 +65,13 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         page_title = mobj.group('title')
         webpage = self._download_webpage(url, page_title)
-        video_id = self._search_regex(r'id-video=(\d+?)"', webpage, u'video id')
+        video_id = self._search_regex(r'id-video=(\d+?)[@"]', webpage, 'video id')
         return self._extract_video(video_id)
 
 
 class FranceTVIE(FranceTVBaseInfoExtractor):
-    IE_NAME = u'francetv'
-    IE_DESC = u'France 2, 3, 4, 5 and Ô'
+    IE_NAME = 'francetv'
+    IE_DESC = 'France 2, 3, 4, 5 and Ô'
     _VALID_URL = r'''(?x)https?://www\.france[2345o]\.fr/
         (?:
             emissions/.*?/(videos|emissions)/(?P<id>[^/?]+)
@@ -78,73 +81,73 @@ class FranceTVIE(FranceTVBaseInfoExtractor):
     _TESTS = [
         # france2
         {
-            u'url': u'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
-            u'file': u'75540104.mp4',
-            u'info_dict': {
-                u'title': u'13h15, le samedi...',
-                u'description': u'md5:2e5b58ba7a2d3692b35c792be081a03d',
+            'url': 'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
+            'file': '75540104.mp4',
+            'info_dict': {
+                'title': '13h15, le samedi...',
+                'description': 'md5:2e5b58ba7a2d3692b35c792be081a03d',
             },
-            u'params': {
+            'params': {
                 # m3u8 download
-                u'skip_download': True,
+                'skip_download': True,
             },
         },
         # france3
         {
-            u'url': u'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575',
-            u'info_dict': {
-                u'id': u'000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au',
-                u'ext': u'flv',
-                u'title': u'Le scandale du prix des médicaments',
-                u'description': u'md5:1384089fbee2f04fc6c9de025ee2e9ce',
+            'url': 'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575',
+            'info_dict': {
+                'id': '000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au',
+                'ext': 'flv',
+                'title': 'Le scandale du prix des médicaments',
+                'description': 'md5:1384089fbee2f04fc6c9de025ee2e9ce',
             },
-            u'params': {
+            'params': {
                 # rtmp download
-                u'skip_download': True,
+                'skip_download': True,
             },
         },
         # france4
         {
-            u'url': u'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
-            u'info_dict': {
-                u'id': u'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
-                u'ext': u'flv',
-                u'title': u'Hero Corp Making of - Extrait 1',
-                u'description': u'md5:c87d54871b1790679aec1197e73d650a',
+            'url': 'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
+            'info_dict': {
+                'id': 'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
+                'ext': 'flv',
+                'title': 'Hero Corp Making of - Extrait 1',
+                'description': 'md5:c87d54871b1790679aec1197e73d650a',
             },
-            u'params': {
+            'params': {
                 # rtmp download
-                u'skip_download': True,
+                'skip_download': True,
             },
         },
         # france5
         {
-            u'url': u'http://www.france5.fr/emissions/c-a-dire/videos/92837968',
-            u'info_dict': {
-                u'id': u'92837968',
-                u'ext': u'mp4',
-                u'title': u'C à dire ?!',
-                u'description': u'md5:fb1db1cbad784dcce7c7a7bd177c8e2f',
+            'url': 'http://www.france5.fr/emissions/c-a-dire/videos/92837968',
+            'info_dict': {
+                'id': '92837968',
+                'ext': 'mp4',
+                'title': 'C à dire ?!',
+                'description': 'md5:fb1db1cbad784dcce7c7a7bd177c8e2f',
             },
-            u'params': {
+            'params': {
                 # m3u8 download
-                u'skip_download': True,
+                'skip_download': True,
             },
         },
         # franceo
         {
-            u'url': u'http://www.franceo.fr/jt/info-afrique/04-12-2013',
-            u'info_dict': {
-                u'id': u'92327925',
-                u'ext': u'mp4',
-                u'title': u'Infô-Afrique',
-                u'description': u'md5:ebf346da789428841bee0fd2a935ea55',
+            'url': 'http://www.franceo.fr/jt/info-afrique/04-12-2013',
+            'info_dict': {
+                'id': '92327925',
+                'ext': 'mp4',
+                'title': 'Infô-Afrique',
+                'description': 'md5:ebf346da789428841bee0fd2a935ea55',
             },
-            u'params': {
+            'params': {
                 # m3u8 download
-                u'skip_download': True,
+                'skip_download': True,
             },
-            u'skip': u'The id changes frequently',
+            'skip': 'The id changes frequently',
         },
     ]
 
@@ -160,27 +163,28 @@ class FranceTVIE(FranceTVBaseInfoExtractor):
                  '\.fr/\?id-video=([^"/&]+)'),
                 (r'<a class="video" id="ftv_player_(.+?)"'),
             ]
-            video_id = self._html_search_regex(id_res, webpage, u'video ID')
+            video_id = self._html_search_regex(id_res, webpage, 'video ID')
         else:
             video_id = mobj.group('id')
         return self._extract_video(video_id)
 
 
 class GenerationQuoiIE(InfoExtractor):
-    IE_NAME = u'france2.fr:generation-quoi'
+    IE_NAME = 'france2.fr:generation-quoi'
     _VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P<name>.*)(\?|$)'
 
     _TEST = {
-        u'url': u'http://generation-quoi.france2.fr/portrait/garde-a-vous',
-        u'file': u'k7FJX8VBcvvLmX4wA5Q.mp4',
-        u'info_dict': {
-            u'title': u'Génération Quoi - Garde à Vous',
-            u'uploader': u'Génération Quoi',
+        'url': 'http://generation-quoi.france2.fr/portrait/garde-a-vous',
+        'file': 'k7FJX8VBcvvLmX4wA5Q.mp4',
+        'info_dict': {
+            'title': 'Génération Quoi - Garde à Vous',
+            'uploader': 'Génération Quoi',
         },
-        u'params': {
+        'params': {
             # It uses Dailymotion
-            u'skip_download': True,
+            'skip_download': True,
         },
+        'skip': 'Only available from France',
     }
 
     def _real_extract(self, url):
@@ -194,20 +198,20 @@ class GenerationQuoiIE(InfoExtractor):
 
 
 class CultureboxIE(FranceTVBaseInfoExtractor):
-    IE_NAME = u'culturebox.francetvinfo.fr'
+    IE_NAME = 'culturebox.francetvinfo.fr'
     _VALID_URL = r'https?://culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)'
 
     _TEST = {
-        u'url': u'http://culturebox.francetvinfo.fr/einstein-on-the-beach-au-theatre-du-chatelet-146813',
-        u'info_dict': {
-            u'id': u'EV_6785',
-            u'ext': u'mp4',
-            u'title': u'Einstein on the beach au Théâtre du Châtelet',
-            u'description': u'md5:9ce2888b1efefc617b5e58b3f6200eeb',
+        'url': 'http://culturebox.francetvinfo.fr/einstein-on-the-beach-au-theatre-du-chatelet-146813',
+        'info_dict': {
+            'id': 'EV_6785',
+            'ext': 'mp4',
+            'title': 'Einstein on the beach au Théâtre du Châtelet',
+            'description': 'md5:9ce2888b1efefc617b5e58b3f6200eeb',
         },
-        u'params': {
+        'params': {
             # m3u8 download
-            u'skip_download': True,
+            'skip_download': True,
         },
     }
 
@@ -215,5 +219,5 @@ class CultureboxIE(FranceTVBaseInfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         name = mobj.group('name')
         webpage = self._download_webpage(url, name)
-        video_id = self._search_regex(r'"http://videos\.francetv\.fr/video/(.*?)"', webpage, u'video id')
+        video_id = self._search_regex(r'"http://videos\.francetv\.fr/video/(.*?)"', webpage, 'video id')
         return self._extract_video(video_id)

youtube_dl/extractor/freesound.py

@@ -1,18 +1,21 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
-from ..utils import determine_ext
+
 
 class FreesoundIE(InfoExtractor):
-    _VALID_URL = r'(?:https?://)?(?:www\.)?freesound\.org/people/([^/]+)/sounds/(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?freesound\.org/people/([^/]+)/sounds/(?P<id>[^/]+)'
     _TEST = {
-        u'url': u'http://www.freesound.org/people/miklovan/sounds/194503/',
-        u'file': u'194503.mp3',
-        u'md5': u'12280ceb42c81f19a515c745eae07650',
-        u'info_dict': {
-            u"title": u"gulls in the city.wav",
-            u"uploader" : u"miklovan",
-            u'description': u'the sounds of seagulls in the city',
+        'url': 'http://www.freesound.org/people/miklovan/sounds/194503/',
+        'md5': '12280ceb42c81f19a515c745eae07650',
+        'info_dict': {
+            'id': '194503',
+            'ext': 'mp3',
+            'title': 'gulls in the city.wav',
+            'uploader': 'miklovan',
+            'description': 'the sounds of seagulls in the city',
         }
     }
 
@@ -20,17 +23,17 @@ class FreesoundIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         music_id = mobj.group('id')
         webpage = self._download_webpage(url, music_id)
-        title = self._html_search_regex(r'<div id="single_sample_header">.*?<a href="#">(.+?)</a>',
-                                webpage, 'music title', flags=re.DOTALL)
-        music_url = self._og_search_property('audio', webpage, 'music url')
-        description = self._html_search_regex(r'<div id="sound_description">(.*?)</div>',
-                                webpage, 'description', fatal=False, flags=re.DOTALL)
+        title = self._html_search_regex(
+            r'<div id="single_sample_header">.*?<a href="#">(.+?)</a>',
+            webpage, 'music title', flags=re.DOTALL)
+        description = self._html_search_regex(
+            r'<div id="sound_description">(.*?)</div>', webpage, 'description',
+            fatal=False, flags=re.DOTALL)
 
-        return [{
-            'id':       music_id,
-            'title':    title,            
-            'url':      music_url,
+        return {
+            'id': music_id,
+            'title': title,
+            'url': self._og_search_property('audio', webpage, 'music url'),
             'uploader': self._og_search_property('audio:artist', webpage, 'music uploader'),
-            'ext':      determine_ext(music_url),
             'description': description,
-        }]
+        }

youtube_dl/extractor/freespeech.py

@@ -0,0 +1,37 @@
+from __future__ import unicode_literals
+
+import re
+import json
+
+from .common import InfoExtractor
+
+
+class FreespeechIE(InfoExtractor):
+    IE_NAME = 'freespeech.org'
+    _VALID_URL = r'https://www\.freespeech\.org/video/(?P<title>.+)'
+    _TEST = {
+        'add_ie': ['Youtube'],
+        'url': 'https://www.freespeech.org/video/obama-romney-campaign-colorado-ahead-debate-0',
+        'info_dict': {
+            'id': 'poKsVCZ64uU',
+            'ext': 'mp4',
+            'title': 'Obama, Romney Campaign in Colorado Ahead of Debate',
+            'description': 'Obama, Romney Campaign in Colorado Ahead of Debate',
+            'uploader': 'freespeechtv',
+            'uploader_id': 'freespeechtv',
+            'upload_date': '20121002',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        title = mobj.group('title')
+        webpage = self._download_webpage(url, title)
+        info_json = self._search_regex(r'jQuery.extend\(Drupal.settings, ({.*?})\);', webpage, 'info')
+        info = json.loads(info_json)
+
+        return {
+            '_type': 'url',
+            'url': info['jw_player']['basic_video_node_player']['file'],
+            'ie_key': 'Youtube',
+        }

youtube_dl/extractor/funnyordie.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -6,13 +8,16 @@ from .common import InfoExtractor
 class FunnyOrDieIE(InfoExtractor):
     _VALID_URL = r'^(?:https?://)?(?:www\.)?funnyordie\.com/videos/(?P<id>[0-9a-f]+)/.*$'
     _TEST = {
-        u'url': u'http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version',
-        u'file': u'0732f586d7.mp4',
-        u'md5': u'f647e9e90064b53b6e046e75d0241fbd',
-        u'info_dict': {
-            u"description": u"Lyrics changed to match the video. Spoken cameo by Obscurus Lupa (from ThatGuyWithTheGlasses.com). Based on a concept by Dustin McLean (DustFilms.com). Performed, edited, and written by David A. Scott.", 
-            u"title": u"Heart-Shaped Box: Literal Video Version"
-        }
+        'url': 'http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version',
+        'file': '0732f586d7.mp4',
+        'md5': 'f647e9e90064b53b6e046e75d0241fbd',
+        'info_dict': {
+            'description': ('Lyrics changed to match the video. Spoken cameo '
+                'by Obscurus Lupa (from ThatGuyWithTheGlasses.com). Based on a '
+                'concept by Dustin McLean (DustFilms.com). Performed, edited, '
+                'and written by David A. Scott.'),
+            'title': 'Heart-Shaped Box: Literal Video Version',
+        },
     }
 
     def _real_extract(self, url):
@@ -23,13 +28,12 @@ class FunnyOrDieIE(InfoExtractor):
 
         video_url = self._search_regex(
             [r'type="video/mp4" src="(.*?)"', r'src="([^>]*?)" type=\'video/mp4\''],
-            webpage, u'video URL', flags=re.DOTALL)
+            webpage, 'video URL', flags=re.DOTALL)
 
-        info = {
+        return {
             'id': video_id,
             'url': video_url,
             'ext': 'mp4',
             'title': self._og_search_title(webpage),
             'description': self._og_search_description(webpage),
         }
-        return [info]

youtube_dl/extractor/gamespot.py

@@ -28,7 +28,7 @@ class GameSpotIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         page_id = mobj.group('page_id')
         webpage = self._download_webpage(url, page_id)
-        data_video_json = self._search_regex(r'data-video=\'(.*?)\'', webpage, u'data video')
+        data_video_json = self._search_regex(r'data-video=["\'](.*?)["\']', webpage, 'data video')
         data_video = json.loads(unescapeHTML(data_video_json))
 
         # Transform the manifest url to a link to the mp4 files
@@ -36,7 +36,7 @@ class GameSpotIE(InfoExtractor):
         f4m_url = data_video['videoStreams']['f4m_stream']
         f4m_path = compat_urlparse.urlparse(f4m_url).path
         QUALITIES_RE = r'((,\d+)+,?)'
-        qualities = self._search_regex(QUALITIES_RE, f4m_path, u'qualities').strip(',').split(',')
+        qualities = self._search_regex(QUALITIES_RE, f4m_path, 'qualities').strip(',').split(',')
         http_path = f4m_path[1:].split('/', 1)[1]
         http_template = re.sub(QUALITIES_RE, r'%s', http_path)
         http_template = http_template.replace('.csmil/manifest.f4m', '')

youtube_dl/extractor/gametrailers.py

@@ -1,7 +1,5 @@
 from __future__ import unicode_literals
 
-import re
-
 from .mtv import MTVServicesInfoExtractor
 
 
@@ -9,21 +7,13 @@ class GametrailersIE(MTVServicesInfoExtractor):
     _VALID_URL = r'http://www\.gametrailers\.com/(?P<type>videos|reviews|full-episodes)/(?P<id>.*?)/(?P<title>.*)'
     _TEST = {
         'url': 'http://www.gametrailers.com/videos/zbvr8i/mirror-s-edge-2-e3-2013--debut-trailer',
-        'file': '70e9a5d7-cf25-4a10-9104-6f3e7342ae0d.mp4',
         'md5': '4c8e67681a0ea7ec241e8c09b3ea8cf7',
         'info_dict': {
-            'title': 'Mirror\'s Edge 2|E3 2013: Debut Trailer',
+            'id': '70e9a5d7-cf25-4a10-9104-6f3e7342ae0d',
+            'ext': 'mp4',
+            'title': 'E3 2013: Debut Trailer',
             'description': 'Faith is back!  Check out the World Premiere trailer for Mirror\'s Edge 2 straight from the EA Press Conference at E3 2013!',
         },
     }
 
     _FEED_URL = 'http://www.gametrailers.com/feeds/mrss'
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        webpage = self._download_webpage(url, video_id)
-        mgid = self._search_regex([r'data-video="(?P<mgid>mgid:.*?)"',
-                                   r'data-contentId=\'(?P<mgid>mgid:.*?)\''],
-                                  webpage, 'mgid')
-        return self._get_videos_info(mgid)

youtube_dl/extractor/generic.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 
 import os
 import re
+import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from .youtube import YoutubeIE
@@ -12,6 +13,7 @@ from ..utils import (
     compat_urllib_parse,
     compat_urllib_request,
     compat_urlparse,
+    compat_xml_parse_error,
 
     ExtractorError,
     HEADRequest,
@@ -38,18 +40,6 @@ class GenericIE(InfoExtractor):
                 'title': 'R\u00e9gis plante sa Jeep',
             }
         },
-        # embedded vimeo video
-        {
-            'add_ie': ['Vimeo'],
-            'url': 'http://skillsmatter.com/podcast/home/move-semanticsperfect-forwarding-and-rvalue-references',
-            'file': '22444065.mp4',
-            'md5': '2903896e23df39722c33f015af0666e2',
-            'info_dict': {
-                'title': 'ACCU 2011: Move Semantics,Perfect Forwarding, and Rvalue references- Scott Meyers- 13/04/2011',
-                'uploader_id': 'skillsmatter',
-                'uploader': 'Skills Matter',
-            }
-        },
         # bandcamp page with custom domain
         {
             'add_ie': ['Bandcamp'],
@@ -78,6 +68,18 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             },
         },
+        {
+            # https://github.com/rg3/youtube-dl/issues/2253
+            'url': 'http://bcove.me/i6nfkrc3',
+            'file': '3101154703001.mp4',
+            'md5': '0ba9446db037002366bab3b3eb30c88c',
+            'info_dict': {
+                'title': 'Still no power',
+                'uploader': 'thestar.com',
+                'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
+            },
+            'add_ie': ['Brightcove'],
+        },
         # Direct link to a video
         {
             'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
@@ -159,11 +161,41 @@ class GenericIE(InfoExtractor):
             raise ExtractorError('Invalid URL protocol')
         return response
 
+    def _extract_rss(self, url, video_id, doc):
+        playlist_title = doc.find('./channel/title').text
+        playlist_desc_el = doc.find('./channel/description')
+        playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
+
+        entries = [{
+            '_type': 'url',
+            'url': e.find('link').text,
+            'title': e.find('title').text,
+        } for e in doc.findall('./channel/item')]
+
+        return {
+            '_type': 'playlist',
+            'id': url,
+            'title': playlist_title,
+            'description': playlist_desc,
+            'entries': entries,
+        }
+
     def _real_extract(self, url):
         parsed_url = compat_urlparse.urlparse(url)
         if not parsed_url.scheme:
-            self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
-            return self.url_result('http://' + url)
+            default_search = self._downloader.params.get('default_search')
+            if default_search is None:
+                default_search = 'auto'
+
+            if default_search == 'auto':
+                if '/' in url:
+                    self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
+                    return self.url_result('http://' + url)
+                else:
+                    return self.url_result('ytsearch:' + url)
+            else:
+                assert ':' in default_search
+                return self.url_result(default_search + url)
         video_id = os.path.splitext(url.split('/')[-1])[0]
 
         self.to_screen('%s: Requesting header' % video_id)
@@ -208,6 +240,14 @@ class GenericIE(InfoExtractor):
 
         self.report_extraction(video_id)
 
+        # Is it an RSS feed?
+        try:
+            doc = xml.etree.ElementTree.fromstring(webpage.encode('utf-8'))
+            if doc.tag == 'rss':
+                return self._extract_rss(url, video_id, doc)
+        except compat_xml_parse_error:
+            pass
+
         # it's tempting to parse this further, but you would
         # have to take into account all the variations like
         #   Video Title - Site Name
@@ -223,15 +263,25 @@ class GenericIE(InfoExtractor):
             r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
 
         # Look for BrightCove:
-        bc_url = BrightcoveIE._extract_brightcove_url(webpage)
-        if bc_url is not None:
+        bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
+        if bc_urls:
             self.to_screen('Brightcove video detected.')
-            surl = smuggle_url(bc_url, {'Referer': url})
-            return self.url_result(surl, 'Brightcove')
+            entries = [{
+                '_type': 'url',
+                'url': smuggle_url(bc_url, {'Referer': url}),
+                'ie_key': 'Brightcove'
+            } for bc_url in bc_urls]
+
+            return {
+                '_type': 'playlist',
+                'title': video_title,
+                'id': video_id,
+                'entries': entries,
+            }
 
         # Look for embedded (iframe) Vimeo player
         mobj = re.search(
-            r'<iframe[^>]+?src="((?:https?:)?//player.vimeo.com/video/.+?)"', webpage)
+            r'<iframe[^>]+?src="((?:https?:)?//player\.vimeo\.com/video/.+?)"', webpage)
         if mobj:
             player_url = unescapeHTML(mobj.group(1))
             surl = smuggle_url(player_url, {'Referer': url})
@@ -239,7 +289,7 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded (swf embed) Vimeo player
         mobj = re.search(
-            r'<embed[^>]+?src="(https?://(?:www\.)?vimeo.com/moogaloop.swf.+?)"', webpage)
+            r'<embed[^>]+?src="(https?://(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
         if mobj:
             return self.url_result(mobj.group(1), 'Vimeo')
 
@@ -309,7 +359,7 @@ class GenericIE(InfoExtractor):
             return self.url_result(mobj.group(1), 'Aparat')
 
         # Look for MPORA videos
-        mobj = re.search(r'<iframe .*?src="(http://mpora\.com/videos/[^"]+)"', webpage)
+        mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
         if mobj is not None:
             return self.url_result(mobj.group(1), 'Mpora')
 
@@ -321,15 +371,21 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded Facebook player
         mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>https://www.facebook.com/video/embed.+?)\1', webpage)
+            r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'Facebook')
 
+        # Look for embedded Huffington Post player
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'HuffPost')
+
         # Start with something easy: JW Player in SWFObject
         mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
         if mobj is None:
             # Look for gorilla-vid style embedding
-            mobj = re.search(r'(?s)jw_plugins.*?file:\s*["\'](.*?)["\']', webpage)
+            mobj = re.search(r'(?s)(?:jw_plugins|JWPlayerOptions).*?file\s*:\s*["\'](.*?)["\']', webpage)
         if mobj is None:
             # Broaden the search a little bit
             mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)

youtube_dl/extractor/googleplus.py

@@ -1,4 +1,5 @@
 # coding: utf-8
+from __future__ import unicode_literals
 
 import datetime
 import re
@@ -10,32 +11,28 @@ from ..utils import (
 
 
 class GooglePlusIE(InfoExtractor):
-    IE_DESC = u'Google Plus'
-    _VALID_URL = r'(?:https://)?plus\.google\.com/(?:[^/]+/)*?posts/(\w+)'
-    IE_NAME = u'plus.google'
+    IE_DESC = 'Google Plus'
+    _VALID_URL = r'https://plus\.google\.com/(?:[^/]+/)*?posts/(?P<id>\w+)'
+    IE_NAME = 'plus.google'
     _TEST = {
-        u"url": u"https://plus.google.com/u/0/108897254135232129896/posts/ZButuJc6CtH",
-        u"file": u"ZButuJc6CtH.flv",
-        u"info_dict": {
-            u"upload_date": u"20120613",
-            u"uploader": u"井上ヨシマサ",
-            u"title": u"嘆きの天使 降臨"
+        'url': 'https://plus.google.com/u/0/108897254135232129896/posts/ZButuJc6CtH',
+        'info_dict': {
+            'id': 'ZButuJc6CtH',
+            'ext': 'flv',
+            'upload_date': '20120613',
+            'uploader': '井上ヨシマサ',
+            'title': '嘆きの天使 降臨',
         }
     }
 
     def _real_extract(self, url):
         # Extract id from URL
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
 
-        post_url = mobj.group(0)
-        video_id = mobj.group(1)
-
-        video_extension = 'flv'
+        video_id = mobj.group('id')
 
         # Step 1, Retrieve post webpage to extract further information
-        webpage = self._download_webpage(post_url, video_id, u'Downloading entry webpage')
+        webpage = self._download_webpage(url, video_id, 'Downloading entry webpage')
 
         self.report_extraction(video_id)
 
@@ -43,7 +40,7 @@ class GooglePlusIE(InfoExtractor):
         upload_date = self._html_search_regex(
             r'''(?x)<a.+?class="o-U-s\s[^"]+"\s+style="display:\s*none"\s*>
                     ([0-9]{4}-[0-9]{2}-[0-9]{2})</a>''',
-            webpage, u'upload date', fatal=False, flags=re.VERBOSE)
+            webpage, 'upload date', fatal=False, flags=re.VERBOSE)
         if upload_date:
             # Convert timestring to a format suitable for filename
             upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d")
@@ -51,28 +48,27 @@ class GooglePlusIE(InfoExtractor):
 
         # Extract uploader
         uploader = self._html_search_regex(r'rel\="author".*?>(.*?)</a>',
-            webpage, u'uploader', fatal=False)
+            webpage, 'uploader', fatal=False)
 
         # Extract title
         # Get the first line for title
         video_title = self._html_search_regex(r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]',
-            webpage, 'title', default=u'NA')
+            webpage, 'title', default='NA')
 
         # Step 2, Simulate clicking the image box to launch video
         DOMAIN = 'https://plus.google.com/'
         video_page = self._search_regex(r'<a href="((?:%s)?photos/.*?)"' % re.escape(DOMAIN),
-            webpage, u'video page URL')
+            webpage, 'video page URL')
         if not video_page.startswith(DOMAIN):
             video_page = DOMAIN + video_page
 
-        webpage = self._download_webpage(video_page, video_id, u'Downloading video page')
+        webpage = self._download_webpage(video_page, video_id, 'Downloading video page')
 
-        # Extract video links on video page
-        """Extract video links of all sizes"""
+        # Extract video links all sizes
         pattern = r'\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"'
         mobj = re.findall(pattern, webpage)
         if len(mobj) == 0:
-            raise ExtractorError(u'Unable to extract video links')
+            raise ExtractorError('Unable to extract video links')
 
         # Sort in resolution
         links = sorted(mobj)
@@ -87,12 +83,11 @@ class GooglePlusIE(InfoExtractor):
         except AttributeError: # Python 3
             video_url = bytes(video_url, 'ascii').decode('unicode-escape')
 
-
-        return [{
-            'id':       video_id,
-            'url':      video_url,
+        return {
+            'id': video_id,
+            'url': video_url,
             'uploader': uploader,
-            'upload_date':  upload_date,
-            'title':    video_title,
-            'ext':      video_extension,
-        }]
+            'upload_date': upload_date,
+            'title': video_title,
+            'ext': 'flv',
+        }

youtube_dl/extractor/googlesearch.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import itertools
 import re
 
@@ -8,32 +10,42 @@ from ..utils import (
 
 
 class GoogleSearchIE(SearchInfoExtractor):
-    IE_DESC = u'Google Video search'
-    _MORE_PAGES_INDICATOR = r'id="pnnext" class="pn"'
+    IE_DESC = 'Google Video search'
     _MAX_RESULTS = 1000
-    IE_NAME = u'video.google:search'
+    IE_NAME = 'video.google:search'
     _SEARCH_KEY = 'gvsearch'
 
     def _get_n_results(self, query, n):
         """Get a specified number of results for a query"""
 
+        entries = []
         res = {
             '_type': 'playlist',
             'id': query,
-            'entries': []
+            'title': query,
         }
 
-        for pagenum in itertools.count(1):
-            result_url = u'http://www.google.com/search?tbm=vid&q=%s&start=%s&hl=en' % (compat_urllib_parse.quote_plus(query), pagenum*10)
-            webpage = self._download_webpage(result_url, u'gvsearch:' + query,
-                                             note='Downloading result page ' + str(pagenum))
+        for pagenum in itertools.count():
+            result_url = (
+                'http://www.google.com/search?tbm=vid&q=%s&start=%s&hl=en'
+                % (compat_urllib_parse.quote_plus(query), pagenum * 10))
 
-            for mobj in re.finditer(r'<h3 class="r"><a href="([^"]+)"', webpage):
-                e = {
+            webpage = self._download_webpage(
+                result_url, 'gvsearch:' + query,
+                note='Downloading result page ' + str(pagenum + 1))
+
+            for hit_idx, mobj in enumerate(re.finditer(
+                    r'<h3 class="r"><a href="([^"]+)"', webpage)):
+
+                # Skip playlists
+                if not re.search(r'id="vidthumb%d"' % (hit_idx + 1), webpage):
+                    continue
+
+                entries.append({
                     '_type': 'url',
                     'url': mobj.group(1)
-                }
-                res['entries'].append(e)
+                })
 
-            if (pagenum * 10 > n) or not re.search(self._MORE_PAGES_INDICATOR, webpage):
+            if (len(entries) >= n) or not re.search(r'class="pn" id="pnnext"', webpage):
+                res['entries'] = entries[:n]
                 return res

youtube_dl/extractor/helsinki.py

@@ -0,0 +1,62 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class HelsinkiIE(InfoExtractor):
+    IE_DESC = 'helsinki.fi'
+    _VALID_URL = r'https?://video\.helsinki\.fi/Arkisto/flash\.php\?id=(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://video.helsinki.fi/Arkisto/flash.php?id=20258',
+        'info_dict': {
+            'id': '20258',
+            'ext': 'mp4',
+            'title': 'Tietotekniikkafoorumi-iltapäivä',
+            'description': 'md5:f5c904224d43c133225130fe156a5ee0',
+        },
+        'params': {
+            'skip_download': True,  # RTMP
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id)
+        formats = []
+
+        mobj = re.search(r'file=((\w+):[^&]+)', webpage)
+        if mobj:
+            formats.append({
+                'ext': mobj.group(2),
+                'play_path': mobj.group(1),
+                'url': 'rtmp://flashvideo.it.helsinki.fi/vod/',
+                'player_url': 'http://video.helsinki.fi/player.swf',
+                'format_note': 'sd',
+                'quality': 0,
+            })
+
+        mobj = re.search(r'hd\.file=((\w+):[^&]+)', webpage)
+        if mobj:
+            formats.append({
+                'ext': mobj.group(2),
+                'play_path': mobj.group(1),
+                'url': 'rtmp://flashvideo.it.helsinki.fi/vod/',
+                'player_url': 'http://video.helsinki.fi/player.swf',
+                'format_note': 'hd',
+                'quality': 1,
+            })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': self._og_search_title(webpage).replace('Video: ', ''),
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'formats': formats,
+        }

youtube_dl/extractor/hotnewhiphop.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 
 class HotNewHipHopIE(InfoExtractor):
-    _VALID_URL = r'http://www\.hotnewhiphop.com/.*\.(?P<id>.*)\.html'
+    _VALID_URL = r'http://www\.hotnewhiphop\.com/.*\.(?P<id>.*)\.html'
     _TEST = {
         'url': 'http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html',
         'file': '1435540.mp3',

youtube_dl/extractor/howcast.py

@@ -1,17 +1,20 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 
 
 class HowcastIE(InfoExtractor):
-    _VALID_URL = r'(?:https?://)?(?:www\.)?howcast\.com/videos/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?howcast\.com/videos/(?P<id>\d+)'
     _TEST = {
-        u'url': u'http://www.howcast.com/videos/390161-How-to-Tie-a-Square-Knot-Properly',
-        u'file': u'390161.mp4',
-        u'md5': u'8b743df908c42f60cf6496586c7f12c3',
-        u'info_dict': {
-            u"description": u"The square knot, also known as the reef knot, is one of the oldest, most basic knots to tie, and can be used in many different ways. Here's the proper way to tie a square knot.", 
-            u"title": u"How to Tie a Square Knot Properly"
+        'url': 'http://www.howcast.com/videos/390161-How-to-Tie-a-Square-Knot-Properly',
+        'md5': '8b743df908c42f60cf6496586c7f12c3',
+        'info_dict': {
+            'id': '390161',
+            'ext': 'mp4',
+            'description': 'The square knot, also known as the reef knot, is one of the oldest, most basic knots to tie, and can be used in many different ways. Here\'s the proper way to tie a square knot.', 
+            'title': 'How to Tie a Square Knot Properly',
         }
     }
 
@@ -24,22 +27,15 @@ class HowcastIE(InfoExtractor):
         self.report_extraction(video_id)
 
         video_url = self._search_regex(r'\'?file\'?: "(http://mobile-media\.howcast\.com/[0-9]+\.mp4)',
-            webpage, u'video URL')
-
-        video_title = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') property=\'og:title\'',
-            webpage, u'title')
+            webpage, 'video URL')
 
         video_description = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') name=\'description\'',
-            webpage, u'description', fatal=False)
+            webpage, 'description', fatal=False)
 
-        thumbnail = self._html_search_regex(r'<meta content=\'(.+?)\' property=\'og:image\'',
-            webpage, u'thumbnail', fatal=False)
-
-        return [{
-            'id':       video_id,
-            'url':      video_url,
-            'ext':      'mp4',
-            'title':    video_title,
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': self._og_search_title(webpage),
             'description': video_description,
-            'thumbnail': thumbnail,
-        }]
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }

youtube_dl/extractor/huffpost.py

@@ -0,0 +1,82 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    unified_strdate,
+)
+
+
+class HuffPostIE(InfoExtractor):
+    IE_DESC = 'Huffington Post'
+    _VALID_URL = r'''(?x)
+        https?://(embed\.)?live\.huffingtonpost\.com/
+        (?:
+            r/segment/[^/]+/|
+            HPLEmbedPlayer/\?segmentId=
+        )
+        (?P<id>[0-9a-f]+)'''
+
+    _TEST = {
+        'url': 'http://live.huffingtonpost.com/r/segment/legalese-it/52dd3e4b02a7602131000677',
+        'file': '52dd3e4b02a7602131000677.mp4',
+        'md5': '55f5e8981c1c80a64706a44b74833de8',
+        'info_dict': {
+            'title': 'Legalese It! with @MikeSacksHP',
+            'description': 'This week on Legalese It, Mike talks to David Bosco about his new book on the ICC, "Rough Justice," he also discusses the Virginia AG\'s historic stance on gay marriage, the execution of Edgar Tamayo, the ICC\'s delay of Kenya\'s President and more.  ',
+            'duration': 1549,
+            'upload_date': '20140124',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        api_url = 'http://embed.live.huffingtonpost.com/api/segments/%s.json' % video_id
+        data = self._download_json(api_url, video_id)['data']
+
+        video_title = data['title']
+        duration = parse_duration(data['running_time'])
+        upload_date = unified_strdate(data['schedule']['starts_at'])
+        description = data.get('description')
+
+        thumbnails = []
+        for url in data['images'].values():
+            m = re.match('.*-([0-9]+x[0-9]+)\.', url)
+            if not m:
+                continue
+            thumbnails.append({
+                'url': url,
+                'resolution': m.group(1),
+            })
+
+        formats = [{
+            'format': key,
+            'format_id': key.replace('/', '.'),
+            'ext': 'mp4',
+            'url': url,
+            'vcodec': 'none' if key.startswith('audio/') else None,
+        } for key, url in data['sources']['live'].items()]
+        if data.get('fivemin_id'):
+            fid = data['fivemin_id']
+            fcat = str(int(fid) // 100 + 1)
+            furl = 'http://avideos.5min.com/2/' + fcat[-3:] + '/' + fcat + '/' + fid + '.mp4'
+            formats.append({
+                'format': 'fivemin',
+                'url': furl,
+                'preference': 1,
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': video_title,
+            'description': description,
+            'formats': formats,
+            'duration': duration,
+            'upload_date': upload_date,
+            'thumbnails': thumbnails,
+        }

youtube_dl/extractor/imdb.py

@@ -67,23 +67,13 @@ class ImdbListIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         list_id = mobj.group('id')
-        
-        # RSS XML is sometimes malformed
-        rss = self._download_webpage('http://rss.imdb.com/list/%s' % list_id, list_id, 'Downloading list RSS')
-        list_title = self._html_search_regex(r'<title>(.*?)</title>', rss, 'list title')
-        
-        # Export is independent of actual author_id, but returns 404 if no author_id is provided.
-        # However, passing dummy author_id seems to be enough.
-        csv = self._download_webpage('http://www.imdb.com/list/export?list_id=%s&author_id=ur00000000' % list_id,
-                                     list_id, 'Downloading list CSV')
-        
-        entries = []
-        for item in csv.split('\n')[1:]:
-            cols = item.split(',')
-            if len(cols) < 2:
-                continue
-            item_id = cols[1][1:-1]
-            if item_id.startswith('vi'):
-                entries.append(self.url_result('http://www.imdb.com/video/imdb/%s' % item_id, 'Imdb'))
-        
+
+        webpage = self._download_webpage(url, list_id)
+        entries = [
+            self.url_result('http://www.imdb.com' + m, 'Imdb')
+            for m in re.findall(r'href="(/video/imdb/vi[^"]+)"\s+data-type="playlist"', webpage)]
+
+        list_title = self._html_search_regex(
+            r'<h1 class="header">(.*?)</h1>', webpage, 'list title')
+
         return self.playlist_result(entries, list_id, list_title)

youtube_dl/extractor/ina.py

@@ -1,39 +1,36 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 
 
 class InaIE(InfoExtractor):
-    """Information Extractor for Ina.fr"""
-    _VALID_URL = r'(?:http://)?(?:www\.)?ina\.fr/video/(?P<id>I?[A-F0-9]+)/.*'
+    _VALID_URL = r'http://(?:www\.)?ina\.fr/video/(?P<id>I?[A-Z0-9]+)'
     _TEST = {
-        u'url': u'http://www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html',
-        u'file': u'I12055569.mp4',
-        u'md5': u'a667021bf2b41f8dc6049479d9bb38a3',
-        u'info_dict': {
-            u"title": u"Fran\u00e7ois Hollande \"Je crois que c'est clair\""
+        'url': 'http://www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html',
+        'md5': 'a667021bf2b41f8dc6049479d9bb38a3',
+        'info_dict': {
+            'id': 'I12055569',
+            'ext': 'mp4',
+            'title': 'François Hollande "Je crois que c\'est clair"',
         }
     }
 
-    def _real_extract(self,url):
+    def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
 
         video_id = mobj.group('id')
-        mrss_url='http://player.ina.fr/notices/%s.mrss' % video_id
-        video_extension = 'mp4'
-        webpage = self._download_webpage(mrss_url, video_id)
+        mrss_url = 'http://player.ina.fr/notices/%s.mrss' % video_id
+        info_doc = self._download_xml(mrss_url, video_id)
 
         self.report_extraction(video_id)
 
-        video_url = self._html_search_regex(r'<media:player url="(?P<mp4url>http://mp4.ina.fr/[^"]+\.mp4)',
-            webpage, u'video URL')
+        video_url = info_doc.find('.//{http://search.yahoo.com/mrss/}player').attrib['url']
 
-        video_title = self._search_regex(r'<title><!\[CDATA\[(?P<titre>.*?)]]></title>',
-            webpage, u'title')
-
-        return [{
-            'id':       video_id,
-            'url':      video_url,
-            'ext':      video_extension,
-            'title':    video_title,
-        }]
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': info_doc.find('.//title').text,
+        }

youtube_dl/extractor/infoq.py

@@ -1,62 +1,55 @@
+from __future__ import unicode_literals
+
 import base64
 import re
 
 from .common import InfoExtractor
 from ..utils import (
     compat_urllib_parse,
-
-    ExtractorError,
 )
 
 
 class InfoQIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$'
+    _VALID_URL = r'https?://(?:www\.)?infoq\.com/[^/]+/(?P<id>[^/]+)$'
     _TEST = {
-        u"name": u"InfoQ",
-        u"url": u"http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things",
-        u"file": u"12-jan-pythonthings.mp4",
-        u"info_dict": {
-            u"description": u"Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.",
-            u"title": u"A Few of My Favorite [Python] Things"
+        "name": "InfoQ",
+        "url": "http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things",
+        "file": "12-jan-pythonthings.mp4",
+        "info_dict": {
+            "description": "Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.",
+            "title": "A Few of My Favorite [Python] Things",
+        },
+        "params": {
+            "skip_download": True,
         },
-        u"params": {
-            u"skip_download": True
-        }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
 
-        webpage = self._download_webpage(url, video_id=url)
-        self.report_extraction(url)
+        webpage = self._download_webpage(url, video_id)
 
         # Extract video URL
-        mobj = re.search(r"jsclassref ?= ?'([^']*)'", webpage)
-        if mobj is None:
-            raise ExtractorError(u'Unable to extract video url')
-        real_id = compat_urllib_parse.unquote(base64.b64decode(mobj.group(1).encode('ascii')).decode('utf-8'))
+        encoded_id = self._search_regex(r"jsclassref ?= ?'([^']*)'", webpage, 'encoded id')
+        real_id = compat_urllib_parse.unquote(base64.b64decode(encoded_id.encode('ascii')).decode('utf-8'))
         video_url = 'rtmpe://video.infoq.com/cfx/st/' + real_id
 
         # Extract title
         video_title = self._search_regex(r'contentTitle = "(.*?)";',
-            webpage, u'title')
+            webpage, 'title')
 
         # Extract description
         video_description = self._html_search_regex(r'<meta name="description" content="(.*)"(?:\s*/)?>',
-            webpage, u'description', fatal=False)
+            webpage, 'description', fatal=False)
 
         video_filename = video_url.split('/')[-1]
         video_id, extension = video_filename.split('.')
 
-        info = {
+        return {
             'id': video_id,
             'url': video_url,
-            'uploader': None,
-            'upload_date': None,
             'title': video_title,
-            'ext': extension, # Extension is always(?) mp4, but seems to be flv
-            'thumbnail': None,
+            'ext': extension,  # Extension is always(?) mp4, but seems to be flv
             'description': video_description,
         }
-
-        return [info]

youtube_dl/extractor/instagram.py

@@ -1,35 +1,39 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 
+
 class InstagramIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?instagram\.com/p/(.*?)/'
+    _VALID_URL = r'http://instagram\.com/p/(?P<id>.*?)/'
     _TEST = {
-        u'url': u'http://instagram.com/p/aye83DjauH/?foo=bar#abc',
-        u'file': u'aye83DjauH.mp4',
-        u'md5': u'0d2da106a9d2631273e192b372806516',
-        u'info_dict': {
-            u"uploader_id": u"naomipq", 
-            u"title": u"Video by naomipq",
-            u'description': u'md5:1f17f0ab29bd6fe2bfad705f58de3cb8',
+        'url': 'http://instagram.com/p/aye83DjauH/?foo=bar#abc',
+        'md5': '0d2da106a9d2631273e192b372806516',
+        'info_dict': {
+            'id': 'aye83DjauH',
+            'ext': 'mp4',
+            'uploader_id': 'naomipq',
+            'title': 'Video by naomipq',
+            'description': 'md5:1f17f0ab29bd6fe2bfad705f58de3cb8',
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
+        video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
         uploader_id = self._search_regex(r'"owner":{"username":"(.+?)"',
-            webpage, u'uploader id', fatal=False)
-        desc = self._search_regex(r'"caption":"(.*?)"', webpage, u'description',
+            webpage, 'uploader id', fatal=False)
+        desc = self._search_regex(r'"caption":"(.*?)"', webpage, 'description',
             fatal=False)
 
-        return [{
-            'id':        video_id,
-            'url':       self._og_search_video_url(webpage, secure=False),
-            'ext':       'mp4',
-            'title':     u'Video by %s' % uploader_id,
+        return {
+            'id': video_id,
+            'url': self._og_search_video_url(webpage, secure=False),
+            'ext': 'mp4',
+            'title': 'Video by %s' % uploader_id,
             'thumbnail': self._og_search_thumbnail(webpage),
-            'uploader_id' : uploader_id,
+            'uploader_id': uploader_id,
             'description': desc,
-        }]
+        }

youtube_dl/extractor/iprima.py

@@ -0,0 +1,85 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import re
+from random import random
+from math import floor
+
+from .common import InfoExtractor
+from ..utils import compat_urllib_request
+
+
+class IPrimaIE(InfoExtractor):
+    _VALID_URL = r'https?://play\.iprima\.cz/(?P<videogroup>.+)/(?P<videoid>.+)'
+
+    _TESTS = [{
+        'url': 'http://play.iprima.cz/particka/particka-92',
+        'info_dict': {
+            'id': '39152',
+            'ext': 'flv',
+            'title': 'Partička (92)',
+            'description': 'md5:3740fda51464da35a2d4d0670b8e4fd6',
+            'thumbnail': 'http://play.iprima.cz/sites/default/files/image_crops/image_620x349/3/491483_particka-92_image_620x349.jpg',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('videoid')
+
+        webpage = self._download_webpage(url, video_id)
+
+        player_url = 'http://embed.livebox.cz/iprimaplay/player-embed-v2.js?__tok%s__=%s' % (
+                         floor(random()*1073741824),
+                         floor(random()*1073741824))
+
+        req = compat_urllib_request.Request(player_url)
+        req.add_header('Referer', url)
+        playerpage = self._download_webpage(req, video_id)
+
+        base_url = ''.join(re.findall(r"embed\['stream'\] = '(.+?)'.+'(\?auth=)'.+'(.+?)';", playerpage)[1])
+
+        zoneGEO = self._html_search_regex(r'"zoneGEO":(.+?),', webpage, 'zoneGEO')
+
+        if zoneGEO != '0':
+            base_url = base_url.replace('token', 'token_'+zoneGEO)
+
+        formats = []
+        for format_id in ['lq', 'hq', 'hd']:
+            filename = self._html_search_regex(r'"%s_id":(.+?),' % format_id, webpage, 'filename')
+
+            if filename == 'null':
+                continue
+
+            real_id = self._search_regex(r'Prima-[0-9]{10}-([0-9]+)_', filename, 'real video id')
+
+            if format_id == 'lq':
+                quality = 0
+            elif format_id == 'hq':
+                quality = 1
+            elif format_id == 'hd':
+                quality = 2
+                filename = 'hq/'+filename
+
+            formats.append({
+                'format_id': format_id,
+                'url': base_url,
+                'quality': quality,
+                'play_path': 'mp4:'+filename.replace('"', '')[:-4],
+                'rtmp_live': True,
+                'ext': 'flv',
+            })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': real_id,
+            'title': self._og_search_title(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'formats': formats,
+            'description': self._og_search_description(webpage),
+        }

youtube_dl/extractor/ivi.py

@@ -1,4 +1,5 @@
 # encoding: utf-8
+from __future__ import unicode_literals
 
 import re
 import json
@@ -11,38 +12,40 @@ from ..utils import (
 
 
 class IviIE(InfoExtractor):
-    IE_DESC = u'ivi.ru'
-    IE_NAME = u'ivi'
-    _VALID_URL = r'^https?://(?:www\.)?ivi\.ru/watch(?:/(?P<compilationid>[^/]+))?/(?P<videoid>\d+)'
+    IE_DESC = 'ivi.ru'
+    IE_NAME = 'ivi'
+    _VALID_URL = r'https?://(?:www\.)?ivi\.ru/watch(?:/(?P<compilationid>[^/]+))?/(?P<videoid>\d+)'
 
     _TESTS = [
         # Single movie
         {
-            u'url': u'http://www.ivi.ru/watch/53141',
-            u'file': u'53141.mp4',
-            u'md5': u'6ff5be2254e796ed346251d117196cf4',
-            u'info_dict': {
-                u'title': u'Иван Васильевич меняет профессию',
-                u'description': u'md5:14d8eda24e9d93d29b5857012c6d6346',
-                u'duration': 5498,
-                u'thumbnail': u'http://thumbs.ivi.ru/f20.vcp.digitalaccess.ru/contents/d/1/c3c885163a082c29bceeb7b5a267a6.jpg',
+            'url': 'http://www.ivi.ru/watch/53141',
+            'md5': '6ff5be2254e796ed346251d117196cf4',
+            'info_dict': {
+                'id': '53141',
+                'ext': 'mp4',
+                'title': 'Иван Васильевич меняет профессию',
+                'description': 'md5:b924063ea1677c8fe343d8a72ac2195f',
+                'duration': 5498,
+                'thumbnail': 'http://thumbs.ivi.ru/f20.vcp.digitalaccess.ru/contents/d/1/c3c885163a082c29bceeb7b5a267a6.jpg',
             },
-            u'skip': u'Only works from Russia',
+            'skip': 'Only works from Russia',
         },
         # Serial's serie
         {
-            u'url': u'http://www.ivi.ru/watch/dezhurnyi_angel/74791',
-            u'file': u'74791.mp4',
-            u'md5': u'3e6cc9a848c1d2ebcc6476444967baa9',
-            u'info_dict': {
-                u'title': u'Дежурный ангел - 1 серия',
-                u'duration': 2490,
-                u'thumbnail': u'http://thumbs.ivi.ru/f7.vcp.digitalaccess.ru/contents/8/e/bc2f6c2b6e5d291152fdd32c059141.jpg',
+            'url': 'http://www.ivi.ru/watch/dezhurnyi_angel/74791',
+            'md5': '3e6cc9a848c1d2ebcc6476444967baa9',
+            'info_dict': {
+                'id': '74791',
+                'ext': 'mp4',
+                'title': 'Дежурный ангел - 1 серия',
+                'duration': 2490,
+                'thumbnail': 'http://thumbs.ivi.ru/f7.vcp.digitalaccess.ru/contents/8/e/bc2f6c2b6e5d291152fdd32c059141.jpg',
             },
-            u'skip': u'Only works from Russia',
+            'skip': 'Only works from Russia',
          }
     ]
-    
+
     # Sorted by quality
     _known_formats = ['MP4-low-mobile', 'MP4-mobile', 'FLV-lo', 'MP4-lo', 'FLV-hi', 'MP4-hi', 'MP4-SHQ']
 
@@ -54,7 +57,7 @@ class IviIE(InfoExtractor):
         return m.group('description') if m is not None else None
 
     def _extract_comment_count(self, html):
-        m = re.search(u'(?s)<a href="#" id="view-comments" class="action-button dim gradient">\s*Комментарии:\s*(?P<commentcount>\d+)\s*</a>', html)
+        m = re.search('(?s)<a href="#" id="view-comments" class="action-button dim gradient">\s*Комментарии:\s*(?P<commentcount>\d+)\s*</a>', html)
         return int(m.group('commentcount')) if m is not None else 0
 
     def _real_extract(self, url):
@@ -63,49 +66,49 @@ class IviIE(InfoExtractor):
 
         api_url = 'http://api.digitalaccess.ru/api/json/'
 
-        data = {u'method': u'da.content.get',
-                u'params': [video_id, {u'site': u's183',
-                                       u'referrer': u'http://www.ivi.ru/watch/%s' % video_id,
-                                       u'contentid': video_id
-                                    }
-                            ]
+        data = {'method': 'da.content.get',
+                'params': [video_id, {'site': 's183',
+                                      'referrer': 'http://www.ivi.ru/watch/%s' % video_id,
+                                      'contentid': video_id
+                                      }
+                           ]
                 }
 
         request = compat_urllib_request.Request(api_url, json.dumps(data))
 
-        video_json_page = self._download_webpage(request, video_id, u'Downloading video JSON')
+        video_json_page = self._download_webpage(request, video_id, 'Downloading video JSON')
         video_json = json.loads(video_json_page)
 
-        if u'error' in video_json:
-            error = video_json[u'error']
-            if error[u'origin'] == u'NoRedisValidData':
-                raise ExtractorError(u'Video %s does not exist' % video_id, expected=True)
-            raise ExtractorError(u'Unable to download video %s: %s' % (video_id, error[u'message']), expected=True)
+        if 'error' in video_json:
+            error = video_json['error']
+            if error['origin'] == 'NoRedisValidData':
+                raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+            raise ExtractorError('Unable to download video %s: %s' % (video_id, error['message']), expected=True)
 
-        result = video_json[u'result']
+        result = video_json['result']
 
         formats = [{
-            'url': x[u'url'],
-            'format_id': x[u'content_format'],
-            'preference': self._known_formats.index(x[u'content_format']),
-        } for x in result[u'files'] if x[u'content_format'] in self._known_formats]
+            'url': x['url'],
+            'format_id': x['content_format'],
+            'preference': self._known_formats.index(x['content_format']),
+        } for x in result['files'] if x['content_format'] in self._known_formats]
 
         self._sort_formats(formats)
 
         if not formats:
-            raise ExtractorError(u'No media links available for %s' % video_id)
+            raise ExtractorError('No media links available for %s' % video_id)
 
-        duration = result[u'duration']
-        compilation = result[u'compilation']
-        title = result[u'title']
+        duration = result['duration']
+        compilation = result['compilation']
+        title = result['title']
 
         title = '%s - %s' % (compilation, title) if compilation is not None else title  
 
-        previews = result[u'preview']
+        previews = result['preview']
         previews.sort(key=lambda fmt: self._known_thumbnails.index(fmt['content_format']))
-        thumbnail = previews[-1][u'url'] if len(previews) > 0 else None
+        thumbnail = previews[-1]['url'] if len(previews) > 0 else None
 
-        video_page = self._download_webpage(url, video_id, u'Downloading video page')
+        video_page = self._download_webpage(url, video_id, 'Downloading video page')
         description = self._extract_description(video_page)
         comment_count = self._extract_comment_count(video_page)
 
@@ -121,9 +124,9 @@ class IviIE(InfoExtractor):
 
 
 class IviCompilationIE(InfoExtractor):
-    IE_DESC = u'ivi.ru compilations'
-    IE_NAME = u'ivi:compilation'
-    _VALID_URL = r'^https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P<compilationid>[a-z\d_-]+)(?:/season(?P<seasonid>\d+))?$'
+    IE_DESC = 'ivi.ru compilations'
+    IE_NAME = 'ivi:compilation'
+    _VALID_URL = r'https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P<compilationid>[a-z\d_-]+)(?:/season(?P<seasonid>\d+))?$'
 
     def _extract_entries(self, html, compilation_id):
         return [self.url_result('http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), 'Ivi')
@@ -135,22 +138,23 @@ class IviCompilationIE(InfoExtractor):
         season_id = mobj.group('seasonid')
 
         if season_id is not None: # Season link
-            season_page = self._download_webpage(url, compilation_id, u'Downloading season %s web page' % season_id)
+            season_page = self._download_webpage(url, compilation_id, 'Downloading season %s web page' % season_id)
             playlist_id = '%s/season%s' % (compilation_id, season_id)
-            playlist_title = self._html_search_meta(u'title', season_page, u'title')
+            playlist_title = self._html_search_meta('title', season_page, 'title')
             entries = self._extract_entries(season_page, compilation_id)
         else: # Compilation link            
-            compilation_page = self._download_webpage(url, compilation_id, u'Downloading compilation web page')
+            compilation_page = self._download_webpage(url, compilation_id, 'Downloading compilation web page')
             playlist_id = compilation_id
-            playlist_title = self._html_search_meta(u'title', compilation_page, u'title')
+            playlist_title = self._html_search_meta('title', compilation_page, 'title')
             seasons = re.findall(r'<a href="/watch/%s/season(\d+)">[^<]+</a>' % compilation_id, compilation_page)
             if len(seasons) == 0: # No seasons in this compilation
                 entries = self._extract_entries(compilation_page, compilation_id)
             else:
                 entries = []
                 for season_id in seasons:
-                    season_page = self._download_webpage('http://www.ivi.ru/watch/%s/season%s' % (compilation_id, season_id),
-                                                         compilation_id, u'Downloading season %s web page' % season_id)
+                    season_page = self._download_webpage(
+                        'http://www.ivi.ru/watch/%s/season%s' % (compilation_id, season_id),
+                        compilation_id, 'Downloading season %s web page' % season_id)
                     entries.extend(self._extract_entries(season_page, compilation_id))
 
         return self.playlist_result(entries, playlist_id, playlist_title)

youtube_dl/extractor/jadorecettepub.py

@@ -0,0 +1,48 @@
+# coding: utf-8
+
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from .youtube import YoutubeIE
+
+
+class JadoreCettePubIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?jadorecettepub\.com/[0-9]{4}/[0-9]{2}/(?P<id>.*?)\.html'
+
+    _TEST = {
+        'url': 'http://www.jadorecettepub.com/2010/12/star-wars-massacre-par-les-japonais.html',
+        'md5': '401286a06067c70b44076044b66515de',
+        'info_dict': {
+            'id': 'jLMja3tr7a4',
+            'ext': 'mp4',
+            'title': 'La pire utilisation de Star Wars',
+            'description': "Jadorecettepub.com vous a gratifié de plusieurs pubs géniales utilisant Star Wars et Dark Vador plus particulièrement... Mais l'heure est venue de vous proposer une version totalement massacrée, venue du Japon.  Quand les Japonais détruisent l'image de Star Wars pour vendre du thon en boite, ça promet...",
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        title = self._html_search_regex(
+            r'<span style="font-size: x-large;"><b>(.*?)</b></span>',
+            webpage, 'title')
+        description = self._html_search_regex(
+            r'(?s)<div id="fb-root">(.*?)<script>', webpage, 'description',
+            fatal=False)
+        real_url = self._search_regex(
+            r'\[/postlink\](.*)endofvid', webpage, 'video URL')
+        video_id = YoutubeIE.extract_id(real_url)
+
+        return {
+            '_type': 'url_transparent',
+            'url': real_url,
+            'id': video_id,
+            'title': title,
+            'description': description,
+        }
+

youtube_dl/extractor/jeuxvideo.py

@@ -1,5 +1,7 @@
 # coding: utf-8
 
+from __future__ import unicode_literals
+
 import json
 import re
 
@@ -10,12 +12,13 @@ class JeuxVideoIE(InfoExtractor):
     _VALID_URL = r'http://.*?\.jeuxvideo\.com/.*/(.*?)-\d+\.htm'
 
     _TEST = {
-        u'url': u'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
-        u'file': u'5182.mp4',
-        u'md5': u'046e491afb32a8aaac1f44dd4ddd54ee',
-        u'info_dict': {
-            u'title': u'GC 2013 : Tearaway nous présente ses papiers d\'identité',
-            u'description': u'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.\n',
+        'url': 'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
+        'md5': '046e491afb32a8aaac1f44dd4ddd54ee',
+        'info_dict': {
+            'id': '5182',
+            'ext': 'mp4',
+            'title': 'GC 2013 : Tearaway nous présente ses papiers d\'identité',
+            'description': 'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.\n',
         },
     }
 
@@ -25,14 +28,14 @@ class JeuxVideoIE(InfoExtractor):
         webpage = self._download_webpage(url, title)
         xml_link = self._html_search_regex(
             r'<param name="flashvars" value="config=(.*?)" />',
-            webpage, u'config URL')
+            webpage, 'config URL')
         
         video_id = self._search_regex(
             r'http://www\.jeuxvideo\.com/config/\w+/\d+/(.*?)/\d+_player\.xml',
-            xml_link, u'video ID')
+            xml_link, 'video ID')
 
         config = self._download_xml(
-            xml_link, title, u'Downloading XML config')
+            xml_link, title, 'Downloading XML config')
         info_json = config.find('format.json').text
         info = json.loads(info_json)['versions'][0]
         

youtube_dl/extractor/keek.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -5,36 +7,34 @@ from .common import InfoExtractor
 
 class KeekIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<videoID>\w+)'
-    IE_NAME = u'keek'
+    IE_NAME = 'keek'
     _TEST = {
-        u'url': u'https://www.keek.com/ytdl/keeks/NODfbab',
-        u'file': u'NODfbab.mp4',
-        u'md5': u'9b0636f8c0f7614afa4ea5e4c6e57e83',
-        u'info_dict': {
-            u"uploader": u"ytdl", 
-            u"title": u"test chars: \"'/\\\u00e4<>This is a test video for youtube-dl.For more information, contact phihag@phihag.de ."
-        }
+        'url': 'https://www.keek.com/ytdl/keeks/NODfbab',
+        'file': 'NODfbab.mp4',
+        'md5': '9b0636f8c0f7614afa4ea5e4c6e57e83',
+        'info_dict': {
+            'uploader': 'ytdl',
+            'title': 'test chars: "\'/\\\u00e4<>This is a test video for youtube-dl.For more information, contact phihag@phihag.de .',
+        },
     }
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)
         video_id = m.group('videoID')
 
-        video_url = u'http://cdn.keek.com/keek/video/%s' % video_id
-        thumbnail = u'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id
+        video_url = 'http://cdn.keek.com/keek/video/%s' % video_id
+        thumbnail = 'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id
         webpage = self._download_webpage(url, video_id)
 
-        video_title = self._og_search_title(webpage)
+        uploader = self._html_search_regex(
+            r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>',
+            webpage, 'uploader', fatal=False)
 
-        uploader = self._html_search_regex(r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>',
-            webpage, u'uploader', fatal=False)
-
-        info = {
-                'id': video_id,
-                'url': video_url,
-                'ext': 'mp4',
-                'title': video_title,
-                'thumbnail': thumbnail,
-                'uploader': uploader
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'title': self._og_search_title(webpage),
+            'thumbnail': thumbnail,
+            'uploader': uploader
         }
-        return [info]

youtube_dl/extractor/kontrtube.py

@@ -0,0 +1,66 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class KontrTubeIE(InfoExtractor):
+    IE_NAME = 'kontrtube'
+    IE_DESC = 'KontrTube.ru - Труба зовёт'
+    _VALID_URL = r'http://(?:www\.)?kontrtube\.ru/videos/(?P<id>\d+)/.+'
+
+    _TEST = {
+        'url': 'http://www.kontrtube.ru/videos/2678/nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag/',
+        'md5': '975a991a4926c9a85f383a736a2e6b80',
+        'info_dict': {
+            'id': '2678',
+            'ext': 'mp4',
+            'title': 'Над олимпийской деревней в Сочи поднят российский флаг',
+            'description': 'md5:80edc4c613d5887ae8ccf1d59432be41',
+            'thumbnail': 'http://www.kontrtube.ru/contents/videos_screenshots/2000/2678/preview.mp4.jpg',
+            'duration': 270,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id, 'Downloading page')
+
+        video_url = self._html_search_regex(r"video_url: '(.+?)/?',", webpage, 'video URL')
+        thumbnail = self._html_search_regex(r"preview_url: '(.+?)/?',", webpage, 'video thumbnail', fatal=False)
+        title = self._html_search_regex(r'<title>(.+?) - Труба зовёт - Интересный видеохостинг</title>', webpage,
+            'video title')
+        description = self._html_search_meta('description', webpage, 'video description')
+
+        mobj = re.search(r'<div class="col_2">Длительность: <span>(?P<minutes>\d+)м:(?P<seconds>\d+)с</span></div>',
+            webpage)
+        duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
+
+        view_count = self._html_search_regex(r'<div class="col_2">Просмотров: <span>(\d+)</span></div>', webpage,
+            'view count', fatal=False)
+        view_count = int(view_count) if view_count is not None else None
+
+        comment_count = None
+        comment_str = self._html_search_regex(r'Комментарии: <span>([^<]+)</span>', webpage, 'comment count',
+            fatal=False)
+        if comment_str.startswith('комментариев нет'):
+            comment_count = 0
+        else:
+            mobj = re.search(r'\d+ из (?P<total>\d+) комментариев', comment_str)
+            if mobj:
+                comment_count = int(mobj.group('total'))
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'thumbnail': thumbnail,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'view_count': view_count,
+            'comment_count': comment_count,
+        }

youtube_dl/extractor/la7.py

@@ -0,0 +1,63 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+)
+
+
+class LA7IE(InfoExtractor):
+    IE_NAME = 'la7.tv'
+    _VALID_URL = r'''(?x)
+        https?://(?:www\.)?la7\.tv/
+        (?:
+            richplayer/\?assetid=|
+            \?contentId=
+        )
+        (?P<id>[0-9]+)'''
+
+    _TEST = {
+        'url': 'http://www.la7.tv/richplayer/?assetid=50355319',
+        'file': '50355319.mp4',
+        'md5': 'ec7d1f0224d20ba293ab56cf2259651f',
+        'info_dict': {
+            'title': 'IL DIVO',
+            'description': 'Un film di Paolo Sorrentino con Toni Servillo, Anna Bonaiuto, Giulio Bosetti  e Flavio Bucci',
+            'duration': 6254,
+        },
+        'skip': 'Blocked in the US',
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        xml_url = 'http://www.la7.tv/repliche/content/index.php?contentId=%s' % video_id
+        doc = self._download_xml(xml_url, video_id)
+
+        video_title = doc.find('title').text
+        description = doc.find('description').text
+        duration = parse_duration(doc.find('duration').text)
+        thumbnail = doc.find('img').text
+        view_count = int(doc.find('views').text)
+
+        prefix = doc.find('.//fqdn').text.strip().replace('auto:', 'http:')
+
+        formats = [{
+            'format': vnode.find('quality').text,
+            'tbr': int(vnode.find('quality').text),
+            'url': vnode.find('fms').text.strip().replace('mp4:', prefix),
+        } for vnode in doc.findall('.//videos/video')]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': video_title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+            'view_count': view_count,
+        }

youtube_dl/extractor/lifenews.py

@@ -0,0 +1,69 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    unified_strdate
+)
+
+
+class LifeNewsIE(InfoExtractor):
+    IE_NAME = 'lifenews'
+    IE_DESC = 'LIFE | NEWS'
+    _VALID_URL = r'http://lifenews\.ru/(?:mobile/)?news/(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://lifenews.ru/news/126342',
+        'md5': 'e1b50a5c5fb98a6a544250f2e0db570a',
+        'info_dict': {
+            'id': '126342',
+            'ext': 'mp4',
+            'title': 'МВД разыскивает мужчин, оставивших в IKEA сумку с автоматом',
+            'description': 'Камеры наблюдения гипермаркета зафиксировали троих мужчин, спрятавших оружейный арсенал в камере хранения.',
+            'thumbnail': 'http://lifenews.ru/static/posts/2014/1/126342/.video.jpg',
+            'upload_date': '20140130',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage('http://lifenews.ru/mobile/news/%s' % video_id, video_id, 'Downloading page')
+
+        video_url = self._html_search_regex(
+            r'<video.*?src="([^"]+)".*?></video>', webpage, 'video URL')
+
+        thumbnail = self._html_search_regex(
+            r'<video.*?poster="([^"]+)".*?"></video>', webpage, 'video thumbnail')
+
+        title = self._og_search_title(webpage)
+        TITLE_SUFFIX = ' - Первый по срочным новостям — LIFE | NEWS'
+        if title.endswith(TITLE_SUFFIX):
+            title = title[:-len(TITLE_SUFFIX)]
+
+        description = self._og_search_description(webpage)
+
+        view_count = self._html_search_regex(
+            r'<div class=\'views\'>(\d+)</div>', webpage, 'view count', fatal=False)
+        comment_count = self._html_search_regex(
+            r'<div class=\'comments\'>(\d+)</div>', webpage, 'comment count', fatal=False)
+
+        upload_date = self._html_search_regex(
+            r'<time datetime=\'([^\']+)\'>', webpage, 'upload date',fatal=False)
+        if upload_date is not None:
+            upload_date = unified_strdate(upload_date)
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'thumbnail': thumbnail,
+            'title': title,
+            'description': description,
+            'view_count': int_or_none(view_count),
+            'comment_count': int_or_none(comment_count),
+            'upload_date': upload_date,
+        }

youtube_dl/extractor/liveleak.py

@@ -1,52 +1,98 @@
+from __future__ import unicode_literals
+
+import json
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-)
+from ..utils import int_or_none
 
 
 class LiveLeakIE(InfoExtractor):
-
     _VALID_URL = r'^(?:http://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
-    IE_NAME = u'liveleak'
-    _TEST = {
-        u'url': u'http://www.liveleak.com/view?i=757_1364311680',
-        u'file': u'757_1364311680.mp4',
-        u'md5': u'0813c2430bea7a46bf13acf3406992f4',
-        u'info_dict': {
-            u"description": u"extremely bad day for this guy..!", 
-            u"uploader": u"ljfriel2", 
-            u"title": u"Most unlucky car accident"
+    _TESTS = [{
+        'url': 'http://www.liveleak.com/view?i=757_1364311680',
+        'md5': '0813c2430bea7a46bf13acf3406992f4',
+        'info_dict': {
+            'id': '757_1364311680',
+            'ext': 'mp4',
+            'description': 'extremely bad day for this guy..!',
+            'uploader': 'ljfriel2',
+            'title': 'Most unlucky car accident'
         }
-    }
+    },
+    {
+        'url': 'http://www.liveleak.com/view?i=f93_1390833151',
+        'md5': 'd3f1367d14cc3c15bf24fbfbe04b9abf',
+        'info_dict': {
+            'id': 'f93_1390833151',
+            'ext': 'mp4',
+            'description': 'German Television Channel NDR does an exclusive interview with Edward Snowden.\r\nUploaded on LiveLeak cause German Television thinks the rest of the world isn\'t intereseted in Edward Snowden.',
+            'uploader': 'ARD_Stinkt',
+            'title': 'German Television does first Edward Snowden Interview (ENGLISH)',
+        }
+    },
+    {
+        'url': 'http://www.liveleak.com/view?i=4f7_1392687779',
+        'md5': '42c6d97d54f1db107958760788c5f48f',
+        'info_dict': {
+            'id': '4f7_1392687779',
+            'ext': 'mp4',
+            'description': "The guy with the cigarette seems amazingly nonchalant about the whole thing...  I really hope my friends' reactions would be a bit stronger.\r\n\r\nAction-go to 0:55.",
+            'uploader': 'CapObveus',
+            'title': 'Man is Fatally Struck by Reckless Car While Packing up a Moving Truck',
+            'age_limit': 18,
+        }
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
-
         video_id = mobj.group('video_id')
-
         webpage = self._download_webpage(url, video_id)
 
-        video_url = self._search_regex(r'file: "(.*?)",',
-            webpage, u'video URL')
-
         video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip()
-
         video_description = self._og_search_description(webpage)
+        video_uploader = self._html_search_regex(
+            r'By:.*?(\w+)</a>', webpage, 'uploader', fatal=False)
+        age_limit = int_or_none(self._search_regex(
+            r'you confirm that you are ([0-9]+) years and over.',
+            webpage, 'age limit', default=None))
 
-        video_uploader = self._html_search_regex(r'By:.*?(\w+)</a>',
-            webpage, u'uploader', fatal=False)
+        sources_raw = self._search_regex(
+            r'(?s)sources:\s*(\[.*?\]),', webpage, 'video URLs', default=None)
+        if sources_raw is None:
+            alt_source = self._search_regex(
+                r'(file: ".*?"),', webpage, 'video URL', default=None)
+            if alt_source:
+                sources_raw = '[{ %s}]' % alt_source
+            else:
+                # Maybe an embed?
+                embed_url = self._search_regex(
+                    r'<iframe[^>]+src="(http://www.prochan.com/embed\?[^"]+)"',
+                    webpage, 'embed URL')
+                return {
+                    '_type': 'url_transparent',
+                    'url': embed_url,
+                    'id': video_id,
+                    'title': video_title,
+                    'description': video_description,
+                    'uploader': video_uploader,
+                    'age_limit': age_limit,
+                }
 
-        info = {
-            'id':  video_id,
-            'url': video_url,
-            'ext': 'mp4',
+        sources_json = re.sub(r'\s([a-z]+):\s', r'"\1": ', sources_raw)
+        sources = json.loads(sources_json)
+
+        formats = [{
+            'format_note': s.get('label'),
+            'url': s['file'],
+        } for s in sources]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
             'title': video_title,
             'description': video_description,
-            'uploader': video_uploader
+            'uploader': video_uploader,
+            'formats': formats,
+            'age_limit': age_limit,
         }
-
-        return [info]

youtube_dl/extractor/m6.py

@@ -0,0 +1,56 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class M6IE(InfoExtractor):
+    IE_NAME = 'm6'
+    _VALID_URL = r'http://(?:www\.)?m6\.fr/[^/]+/videos/(?P<id>\d+)-[^\.]+\.html'
+
+    _TEST = {
+        'url': 'http://www.m6.fr/emission-les_reines_du_shopping/videos/11323908-emeline_est_la_reine_du_shopping_sur_le_theme_ma_fete_d_8217_anniversaire.html',
+        'md5': '242994a87de2c316891428e0176bcb77',
+        'info_dict': {
+            'id': '11323908',
+            'ext': 'mp4',
+            'title': 'Emeline est la Reine du Shopping sur le thème « Ma fête d’anniversaire ! »',
+            'description': 'md5:1212ae8fb4b7baa4dc3886c5676007c2',
+            'duration': 100,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        rss = self._download_xml('http://ws.m6.fr/v1/video/info/m6/bonus/%s' % video_id, video_id,
+            'Downloading video RSS')
+
+        title = rss.find('./channel/item/title').text
+        description = rss.find('./channel/item/description').text
+        thumbnail = rss.find('./channel/item/visuel_clip_big').text
+        duration = int(rss.find('./channel/item/duration').text)
+        view_count = int(rss.find('./channel/item/nombre_vues').text)
+
+        formats = []
+        for format_id in ['lq', 'sd', 'hq', 'hd']:
+            video_url = rss.find('./channel/item/url_video_%s' % format_id)
+            if video_url is None:
+                continue
+            formats.append({
+                'url': video_url.text,
+                'format_id': format_id,
+            })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'view_count': view_count,
+            'formats': formats,
+        }

youtube_dl/extractor/malemotion.py

@@ -0,0 +1,59 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+)
+
+class MalemotionIE(InfoExtractor):
+    _VALID_URL = r'^(?:https?://)?malemotion\.com/video/(.+?)\.(?P<id>.+?)(#|$)'
+    _TEST = {
+        'url': 'http://malemotion.com/video/bien-dur.10ew',
+        'file': '10ew.mp4',
+        'md5': 'b3cc49f953b107e4a363cdff07d100ce',
+        'info_dict': {
+            "title": "Bien dur",
+            "age_limit": 18,
+        },
+        'skip': 'This video has been deleted.'
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group("id")
+
+        webpage = self._download_webpage(url, video_id)
+
+        self.report_extraction(video_id)
+
+        # Extract video URL
+        video_url = compat_urllib_parse.unquote(
+            self._search_regex(r'<source type="video/mp4" src="(.+?)"', webpage, 'video URL'))
+
+        # Extract title
+        video_title = self._html_search_regex(
+            r'<title>(.*?)</title', webpage, 'title')
+
+        # Extract video thumbnail
+        video_thumbnail = self._search_regex(
+            r'<video .+?poster="(.+?)"', webpage, 'thumbnail', fatal=False)
+
+        formats = [{
+            'url': video_url,
+            'ext': 'mp4',
+            'format_id': 'mp4',
+            'preference': 1,
+        }]
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'uploader': None,
+            'upload_date': None,
+            'title': video_title,
+            'thumbnail': video_thumbnail,
+            'description': None,
+            'age_limit': 18,
+        }

youtube_dl/extractor/mooshare.py

@@ -0,0 +1,114 @@
+from __future__ import unicode_literals
+
+import re
+import time
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    compat_urllib_request,
+    compat_urllib_parse,
+)
+
+
+class MooshareIE(InfoExtractor):
+    IE_NAME = 'mooshare'
+    IE_DESC = 'Mooshare.biz'
+    _VALID_URL = r'http://mooshare\.biz/(?P<id>[\da-z]{12})'
+
+    _TESTS = [
+        {
+            'url': 'http://mooshare.biz/8dqtk4bjbp8g',
+            'md5': '4e14f9562928aecd2e42c6f341c8feba',
+            'info_dict': {
+                'id': '8dqtk4bjbp8g',
+                'ext': 'mp4',
+                'title': 'Comedy Football 2011 - (part 1-2)',
+                'duration': 893,
+            },
+        },
+        {
+            'url': 'http://mooshare.biz/aipjtoc4g95j',
+            'info_dict': {
+                'id': 'aipjtoc4g95j',
+                'ext': 'mp4',
+                'title': 'Orange Caramel  Dashing Through the Snow',
+                'duration': 212,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            }
+        }
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        page = self._download_webpage(url, video_id, 'Downloading page')
+
+        if re.search(r'>Video Not Found or Deleted<', page) is not None:
+            raise ExtractorError(u'Video %s does not exist' % video_id, expected=True)
+
+        hash_key = self._html_search_regex(r'<input type="hidden" name="hash" value="([^"]+)">', page, 'hash')
+        title = self._html_search_regex(r'(?m)<div class="blockTitle">\s*<h2>Watch ([^<]+)</h2>', page, 'title')
+
+        download_form = {
+            'op': 'download1',
+            'id': video_id,
+            'hash': hash_key,
+        }
+
+        request = compat_urllib_request.Request(
+            'http://mooshare.biz/%s' % video_id, compat_urllib_parse.urlencode(download_form))
+        request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+
+        self.to_screen('%s: Waiting for timeout' % video_id)
+        time.sleep(5)
+
+        video_page = self._download_webpage(request, video_id, 'Downloading video page')
+
+        thumbnail = self._html_search_regex(r'image:\s*"([^"]+)",', video_page, 'thumbnail', fatal=False)
+        duration_str = self._html_search_regex(r'duration:\s*"(\d+)",', video_page, 'duration', fatal=False)
+        duration = int(duration_str) if duration_str is not None else None
+
+        formats = []
+
+        # SD video
+        mobj = re.search(r'(?m)file:\s*"(?P<url>[^"]+)",\s*provider:', video_page)
+        if mobj is not None:
+            formats.append({
+                'url': mobj.group('url'),
+                'format_id': 'sd',
+                'format': 'SD',
+            })
+
+        # HD video
+        mobj = re.search(r'\'hd-2\': { file: \'(?P<url>[^\']+)\' },', video_page)
+        if mobj is not None:
+            formats.append({
+                'url': mobj.group('url'),
+                'format_id': 'hd',
+                'format': 'HD',
+            })
+
+        # rtmp video
+        mobj = re.search(r'(?m)file: "(?P<playpath>[^"]+)",\s*streamer: "(?P<rtmpurl>rtmp://[^"]+)",', video_page)
+        if mobj is not None:
+            formats.append({
+                'url': mobj.group('rtmpurl'),
+                'play_path': mobj.group('playpath'),
+                'rtmp_live': False,
+                'ext': 'mp4',
+                'format_id': 'rtmp',
+                'format': 'HD',
+            })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/mtv.py

@@ -86,9 +86,13 @@ class MTVServicesInfoExtractor(InfoExtractor):
             title_el = itemdoc.find('.//{http://search.yahoo.com/mrss/}title')
         if title_el is None:
             title_el = itemdoc.find('.//title')
+            if title_el.text is None:
+                title_el = None
+
         title = title_el.text
         if title is None:
             raise ExtractorError('Could not find video title')
+        title = title.strip()
 
         return {
             'title': title,
@@ -111,11 +115,16 @@ class MTVServicesInfoExtractor(InfoExtractor):
         title = url_basename(url)
         webpage = self._download_webpage(url, title)
         try:
-            # the url is in the format http://media.mtvnservices.com/fb/{mgid}.swf
-            fb_url = self._og_search_video_url(webpage)
-            mgid = url_basename(fb_url).rpartition('.')[0]
+            # the url can be http://media.mtvnservices.com/fb/{mgid}.swf
+            # or http://media.mtvnservices.com/{mgid}
+            og_url = self._og_search_video_url(webpage)
+            mgid = url_basename(og_url)
+            if mgid.endswith('.swf'):
+                mgid = mgid[:-4]
         except RegexNotFoundError:
-            mgid = self._search_regex(r'data-mgid="(.*?)"', webpage, u'mgid')
+            mgid = self._search_regex(
+                [r'data-mgid="(.*?)"', r'swfobject.embedSWF\(".*?(mgid:.*?)"'],
+                webpage, u'mgid')
         return self._get_videos_info(mgid)
 
 

youtube_dl/extractor/myspass.py

@@ -1,3 +1,4 @@
+from __future__ import unicode_literals
 import os.path
 
 from .common import InfoExtractor
@@ -11,13 +12,13 @@ from ..utils import (
 class MySpassIE(InfoExtractor):
     _VALID_URL = r'http://www\.myspass\.de/.*'
     _TEST = {
-        u'url': u'http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/',
-        u'file': u'11741.mp4',
-        u'md5': u'0b49f4844a068f8b33f4b7c88405862b',
-        u'info_dict': {
-            u"description": u"Wer kann in die Fu\u00dfstapfen von Wolfgang Kubicki treten und die Mehrheit der Zuschauer hinter sich versammeln? Wird vielleicht sogar die Absolute Mehrheit geknackt und der Jackpot von 200.000 Euro mit nach Hause genommen?", 
-            u"title": u"Absolute Mehrheit vom 17.02.2013 - Die Highlights, Teil 2"
-        }
+        'url': 'http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/',
+        'file': '11741.mp4',
+        'md5': '0b49f4844a068f8b33f4b7c88405862b',
+        'info_dict': {
+            "description": "Wer kann in die Fu\u00dfstapfen von Wolfgang Kubicki treten und die Mehrheit der Zuschauer hinter sich versammeln? Wird vielleicht sogar die Absolute Mehrheit geknackt und der Jackpot von 200.000 Euro mit nach Hause genommen?",
+            "title": "Absolute Mehrheit vom 17.02.2013 - Die Highlights, Teil 2",
+        },
     }
 
     def _real_extract(self, url):
@@ -37,12 +38,11 @@ class MySpassIE(InfoExtractor):
         # extract values from metadata
         url_flv_el = metadata.find('url_flv')
         if url_flv_el is None:
-            raise ExtractorError(u'Unable to extract download url')
+            raise ExtractorError('Unable to extract download url')
         video_url = url_flv_el.text
-        extension = os.path.splitext(video_url)[1][1:]
         title_el = metadata.find('title')
         if title_el is None:
-            raise ExtractorError(u'Unable to extract title')
+            raise ExtractorError('Unable to extract title')
         title = title_el.text
         format_id_el = metadata.find('format_id')
         if format_id_el is None:
@@ -59,13 +59,12 @@ class MySpassIE(InfoExtractor):
             thumbnail = imagePreview_el.text
         else:
             thumbnail = None
-        info = {
+
+        return {
             'id': video_id,
             'url': video_url,
             'title': title,
-            'ext': extension,
             'format': format,
             'thumbnail': thumbnail,
-            'description': description
+            'description': description,
         }
-        return [info]

youtube_dl/extractor/nba.py

@@ -1,48 +1,39 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-)
 
 
 class NBAIE(InfoExtractor):
     _VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*?)(?:/index\.html)?(?:\?.*)?$'
     _TEST = {
-        u'url': u'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html',
-        u'file': u'0021200253-okc-bkn-recap.nba.mp4',
-        u'md5': u'c0edcfc37607344e2ff8f13c378c88a4',
-        u'info_dict': {
-            u"description": u"Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.", 
-            u"title": u"Thunder vs. Nets"
-        }
+        'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html',
+        'file': u'0021200253-okc-bkn-recap.nba.mp4',
+        'md5': u'c0edcfc37607344e2ff8f13c378c88a4',
+        'info_dict': {
+            'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.',
+            'title': 'Thunder vs. Nets',
+        },
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
-
         video_id = mobj.group(1)
 
         webpage = self._download_webpage(url, video_id)
 
-        video_url = u'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
+        video_url = 'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
 
         shortened_video_id = video_id.rpartition('/')[2]
         title = self._og_search_title(webpage, default=shortened_video_id).replace('NBA.com: ', '')
 
-        # It isn't there in the HTML it returns to us
-        # uploader_date = self._html_search_regex(r'<b>Date:</b> (.*?)</div>', webpage, 'upload_date', fatal=False)
-
         description = self._html_search_regex(r'<meta name="description" (?:content|value)="(.*?)" />', webpage, 'description', fatal=False)
 
-        info = {
+        return {
             'id': shortened_video_id,
             'url': video_url,
             'ext': 'mp4',
             'title': title,
-            # 'uploader_date': uploader_date,
             'description': description,
         }
-        return [info]

youtube_dl/extractor/ndr.py

@@ -0,0 +1,89 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class NDRIE(InfoExtractor):
+    IE_NAME = 'ndr'
+    IE_DESC = 'NDR.de - Mediathek'
+    _VALID_URL = r'https?://www\.ndr\.de/.+?(?P<id>\d+)\.html'
+
+    _TESTS = [
+        {
+            'url': 'http://www.ndr.de/fernsehen/sendungen/markt/markt7959.html',
+            'md5': 'e7a6079ca39d3568f4996cb858dd6708',
+            'note': 'Video file',
+            'info_dict': {
+                'id': '7959',
+                'ext': 'mp4',
+                'title': 'Markt - die ganze Sendung',
+                'description': 'md5:af9179cf07f67c5c12dc6d9997e05725',
+                'duration': 2655,
+            },
+        },
+        {
+            'url': 'http://www.ndr.de/info/audio51535.html',
+            'md5': 'bb3cd38e24fbcc866d13b50ca59307b8',
+            'note': 'Audio file',
+            'info_dict': {
+                'id': '51535',
+                'ext': 'mp3',
+                'title': 'La Valette entgeht der Hinrichtung',
+                'description': 'md5:22f9541913a40fe50091d5cdd7c9f536',
+                'duration': 884,
+            }
+        }
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        page = self._download_webpage(url, video_id, 'Downloading page')
+
+        title = self._og_search_title(page)
+        description = self._og_search_description(page)
+
+        mobj = re.search(
+            r'<div class="duration"><span class="min">(?P<minutes>\d+)</span>:<span class="sec">(?P<seconds>\d+)</span></div>',
+            page)
+        duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
+
+        formats = []
+
+        mp3_url = re.search(r'''{src:'(?P<audio>[^']+)', type:"audio/mp3"},''', page)
+        if mp3_url:
+            formats.append({
+                'url': mp3_url.group('audio'),
+                'format_id': 'mp3',
+            })
+
+        thumbnail = None
+
+        video_url = re.search(r'''3: {src:'(?P<video>.+?)\.hi\.mp4', type:"video/mp4"},''', page)
+        if video_url:
+            thumbnail = self._html_search_regex(r'(?m)title: "NDR PLAYER",\s*poster: "([^"]+)",',
+                page, 'thumbnail', fatal=False)
+            if thumbnail:
+                thumbnail = 'http://www.ndr.de' + thumbnail
+            for format_id in ['lo', 'hi', 'hq']:
+                formats.append({
+                    'url': '%s.%s.mp4' % (video_url.group('video'), format_id),
+                    'format_id': format_id,
+                })
+
+        if not formats:
+            raise ExtractorError('No media links available for %s' % video_id)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/newgrounds.py

@@ -1,19 +1,21 @@
+from __future__ import unicode_literals
+
 import json
 import re
 
 from .common import InfoExtractor
-from ..utils import determine_ext
 
 
 class NewgroundsIE(InfoExtractor):
-    _VALID_URL = r'(?:https?://)?(?:www\.)?newgrounds\.com/audio/listen/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/audio/listen/(?P<id>[0-9]+)'
     _TEST = {
-        u'url': u'http://www.newgrounds.com/audio/listen/549479',
-        u'file': u'549479.mp3',
-        u'md5': u'fe6033d297591288fa1c1f780386f07a',
-        u'info_dict': {
-            u"title": u"B7 - BusMode",
-            u"uploader": u"Burn7",
+        'url': 'http://www.newgrounds.com/audio/listen/549479',
+        'md5': 'fe6033d297591288fa1c1f780386f07a',
+        'info_dict': {
+            'id': '549479',
+            'ext': 'mp3',
+            'title': 'B7 - BusMode',
+            'uploader': 'Burn7',
         }
     }
 
@@ -22,17 +24,19 @@ class NewgroundsIE(InfoExtractor):
         music_id = mobj.group('id')
         webpage = self._download_webpage(url, music_id)
         
-        title = self._html_search_regex(r',"name":"([^"]+)",', webpage, u'music title')
-        uploader = self._html_search_regex(r',"artist":"([^"]+)",', webpage, u'music uploader')
+        title = self._html_search_regex(
+            r',"name":"([^"]+)",', webpage, 'music title')
+        uploader = self._html_search_regex(
+            r',"artist":"([^"]+)",', webpage, 'music uploader')
         
-        music_url_json_string = self._html_search_regex(r'({"url":"[^"]+"),', webpage, u'music url') + '}'
+        music_url_json_string = self._html_search_regex(
+            r'({"url":"[^"]+"),', webpage, 'music url') + '}'
         music_url_json = json.loads(music_url_json_string)
         music_url = music_url_json['url']
 
         return {
-            'id':       music_id,
-            'title':    title,
-            'url':      music_url,
+            'id': music_id,
+            'title': title,
+            'url': music_url,
             'uploader': uploader,
-            'ext':      determine_ext(music_url),
         }

youtube_dl/extractor/nfb.py

@@ -0,0 +1,94 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_request,
+    compat_urllib_parse,
+)
+
+
+class NFBIE(InfoExtractor):
+    IE_NAME = 'nfb'
+    IE_DESC = 'National Film Board of Canada'
+    _VALID_URL = r'https?://(?:www\.)?(nfb|onf)\.ca/film/(?P<id>[\da-z_-]+)'
+
+    _TEST = {
+        'url': 'https://www.nfb.ca/film/qallunaat_why_white_people_are_funny',
+        'info_dict': {
+            'id': 'qallunaat_why_white_people_are_funny',
+            'ext': 'mp4',
+            'title': 'Qallunaat! Why White People Are Funny ',
+            'description': 'md5:836d8aff55e087d04d9f6df554d4e038',
+            'duration': 3128,
+            'uploader': 'Mark Sandiford',
+            'uploader_id': 'mark-sandiford',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        page = self._download_webpage('https://www.nfb.ca/film/%s' % video_id, video_id, 'Downloading film page')
+
+        uploader_id = self._html_search_regex(r'<a class="director-link" href="/explore-all-directors/([^/]+)/"',
+            page, 'director id', fatal=False)
+        uploader = self._html_search_regex(r'<em class="director-name" itemprop="name">([^<]+)</em>',
+            page, 'director name', fatal=False)
+
+        request = compat_urllib_request.Request('https://www.nfb.ca/film/%s/player_config' % video_id,
+            compat_urllib_parse.urlencode({'getConfig': 'true'}).encode('ascii'))
+        request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+        request.add_header('X-NFB-Referer', 'http://www.nfb.ca/medias/flash/NFBVideoPlayer.swf')
+
+        config = self._download_xml(request, video_id, 'Downloading player config XML')
+
+        title = None
+        description = None
+        thumbnail = None
+        duration = None
+        formats = []
+
+        def extract_thumbnail(media):
+            thumbnails = {}
+            for asset in media.findall('assets/asset'):
+                thumbnails[asset.get('quality')] = asset.find('default/url').text
+            if not thumbnails:
+                return None
+            if 'high' in thumbnails:
+                return thumbnails['high']
+            return list(thumbnails.values())[0]
+
+        for media in config.findall('./player/stream/media'):
+            if media.get('type') == 'posterImage':
+                thumbnail = extract_thumbnail(media)
+            elif media.get('type') == 'video':
+                duration = int(media.get('duration'))
+                title = media.find('title').text
+                description = media.find('description').text
+                # It seems assets always go from lower to better quality, so no need to sort
+                formats = [{
+                    'url': x.find('default/streamerURI').text,
+                    'app': x.find('default/streamerURI').text.split('/', 3)[3],
+                    'play_path': x.find('default/url').text,
+                    'rtmp_live': False,
+                    'ext': 'mp4',
+                    'format_id': x.get('quality'),
+                } for x in media.findall('assets/asset')]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'formats': formats,
+        }

youtube_dl/extractor/ninegag.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import json
 import re
 
@@ -9,13 +11,13 @@ class NineGagIE(InfoExtractor):
     _VALID_URL = r'^https?://(?:www\.)?9gag\.tv/v/(?P<id>[0-9]+)'
 
     _TEST = {
-        u"url": u"http://9gag.tv/v/1912",
-        u"file": u"1912.mp4",
-        u"info_dict": {
-            u"description": u"This 3-minute video will make you smile and then make you feel untalented and insignificant. Anyway, you should share this awesomeness. (Thanks, Dino!)",
-            u"title": u"\"People Are Awesome 2013\" Is Absolutely Awesome"
+        "url": "http://9gag.tv/v/1912",
+        "file": "1912.mp4",
+        "info_dict": {
+            "description": "This 3-minute video will make you smile and then make you feel untalented and insignificant. Anyway, you should share this awesomeness. (Thanks, Dino!)",
+            "title": "\"People Are Awesome 2013\" Is Absolutely Awesome"
         },
-        u'add_ie': [u'Youtube']
+        'add_ie': ['Youtube']
     }
 
     def _real_extract(self, url):
@@ -25,7 +27,7 @@ class NineGagIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
         data_json = self._html_search_regex(r'''(?x)
             <div\s*id="tv-video"\s*data-video-source="youtube"\s*
-                data-video-meta="([^"]+)"''', webpage, u'video metadata')
+                data-video-meta="([^"]+)"''', webpage, 'video metadata')
 
         data = json.loads(data_json)
 

youtube_dl/extractor/normalboots.py

@@ -0,0 +1,61 @@
+import re
+
+from .common import InfoExtractor
+
+from ..utils import (
+    ExtractorError,
+    unified_strdate,
+)
+
+class NormalbootsIE(InfoExtractor):
+    _VALID_URL = r'(?:http://)?(?:www\.)?normalboots\.com/video/(?P<videoid>[0-9a-z-]*)/?$'
+    _TEST = {
+        u'url': u'http://normalboots.com/video/home-alone-games-jontron/',
+        u'file': u'home-alone-games-jontron.mp4',
+        u'md5': u'8bf6de238915dd501105b44ef5f1e0f6',
+        u'info_dict': {
+            u'title': u'Home Alone Games - JonTron - NormalBoots',
+            u'description': u'Jon is late for Christmas. Typical. Thanks to: Paul Ritchey for Co-Writing/Filming: http://www.youtube.com/user/ContinueShow Michael Azzi for Christmas Intro Animation: http://michafrar.tumblr.com/ Jerrod Waters for Christmas Intro Music: http://www.youtube.com/user/xXJerryTerryXx Casey Ormond for \u2018Tense Battle Theme\u2019:\xa0http://www.youtube.com/Kiamet/',
+            u'uploader': u'JonTron',
+            u'upload_date': u'20140125',
+        }
+    }
+    
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        if mobj is None:
+            raise ExtractorError(u'Invalid URL: %s' % url)
+        video_id = mobj.group('videoid')
+        
+        info = {
+            'id': video_id,
+            'uploader': None,
+            'upload_date': None,
+        }
+        
+        if url[:4] != 'http':
+            url = 'http://' + url
+        
+        webpage = self._download_webpage(url, video_id)
+        video_title = self._og_search_title(webpage)
+        video_description = self._og_search_description(webpage)
+        video_thumbnail = self._og_search_thumbnail(webpage)
+        video_uploader = self._html_search_regex(r'Posted\sby\s<a\shref="[A-Za-z0-9/]*">(?P<uploader>[A-Za-z]*)\s</a>',
+            webpage, 'uploader')
+        raw_upload_date = self._html_search_regex('<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>', 
+            webpage, 'date')
+        video_upload_date = unified_strdate(raw_upload_date)
+        video_upload_date = unified_strdate(raw_upload_date)
+            
+        player_url = self._html_search_regex(r'<iframe\swidth="[0-9]+"\sheight="[0-9]+"\ssrc="(?P<url>[\S]+)"', webpage, 'url')
+        player_page = self._download_webpage(player_url, video_id)
+        video_url = u'http://player.screenwavemedia.com/' + self._html_search_regex(r"'file':\s'(?P<file>[0-9A-Za-z-_\.]+)'", player_page, 'file')
+        
+        info['url'] = video_url
+        info['title'] = video_title
+        info['description'] = video_description
+        info['thumbnail'] = video_thumbnail
+        info['uploader'] = video_uploader
+        info['upload_date'] = video_upload_date
+        
+        return info

youtube_dl/extractor/novamov.py

@@ -19,7 +19,8 @@ class NovamovIE(InfoExtractor):
         'info_dict': {
             'title': 'search engine optimization',
             'description': 'search engine optimization is used to rank the web page in the google search engine'
-        }
+        },
+        'skip': '"Invalid token" errors abound (in web interface as well as youtube-dl, there is nothing we can do about it.)'
     }
 
     def _real_extract(self, url):

youtube_dl/extractor/nowness.py

@@ -0,0 +1,49 @@
+from __future__ import unicode_literals
+
+import re
+
+from .brightcove import BrightcoveIE
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+)
+
+
+class NownessIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?nowness\.com/[^?#]*?/(?P<id>[0-9]+)/(?P<slug>[^/]+?)(?:$|[?#])'
+
+    _TEST = {
+        'url': 'http://www.nowness.com/day/2013/6/27/3131/candor--the-art-of-gesticulation',
+        'file': '2520295746001.mp4',
+        'md5': '0ece2f70a7bd252c7b00f3070182d418',
+        'info_dict': {
+            'description': 'Candor: The Art of Gesticulation',
+            'uploader': 'Nowness',
+            'title': 'Candor: The Art of Gesticulation',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('slug')
+
+        webpage = self._download_webpage(url, video_id)
+        player_url = self._search_regex(
+            r'"([^"]+/content/issue-[0-9.]+.js)"', webpage, 'player URL')
+        real_id = self._search_regex(
+            r'\sdata-videoId="([0-9]+)"', webpage, 'internal video ID')
+
+        player_code = self._download_webpage(
+            player_url, video_id,
+            note='Downloading player JavaScript',
+            errnote='Player download failed')
+        player_code = player_code.replace("'+d+'", real_id)
+
+        bc_url = BrightcoveIE._extract_brightcove_url(player_code)
+        if bc_url is None:
+            raise ExtractorError('Could not find player definition')
+        return {
+            '_type': 'url',
+            'url': bc_url,
+            'ie_key': 'Brightcove',
+        }

youtube_dl/extractor/ooyala.py

@@ -5,7 +5,7 @@ from .common import InfoExtractor
 from ..utils import unescapeHTML
 
 class OoyalaIE(InfoExtractor):
-    _VALID_URL = r'https?://.+?\.ooyala\.com/.*?embedCode=(?P<id>.+?)(&|$)'
+    _VALID_URL = r'https?://.+?\.ooyala\.com/.*?(?:embedCode|ec)=(?P<id>.+?)(&|$)'
 
     _TEST = {
         # From http://it.slashdot.org/story/13/04/25/178216/recovering-data-from-broken-hard-drives-and-ssds-video

youtube_dl/extractor/pbs.py

@@ -1,34 +1,68 @@
+from __future__ import unicode_literals
+
 import re
-import json
 
 from .common import InfoExtractor
 
 
 class PBSIE(InfoExtractor):
-    _VALID_URL = r'https?://video\.pbs\.org/video/(?P<id>\d+)/?'
+    _VALID_URL = r'''(?x)https?://
+        (?:
+            # Direct video URL
+            video\.pbs\.org/(?:viralplayer|video)/(?P<id>[0-9]+)/? |
+            # Article with embedded player
+           (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P<presumptive_id>[^/]+)/?(?:$|[?\#]) |
+           # Player
+           video\.pbs\.org/partnerplayer/(?P<player_id>[^/]+)/
+        )
+    '''
 
     _TEST = {
-        u'url': u'http://video.pbs.org/video/2365006249/',
-        u'file': u'2365006249.mp4',
-        u'md5': 'ce1888486f0908d555a8093cac9a7362',
-        u'info_dict': {
-            u'title': u'A More Perfect Union',
-            u'description': u'md5:ba0c207295339c8d6eced00b7c363c6a',
-            u'duration': 3190,
+        'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/',
+        'md5': 'ce1888486f0908d555a8093cac9a7362',
+        'info_dict': {
+            'id': '2365006249',
+            'ext': 'mp4',
+            'title': 'A More Perfect Union',
+            'description': 'md5:ba0c207295339c8d6eced00b7c363c6a',
+            'duration': 3190,
         },
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+
+        presumptive_id = mobj.group('presumptive_id')
+        display_id = presumptive_id
+        if presumptive_id:
+            webpage = self._download_webpage(url, display_id)
+            url = self._search_regex(
+                r'<iframe\s+id=["\']partnerPlayer["\'].*?\s+src=["\'](.*?)["\']>',
+                webpage, 'player URL')
+            mobj = re.match(self._VALID_URL, url)
+
+        player_id = mobj.group('player_id')
+        if not display_id:
+            display_id = player_id
+        if player_id:
+            player_page = self._download_webpage(
+                url, display_id, note='Downloading player page',
+                errnote='Could not download player page')
+            video_id = self._search_regex(
+                r'<div\s+id="video_([0-9]+)"', player_page, 'video ID')
+        else:
+            video_id = mobj.group('id')
+            display_id = video_id
+
         info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id
-        info_page = self._download_webpage(info_url, video_id)
-        info =json.loads(info_page)
-        return {'id': video_id,
-                'title': info['title'],
-                'url': info['alternate_encoding']['url'],
-                'ext': 'mp4',
-                'description': info['program'].get('description'),
-                'thumbnail': info.get('image_url'),
-                'duration': info.get('duration'),
-                }
+        info = self._download_json(info_url, display_id)
+
+        return {
+            'id': video_id,
+            'title': info['title'],
+            'url': info['alternate_encoding']['url'],
+            'ext': 'mp4',
+            'description': info['program'].get('description'),
+            'thumbnail': info.get('image_url'),
+            'duration': info.get('duration'),
+        }

youtube_dl/extractor/pornhd.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -7,12 +9,12 @@ from ..utils import compat_urllib_parse
 class PornHdIE(InfoExtractor):
     _VALID_URL = r'(?:http://)?(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<video_id>[0-9]+)/(?P<video_title>.+)'
     _TEST = {
-        u'url': u'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
-        u'file': u'1962.flv',
-        u'md5': u'35272469887dca97abd30abecc6cdf75',
-        u'info_dict': {
-            u"title": u"sierra-day-gets-his-cum-all-over-herself-hd-porn-video",
-            u"age_limit": 18,
+        'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
+        'file': '1962.flv',
+        'md5': '35272469887dca97abd30abecc6cdf75',
+        'info_dict': {
+            "title": "sierra-day-gets-his-cum-all-over-herself-hd-porn-video",
+            "age_limit": 18,
         }
     }
 
@@ -24,9 +26,13 @@ class PornHdIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
-        video_url = self._html_search_regex(
-            r'&hd=(http.+?)&', webpage, u'video URL')
-        video_url = compat_urllib_parse.unquote(video_url)
+        next_url = self._html_search_regex(
+            r'&hd=(http.+?)&', webpage, 'video URL')
+        next_url = compat_urllib_parse.unquote(next_url)
+
+        video_url = self._download_webpage(
+            next_url, video_id, note='Retrieving video URL',
+            errnote='Could not retrieve video URL')
         age_limit = 18
 
         return {

youtube_dl/extractor/rbmaradio.py

@@ -1,10 +1,11 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
 import json
 import re
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_urllib_parse_urlparse,
-
     ExtractorError,
 )
 
@@ -12,16 +13,17 @@ from ..utils import (
 class RBMARadioIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P<videoID>[^/]+)$'
     _TEST = {
-        u'url': u'http://www.rbmaradio.com/shows/ford-lopatin-live-at-primavera-sound-2011',
-        u'file': u'ford-lopatin-live-at-primavera-sound-2011.mp3',
-        u'md5': u'6bc6f9bcb18994b4c983bc3bf4384d95',
-        u'info_dict': {
-            u"uploader_id": u"ford-lopatin", 
-            u"location": u"Spain", 
-            u"description": u"Joel Ford and Daniel \u2019Oneohtrix Point Never\u2019 Lopatin fly their midified pop extravaganza to Spain. Live at Primavera Sound 2011.", 
-            u"uploader": u"Ford & Lopatin", 
-            u"title": u"Live at Primavera Sound 2011"
-        }
+        'url': 'http://www.rbmaradio.com/shows/ford-lopatin-live-at-primavera-sound-2011',
+        'md5': '6bc6f9bcb18994b4c983bc3bf4384d95',
+        'info_dict': {
+            'id': 'ford-lopatin-live-at-primavera-sound-2011',
+            'ext': 'mp3',
+            "uploader_id": "ford-lopatin",
+            "location": "Spain",
+            "description": "Joel Ford and Daniel ’Oneohtrix Point Never’ Lopatin fly their midified pop extravaganza to Spain. Live at Primavera Sound 2011.",
+            "uploader": "Ford & Lopatin",
+            "title": "Live at Primavera Sound 2011",
+        },
     }
 
     def _real_extract(self, url):
@@ -31,26 +33,23 @@ class RBMARadioIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         json_data = self._search_regex(r'window\.gon.*?gon\.show=(.+?);$',
-            webpage, u'json data', flags=re.MULTILINE)
+            webpage, 'json data', flags=re.MULTILINE)
 
         try:
             data = json.loads(json_data)
         except ValueError as e:
-            raise ExtractorError(u'Invalid JSON: ' + str(e))
+            raise ExtractorError('Invalid JSON: ' + str(e))
 
         video_url = data['akamai_url'] + '&cbr=256'
-        url_parts = compat_urllib_parse_urlparse(video_url)
-        video_ext = url_parts.path.rpartition('.')[2]
-        info = {
-                'id': video_id,
-                'url': video_url,
-                'ext': video_ext,
-                'title': data['title'],
-                'description': data.get('teaser_text'),
-                'location': data.get('country_of_origin'),
-                'uploader': data.get('host', {}).get('name'),
-                'uploader_id': data.get('host', {}).get('slug'),
-                'thumbnail': data.get('image', {}).get('large_url_2x'),
-                'duration': data.get('duration'),
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': data['title'],
+            'description': data.get('teaser_text'),
+            'location': data.get('country_of_origin'),
+            'uploader': data.get('host', {}).get('name'),
+            'uploader_id': data.get('host', {}).get('slug'),
+            'thumbnail': data.get('image', {}).get('large_url_2x'),
+            'duration': data.get('duration'),
         }
-        return [info]

youtube_dl/extractor/ro220.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -11,12 +13,12 @@ class Ro220IE(InfoExtractor):
     IE_NAME = '220.ro'
     _VALID_URL = r'(?x)(?:https?://)?(?:www\.)?220\.ro/(?P<category>[^/]+)/(?P<shorttitle>[^/]+)/(?P<video_id>[^/]+)'
     _TEST = {
-        u"url": u"http://www.220.ro/sport/Luati-Le-Banii-Sez-4-Ep-1/LYV6doKo7f/",
-        u'file': u'LYV6doKo7f.mp4',
-        u'md5': u'03af18b73a07b4088753930db7a34add',
-        u'info_dict': {
-            u"title": u"Luati-le Banii sez 4 ep 1",
-            u"description": u"Iata-ne reveniti dupa o binemeritata vacanta. Va astept si pe Facebook cu pareri si comentarii.",
+        "url": "http://www.220.ro/sport/Luati-Le-Banii-Sez-4-Ep-1/LYV6doKo7f/",
+        'file': 'LYV6doKo7f.mp4',
+        'md5': '03af18b73a07b4088753930db7a34add',
+        'info_dict': {
+            "title": "Luati-le Banii sez 4 ep 1",
+            "description": "Iata-ne reveniti dupa o binemeritata vacanta. Va astept si pe Facebook cu pareri si comentarii.",
         }
     }
 
@@ -27,10 +29,10 @@ class Ro220IE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
         flashVars_str = self._search_regex(
             r'<param name="flashVars" value="([^"]+)"',
-            webpage, u'flashVars')
+            webpage, 'flashVars')
         flashVars = compat_parse_qs(flashVars_str)
 
-        info = {
+        return {
             '_type': 'video',
             'id': video_id,
             'ext': 'mp4',
@@ -39,4 +41,3 @@ class Ro220IE(InfoExtractor):
             'description': clean_html(flashVars['desc'][0]),
             'thumbnail': flashVars['preview'][0],
         }
-        return info

youtube_dl/extractor/rottentomatoes.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 from .videodetective import VideoDetectiveIE
 
 
@@ -7,10 +9,10 @@ class RottenTomatoesIE(VideoDetectiveIE):
     _VALID_URL = r'https?://www\.rottentomatoes\.com/m/[^/]+/trailers/(?P<id>\d+)'
 
     _TEST = {
-        u'url': u'http://www.rottentomatoes.com/m/toy_story_3/trailers/11028566/',
-        u'file': '613340.mp4',
-        u'info_dict': {
-            u'title': u'TOY STORY 3',
-            u'description': u'From the creators of the beloved TOY STORY films, comes a story that will reunite the gang in a whole new way.',
+        'url': 'http://www.rottentomatoes.com/m/toy_story_3/trailers/11028566/',
+        'file': '613340.mp4',
+        'info_dict': {
+            'title': 'TOY STORY 3',
+            'description': 'From the creators of the beloved TOY STORY films, comes a story that will reunite the gang in a whole new way.',
         },
     }

youtube_dl/extractor/rtlnow.py

@@ -1,4 +1,7 @@
 # encoding: utf-8
+
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -12,78 +15,77 @@ class RTLnowIE(InfoExtractor):
     """Information Extractor for RTL NOW, RTL2 NOW, RTL NITRO, SUPER RTL NOW, VOX NOW and n-tv NOW"""
     _VALID_URL = r'(?:http://)?(?P<url>(?P<domain>rtl-now\.rtl\.de|rtl2now\.rtl2\.de|(?:www\.)?voxnow\.de|(?:www\.)?rtlnitronow\.de|(?:www\.)?superrtlnow\.de|(?:www\.)?n-tvnow\.de)/+[a-zA-Z0-9-]+/[a-zA-Z0-9-]+\.php\?(?:container_id|film_id)=(?P<video_id>[0-9]+)&player=1(?:&season=[0-9]+)?(?:&.*)?)'
     _TESTS = [{
-        u'url': u'http://rtl-now.rtl.de/ahornallee/folge-1.php?film_id=90419&player=1&season=1',
-        u'file': u'90419.flv',
-        u'info_dict': {
-            u'upload_date': u'20070416',
-            u'title': u'Ahornallee - Folge 1 - Der Einzug',
-            u'description': u'Folge 1 - Der Einzug',
+        'url': 'http://rtl-now.rtl.de/ahornallee/folge-1.php?film_id=90419&player=1&season=1',
+        'file': '90419.flv',
+        'info_dict': {
+            'upload_date': '20070416',
+            'title': 'Ahornallee - Folge 1 - Der Einzug',
+            'description': 'Folge 1 - Der Einzug',
         },
-        u'params': {
-            u'skip_download': True,
+        'params': {
+            'skip_download': True,
         },
-        u'skip': u'Only works from Germany',
+        'skip': 'Only works from Germany',
     },
     {
-        u'url': u'http://rtl2now.rtl2.de/aerger-im-revier/episode-15-teil-1.php?film_id=69756&player=1&season=2&index=5',
-        u'file': u'69756.flv',
-        u'info_dict': {
-            u'upload_date': u'20120519', 
-            u'title': u'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit...',
-            u'description': u'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit u.a.',
-            u'thumbnail': u'http://autoimg.static-fra.de/rtl2now/219850/1500x1500/image2.jpg',
+        'url': 'http://rtl2now.rtl2.de/aerger-im-revier/episode-15-teil-1.php?film_id=69756&player=1&season=2&index=5',
+        'file': '69756.flv',
+        'info_dict': {
+            'upload_date': '20120519',
+            'title': 'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit...',
+            'description': 'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit u.a.',
+            'thumbnail': 'http://autoimg.static-fra.de/rtl2now/219850/1500x1500/image2.jpg',
         },
-        u'params': {
-            u'skip_download': True,
+        'params': {
+            'skip_download': True,
         },
-        u'skip': u'Only works from Germany',
+        'skip': 'Only works from Germany',
     },
     {
-        u'url': u'http://www.voxnow.de/voxtours/suedafrika-reporter-ii.php?film_id=13883&player=1&season=17',
-        u'file': u'13883.flv',
-        u'info_dict': {
-            u'upload_date': u'20090627', 
-            u'title': u'Voxtours - Südafrika-Reporter II',
-            u'description': u'Südafrika-Reporter II',
+        'url': 'http://www.voxnow.de/voxtours/suedafrika-reporter-ii.php?film_id=13883&player=1&season=17',
+        'file': '13883.flv',
+        'info_dict': {
+            'upload_date': '20090627',
+            'title': 'Voxtours - Südafrika-Reporter II',
+            'description': 'Südafrika-Reporter II',
         },
-        u'params': {
-            u'skip_download': True,
+        'params': {
+            'skip_download': True,
         },
     },
     {
-        u'url': u'http://superrtlnow.de/medicopter-117/angst.php?film_id=99205&player=1',
-        u'file': u'99205.flv',
-        u'info_dict': {
-            u'upload_date': u'20080928', 
-            u'title': u'Medicopter 117 - Angst!',
-            u'description': u'Angst!',
-            u'thumbnail': u'http://autoimg.static-fra.de/superrtlnow/287529/1500x1500/image2.jpg'
+        'url': 'http://superrtlnow.de/medicopter-117/angst.php?film_id=99205&player=1',
+        'file': '99205.flv',
+        'info_dict': {
+            'upload_date': '20080928', 
+            'title': 'Medicopter 117 - Angst!',
+            'description': 'Angst!',
+            'thumbnail': 'http://autoimg.static-fra.de/superrtlnow/287529/1500x1500/image2.jpg'
         },
-        u'params': {
-            u'skip_download': True,
+        'params': {
+            'skip_download': True,
         },
     },
     {
-        u'url': u'http://www.n-tvnow.de/top-gear/episode-1-2013-01-01-00-00-00.php?film_id=124903&player=1&season=10',
-        u'file': u'124903.flv',
-        u'info_dict': {
-            u'upload_date': u'20130101', 
-            u'title': u'Top Gear vom 01.01.2013',
-            u'description': u'Episode 1',
+        'url': 'http://www.n-tvnow.de/top-gear/episode-1-2013-01-01-00-00-00.php?film_id=124903&player=1&season=10',
+        'file': '124903.flv',
+        'info_dict': {
+            'upload_date': '20130101',
+            'title': 'Top Gear vom 01.01.2013',
+            'description': 'Episode 1',
         },
-        u'params': {
-            u'skip_download': True,
+        'params': {
+            'skip_download': True,
         },
-        u'skip': u'Only works from Germany',
+        'skip': 'Only works from Germany',
     }]
 
-
-    def _real_extract(self,url):
+    def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
 
-        webpage_url = u'http://' + mobj.group('url')
-        video_page_url = u'http://' + mobj.group('domain') + u'/'
-        video_id = mobj.group(u'video_id')
+        webpage_url = 'http://' + mobj.group('url')
+        video_page_url = 'http://' + mobj.group('domain') + '/'
+        video_id = mobj.group('video_id')
 
         webpage = self._download_webpage(webpage_url, video_id)
 
@@ -94,51 +96,53 @@ class RTLnowIE(InfoExtractor):
             msg = clean_html(note_m.group(1))
             raise ExtractorError(msg)
 
-        video_title = self._html_search_regex(r'<title>(?P<title>[^<]+?)( \| [^<]*)?</title>',
-            webpage, u'title')
-        playerdata_url = self._html_search_regex(r'\'playerdata\': \'(?P<playerdata_url>[^\']+)\'',
-            webpage, u'playerdata_url')
+        video_title = self._html_search_regex(
+            r'<title>(?P<title>[^<]+?)( \| [^<]*)?</title>',
+            webpage, 'title')
+        playerdata_url = self._html_search_regex(
+            r'\'playerdata\': \'(?P<playerdata_url>[^\']+)\'',
+            webpage, 'playerdata_url')
 
         playerdata = self._download_webpage(playerdata_url, video_id)
         mobj = re.search(r'<title><!\[CDATA\[(?P<description>.+?)(?:\s+- (?:Sendung )?vom (?P<upload_date_d>[0-9]{2})\.(?P<upload_date_m>[0-9]{2})\.(?:(?P<upload_date_Y>[0-9]{4})|(?P<upload_date_y>[0-9]{2})) [0-9]{2}:[0-9]{2} Uhr)?\]\]></title>', playerdata)
         if mobj:
-            video_description = mobj.group(u'description')
+            video_description = mobj.group('description')
             if mobj.group('upload_date_Y'):
                 video_upload_date = mobj.group('upload_date_Y')
             elif mobj.group('upload_date_y'):
-                video_upload_date = u'20' + mobj.group('upload_date_y')
+                video_upload_date = '20' + mobj.group('upload_date_y')
             else:
                 video_upload_date = None
             if video_upload_date:
-                video_upload_date += mobj.group('upload_date_m')+mobj.group('upload_date_d')
+                video_upload_date += mobj.group('upload_date_m') + mobj.group('upload_date_d')
         else:
             video_description = None
             video_upload_date = None
-            self._downloader.report_warning(u'Unable to extract description and upload date')
+            self._downloader.report_warning('Unable to extract description and upload date')
 
         # Thumbnail: not every video has an thumbnail
         mobj = re.search(r'<meta property="og:image" content="(?P<thumbnail>[^"]+)">', webpage)
         if mobj:
-            video_thumbnail = mobj.group(u'thumbnail')
+            video_thumbnail = mobj.group('thumbnail')
         else:
             video_thumbnail = None
 
         mobj = re.search(r'<filename [^>]+><!\[CDATA\[(?P<url>rtmpe://(?:[^/]+/){2})(?P<play_path>[^\]]+)\]\]></filename>', playerdata)
         if mobj is None:
-            raise ExtractorError(u'Unable to extract media URL')
-        video_url = mobj.group(u'url')
-        video_play_path = u'mp4:' + mobj.group(u'play_path')
-        video_player_url = video_page_url + u'includes/vodplayer.swf'
+            raise ExtractorError('Unable to extract media URL')
+        video_url = mobj.group('url')
+        video_play_path = 'mp4:' + mobj.group('play_path')
+        video_player_url = video_page_url + 'includes/vodplayer.swf'
 
-        return [{
-            'id':          video_id,
-            'url':         video_url,
-            'play_path':   video_play_path,
-            'page_url':    video_page_url,
-            'player_url':  video_player_url,
-            'ext':         'flv',
-            'title':       video_title,
+        return {
+            'id': video_id,
+            'url': video_url,
+            'play_path': video_play_path,
+            'page_url': video_page_url,
+            'player_url': video_player_url,
+            'ext': 'flv',
+            'title': video_title,
             'description': video_description,
             'upload_date': video_upload_date,
-            'thumbnail':   video_thumbnail,
-        }]
+            'thumbnail': video_thumbnail,
+        }

youtube_dl/extractor/rutube.py

@@ -1,58 +1,124 @@
 # encoding: utf-8
+from __future__ import unicode_literals
+
 import re
 import json
+import itertools
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_urlparse,
     compat_str,
+    unified_strdate,
     ExtractorError,
 )
 
 
 class RutubeIE(InfoExtractor):
-    _VALID_URL = r'https?://rutube\.ru/video/(?P<long_id>\w+)'
+    IE_NAME = 'rutube'
+    IE_DESC = 'Rutube videos'
+    _VALID_URL = r'https?://rutube\.ru/video/(?P<id>[\da-z]{32})'
 
     _TEST = {
-        u'url': u'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
-        u'file': u'3eac3b4561676c17df9132a9a1e62e3e.mp4',
-        u'info_dict': {
-            u'title': u'Раненный кенгуру забежал в аптеку',
-            u'uploader': u'NTDRussian',
-            u'uploader_id': u'29790',
+        'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
+        'file': '3eac3b4561676c17df9132a9a1e62e3e.mp4',
+        'info_dict': {
+            'title': 'Раненный кенгуру забежал в аптеку',
+            'description': 'http://www.ntdtv.ru ',
+            'duration': 80,
+            'uploader': 'NTDRussian',
+            'uploader_id': '29790',
+            'upload_date': '20131016',
         },
-        u'params': {
+        'params': {
             # It requires ffmpeg (m3u8 download)
-            u'skip_download': True,
+            'skip_download': True,
         },
     }
 
-    def _get_api_response(self, short_id, subpath):
-        api_url = 'http://rutube.ru/api/play/%s/%s/?format=json' % (subpath, short_id)
-        response_json = self._download_webpage(api_url, short_id,
-            u'Downloading %s json' % subpath)
-        return json.loads(response_json)
-
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        long_id = mobj.group('long_id')
-        webpage = self._download_webpage(url, long_id)
-        og_video = self._og_search_video_url(webpage)
-        short_id = compat_urlparse.urlparse(og_video).path[1:]
-        options = self._get_api_response(short_id, 'options')
-        trackinfo = self._get_api_response(short_id, 'trackinfo')
+        video_id = mobj.group('id')
+        
+        api_response = self._download_webpage('http://rutube.ru/api/video/%s/?format=json' % video_id,
+                                              video_id, 'Downloading video JSON')
+        video = json.loads(api_response)
+        
+        api_response = self._download_webpage('http://rutube.ru/api/play/trackinfo/%s/?format=json' % video_id,
+                                              video_id, 'Downloading trackinfo JSON')
+        trackinfo = json.loads(api_response)
+        
         # Some videos don't have the author field
         author = trackinfo.get('author') or {}
         m3u8_url = trackinfo['video_balancer'].get('m3u8')
         if m3u8_url is None:
-            raise ExtractorError(u'Couldn\'t find m3u8 manifest url')
+            raise ExtractorError('Couldn\'t find m3u8 manifest url')
 
         return {
-            'id': trackinfo['id'],
-            'title': trackinfo['title'],
+            'id': video['id'],
+            'title': video['title'],
+            'description': video['description'],
+            'duration': video['duration'],
+            'view_count': video['hits'],
             'url': m3u8_url,
             'ext': 'mp4',
-            'thumbnail': options['thumbnail_url'],
+            'thumbnail': video['thumbnail_url'],
             'uploader': author.get('name'),
             'uploader_id': compat_str(author['id']) if author else None,
+            'upload_date': unified_strdate(video['created_ts']),
+            'age_limit': 18 if video['is_adult'] else 0,
         }
+
+
+class RutubeChannelIE(InfoExtractor):
+    IE_NAME = 'rutube:channel'
+    IE_DESC = 'Rutube channels'
+    _VALID_URL = r'http://rutube\.ru/tags/video/(?P<id>\d+)'
+
+    _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
+
+    def _extract_videos(self, channel_id, channel_title=None):
+        entries = []
+        for pagenum in itertools.count(1):
+            api_response = self._download_webpage(
+                self._PAGE_TEMPLATE % (channel_id, pagenum),
+                channel_id, 'Downloading page %s' % pagenum)
+            page = json.loads(api_response)
+            results = page['results']
+            if not results:
+                break
+            entries.extend(self.url_result(result['video_url'], 'Rutube') for result in results)
+            if not page['has_next']:
+                break
+        return self.playlist_result(entries, channel_id, channel_title)
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        channel_id = mobj.group('id')
+        return self._extract_videos(channel_id)
+
+
+class RutubeMovieIE(RutubeChannelIE):
+    IE_NAME = 'rutube:movie'
+    IE_DESC = 'Rutube movies'
+    _VALID_URL = r'http://rutube\.ru/metainfo/tv/(?P<id>\d+)'
+
+    _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
+    _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        movie_id = mobj.group('id')
+        api_response = self._download_webpage(
+            self._MOVIE_TEMPLATE % movie_id, movie_id,
+            'Downloading movie JSON')
+        movie = json.loads(api_response)
+        movie_name = movie['name']
+        return self._extract_videos(movie_id, movie_name)
+
+
+class RutubePersonIE(RutubeChannelIE):
+    IE_NAME = 'rutube:person'
+    IE_DESC = 'Rutube person videos'
+    _VALID_URL = r'http://rutube\.ru/video/person/(?P<id>\d+)'
+
+    _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'

youtube_dl/extractor/savefrom.py

@@ -0,0 +1,37 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import os.path
+import re
+
+from .common import InfoExtractor
+
+
+class SaveFromIE(InfoExtractor):
+    IE_NAME = 'savefrom.net'
+    _VALID_URL = r'https?://[^.]+\.savefrom\.net/\#url=(?P<url>.*)$'
+
+    _TEST = {
+        'url': 'http://en.savefrom.net/#url=http://youtube.com/watch?v=UlVRAPW2WJY&utm_source=youtube.com&utm_medium=short_domains&utm_campaign=ssyoutube.com',
+        'info_dict': {
+            'id': 'UlVRAPW2WJY',
+            'ext': 'mp4',
+            'title': 'About Team Radical MMA | MMA Fighting',
+            'upload_date': '20120816',
+            'uploader': 'Howcast',
+            'uploader_id': 'Howcast',
+            'description': 'md5:4f0aac94361a12e1ce57d74f85265175',
+        },
+        'params': {
+            'skip_download': True
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = os.path.splitext(url.split('/')[-1])[0]
+        return {
+            '_type': 'url',
+            'id': video_id,
+            'url': mobj.group('url'),
+        }

youtube_dl/extractor/sina.py

@@ -1,4 +1,5 @@
 # coding: utf-8
+from __future__ import unicode_literals
 
 import re
 
@@ -12,21 +13,31 @@ from ..utils import (
 class SinaIE(InfoExtractor):
     _VALID_URL = r'''https?://(.*?\.)?video\.sina\.com\.cn/
                         (
-                            (.+?/(((?P<pseudo_id>\d+).html)|(.*?(\#|(vid=))(?P<id>\d+?)($|&))))
+                            (.+?/(((?P<pseudo_id>\d+).html)|(.*?(\#|(vid=)|b/)(?P<id>\d+?)($|&|\-))))
                             |
                             # This is used by external sites like Weibo
                             (api/sinawebApi/outplay.php/(?P<token>.+?)\.swf)
                         )
                   '''
 
-    _TEST = {
-        u'url': u'http://video.sina.com.cn/news/vlist/zt/chczlj2013/?opsubject_id=top12#110028898',
-        u'file': u'110028898.flv',
-        u'md5': u'd65dd22ddcf44e38ce2bf58a10c3e71f',
-        u'info_dict': {
-            u'title': u'《中国新闻》 朝鲜要求巴拿马立即释放被扣船员',
-        }
-    }
+    _TESTS = [
+        {
+            'url': 'http://video.sina.com.cn/news/vlist/zt/chczlj2013/?opsubject_id=top12#110028898',
+            'file': '110028898.flv',
+            'md5': 'd65dd22ddcf44e38ce2bf58a10c3e71f',
+            'info_dict': {
+                'title': '《中国新闻》 朝鲜要求巴拿马立即释放被扣船员',
+            }
+        },
+        {
+            'url': 'http://video.sina.com.cn/v/b/101314253-1290078633.html',
+            'info_dict': {
+                'id': '101314253',
+                'ext': 'flv',
+                'title': '军方提高对朝情报监视级别',
+            },
+        },
+    ]
 
     @classmethod
     def suitable(cls, url):
@@ -35,10 +46,10 @@ class SinaIE(InfoExtractor):
     def _extract_video(self, video_id):
         data = compat_urllib_parse.urlencode({'vid': video_id})
         url_doc = self._download_xml('http://v.iask.com/v_play.php?%s' % data,
-            video_id, u'Downloading video url')
+            video_id, 'Downloading video url')
         image_page = self._download_webpage(
             'http://interface.video.sina.com.cn/interface/common/getVideoImage.php?%s' % data,
-            video_id, u'Downloading thumbnail info')
+            video_id, 'Downloading thumbnail info')
 
         return {'id': video_id,
                 'url': url_doc.find('./durl/url').text,
@@ -52,7 +63,7 @@ class SinaIE(InfoExtractor):
         video_id = mobj.group('id')
         if mobj.group('token') is not None:
             # The video id is in the redirected url
-            self.to_screen(u'Getting video id')
+            self.to_screen('Getting video id')
             request = compat_urllib_request.Request(url)
             request.get_method = lambda: 'HEAD'
             (_, urlh) = self._download_webpage_handle(request, 'NA', False)
@@ -60,6 +71,6 @@ class SinaIE(InfoExtractor):
         elif video_id is None:
             pseudo_id = mobj.group('pseudo_id')
             webpage = self._download_webpage(url, pseudo_id)
-            video_id = self._search_regex(r'vid:\'(\d+?)\'', webpage, u'video id')
+            video_id = self._search_regex(r'vid:\'(\d+?)\'', webpage, 'video id')
 
         return self._extract_video(video_id)

youtube_dl/extractor/slideshare.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 import json
 
@@ -12,11 +14,12 @@ class SlideshareIE(InfoExtractor):
     _VALID_URL = r'https?://www\.slideshare\.net/[^/]+?/(?P<title>.+?)($|\?)'
 
     _TEST = {
-        u'url': u'http://www.slideshare.net/Dataversity/keynote-presentation-managing-scale-and-complexity',
-        u'file': u'25665706.mp4',
-        u'info_dict': {
-            u'title': u'Managing Scale and Complexity',
-            u'description': u'This was a keynote presentation at the NoSQL Now! 2013 Conference & Expo (http://www.nosqlnow.com). This presentation was given by Adrian Cockcroft from Netflix',
+        'url': 'http://www.slideshare.net/Dataversity/keynote-presentation-managing-scale-and-complexity',
+        'info_dict': {
+            'id': '25665706',
+            'ext': 'mp4',
+            'title': 'Managing Scale and Complexity',
+            'description': 'This was a keynote presentation at the NoSQL Now! 2013 Conference & Expo (http://www.nosqlnow.com). This presentation was given by Adrian Cockcroft from Netflix.',
         },
     }
 
@@ -26,15 +29,17 @@ class SlideshareIE(InfoExtractor):
         webpage = self._download_webpage(url, page_title)
         slideshare_obj = self._search_regex(
             r'var slideshare_object =  ({.*?}); var user_info =',
-            webpage, u'slideshare object')
+            webpage, 'slideshare object')
         info = json.loads(slideshare_obj)
-        if info['slideshow']['type'] != u'video':
-            raise ExtractorError(u'Webpage type is "%s": only video extraction is supported for Slideshare' % info['slideshow']['type'], expected=True)
+        if info['slideshow']['type'] != 'video':
+            raise ExtractorError('Webpage type is "%s": only video extraction is supported for Slideshare' % info['slideshow']['type'], expected=True)
 
         doc = info['doc']
         bucket = info['jsplayer']['video_bucket']
         ext = info['jsplayer']['video_extension']
         video_url = compat_urlparse.urljoin(bucket, doc + '-SD.' + ext)
+        description = self._html_search_regex(
+            r'<p class="description.*?"[^>]*>(.*?)</p>', webpage, 'description')
 
         return {
             '_type': 'video',
@@ -43,5 +48,5 @@ class SlideshareIE(InfoExtractor):
             'ext': ext,
             'url': video_url,
             'thumbnail': info['slideshow']['pin_image_url'],
-            'description': self._og_search_description(webpage),
+            'description': description,
         }

youtube_dl/extractor/smotri.py

@@ -1,4 +1,5 @@
 # encoding: utf-8
+from __future__ import unicode_literals
 
 import os.path
 import re
@@ -16,76 +17,77 @@ from ..utils import (
 
 
 class SmotriIE(InfoExtractor):
-    IE_DESC = u'Smotri.com'
-    IE_NAME = u'smotri'
+    IE_DESC = 'Smotri.com'
+    IE_NAME = 'smotri'
     _VALID_URL = r'^https?://(?:www\.)?(?P<url>smotri\.com/video/view/\?id=(?P<videoid>v(?P<realvideoid>[0-9]+)[a-z0-9]{4}))'
+    _NETRC_MACHINE = 'smotri'
 
     _TESTS = [
         # real video id 2610366
         {
-            u'url': u'http://smotri.com/video/view/?id=v261036632ab',
-            u'file': u'v261036632ab.mp4',
-            u'md5': u'2a7b08249e6f5636557579c368040eb9',
-            u'info_dict': {
-                u'title': u'катастрофа с камер видеонаблюдения',
-                u'uploader': u'rbc2008',
-                u'uploader_id': u'rbc08',
-                u'upload_date': u'20131118',
-                u'description': u'катастрофа с камер видеонаблюдения, видео катастрофа с камер видеонаблюдения',
-                u'thumbnail': u'http://frame6.loadup.ru/8b/a9/2610366.3.3.jpg',
+            'url': 'http://smotri.com/video/view/?id=v261036632ab',
+            'file': 'v261036632ab.mp4',
+            'md5': '2a7b08249e6f5636557579c368040eb9',
+            'info_dict': {
+                'title': 'катастрофа с камер видеонаблюдения',
+                'uploader': 'rbc2008',
+                'uploader_id': 'rbc08',
+                'upload_date': '20131118',
+                'description': 'катастрофа с камер видеонаблюдения, видео катастрофа с камер видеонаблюдения',
+                'thumbnail': 'http://frame6.loadup.ru/8b/a9/2610366.3.3.jpg',
             },
         },
         # real video id 57591
         {
-            u'url': u'http://smotri.com/video/view/?id=v57591cb20',
-            u'file': u'v57591cb20.flv',
-            u'md5': u'830266dfc21f077eac5afd1883091bcd',
-            u'info_dict': {
-                u'title': u'test',
-                u'uploader': u'Support Photofile@photofile',
-                u'uploader_id': u'support-photofile',
-                u'upload_date': u'20070704',
-                u'description': u'test, видео test',
-                u'thumbnail': u'http://frame4.loadup.ru/03/ed/57591.2.3.jpg',
+            'url': 'http://smotri.com/video/view/?id=v57591cb20',
+            'file': 'v57591cb20.flv',
+            'md5': '830266dfc21f077eac5afd1883091bcd',
+            'info_dict': {
+                'title': 'test',
+                'uploader': 'Support Photofile@photofile',
+                'uploader_id': 'support-photofile',
+                'upload_date': '20070704',
+                'description': 'test, видео test',
+                'thumbnail': 'http://frame4.loadup.ru/03/ed/57591.2.3.jpg',
             },
         },
         # video-password
         {
-            u'url': u'http://smotri.com/video/view/?id=v1390466a13c',
-            u'file': u'v1390466a13c.mp4',
-            u'md5': u'f6331cef33cad65a0815ee482a54440b',
-            u'info_dict': {
-                u'title': u'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1',
-                u'uploader': u'timoxa40',
-                u'uploader_id': u'timoxa40',
-                u'upload_date': u'20100404',
-                u'thumbnail': u'http://frame7.loadup.ru/af/3f/1390466.3.3.jpg',
-                u'description': u'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1, видео TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1',
+            'url': 'http://smotri.com/video/view/?id=v1390466a13c',
+            'file': 'v1390466a13c.mp4',
+            'md5': 'f6331cef33cad65a0815ee482a54440b',
+            'info_dict': {
+                'title': 'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1',
+                'uploader': 'timoxa40',
+                'uploader_id': 'timoxa40',
+                'upload_date': '20100404',
+                'thumbnail': 'http://frame7.loadup.ru/af/3f/1390466.3.3.jpg',
+                'description': 'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1, видео TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1',
             },
-            u'params': {
-                u'videopassword': u'qwerty',
+            'params': {
+                'videopassword': 'qwerty',
             },
         },
         # age limit + video-password
         {
-            u'url': u'http://smotri.com/video/view/?id=v15408898bcf',
-            u'file': u'v15408898bcf.flv',
-            u'md5': u'91e909c9f0521adf5ee86fbe073aad70',
-            u'info_dict': {
-                u'title': u'этот ролик не покажут по ТВ',
-                u'uploader': u'zzxxx',
-                u'uploader_id': u'ueggb',
-                u'upload_date': u'20101001',
-                u'thumbnail': u'http://frame3.loadup.ru/75/75/1540889.1.3.jpg',
-                u'age_limit': 18,
-                u'description': u'этот ролик не покажут по ТВ, видео этот ролик не покажут по ТВ',
+            'url': 'http://smotri.com/video/view/?id=v15408898bcf',
+            'file': 'v15408898bcf.flv',
+            'md5': '91e909c9f0521adf5ee86fbe073aad70',
+            'info_dict': {
+                'title': 'этот ролик не покажут по ТВ',
+                'uploader': 'zzxxx',
+                'uploader_id': 'ueggb',
+                'upload_date': '20101001',
+                'thumbnail': 'http://frame3.loadup.ru/75/75/1540889.1.3.jpg',
+                'age_limit': 18,
+                'description': 'этот ролик не покажут по ТВ, видео этот ролик не покажут по ТВ',
             },
-            u'params': {
-                u'videopassword': u'333'
+            'params': {
+                'videopassword': '333'
             }
         }
     ]
-    
+
     _SUCCESS = 0
     _PASSWORD_NOT_VERIFIED = 1
     _PASSWORD_DETECTED = 2
@@ -106,71 +108,71 @@ class SmotriIE(InfoExtractor):
 
         # Download video JSON data
         video_json_url = 'http://smotri.com/vt.php?id=%s' % real_video_id
-        video_json_page = self._download_webpage(video_json_url, video_id, u'Downloading video JSON')
+        video_json_page = self._download_webpage(video_json_url, video_id, 'Downloading video JSON')
         video_json = json.loads(video_json_page)
-        
+
         status = video_json['status']
         if status == self._VIDEO_NOT_FOUND:
-            raise ExtractorError(u'Video %s does not exist' % video_id, expected=True)
-        elif status == self._PASSWORD_DETECTED:  # The video is protected by a password, retry with
+            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+        elif status == self._PASSWORD_DETECTED: # The video is protected by a password, retry with
                                                 # video-password set
             video_password = self._downloader.params.get('videopassword', None)
             if not video_password:
-                raise ExtractorError(u'This video is protected by a password, use the --video-password option', expected=True)
+                raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
             video_json_url += '&md5pass=%s' % hashlib.md5(video_password.encode('utf-8')).hexdigest()
-            video_json_page = self._download_webpage(video_json_url, video_id, u'Downloading video JSON (video-password set)')
+            video_json_page = self._download_webpage(video_json_url, video_id, 'Downloading video JSON (video-password set)')
             video_json = json.loads(video_json_page)
             status = video_json['status']
             if status == self._PASSWORD_NOT_VERIFIED:
-                raise ExtractorError(u'Video password is invalid', expected=True)
-        
+                raise ExtractorError('Video password is invalid', expected=True)
+
         if status != self._SUCCESS:
-            raise ExtractorError(u'Unexpected status value %s' % status)
-        
+            raise ExtractorError('Unexpected status value %s' % status)
+
         # Extract the URL of the video
         video_url = video_json['file_data']
-        
+
         # Video JSON does not provide enough meta data
         # We will extract some from the video web page instead
         video_page_url = 'http://' + mobj.group('url')
-        video_page = self._download_webpage(video_page_url, video_id, u'Downloading video page')
+        video_page = self._download_webpage(video_page_url, video_id, 'Downloading video page')
 
         # Warning if video is unavailable
         warning = self._html_search_regex(
             r'<div class="videoUnModer">(.*?)</div>', video_page,
-            u'warning message', default=None)
+            'warning message', default=None)
         if warning is not None:
             self._downloader.report_warning(
-                u'Video %s may not be available; smotri said: %s ' %
+                'Video %s may not be available; smotri said: %s ' %
                 (video_id, warning))
 
         # Adult content
-        if re.search(u'EroConfirmText">', video_page) is not None:
+        if re.search('EroConfirmText">', video_page) is not None:
             self.report_age_confirmation()
             confirm_string = self._html_search_regex(
                 r'<a href="/video/view/\?id=%s&confirm=([^"]+)" title="[^"]+">' % video_id,
-                video_page, u'confirm string')
+                video_page, 'confirm string')
             confirm_url = video_page_url + '&confirm=%s' % confirm_string
-            video_page = self._download_webpage(confirm_url, video_id, u'Downloading video page (age confirmed)')
+            video_page = self._download_webpage(confirm_url, video_id, 'Downloading video page (age confirmed)')
             adult_content = True
         else:
             adult_content = False
-        
+
         # Extract the rest of meta data
-        video_title = self._search_meta(u'name', video_page, u'title')
+        video_title = self._search_meta('name', video_page, 'title')
         if not video_title:
             video_title = os.path.splitext(url_basename(video_url))[0]
 
-        video_description = self._search_meta(u'description', video_page)
-        END_TEXT = u' на сайте Smotri.com'
+        video_description = self._search_meta('description', video_page)
+        END_TEXT = ' на сайте Smotri.com'
         if video_description and video_description.endswith(END_TEXT):
             video_description = video_description[:-len(END_TEXT)]
-        START_TEXT = u'Смотреть онлайн ролик '
+        START_TEXT = 'Смотреть онлайн ролик '
         if video_description and video_description.startswith(START_TEXT):
             video_description = video_description[len(START_TEXT):]
-        video_thumbnail = self._search_meta(u'thumbnail', video_page)
+        video_thumbnail = self._search_meta('thumbnail', video_page)
 
-        upload_date_str = self._search_meta(u'uploadDate', video_page, u'upload date')
+        upload_date_str = self._search_meta('uploadDate', video_page, 'upload date')
         if upload_date_str:
             upload_date_m = re.search(r'(?P<year>\d{4})\.(?P<month>\d{2})\.(?P<day>\d{2})T', upload_date_str)
             video_upload_date = (
@@ -183,8 +185,8 @@ class SmotriIE(InfoExtractor):
             )
         else:
             video_upload_date = None
-        
-        duration_str = self._search_meta(u'duration', video_page)
+
+        duration_str = self._search_meta('duration', video_page)
         if duration_str:
             duration_m = re.search(r'T(?P<hours>[0-9]{2})H(?P<minutes>[0-9]{2})M(?P<seconds>[0-9]{2})S', duration_str)
             video_duration = (
@@ -197,19 +199,19 @@ class SmotriIE(InfoExtractor):
             )
         else:
             video_duration = None
-        
+
         video_uploader = self._html_search_regex(
-            u'<div class="DescrUser"><div>Автор.*?onmouseover="popup_user_info[^"]+">(.*?)</a>',
-            video_page, u'uploader', fatal=False, flags=re.MULTILINE|re.DOTALL)
-        
+            '<div class="DescrUser"><div>Автор.*?onmouseover="popup_user_info[^"]+">(.*?)</a>',
+            video_page, 'uploader', fatal=False, flags=re.MULTILINE|re.DOTALL)
+
         video_uploader_id = self._html_search_regex(
-            u'<div class="DescrUser"><div>Автор.*?onmouseover="popup_user_info\\(.*?\'([^\']+)\'\\);">',
-            video_page, u'uploader id', fatal=False, flags=re.MULTILINE|re.DOTALL)
-        
+            '<div class="DescrUser"><div>Автор.*?onmouseover="popup_user_info\\(.*?\'([^\']+)\'\\);">',
+            video_page, 'uploader id', fatal=False, flags=re.MULTILINE|re.DOTALL)
+
         video_view_count = self._html_search_regex(
-            u'Общее количество просмотров.*?<span class="Number">(\\d+)</span>',
-            video_page, u'view count', fatal=False, flags=re.MULTILINE|re.DOTALL)
-                
+            'Общее количество просмотров.*?<span class="Number">(\\d+)</span>',
+            video_page, 'view count', fatal=False, flags=re.MULTILINE|re.DOTALL)
+
         return {
             'id': video_id,
             'url': video_url,
@@ -227,8 +229,8 @@ class SmotriIE(InfoExtractor):
 
 
 class SmotriCommunityIE(InfoExtractor):
-    IE_DESC = u'Smotri.com community videos'
-    IE_NAME = u'smotri:community'
+    IE_DESC = 'Smotri.com community videos'
+    IE_NAME = 'smotri:community'
     _VALID_URL = r'^https?://(?:www\.)?smotri\.com/community/video/(?P<communityid>[0-9A-Za-z_\'-]+)'
     
     def _real_extract(self, url):
@@ -236,21 +238,21 @@ class SmotriCommunityIE(InfoExtractor):
         community_id = mobj.group('communityid')
 
         url = 'http://smotri.com/export/rss/video/by/community/-/%s/video.xml' % community_id
-        rss = self._download_xml(url, community_id, u'Downloading community RSS')
+        rss = self._download_xml(url, community_id, 'Downloading community RSS')
 
         entries = [self.url_result(video_url.text, 'Smotri')
                    for video_url in rss.findall('./channel/item/link')]
 
         description_text = rss.find('./channel/description').text
         community_title = self._html_search_regex(
-            u'^Видео сообщества "([^"]+)"$', description_text, u'community title')
+            '^Видео сообщества "([^"]+)"$', description_text, 'community title')
 
         return self.playlist_result(entries, community_id, community_title)
 
 
 class SmotriUserIE(InfoExtractor):
-    IE_DESC = u'Smotri.com user videos'
-    IE_NAME = u'smotri:user'
+    IE_DESC = 'Smotri.com user videos'
+    IE_NAME = 'smotri:user'
     _VALID_URL = r'^https?://(?:www\.)?smotri\.com/user/(?P<userid>[0-9A-Za-z_\'-]+)'
 
     def _real_extract(self, url):
@@ -258,22 +260,22 @@ class SmotriUserIE(InfoExtractor):
         user_id = mobj.group('userid')
 
         url = 'http://smotri.com/export/rss/user/video/-/%s/video.xml' % user_id
-        rss = self._download_xml(url, user_id, u'Downloading user RSS')
+        rss = self._download_xml(url, user_id, 'Downloading user RSS')
 
         entries = [self.url_result(video_url.text, 'Smotri')
                    for video_url in rss.findall('./channel/item/link')]
 
         description_text = rss.find('./channel/description').text
         user_nickname = self._html_search_regex(
-            u'^Видео режиссера (.*)$', description_text,
-            u'user nickname')
+            '^Видео режиссера (.*)$', description_text,
+            'user nickname')
 
         return self.playlist_result(entries, user_id, user_nickname)
 
 
 class SmotriBroadcastIE(InfoExtractor):
-    IE_DESC = u'Smotri.com broadcasts'
-    IE_NAME = u'smotri:broadcast'
+    IE_DESC = 'Smotri.com broadcasts'
+    IE_NAME = 'smotri:broadcast'
     _VALID_URL = r'^https?://(?:www\.)?(?P<url>smotri\.com/live/(?P<broadcastid>[^/]+))/?.*'
 
     def _real_extract(self, url):
@@ -281,46 +283,40 @@ class SmotriBroadcastIE(InfoExtractor):
         broadcast_id = mobj.group('broadcastid')
 
         broadcast_url = 'http://' + mobj.group('url')
-        broadcast_page = self._download_webpage(broadcast_url, broadcast_id, u'Downloading broadcast page')
+        broadcast_page = self._download_webpage(broadcast_url, broadcast_id, 'Downloading broadcast page')
 
-        if re.search(u'>Режиссер с логином <br/>"%s"<br/> <span>не существует<' % broadcast_id, broadcast_page) is not None:
-            raise ExtractorError(u'Broadcast %s does not exist' % broadcast_id, expected=True)
+        if re.search('>Режиссер с логином <br/>"%s"<br/> <span>не существует<' % broadcast_id, broadcast_page) is not None:
+            raise ExtractorError('Broadcast %s does not exist' % broadcast_id, expected=True)
 
         # Adult content
-        if re.search(u'EroConfirmText">', broadcast_page) is not None:
+        if re.search('EroConfirmText">', broadcast_page) is not None:
 
             (username, password) = self._get_login_info()
             if username is None:
-                raise ExtractorError(u'Erotic broadcasts allowed only for registered users, '
-                    u'use --username and --password options to provide account credentials.', expected=True)
+                raise ExtractorError('Erotic broadcasts allowed only for registered users, '
+                    'use --username and --password options to provide account credentials.', expected=True)
 
-            # Log in
-            login_form_strs = {
-                u'login-hint53': '1',
-                u'confirm_erotic': '1',
-                u'login': username,
-                u'password': password,
+            login_form = {
+                'login-hint53': '1',
+                'confirm_erotic': '1',
+                'login': username,
+                'password': password,
             }
-            # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
-            # chokes on unicode
-            login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in login_form_strs.items())
-            login_data = compat_urllib_parse.urlencode(login_form).encode('utf-8')
-            login_url = broadcast_url + '/?no_redirect=1'
-            request = compat_urllib_request.Request(login_url, login_data)
-            request.add_header('Content-Type', 'application/x-www-form-urlencoded')
-            broadcast_page = self._download_webpage(
-                request, broadcast_id, note=u'Logging in and confirming age')
 
-            if re.search(u'>Неверный логин или пароль<', broadcast_page) is not None:
-                raise ExtractorError(u'Unable to log in: bad username or password', expected=True)
+            request = compat_urllib_request.Request(broadcast_url + '/?no_redirect=1', compat_urllib_parse.urlencode(login_form))
+            request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+            broadcast_page = self._download_webpage(request, broadcast_id, 'Logging in and confirming age')
+
+            if re.search('>Неверный логин или пароль<', broadcast_page) is not None:
+                raise ExtractorError('Unable to log in: bad username or password', expected=True)
 
             adult_content = True
         else:
             adult_content = False
 
         ticket = self._html_search_regex(
-            u'window\.broadcast_control\.addFlashVar\\(\'file\', \'([^\']+)\'\\);',
-            broadcast_page, u'broadcast ticket')
+            'window\.broadcast_control\.addFlashVar\\(\'file\', \'([^\']+)\'\\);',
+            broadcast_page, 'broadcast ticket')
 
         url = 'http://smotri.com/broadcast/view/url/?ticket=%s' % ticket
 
@@ -328,22 +324,22 @@ class SmotriBroadcastIE(InfoExtractor):
         if broadcast_password:
             url += '&pass=%s' % hashlib.md5(broadcast_password.encode('utf-8')).hexdigest()
 
-        broadcast_json_page = self._download_webpage(url, broadcast_id, u'Downloading broadcast JSON')
+        broadcast_json_page = self._download_webpage(url, broadcast_id, 'Downloading broadcast JSON')
 
         try:
             broadcast_json = json.loads(broadcast_json_page)
 
             protected_broadcast = broadcast_json['_pass_protected'] == 1
             if protected_broadcast and not broadcast_password:
-                raise ExtractorError(u'This broadcast is protected by a password, use the --video-password option', expected=True)
+                raise ExtractorError('This broadcast is protected by a password, use the --video-password option', expected=True)
 
             broadcast_offline = broadcast_json['is_play'] == 0
             if broadcast_offline:
-                raise ExtractorError(u'Broadcast %s is offline' % broadcast_id, expected=True)
+                raise ExtractorError('Broadcast %s is offline' % broadcast_id, expected=True)
 
             rtmp_url = broadcast_json['_server']
             if not rtmp_url.startswith('rtmp://'):
-                raise ExtractorError(u'Unexpected broadcast rtmp URL')
+                raise ExtractorError('Unexpected broadcast rtmp URL')
 
             broadcast_playpath = broadcast_json['_streamName']
             broadcast_thumbnail = broadcast_json['_imgURL']
@@ -354,8 +350,8 @@ class SmotriBroadcastIE(InfoExtractor):
             rtmp_conn = 'S:%s' % uuid.uuid4().hex
         except KeyError:
             if protected_broadcast:
-                raise ExtractorError(u'Bad broadcast password', expected=True)
-            raise ExtractorError(u'Unexpected broadcast JSON')
+                raise ExtractorError('Bad broadcast password', expected=True)
+            raise ExtractorError('Unexpected broadcast JSON')
 
         return {
             'id': broadcast_id,

youtube_dl/extractor/sohu.py

@@ -17,6 +17,7 @@ class SohuIE(InfoExtractor):
         u'info_dict': {
             u'title': u'MV：Far East Movement《The Illest》',
         },
+        u'skip': u'Only available from China',
     }
 
     def _real_extract(self, url):