release 2014.01.27.2

Signed-off-by: Philipp Hagemeister <phihag@phihag.de>

README.md

@@ -14,193 +14,229 @@ 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
+                                     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.
 
 ## 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.
+    --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
 
@@ -289,11 +325,27 @@ 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
+# BUILD 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
 
 # BUGS
 
@@ -352,3 +404,9 @@ 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.

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_subtitles.py

@@ -167,13 +167,13 @@ class TestTedSubtitles(BaseTestSubtitles):
     def test_subtitles(self):
         self.DL.params['writesubtitles'] = True
         subtitles = self.getSubtitles()
-        self.assertEqual(md5(subtitles['en']), '2154f31ff9b9f89a0aa671537559c21d')
+        self.assertEqual(md5(subtitles['en']), '4262c1665ff928a2dada178f62cb8d14')
 
     def test_subtitles_lang(self):
         self.DL.params['writesubtitles'] = True
         self.DL.params['subtitleslangs'] = ['fr']
         subtitles = self.getSubtitles()
-        self.assertEqual(md5(subtitles['fr']), '7616cbc6df20ec2c1204083c83871cf6')
+        self.assertEqual(md5(subtitles['fr']), '66a63f7f42c97a50f8c0e90bc7797bb5')
 
     def test_allsubtitles(self):
         self.DL.params['writesubtitles'] = True

test/test_utils.py

@@ -16,8 +16,10 @@ from youtube_dl.utils import (
     DateRange,
     encodeFilename,
     find_xpath_attr,
+    fix_xml_ampersands,
     get_meta_content,
     orderedSet,
+    PagedList,
     parse_duration,
     sanitize_filename,
     shell_quote,
@@ -200,5 +202,39 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(parse_duration('9:12:43'), 33163)
         self.assertEqual(parse_duration('x:y'), None)
 
+    def test_fix_xml_ampersands(self):
+        self.assertEqual(
+            fix_xml_ampersands('"&x=y&z=a'), '"&x=y&z=a')
+        self.assertEqual(
+            fix_xml_ampersands('"&x=y&wrong;&z=a'),
+            '"&x=y&wrong;&z=a')
+        self.assertEqual(
+            fix_xml_ampersands('&'><"'),
+            '&'><"')
+        self.assertEqual(
+            fix_xml_ampersands('Ӓ᪼'), 'Ӓ᪼')
+        self.assertEqual(fix_xml_ampersands('&#&#'), '&#&#')
+
+    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), [])
+
 if __name__ == '__main__':
     unittest.main()

test/test_youtube_lists.py

@@ -120,7 +120,7 @@ class TestYoutubeLists(unittest.TestCase):
     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

@@ -27,12 +27,6 @@ _TESTS = [
         85,
         u'3456789a0cdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRS[UVWXYZ!"#$%&\'()*+,-./:;<=>?@',
     ),
-    (
-        u'https://s.ytimg.com/yts/swfbin/watch_as3-vflg5GhxU.swf',
-        u'swf',
-        82,
-        u':/.-,+*)=\'&%$#"!ZYX0VUTSRQPONMLKJIHGFEDCBAzyxw>utsrqponmlkjihgfedcba987654321'
-    ),
 ]
 
 

youtube_dl/YoutubeDL.py

@@ -39,6 +39,7 @@ from .utils import (
     locked_file,
     make_HTTPS_handler,
     MaxDownloadsReached,
+    PagedList,
     PostProcessingError,
     platform_name,
     preferredencoding,
@@ -151,6 +152,9 @@ class YoutubeDL(object):
     bidi_workaround:   Work around buggy terminals without bidirectional text
                        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:
@@ -392,10 +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:
@@ -513,6 +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()))
@@ -575,19 +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))
@@ -634,6 +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:
@@ -698,7 +720,7 @@ class YoutubeDL(object):
             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 = []
@@ -747,8 +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:
@@ -765,10 +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)
 
@@ -908,6 +930,14 @@ class YoutubeDL(object):
                     if info_dict.get('requested_formats') is not None:
                         downloaded = []
                         success = True
+                        merger = FFmpegMergerPP(self)
+                        if not merger._get_executable():
+                            postprocessors = []
+                            self.report_warning('You have requested multiple '
+                                'formats but ffmpeg or avconv are not installed.'
+                                ' The formats won\'t be merged')
+                        else:
+                            postprocessors = [merger]
                         for f in info_dict['requested_formats']:
                             new_info = dict(info_dict)
                             new_info.update(f)
@@ -916,7 +946,7 @@ class YoutubeDL(object):
                             downloaded.append(fname)
                             partial_success = dl(fname, new_info)
                             success = success and partial_success
-                        info_dict['__postprocessors'] = [FFmpegMergerPP(self)]
+                        info_dict['__postprocessors'] = postprocessors
                         info_dict['__files_to_merge'] = downloaded
                     else:
                         # Just a single file
@@ -1064,9 +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:
@@ -1076,13 +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

@@ -39,6 +39,8 @@ __authors__  = (
     'Sergey M.',
     'Michael Orlitzky',
     'Chris Gahan',
+    'Saimadhav Heblikar',
+    'Mike Col',
 )
 
 __license__ = 'Public Domain'
@@ -198,7 +200,9 @@ 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.')
 
     selection.add_option(
         '--playlist-start',
@@ -237,7 +241,14 @@ def parseOpts(overrideArguments=None):
     selection.add_option('--download-archive', metavar='FILE',
                          dest='download_archive',
                          help='Download only videos not listed in the archive file. Record the IDs of all downloaded videos in it.')
-
+    selection.add_option(
+        '--include-ads', dest='include_ads',
+        action='store_true',
+        help='Download advertisements as well (experimental)')
+    selection.add_option(
+        '--youtube-include-dash-manifest', action='store_true',
+        dest='youtube_include_dash_manifest', default=False,
+        help='Try to download the DASH manifest on YouTube videos (experimental)')
 
     authentication.add_option('-u', '--username',
             dest='username', metavar='USERNAME', help='account username')
@@ -250,8 +261,8 @@ 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',
@@ -342,7 +353,8 @@ 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)
@@ -615,6 +627,12 @@ 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.
@@ -715,6 +733,9 @@ def _real_main(argv=None):
         'bidi_workaround': opts.bidi_workaround,
         'debug_printtraffic': opts.debug_printtraffic,
         'prefer_ffmpeg': opts.prefer_ffmpeg,
+        'include_ads': opts.include_ads,
+        'default_search': opts.default_search,
+        'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
     }
 
     with YoutubeDL(ydl_opts) as ydl:

youtube_dl/downloader/__init__.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 from .common import FileDownloader
 from .hls import HlsFD
 from .http import HttpFD
@@ -8,16 +10,17 @@ 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
     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/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

@@ -18,7 +18,7 @@ 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.

youtube_dl/extractor/__init__.py

@@ -27,6 +27,7 @@ from .cbs import CBSIE
 from .channel9 import Channel9IE
 from .cinemassacre import CinemassacreIE
 from .clipfish import ClipfishIE
+from .cliphunter import CliphunterIE
 from .clipsyndicate import ClipsyndicateIE
 from .cmt import CMTIE
 from .cnn import CNNIE
@@ -47,6 +48,8 @@ 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
@@ -62,6 +65,7 @@ from .fktv import (
     FKTVPosteckeIE,
 )
 from .flickr import FlickrIE
+from .franceinter import FranceInterIE
 from .francetv import (
     PluzzIE,
     FranceTvInfoIE,
@@ -70,6 +74,7 @@ from .francetv import (
     CultureboxIE,
 )
 from .freesound import FreesoundIE
+from .freespeech import FreespeechIE
 from .funnyordie import FunnyOrDieIE
 from .gamekings import GamekingsIE
 from .gamespot import GameSpotIE
@@ -80,6 +85,7 @@ from .googlesearch import GoogleSearchIE
 from .hark import HarkIE
 from .hotnewhiphop import HotNewHipHopIE
 from .howcast import HowcastIE
+from .huffpost import HuffPostIE
 from .hypem import HypemIE
 from .ign import IGNIE, OneUPIE
 from .imdb import (
@@ -103,6 +109,7 @@ from .keezmovies import KeezMoviesIE
 from .khanacademy import KhanAcademyIE
 from .kickstarter import KickStarterIE
 from .keek import KeekIE
+from .la7 import LA7IE
 from .liveleak import LiveLeakIE
 from .livestream import LivestreamIE, LivestreamOriginalIE
 from .lynda import (
@@ -110,6 +117,7 @@ from .lynda import (
     LyndaCourseIE
 )
 from .macgamestore import MacGameStoreIE
+from .malemotion import MalemotionIE
 from .mdr import MDRIE
 from .metacafe import MetacafeIE
 from .metacritic import MetacriticIE
@@ -117,7 +125,10 @@ from .mit import TechTVMITIE, MITIE
 from .mixcloud import MixcloudIE
 from .mpora import MporaIE
 from .mofosex import MofosexIE
-from .mtv import MTVIE
+from .mtv import (
+    MTVIE,
+    MTVIggyIE,
+)
 from .muzu import MuzuTVIE
 from .myspace import MySpaceIE
 from .myspass import MySpassIE
@@ -131,6 +142,7 @@ from .nhl import NHLIE, NHLVideocenterIE
 from .niconico import NiconicoIE
 from .ninegag import NineGagIE
 from .novamov import NovamovIE
+from .nowness import NownessIE
 from .nowvideo import NowVideoIE
 from .ooyala import OoyalaIE
 from .orf import ORFIE
@@ -150,6 +162,7 @@ from .rottentomatoes import RottenTomatoesIE
 from .roxwel import RoxwelIE
 from .rtlnow import RTLnowIE
 from .rutube import RutubeIE
+from .servingsys import ServingSysIE
 from .sina import SinaIE
 from .slashdot import SlashdotIE
 from .slideshare import SlideshareIE
@@ -168,6 +181,7 @@ from .southparkstudios import (
 from .space import SpaceIE
 from .spankwire import SpankwireIE
 from .spiegel import SpiegelIE
+from .spike import SpikeIE
 from .stanfordoc import StanfordOpenClassroomIE
 from .statigram import StatigramIE
 from .steam import SteamIE
@@ -210,7 +224,6 @@ from .vine import VineIE
 from .viki import VikiIE
 from .vk import VKIE
 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/brightcove.py

@@ -9,9 +9,11 @@ from .common import InfoExtractor
 from ..utils import (
     compat_urllib_parse,
     find_xpath_attr,
+    fix_xml_ampersands,
     compat_urlparse,
     compat_str,
     compat_urllib_request,
+    compat_parse_qs,
 
     ExtractorError,
     unsmuggle_url,
@@ -83,17 +85,33 @@ class BrightcoveIE(InfoExtractor):
                             lambda m: m.group(1) + '/>', object_str)
         # Fix up some stupid XML, see https://github.com/rg3/youtube-dl/issues/1608
         object_str = object_str.replace('<--', '<!--')
+        object_str = fix_xml_ampersands(object_str)
 
         object_doc = xml.etree.ElementTree.fromstring(object_str)
-        assert 'BrightcoveExperience' in object_doc.attrib['class']
-        params = {
-            'playerID': find_xpath_attr(object_doc, './param', 'name', 'playerID').attrib['value'],
-        }
+
+        fv_el = find_xpath_attr(object_doc, './param', 'name', 'flashVars')
+        if fv_el is not None:
+            flashvars = dict(
+                (k, v[0])
+                for k, v in compat_parse_qs(fv_el.attrib['value']).items())
+        else:
+            flashvars = {}
+
         def find_param(name):
+            if name in flashvars:
+                return flashvars[name]
             node = find_xpath_attr(object_doc, './param', 'name', name)
             if node is not None:
                 return node.attrib['value']
             return None
+
+        params = {}
+
+        playerID = find_param('playerID')
+        if playerID is None:
+            raise ExtractorError('Cannot find player ID')
+        params['playerID'] = playerID
+
         playerKey = find_param('playerKey')
         # Not all pages define this value
         if playerKey is not None:
@@ -114,8 +132,12 @@ class BrightcoveIE(InfoExtractor):
         if it can't be found
         """
         m_brightcove = re.search(
-            r'<object[^>]+?class=([\'"])[^>]*?BrightcoveExperience.*?\1.+?</object>',
-            webpage, re.DOTALL)
+            r'''(?sx)<object
+            (?:
+                [^>]+?class=([\'"])[^>]*?BrightcoveExperience.*?\1 |
+                [^>]*?>\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:
@@ -156,6 +178,7 @@ class BrightcoveIE(InfoExtractor):
         info = self._search_regex(r'var experienceJSON = ({.*?});', webpage, 'json')
         info = json.loads(info)['data']
         video_info = info['programmedContent']['videoPlayer']['mediaDTO']
+        video_info['_youtubedl_adServerURL'] = info.get('adServerURL')
 
         return self._extract_video_info(video_info)
 
@@ -175,7 +198,7 @@ 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'),
@@ -193,6 +216,23 @@ class BrightcoveIE(InfoExtractor):
             info.update({
                 'url': video_info['FLVFullLengthURL'],
             })
-        else:
+
+        if self._downloader.params.get('include_ads', False):
+            adServerURL = video_info.get('_youtubedl_adServerURL')
+            if adServerURL:
+                ad_info = {
+                    '_type': 'url',
+                    'url': adServerURL,
+                }
+                if 'url' in info:
+                    return {
+                        '_type': 'playlist',
+                        'title': info['title'],
+                        'entries': [ad_info, info],
+                    }
+                else:
+                    return ad_info
+
+        if 'url' not in info and not info.get('formats'):
             raise ExtractorError('Unable to extract video url for %s' % info['id'])
         return info

youtube_dl/extractor/cliphunter.py

@@ -0,0 +1,59 @@
+from __future__ import unicode_literals
+
+import re
+import string
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+)
+
+translation_table = {
+    'a': 'h', 'd': 'e', 'e': 'v', 'f': 'o', 'g': 'f', 'i': 'd', 'l': 'n',
+    'm': 'a', 'n': 'm', 'p': 'u', 'q': 't', 'r': 's', 'v': 'p', 'x': 'r',
+    'y': 'l', 'z': 'i',
+    '$': ':', '&': '.', '(': '=', '^': '&', '=': '/',
+}
+
+
+class CliphunterIE(InfoExtractor):
+    IE_NAME = 'cliphunter'
+
+    _VALID_URL = r'''(?x)http://(?:www\.)?cliphunter\.com/w/
+        (?P<id>[0-9]+)/
+        (?P<seo>.+?)(?:$|[#\?])
+    '''
+    _TEST = {
+        'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
+        'file': '1012420.flv',
+        'md5': '15e7740f30428abf70f4223478dc1225',
+        'info_dict': {
+            'title': 'Fun Jynx Maze solo',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        pl_fiji = self._search_regex(
+            r'pl_fiji = \'([^\']+)\'', webpage, 'video data')
+        pl_c_qual = self._search_regex(
+            r'pl_c_qual = "(.)"', webpage, 'video quality')
+        video_title = self._search_regex(
+            r'mediaTitle = "([^"]+)"', webpage, 'title')
+
+        video_url = ''.join(translation_table.get(c, c) for c in pl_fiji)
+
+        formats = [{
+            'url': video_url,
+            'format_id': pl_c_qual,
+        }]
+
+        return {
+            'id': video_id,
+            'title': video_title,
+            'formats': formats,
+        }

youtube_dl/extractor/clipsyndicate.py

@@ -3,7 +3,7 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     find_xpath_attr,
-    fix_xml_all_ampersand,
+    fix_xml_ampersands
 )
 
 
@@ -33,7 +33,7 @@ class ClipsyndicateIE(InfoExtractor):
         pdoc = self._download_xml(
             'http://eplayer.clipsyndicate.com/osmf/playlist?%s' % flvars,
             video_id, u'Downloading video info',
-            transform_source=fix_xml_all_ampersand) 
+            transform_source=fix_xml_ampersands)
 
         track_doc = pdoc.find('trackList/track')
         def find_param(name):

youtube_dl/extractor/cnn.py

@@ -25,12 +25,13 @@ class CNNIE(InfoExtractor):
         },
     },
     {
-        u"url": u"http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29",
-        u"file": u"us_2013_08_21_sot-student-gives-epic-speech.georgia-institute-of-technology.mp4",
-        u"md5": u"b5cc60c60a3477d185af8f19a2a26f4e",
-        u"info_dict": {
-            u"title": "Student's epic speech stuns new freshmen",
-            u"description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\""
+        "url": "http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29",
+        "file": "us_2013_08_21_sot-student-gives-epic-speech.georgia-institute-of-technology.mp4",
+        "md5": "b5cc60c60a3477d185af8f19a2a26f4e",
+        "info_dict": {
+            "title": "Student's epic speech stuns new freshmen",
+            "description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"",
+            "upload_date": "20130821",
         }
     }]
 

youtube_dl/extractor/comedycentral.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -15,30 +17,22 @@ class ComedyCentralIE(MTVServicesInfoExtractor):
     _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"
         }
     }
 
@@ -94,20 +88,20 @@ class ComedyCentralShowsIE(InfoExtractor):
     def _transform_rtmp_url(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

@@ -1,4 +1,5 @@
 import base64
+import hashlib
 import json
 import os
 import re
@@ -62,13 +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.
@@ -219,6 +222,8 @@ class InfoExtractor(object):
                           webpage_bytes[:1024])
             if m:
                 encoding = m.group(1).decode('ascii')
+            elif webpage_bytes.startswith(b'\xff\xfe'):
+                encoding = 'utf-16'
             else:
                 encoding = 'utf-8'
         if self._downloader.params.get('dump_intermediate_pages', False):
@@ -234,6 +239,9 @@ class InfoExtractor(object):
                 url = url_or_request.get_full_url()
             except AttributeError:
                 url = url_or_request
+            if len(url) > 200:
+                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)
             self.to_screen(u'Saving request to ' + filename)
@@ -458,6 +466,9 @@ class InfoExtractor(object):
         return RATING_TABLE.get(rating.lower(), None)
 
     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

@@ -1,4 +1,5 @@
 # coding: utf-8
+from __future__ import unicode_literals
 
 import re
 import json
@@ -20,30 +21,31 @@ class CondeNastIE(InfoExtractor):
 
     # The keys are the supported sites and the values are the name to be shown
     # to the user and in the extractor description.
-    _SITES = {'wired': u'WIRED',
-              'gq': u'GQ',
-              'vogue': u'Vogue',
-              'glamour': u'Glamour',
-              'wmagazine': u'W Magazine',
-              'vanityfair': u'Vanity Fair',
-              }
+    _SITES = {
+        'wired': 'WIRED',
+        'gq': 'GQ',
+        'vogue': 'Vogue',
+        'glamour': 'Glamour',
+        'wmagazine': 'W Magazine',
+        'vanityfair': 'Vanity Fair',
+    }
 
-    _VALID_URL = r'http://(video|www).(?P<site>%s).com/(?P<type>watch|series|video)/(?P<id>.+)' % '|'.join(_SITES.keys())
-    IE_DESC = u'Condé Nast media group: %s' % ', '.join(sorted(_SITES.values()))
+    _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 = {
-        u'url': u'http://video.wired.com/watch/3d-printed-speakers-lit-with-led',
-        u'file': u'5171b343c2b4c00dd0c1ccb3.mp4',
-        u'md5': u'1921f713ed48aabd715691f774c451f7',
-        u'info_dict': {
-            u'title': u'3D Printed Speakers Lit With LED',
-            u'description': u'Check out these beautiful 3D printed LED speakers.  You can\'t actually buy them, but LumiGeek is working on a board that will let you make you\'re own.',
+        'url': 'http://video.wired.com/watch/3d-printed-speakers-lit-with-led',
+        'file': '5171b343c2b4c00dd0c1ccb3.mp4',
+        'md5': '1921f713ed48aabd715691f774c451f7',
+        'info_dict': {
+            'title': '3D Printed Speakers Lit With LED',
+            'description': 'Check out these beautiful 3D printed LED speakers.  You can\'t actually buy them, but LumiGeek is working on a board that will let you make you\'re own.',
         }
     }
 
     def _extract_series(self, url, webpage):
         title = self._html_search_regex(r'<div class="cne-series-info">.*?<h1>(.+?)</h1>',
-                                        webpage, u'series title', flags=re.DOTALL)
+                                        webpage, 'series title', flags=re.DOTALL)
         url_object = compat_urllib_parse_urlparse(url)
         base_url = '%s://%s' % (url_object.scheme, url_object.netloc)
         m_paths = re.finditer(r'<p class="cne-thumb-title">.*?<a href="(/watch/.+?)["\?]',
@@ -57,39 +59,41 @@ class CondeNastIE(InfoExtractor):
         description = self._html_search_regex([r'<div class="cne-video-description">(.+?)</div>',
                                                r'<div class="video-post-content">(.+?)</div>',
                                                ],
-                                              webpage, u'description',
+                                              webpage, 'description',
                                               fatal=False, flags=re.DOTALL)
         params = self._search_regex(r'var params = {(.+?)}[;,]', webpage,
-                                    u'player params', flags=re.DOTALL)
-        video_id = self._search_regex(r'videoId: [\'"](.+?)[\'"]', params, u'video id')
-        player_id = self._search_regex(r'playerId: [\'"](.+?)[\'"]', params, u'player id')
-        target = self._search_regex(r'target: [\'"](.+?)[\'"]', params, u'target')
+                                    'player params', flags=re.DOTALL)
+        video_id = self._search_regex(r'videoId: [\'"](.+?)[\'"]', params, 'video id')
+        player_id = self._search_regex(r'playerId: [\'"](.+?)[\'"]', params, 'player id')
+        target = self._search_regex(r'target: [\'"](.+?)[\'"]', params, 'target')
         data = compat_urllib_parse.urlencode({'videoId': video_id,
                                               'playerId': player_id,
                                               'target': target,
                                               })
         base_info_url = self._search_regex(r'url = [\'"](.+?)[\'"][,;]',
-                                           webpage, u'base info url',
+                                           webpage, 'base info url',
                                            default='http://player.cnevids.com/player/loader.js?')
         info_url = base_info_url + data
         info_page = self._download_webpage(info_url, video_id,
-                                           u'Downloading video info')
-        video_info = self._search_regex(r'var video = ({.+?});', info_page, u'video info')
+                                           'Downloading video info')
+        video_info = self._search_regex(r'var video = ({.+?});', info_page, 'video info')
         video_info = json.loads(video_info)
 
-        def _formats_sort_key(f):
-            type_ord = 1 if f['type'] == 'video/mp4' else 0
-            quality_ord = 1 if f['quality'] == 'high' else 0
-            return (quality_ord, type_ord)
-        best_format = sorted(video_info['sources'][0], key=_formats_sort_key)[-1]
+        formats = [{
+            'format_id': '%s-%s' % (fdata['type'].split('/')[-1], fdata['quality']),
+            'url': fdata['src'],
+            'ext': fdata['type'].split('/')[-1],
+            'quality': 1 if fdata['quality'] == 'high' else 0,
+        } for fdata in video_info['sources'][0]]
+        self._sort_formats(formats)
 
-        return {'id': video_id,
-                'url': best_format['src'],
-                'ext': best_format['type'].split('/')[-1],
-                'title': video_info['title'],
-                'thumbnail': video_info['poster_frame'],
-                'description': description,
-                }
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': video_info['title'],
+            'thumbnail': video_info['poster_frame'],
+            'description': description,
+        }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/cspan.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 
 class CSpanIE(InfoExtractor):
-    _VALID_URL = r'http://www\.c-spanvideo\.org/program/(.*)'
+    _VALID_URL = r'http://(?:www\.)?c-spanvideo\.org/program/(?P<name>.*)'
     IE_DESC = 'C-SPAN'
     _TEST = {
         'url': 'http://www.c-spanvideo.org/program/HolderonV',
@@ -20,13 +20,14 @@ class CSpanIE(InfoExtractor):
             '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.',
         },
+        '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)
+        prog_name = mobj.group('name')
         webpage = self._download_webpage(url, prog_name)
-        video_id = self._search_regex(r'programid=(.*?)&', webpage, 'video id')
+        video_id = self._search_regex(r'prog(?:ram)?id=(.*?)&', webpage, 'video id')
 
         title = self._html_search_regex(
             r'<!-- title -->\n\s*<h1[^>]*>(.*?)</h1>', webpage, 'title')

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/dropbox.py

@@ -0,0 +1,31 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import os.path
+import re
+
+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',
+        'info_dict': {
+            'title': '20131219_085616'
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        title = os.path.splitext(mobj.group('title'))[0]
+        video_url = url + '?dl=1'
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': video_url,
+        }

youtube_dl/extractor/facebook.py

@@ -17,7 +17,12 @@ from ..utils import (
 class FacebookIE(InfoExtractor):
     """Information Extractor for Facebook"""
 
-    _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:[^#?]*#!/)?(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
+    _VALID_URL = r'''(?x)
+        (?:https?://)?(?:\w+\.)?facebook\.com/
+        (?:[^#?]*\#!/)?
+        (?:video/video\.php|photo\.php|video/embed)\?(?:.*?)
+        (?:v|video_id)=(?P<id>[0-9]+)
+        (?:.*)'''
     _LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1'
     _CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1'
     _NETRC_MACHINE = 'facebook'
@@ -90,7 +95,7 @@ class FacebookIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         if mobj is None:
             raise ExtractorError(u'Invalid URL: %s' % url)
-        video_id = mobj.group('ID')
+        video_id = mobj.group('id')
 
         url = 'https://www.facebook.com/video/video.php?v=%s' % video_id
         webpage = self._download_webpage(url, video_id)

youtube_dl/extractor/flickr.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -11,13 +13,13 @@ class FlickrIE(InfoExtractor):
     """Information Extractor for Flickr videos"""
     _VALID_URL = r'(?:https?://)?(?:www\.|secure\.)?flickr\.com/photos/(?P<uploader_id>[\w\-_@]+)/(?P<id>\d+).*'
     _TEST = {
-        u'url': u'http://www.flickr.com/photos/forestwander-nature-pictures/5645318632/in/photostream/',
-        u'file': u'5645318632.mp4',
-        u'md5': u'6fdc01adbc89d72fc9c4f15b4a4ba87b',
-        u'info_dict': {
-            u"description": u"Waterfalls in the Springtime at Dark Hollow Waterfalls. These are located just off of Skyline Drive in Virginia. They are only about 6/10 of a mile hike but it is a pretty steep hill and a good climb back up.", 
-            u"uploader_id": u"forestwander-nature-pictures", 
-            u"title": u"Dark Hollow Waterfalls"
+        'url': 'http://www.flickr.com/photos/forestwander-nature-pictures/5645318632/in/photostream/',
+        'file': '5645318632.mp4',
+        'md5': '6fdc01adbc89d72fc9c4f15b4a4ba87b',
+        'info_dict': {
+            "description": "Waterfalls in the Springtime at Dark Hollow Waterfalls. These are located just off of Skyline Drive in Virginia. They are only about 6/10 of a mile hike but it is a pretty steep hill and a good climb back up.", 
+            "uploader_id": "forestwander-nature-pictures", 
+            "title": "Dark Hollow Waterfalls"
         }
     }
 
@@ -29,13 +31,13 @@ class FlickrIE(InfoExtractor):
         webpage_url = 'http://www.flickr.com/photos/' + video_uploader_id + '/' + video_id
         webpage = self._download_webpage(webpage_url, video_id)
 
-        secret = self._search_regex(r"photo_secret: '(\w+)'", webpage, u'secret')
+        secret = self._search_regex(r"photo_secret: '(\w+)'", webpage, 'secret')
 
         first_url = 'https://secure.flickr.com/apps/video/video_mtl_xml.gne?v=x&photo_id=' + video_id + '&secret=' + secret + '&bitrate=700&target=_self'
         first_xml = self._download_webpage(first_url, video_id, 'Downloading first data webpage')
 
         node_id = self._html_search_regex(r'<Item id="id">(\d+-\d+)</Item>',
-            first_xml, u'node_id')
+            first_xml, 'node_id')
 
         second_url = 'https://secure.flickr.com/video_playlist.gne?node_id=' + node_id + '&tech=flash&mode=playlist&bitrate=700&secret=' + secret + '&rd=video.yahoo.com&noad=1'
         second_xml = self._download_webpage(second_url, video_id, 'Downloading second data webpage')
@@ -44,7 +46,7 @@ class FlickrIE(InfoExtractor):
 
         mobj = re.search(r'<STREAM APP="(.+?)" FULLPATH="(.+?)"', second_xml)
         if mobj is None:
-            raise ExtractorError(u'Unable to extract video url')
+            raise ExtractorError('Unable to extract video url')
         video_url = mobj.group(1) + unescapeHTML(mobj.group(2))
 
         return [{

youtube_dl/extractor/franceinter.py

@@ -0,0 +1,38 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class FranceInterIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]{6})'
+    _TEST = {
+        'url': 'http://www.franceinter.fr/player/reecouter?play=793962',
+        'file': '793962.mp3',
+        'md5': '4764932e466e6f6c79c317d2e74f6884',
+        "info_dict": {
+            "title": "L’Histoire dans les jeux vidéo",
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        title = self._html_search_regex(
+            r'<span class="roll_overflow">(.*?)</span></h1>', webpage, 'title')
+        path = self._search_regex(
+            r'&urlAOD=(.*?)&startTime', webpage, 'video url')
+        video_url = 'http://www.franceinter.fr/' + path
+
+        return {
+            'id': video_id,
+            'formats': [{
+                'url': video_url,
+                'vcodec': 'none',
+            }],
+            'title': title,
+        }

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/gamespot.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 import json
 
@@ -13,12 +15,12 @@ from ..utils import (
 class GameSpotIE(InfoExtractor):
     _VALID_URL = r'(?:http://)?(?:www\.)?gamespot\.com/.*-(?P<page_id>\d+)/?'
     _TEST = {
-        u"url": u"http://www.gamespot.com/arma-iii/videos/arma-iii-community-guide-sitrep-i-6410818/",
-        u"file": u"gs-2300-6410818.mp4",
-        u"md5": u"b2a30deaa8654fcccd43713a6b6a4825",
-        u"info_dict": {
-            u"title": u"Arma 3 - Community Guide: SITREP I",
-            u'description': u'Check out this video where some of the basics of Arma 3 is explained.',
+        "url": "http://www.gamespot.com/arma-iii/videos/arma-iii-community-guide-sitrep-i-6410818/",
+        "file": "gs-2300-6410818.mp4",
+        "md5": "b2a30deaa8654fcccd43713a6b6a4825",
+        "info_dict": {
+            "title": "Arma 3 - Community Guide: SITREP I",
+            'description': 'Check out this video where some of the basics of Arma 3 is explained.',
         }
     }
 
@@ -26,7 +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
@@ -34,7 +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

@@ -1,4 +1,4 @@
-import re
+from __future__ import unicode_literals
 
 from .mtv import MTVServicesInfoExtractor
 
@@ -6,22 +6,13 @@ from .mtv import MTVServicesInfoExtractor
 class GametrailersIE(MTVServicesInfoExtractor):
     _VALID_URL = r'http://www\.gametrailers\.com/(?P<type>videos|reviews|full-episodes)/(?P<id>.*?)/(?P<title>.*)'
     _TEST = {
-        u'url': u'http://www.gametrailers.com/videos/zbvr8i/mirror-s-edge-2-e3-2013--debut-trailer',
-        u'file': u'70e9a5d7-cf25-4a10-9104-6f3e7342ae0d.mp4',
-        u'md5': u'4c8e67681a0ea7ec241e8c09b3ea8cf7',
-        u'info_dict': {
-            u'title': u'E3 2013: Debut Trailer',
-            u'description': u'Faith is back!  Check out the World Premiere trailer for Mirror\'s Edge 2 straight from the EA Press Conference at E3 2013!',
+        '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',
+            '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, u'mgid')
-        return self._get_videos_info(mgid)

youtube_dl/extractor/generic.py

@@ -92,11 +92,12 @@ class GenericIE(InfoExtractor):
         # ooyala video
         {
             'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
+            'file': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ.mp4',
             'md5': '5644c6ca5d5782c1d0d350dad9bd840c',
             'info_dict': {
                 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
                 'ext': 'mp4',
-                'title': '2cc213299525360.mov', #that's what we get
+                'title': '2cc213299525360.mov',  # that's what we get
             },
         },
     ]
@@ -161,8 +162,19 @@ class GenericIE(InfoExtractor):
     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)
@@ -318,6 +330,18 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'Novamov')
 
+        # Look for embedded Facebook player
+        mobj = re.search(
+            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:

youtube_dl/extractor/hotnewhiphop.py

@@ -1,17 +1,25 @@
+from __future__ import unicode_literals
+
 import re
 import base64
 
 from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+    compat_urllib_request,
+    ExtractorError,
+    HEADRequest,
+)
 
 
 class HotNewHipHopIE(InfoExtractor):
-    _VALID_URL = r'http://www\.hotnewhiphop.com/.*\.(?P<id>.*)\.html'
+    _VALID_URL = r'http://www\.hotnewhiphop\.com/.*\.(?P<id>.*)\.html'
     _TEST = {
-        u'url': u"http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html",
-        u'file': u'1435540.mp3',
-        u'md5': u'2c2cd2f76ef11a9b3b581e8b232f3d96',
-        u'info_dict': {
-            u"title": u'Freddie Gibbs "Lay It Down"'
+        'url': 'http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html',
+        'file': '1435540.mp3',
+        'md5': '2c2cd2f76ef11a9b3b581e8b232f3d96',
+        'info_dict': {
+            'title': 'Freddie Gibbs - Lay It Down'
         }
     }
 
@@ -21,24 +29,41 @@ class HotNewHipHopIE(InfoExtractor):
 
         webpage_src = self._download_webpage(url, video_id)
 
-        video_url_base64 = self._search_regex(r'data-path="(.*?)"',
-            webpage_src, u'video URL', fatal=False)
+        video_url_base64 = self._search_regex(
+            r'data-path="(.*?)"', webpage_src, u'video URL', fatal=False)
 
-        if video_url_base64 == None:
-            video_url = self._search_regex(r'"contentUrl" content="(.*?)"', webpage_src,
-                u'video URL')
+        if video_url_base64 is None:
+            video_url = self._search_regex(
+                r'"contentUrl" content="(.*?)"', webpage_src, u'video URL')
             return self.url_result(video_url, ie='Youtube')
 
-        video_url = base64.b64decode(video_url_base64).decode('utf-8')
+        reqdata = compat_urllib_parse.urlencode([
+            ('mediaType', 's'),
+            ('mediaId', video_id),
+        ])
+        r = compat_urllib_request.Request(
+            'http://www.hotnewhiphop.com/ajax/media/getActions/', data=reqdata)
+        r.add_header('Content-Type', 'application/x-www-form-urlencoded')
+        mkd = self._download_json(
+            r, video_id, note='Requesting media key',
+            errnote='Could not download media key')
+        if 'mediaKey' not in mkd:
+            raise ExtractorError('Did not get a media key')
 
-        video_title = self._html_search_regex(r"<title>(.*)</title>",
-            webpage_src, u'title')
+        redirect_url = base64.b64decode(video_url_base64).decode('utf-8')
+        redirect_req = HEADRequest(redirect_url)
+        req = self._request_webpage(
+            redirect_req, video_id,
+            note='Resolving final URL', errnote='Could not resolve final URL')
+        video_url = req.geturl()
+        if video_url.endswith('.html'):
+            raise ExtractorError('Redirect failed')
 
-        results = [{
-                    'id': video_id,
-                    'url' : video_url,
-                    'title' : video_title,
-                    'thumbnail' : self._og_search_thumbnail(webpage_src),
-                    'ext' : 'mp3',
-                    }]
-        return results
+        video_title = self._og_search_title(webpage_src).strip()
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': video_title,
+            'thumbnail': self._og_search_thumbnail(webpage_src),
+        }

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

@@ -68,22 +68,15 @@ class ImdbListIE(InfoExtractor):
         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')
+        webpage = self._download_webpage(url, list_id)
+        list_code = self._search_regex(
+            r'(?s)<div\s+class="list\sdetail">(.*?)class="see-more"',
+            webpage, 'list code')
+        entries = [
+            self.url_result('http://www.imdb.com' + m, 'Imdb')
+            for m in re.findall(r'href="(/video/imdb/vi[^"]+)"', webpage)]
 
-        # 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'))
+        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/kankan.py

@@ -1,21 +1,24 @@
+from __future__ import unicode_literals
+
 import re
 import hashlib
 
 from .common import InfoExtractor
-from ..utils import determine_ext
 
 _md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
 
+
 class KankanIE(InfoExtractor):
     _VALID_URL = r'https?://(?:.*?\.)?kankan\.com/.+?/(?P<id>\d+)\.shtml'
     
     _TEST = {
-        u'url': u'http://yinyue.kankan.com/vod/48/48863.shtml',
-        u'file': u'48863.flv',
-        u'md5': u'29aca1e47ae68fc28804aca89f29507e',
-        u'info_dict': {
-            u'title': u'Ready To Go',
+        'url': 'http://yinyue.kankan.com/vod/48/48863.shtml',
+        'file': '48863.flv',
+        'md5': '29aca1e47ae68fc28804aca89f29507e',
+        'info_dict': {
+            'title': 'Ready To Go',
         },
+        'skip': 'Only available from China',
     }
 
     def _real_extract(self, url):
@@ -23,22 +26,23 @@ class KankanIE(InfoExtractor):
         video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
 
-        title = self._search_regex(r'(?:G_TITLE=|G_MOVIE_TITLE = )[\'"](.+?)[\'"]', webpage, u'video title')
+        title = self._search_regex(r'(?:G_TITLE=|G_MOVIE_TITLE = )[\'"](.+?)[\'"]', webpage, 'video title')
         surls = re.search(r'surls:\[\'.+?\'\]|lurl:\'.+?\.flv\'', webpage).group(0)
         gcids = re.findall(r"http://.+?/.+?/(.+?)/", surls)
         gcid = gcids[-1]
 
-        video_info_page = self._download_webpage('http://p2s.cl.kankan.com/getCdnresource_flv?gcid=%s' % gcid,
-                                                 video_id, u'Downloading video url info')
-        ip = self._search_regex(r'ip:"(.+?)"', video_info_page, u'video url ip')
-        path = self._search_regex(r'path:"(.+?)"', video_info_page, u'video url path')
-        param1 = self._search_regex(r'param1:(\d+)', video_info_page, u'param1')
-        param2 = self._search_regex(r'param2:(\d+)', video_info_page, u'param2')
+        info_url = 'http://p2s.cl.kankan.com/getCdnresource_flv?gcid=%s' % gcid
+        video_info_page = self._download_webpage(
+            info_url, video_id, 'Downloading video url info')
+        ip = self._search_regex(r'ip:"(.+?)"', video_info_page, 'video url ip')
+        path = self._search_regex(r'path:"(.+?)"', video_info_page, 'video url path')
+        param1 = self._search_regex(r'param1:(\d+)', video_info_page, 'param1')
+        param2 = self._search_regex(r'param2:(\d+)', video_info_page, 'param2')
         key = _md5('xl_mp43651' + param1 + param2)
         video_url = 'http://%s%s?key=%s&key1=%s' % (ip, path, key, param2)
 
-        return {'id': video_id,
-                'title': title,
-                'url': video_url,
-                'ext': determine_ext(video_url),
-                }
+        return {
+            'id': video_id,
+            'title': title,
+            'url': video_url,
+        }

youtube_dl/extractor/la7.py

@@ -0,0 +1,62 @@
+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,
+        }
+    }
+
+    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/malemotion.py

@@ -0,0 +1,58 @@
+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,
+        }
+    }
+
+    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/metacritic.py

@@ -4,7 +4,7 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
-    fix_xml_all_ampersand,
+    fix_xml_ampersands,
 )
 
 
@@ -27,7 +27,7 @@ class MetacriticIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
         # The xml is not well formatted, there are raw '&'
         info = self._download_xml('http://www.metacritic.com/video_data?video=' + video_id,
-            video_id, 'Downloading info xml', transform_source=fix_xml_all_ampersand)
+            video_id, 'Downloading info xml', transform_source=fix_xml_ampersands)
 
         clip = next(c for c in info.findall('playList/clip') if c.find('id').text == video_id)
         formats = []

youtube_dl/extractor/mixcloud.py

@@ -1,4 +1,5 @@
-import json
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -10,17 +11,17 @@ from ..utils import (
 
 class MixcloudIE(InfoExtractor):
     _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)'
-    IE_NAME = u'mixcloud'
+    IE_NAME = 'mixcloud'
 
     _TEST = {
-        u'url': u'http://www.mixcloud.com/dholbach/cryptkeeper/',
-        u'file': u'dholbach-cryptkeeper.mp3',
-        u'info_dict': {
-            u'title': u'Cryptkeeper',
-            u'description': u'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
-            u'uploader': u'Daniel Holbach',
-            u'uploader_id': u'dholbach',
-            u'upload_date': u'20111115',
+        'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/',
+        'file': 'dholbach-cryptkeeper.mp3',
+        'info_dict': {
+            'title': 'Cryptkeeper',
+            'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
+            'uploader': 'Daniel Holbach',
+            'uploader_id': 'dholbach',
+            'upload_date': '20111115',
         },
     }
 
@@ -42,17 +43,18 @@ class MixcloudIE(InfoExtractor):
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-
         uploader = mobj.group(1)
         cloudcast_name = mobj.group(2)
         track_id = '-'.join((uploader, cloudcast_name))
-        api_url = 'http://api.mixcloud.com/%s/%s/' % (uploader, cloudcast_name)
-        webpage = self._download_webpage(url, track_id)
-        json_data = self._download_webpage(api_url, track_id,
-            u'Downloading cloudcast info')
-        info = json.loads(json_data)
 
-        preview_url = self._search_regex(r'data-preview-url="(.+?)"', webpage, u'preview url')
+        webpage = self._download_webpage(url, track_id)
+
+        api_url = 'http://api.mixcloud.com/%s/%s/' % (uploader, cloudcast_name)
+        info = self._download_json(
+            api_url, track_id, 'Downloading cloudcast info')
+
+        preview_url = self._search_regex(
+            r'\s(?:data-preview-url|m-preview)="(.+?)"', webpage, 'preview url')
         song_url = preview_url.replace('/previews/', '/c/originals/')
         template_url = re.sub(r'(stream\d*)', 'stream%d', song_url)
         final_song_url = self._get_url(template_url)

youtube_dl/extractor/mpora.py

@@ -34,7 +34,7 @@ class MporaIE(InfoExtractor):
 
         data = json.loads(data_json)
 
-        uploader = data['info_overlay']['name']
+        uploader = data['info_overlay'].get('username')
         duration = data['video']['duration'] // 1000
         thumbnail = data['video']['encodings']['sd']['poster']
         title = data['info_overlay']['title']

youtube_dl/extractor/mtv.py

@@ -1,12 +1,18 @@
+from __future__ import unicode_literals
+
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
     compat_urllib_parse,
     ExtractorError,
+    find_xpath_attr,
+    fix_xml_ampersands,
+    url_basename,
+    RegexNotFoundError,
 )
 
+
 def _media_xml_tag(tag):
     return '{http://search.yahoo.com/mrss/}%s' % tag
 
@@ -33,10 +39,9 @@ class MTVServicesInfoExtractor(InfoExtractor):
         else:
             return thumb_node.attrib['url']
 
-    def _extract_video_formats(self, metadataXml):
-        if '/error_country_block.swf' in metadataXml:
-            raise ExtractorError(u'This video is not available from your country.', expected=True)
-        mdoc = xml.etree.ElementTree.fromstring(metadataXml.encode('utf-8'))
+    def _extract_video_formats(self, mdoc):
+        if re.match(r'.*/error_country_block\.swf$', mdoc.find('.//src').text) is not None:
+            raise ExtractorError('This video is not available from your country.', expected=True)
 
         formats = []
         for rendition in mdoc.findall('.//rendition'):
@@ -59,11 +64,12 @@ class MTVServicesInfoExtractor(InfoExtractor):
         self.report_extraction(video_id)
         mediagen_url = itemdoc.find('%s/%s' % (_media_xml_tag('group'), _media_xml_tag('content'))).attrib['url']
         # Remove the templates, like &device={device}
-        mediagen_url = re.sub(r'&[^=]*?={.*?}(?=(&|$))', u'', mediagen_url)
+        mediagen_url = re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', mediagen_url)
         if 'acceptMethods' not in mediagen_url:
             mediagen_url += '&acceptMethods=fms'
-        mediagen_page = self._download_webpage(mediagen_url, video_id,
-                                               u'Downloading video urls')
+
+        mediagen_doc = self._download_xml(mediagen_url, video_id,
+            'Downloading video urls')
 
         description_node = itemdoc.find('description')
         if description_node is not None:
@@ -71,9 +77,23 @@ class MTVServicesInfoExtractor(InfoExtractor):
         else:
             description = None
 
+        title_el = None
+        if title_el is None:
+            title_el = find_xpath_attr(
+                itemdoc, './/{http://search.yahoo.com/mrss/}category',
+                'scheme', 'urn:mtvn:video_title')
+        if title_el is None:
+            title_el = itemdoc.find('.//{http://search.yahoo.com/mrss/}title')
+        if title_el is None:
+            title_el = itemdoc.find('.//title')
+        title = title_el.text
+        if title is None:
+            raise ExtractorError('Could not find video title')
+        title = title.strip()
+
         return {
-            'title': itemdoc.find('title').text,
-            'formats': self._extract_video_formats(mediagen_page),
+            'title': title,
+            'formats': self._extract_video_formats(mediagen_doc),
             'id': video_id,
             'thumbnail': self._get_thumbnail_url(uri, itemdoc),
             'description': description,
@@ -83,14 +103,25 @@ class MTVServicesInfoExtractor(InfoExtractor):
         video_id = self._id_from_uri(uri)
         data = compat_urllib_parse.urlencode({'uri': uri})
 
-        def fix_ampersand(s):
-            """ Fix unencoded ampersand in XML """
-            return s.replace(u'& ', '& ')
         idoc = self._download_xml(
             self._FEED_URL + '?' + data, video_id,
-            u'Downloading info', transform_source=fix_ampersand)
+            'Downloading info', transform_source=fix_xml_ampersands)
         return [self._get_video_info(item) for item in idoc.findall('.//item')]
 
+    def _real_extract(self, url):
+        title = url_basename(url)
+        webpage = self._download_webpage(url, title)
+        try:
+            # 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')
+        return self._get_videos_info(mgid)
+
 
 class MTVIE(MTVServicesInfoExtractor):
     _VALID_URL = r'''(?x)^https?://
@@ -101,25 +132,25 @@ class MTVIE(MTVServicesInfoExtractor):
 
     _TESTS = [
         {
-            u'url': u'http://www.mtv.com/videos/misc/853555/ours-vh1-storytellers.jhtml',
-            u'file': u'853555.mp4',
-            u'md5': u'850f3f143316b1e71fa56a4edfd6e0f8',
-            u'info_dict': {
-                u'title': u'Taylor Swift - "Ours (VH1 Storytellers)"',
-                u'description': u'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.',
+            'url': 'http://www.mtv.com/videos/misc/853555/ours-vh1-storytellers.jhtml',
+            'file': '853555.mp4',
+            'md5': '850f3f143316b1e71fa56a4edfd6e0f8',
+            'info_dict': {
+                'title': 'Taylor Swift - "Ours (VH1 Storytellers)"',
+                'description': 'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.',
             },
         },
         {
-            u'add_ie': ['Vevo'],
-            u'url': u'http://www.mtv.com/videos/taylor-swift/916187/everything-has-changed-ft-ed-sheeran.jhtml',
-            u'file': u'USCJY1331283.mp4',
-            u'md5': u'73b4e7fcadd88929292fe52c3ced8caf',
-            u'info_dict': {
-                u'title': u'Everything Has Changed',
-                u'upload_date': u'20130606',
-                u'uploader': u'Taylor Swift',
+            'add_ie': ['Vevo'],
+            'url': 'http://www.mtv.com/videos/taylor-swift/916187/everything-has-changed-ft-ed-sheeran.jhtml',
+            'file': 'USCJY1331283.mp4',
+            'md5': '73b4e7fcadd88929292fe52c3ced8caf',
+            'info_dict': {
+                'title': 'Everything Has Changed',
+                'upload_date': '20130606',
+                'uploader': 'Taylor Swift',
             },
-            u'skip': u'VEVO is only available in some countries',
+            'skip': 'VEVO is only available in some countries',
         },
     ]
 
@@ -138,8 +169,22 @@ class MTVIE(MTVServicesInfoExtractor):
                                webpage, re.DOTALL)
             if m_vevo:
                 vevo_id = m_vevo.group(1);
-                self.to_screen(u'Vevo video detected: %s' % vevo_id)
+                self.to_screen('Vevo video detected: %s' % vevo_id)
                 return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
     
-            uri = self._html_search_regex(r'/uri/(.*?)\?', webpage, u'uri')
+            uri = self._html_search_regex(r'/uri/(.*?)\?', webpage, 'uri')
         return self._get_videos_info(uri)
+
+
+class MTVIggyIE(MTVServicesInfoExtractor):
+    IE_NAME = 'mtviggy.com'
+    _VALID_URL = r'https?://www\.mtviggy\.com/videos/.+'
+    _TEST = {
+        'url': 'http://www.mtviggy.com/videos/arcade-fire-behind-the-scenes-at-the-biggest-music-experiment-yet/',
+        'info_dict': {
+            'id': '984696',
+            'ext': 'mp4',
+            'title': 'Arcade Fire: Behind the Scenes at the Biggest Music Experiment Yet',
+        }
+    }
+    _FEED_URL = 'http://all.mtvworldverticals.com/feed-xml/'

youtube_dl/extractor/myspace.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 import json
 
@@ -8,41 +10,75 @@ from ..utils import (
 
 
 class MySpaceIE(InfoExtractor):
-    _VALID_URL = r'https?://myspace\.com/([^/]+)/video/[^/]+/(?P<id>\d+)'
+    _VALID_URL = r'https?://myspace\.com/([^/]+)/(?P<mediatype>video/[^/]+/|music/song/.*?)(?P<id>\d+)'
 
-    _TEST = {
-        u'url': u'https://myspace.com/coldplay/video/viva-la-vida/100008689',
-        u'info_dict': {
-            u'id': u'100008689',
-            u'ext': u'flv',
-            u'title': u'Viva La Vida',
-            u'description': u'The official Viva La Vida video, directed by Hype Williams',
-            u'uploader': u'Coldplay',
-            u'uploader_id': u'coldplay',
+    _TESTS = [
+        {
+            'url': 'https://myspace.com/coldplay/video/viva-la-vida/100008689',
+            'info_dict': {
+                'id': '100008689',
+                'ext': 'flv',
+                'title': 'Viva La Vida',
+                'description': 'The official Viva La Vida video, directed by Hype Williams',
+                'uploader': 'Coldplay',
+                'uploader_id': 'coldplay',
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
         },
-        u'params': {
-            # rtmp download
-            u'skip_download': True,
+        # song
+        {
+            'url': 'https://myspace.com/spiderbags/music/song/darkness-in-my-heart-39008454-27041242',
+            'info_dict': {
+                'id': '39008454',
+                'ext': 'flv',
+                'title': 'Darkness In My Heart',
+                'uploader_id': 'spiderbags',
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
         },
-    }
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
-        context = json.loads(self._search_regex(r'context = ({.*?});', webpage,
-            u'context'))
-        video = context['video']
-        rtmp_url, play_path = video['streamUrl'].split(';', 1)
 
-        return {
-            'id': compat_str(video['mediaId']),
-            'title': video['title'],
+        if mobj.group('mediatype').startswith('music/song'):
+            # songs don't store any useful info in the 'context' variable
+            def search_data(name):
+                return self._search_regex(r'data-%s="(.*?)"' % name, webpage,
+                    name)
+            streamUrl = search_data('stream-url')
+            info = {
+                'id': video_id,
+                'title': self._og_search_title(webpage),
+                'uploader_id': search_data('artist-username'),
+                'thumbnail': self._og_search_thumbnail(webpage),
+            }
+        else:
+            context = json.loads(self._search_regex(r'context = ({.*?});', webpage,
+                u'context'))
+            video = context['video']
+            streamUrl = video['streamUrl']
+            info = {
+                'id': compat_str(video['mediaId']),
+                'title': video['title'],
+                'description': video['description'],
+                'thumbnail': video['imageUrl'],
+                'uploader': video['artistName'],
+                'uploader_id': video['artistUsername'],
+            }
+
+        rtmp_url, play_path = streamUrl.split(';', 1)
+        info.update({
             'url': rtmp_url,
             'play_path': play_path,
             'ext': 'flv',
-            'description': video['description'],
-            'thumbnail': video['imageUrl'],
-            'uploader': video['artistName'],
-            'uploader_id': video['artistUsername'],
-        }
+        })
+        return info

youtube_dl/extractor/newgrounds.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import json
 import re
 
@@ -8,12 +10,12 @@ from ..utils import determine_ext
 class NewgroundsIE(InfoExtractor):
     _VALID_URL = r'(?:https?://)?(?:www\.)?newgrounds\.com/audio/listen/(?P<id>\d+)'
     _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',
+        'file': '549479.mp3',
+        'md5': 'fe6033d297591288fa1c1f780386f07a',
+        'info_dict': {
+            "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/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/redtube.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -6,14 +8,14 @@ from .common import InfoExtractor
 class RedTubeIE(InfoExtractor):
     _VALID_URL = r'http://(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
     _TEST = {
-        u'url': u'http://www.redtube.com/66418',
-        u'file': u'66418.mp4',
+        'url': 'http://www.redtube.com/66418',
+        'file': '66418.mp4',
         # md5 varies from time to time, as in
         # https://travis-ci.org/rg3/youtube-dl/jobs/14052463#L295
-        #u'md5': u'7b8c22b5e7098a3e1c09709df1126d2d',
-        u'info_dict': {
-            u"title": u"Sucked on a toilet",
-            u"age_limit": 18,
+        #'md5': u'7b8c22b5e7098a3e1c09709df1126d2d',
+        'info_dict': {
+            "title": "Sucked on a toilet",
+            "age_limit": 18,
         }
     }
 
@@ -33,14 +35,19 @@ class RedTubeIE(InfoExtractor):
             r'<h1 class="videoTitle[^"]*">(.+?)</h1>',
             webpage, u'title')
 
+        video_thumbnail = self._html_search_regex(
+            r'playerInnerHTML.+?<img\s+src="(.+?)"',
+            webpage, u'thumbnail', fatal=False)
+
         # No self-labeling, but they describe themselves as
         # "Home of Videos Porno"
         age_limit = 18
 
         return {
-            'id':        video_id,
-            'url':       video_url,
-            'ext':       video_extension,
-            'title':     video_title,
+            'id': video_id,
+            'url': video_url,
+            'ext': video_extension,
+            'title': video_title,
+            'thumbnail': video_thumbnail,
             'age_limit': age_limit,
         }

youtube_dl/extractor/ringtv.py

@@ -1,37 +1,44 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 
 
 class RingTVIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?ringtv\.craveonline\.com/videos/video/([^/]+)'
+    _VALID_URL = r'(?:http://)?(?:www\.)?ringtv\.craveonline\.com/(?P<type>news|videos/video)/(?P<id>[^/?#]+)'
     _TEST = {
-        u"url": u"http://ringtv.craveonline.com/videos/video/746619-canelo-alvarez-talks-about-mayweather-showdown",
-        u"file": u"746619.mp4",
-        u"md5": u"7c46b4057d22de32e0a539f017e64ad3",
-        u"info_dict": {
-            u"title": u"Canelo Alvarez talks about Mayweather showdown",
-            u"description": u"Saul \\\"Canelo\\\" Alvarez spoke to the media about his Sept. 14 showdown with Floyd Mayweather after their kick-off presser in NYC. Canelo is motivated and confident that he will have the speed and gameplan to beat the pound-for-pound king."
+        "url": "http://ringtv.craveonline.com/news/310833-luis-collazo-says-victor-ortiz-better-not-quit-on-jan-30",
+        "file": "857645.mp4",
+        "md5": "d25945f5df41cdca2d2587165ac28720",
+        "info_dict": {
+            "title": 'Video: Luis Collazo says Victor Ortiz "better not quit on Jan. 30" - Ring TV',
+            "description": 'Luis Collazo is excited about his Jan. 30 showdown with fellow former welterweight titleholder Victor Ortiz at Barclays Center in his hometown of Brooklyn. The SuperBowl week fight headlines a Golden Boy Live! card on Fox Sports 1.',
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1).split('-')[0]
+        video_id = mobj.group('id').split('-')[0]
         webpage = self._download_webpage(url, video_id)
-        title = self._search_regex(r'<title>(.+?)</title>',
-        		webpage, 'video title').replace(' | RingTV','')
-        description = self._search_regex(r'<div class="blurb">(.+?)</div>',
-        		webpage, 'Description')
-        final_url = "http://ringtv.craveonline.springboardplatform.com/storage/ringtv.craveonline.com/conversion/%s.mp4" %(str(video_id))
-        thumbnail_url = "http://ringtv.craveonline.springboardplatform.com/storage/ringtv.craveonline.com/snapshots/%s.jpg" %(str(video_id))
-        ext = final_url.split('.')[-1]
-        return [{
-            'id'          : video_id,
-            'url'         : final_url,
-            'ext'         : ext,
-            'title'       : title,
-            'thumbnail'   : thumbnail_url,
-            'description' : description,
-        }]
+
+        if mobj.group('type') == 'news':
+            video_id = self._search_regex(
+                r'''(?x)<iframe[^>]+src="http://cms\.springboardplatform\.com/
+                        embed_iframe/[0-9]+/video/([0-9]+)/''',
+                webpage, 'real video ID')
+        title = self._og_search_title(webpage)
+        description = self._html_search_regex(
+            r'addthis:description="([^"]+)"',
+            webpage, 'description', fatal=False)
+        final_url = "http://ringtv.craveonline.springboardplatform.com/storage/ringtv.craveonline.com/conversion/%s.mp4" % video_id
+        thumbnail_url = "http://ringtv.craveonline.springboardplatform.com/storage/ringtv.craveonline.com/snapshots/%s.jpg" % video_id
+
+        return {
+            'id': video_id,
+            'url': final_url,
+            'title': title,
+            'thumbnail': thumbnail_url,
+            'description': description,
+        }
 

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/servingsys.py

@@ -0,0 +1,71 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+)
+
+
+class ServingSysIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:[^.]+\.)?serving-sys\.com/BurstingPipe/adServer\.bs\?.*?&pli=(?P<id>[0-9]+)'
+
+    _TEST = {
+        'url': 'http://bs.serving-sys.com/BurstingPipe/adServer.bs?cn=is&c=23&pl=VAST&pli=5349193&PluID=0&pos=7135&ord=[timestamp]&cim=1?',
+        'playlist': [{
+            'file': '29955898.flv',
+            'md5': 'baed851342df6846eb8677a60a011a0f',
+            'info_dict': {
+                'title': 'AdAPPter_Hyundai_demo (1)',
+                'duration': 74,
+                'tbr': 1378,
+                'width': 640,
+                'height': 400,
+            },
+        }, {
+            'file': '29907998.flv',
+            'md5': '979b4da2655c4bc2d81aeb915a8c5014',
+            'info_dict': {
+                'title': 'AdAPPter_Hyundai_demo (2)',
+                'duration': 34,
+                'width': 854,
+                'height': 480,
+                'tbr': 516,
+            },
+        }],
+        'params': {
+            'playlistend': 2,
+        },
+        'skip': 'Blocked in the US [sic]',
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        pl_id = mobj.group('id')
+
+        vast_doc = self._download_xml(url, pl_id)
+        title = vast_doc.find('.//AdTitle').text
+        media = vast_doc.find('.//MediaFile').text
+        info_url = self._search_regex(r'&adData=([^&]+)&', media, 'info URL')
+
+        doc = self._download_xml(info_url, pl_id, 'Downloading video info')
+        entries = [{
+            '_type': 'video',
+            'id': a.attrib['id'],
+            'title': '%s (%s)' % (title, a.attrib['assetID']),
+            'url': a.attrib['URL'],
+            'duration': int_or_none(a.attrib.get('length')),
+            'tbr': int_or_none(a.attrib.get('bitrate')),
+            'height': int_or_none(a.attrib.get('height')),
+            'width': int_or_none(a.attrib.get('width')),
+        } for a in doc.findall('.//AdditionalAssets/asset')]
+
+        return {
+            '_type': 'playlist',
+            'id': pl_id,
+            'title': title,
+            'entries': entries,
+        }
+
+ 

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/soundcloud.py

@@ -1,4 +1,6 @@
 # encoding: utf-8
+from __future__ import unicode_literals
+
 import json
 import re
 import itertools
@@ -32,58 +34,58 @@ class SoundcloudIE(InfoExtractor):
                        |(?P<player>(?:w|player|p.)\.soundcloud\.com/player/?.*?url=.*)
                     )
                     '''
-    IE_NAME = u'soundcloud'
+    IE_NAME = 'soundcloud'
     _TESTS = [
         {
-            u'url': u'http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy',
-            u'file': u'62986583.mp3',
-            u'md5': u'ebef0a451b909710ed1d7787dddbf0d7',
-            u'info_dict': {
-                u"upload_date": u"20121011", 
-                u"description": u"No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o'd", 
-                u"uploader": u"E.T. ExTerrestrial Music", 
-                u"title": u"Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1"
+            'url': 'http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy',
+            'file': '62986583.mp3',
+            'md5': 'ebef0a451b909710ed1d7787dddbf0d7',
+            'info_dict': {
+                "upload_date": "20121011",
+                "description": "No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o'd",
+                "uploader": "E.T. ExTerrestrial Music",
+                "title": "Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1"
             }
         },
         # not streamable song
         {
-            u'url': u'https://soundcloud.com/the-concept-band/goldrushed-mastered?in=the-concept-band/sets/the-royal-concept-ep',
-            u'info_dict': {
-                u'id': u'47127627',
-                u'ext': u'mp3',
-                u'title': u'Goldrushed',
-                u'uploader': u'The Royal Concept',
-                u'upload_date': u'20120521',
+            'url': 'https://soundcloud.com/the-concept-band/goldrushed-mastered?in=the-concept-band/sets/the-royal-concept-ep',
+            'info_dict': {
+                'id': '47127627',
+                'ext': 'mp3',
+                'title': 'Goldrushed',
+                'uploader': 'The Royal Concept',
+                'upload_date': '20120521',
             },
-            u'params': {
+            'params': {
                 # rtmp
-                u'skip_download': True,
+                'skip_download': True,
             },
         },
         # private link
         {
-            u'url': u'https://soundcloud.com/jaimemf/youtube-dl-test-video-a-y-baw/s-8Pjrp',
-            u'md5': u'aa0dd32bfea9b0c5ef4f02aacd080604',
-            u'info_dict': {
-                u'id': u'123998367',
-                u'ext': u'mp3',
-                u'title': u'Youtube - Dl Test Video \'\' Ä↭',
-                u'uploader': u'jaimeMF',
-                u'description': u'test chars:  \"\'/\\ä↭',
-                u'upload_date': u'20131209',
+            'url': 'https://soundcloud.com/jaimemf/youtube-dl-test-video-a-y-baw/s-8Pjrp',
+            'md5': 'aa0dd32bfea9b0c5ef4f02aacd080604',
+            'info_dict': {
+                'id': '123998367',
+                'ext': 'mp3',
+                'title': 'Youtube - Dl Test Video \'\' Ä↭',
+                'uploader': 'jaimeMF',
+                'description': 'test chars:  \"\'/\\ä↭',
+                'upload_date': '20131209',
             },
         },
         # downloadable song
         {
-            u'url': u'https://soundcloud.com/simgretina/just-your-problem-baby-1',
-            u'md5': u'56a8b69568acaa967b4c49f9d1d52d19',
-            u'info_dict': {
-                u'id': u'105614606',
-                u'ext': u'wav',
-                u'title': u'Just Your Problem Baby (Acapella)',
-                u'description': u'Vocals',
-                u'uploader': u'Sim Gretina',
-                u'upload_date': u'20130815',
+            'url': 'https://soundcloud.com/simgretina/just-your-problem-baby-1',
+            'md5': '56a8b69568acaa967b4c49f9d1d52d19',
+            'info_dict': {
+                'id': '105614606',
+                'ext': 'wav',
+                'title': 'Just Your Problem Baby (Acapella)',
+                'description': 'Vocals',
+                'uploader': 'Sim Gretina',
+                'upload_date': '20130815',
             },
         },
     ]
@@ -112,7 +114,7 @@ class SoundcloudIE(InfoExtractor):
         thumbnail = info['artwork_url']
         if thumbnail is not None:
             thumbnail = thumbnail.replace('-large', '-t500x500')
-        ext = u'mp3'
+        ext = 'mp3'
         result = {
             'id': track_id,
             'uploader': info['user']['username'],
@@ -124,11 +126,11 @@ class SoundcloudIE(InfoExtractor):
         if info.get('downloadable', False):
             # We can build a direct link to the song
             format_url = (
-                u'https://api.soundcloud.com/tracks/{0}/download?client_id={1}'.format(
+                'https://api.soundcloud.com/tracks/{0}/download?client_id={1}'.format(
                     track_id, self._CLIENT_ID))
             result['formats'] = [{
                 'format_id': 'download',
-                'ext': info.get('original_format', u'mp3'),
+                'ext': info.get('original_format', 'mp3'),
                 'url': format_url,
                 'vcodec': 'none',
             }]
@@ -138,7 +140,7 @@ class SoundcloudIE(InfoExtractor):
                 'client_id={1}&secret_token={2}'.format(track_id, self._IPHONE_CLIENT_ID, secret_token))
             stream_json = self._download_webpage(
                 streams_url,
-                track_id, u'Downloading track url')
+                track_id, 'Downloading track url')
 
             formats = []
             format_dict = json.loads(stream_json)
@@ -165,20 +167,19 @@ class SoundcloudIE(InfoExtractor):
                 # We fallback to the stream_url in the original info, this
                 # cannot be always used, sometimes it can give an HTTP 404 error
                 formats.append({
-                    'format_id': u'fallback',
+                    'format_id': 'fallback',
                     'url': info['stream_url'] + '?client_id=' + self._CLIENT_ID,
                     'ext': ext,
                     'vcodec': 'none',
                 })
 
-            def format_pref(f):
+            for f in formats:
                 if f['format_id'].startswith('http'):
-                    return 2
+                    f['protocol'] = 'http'
                 if f['format_id'].startswith('rtmp'):
-                    return 1
-                return 0
+                    f['protocol'] = 'rtmp'
 
-            formats.sort(key=format_pref)
+            self._sort_formats(formats)
             result['formats'] = formats
 
         return result
@@ -210,14 +211,14 @@ class SoundcloudIE(InfoExtractor):
     
             url = 'http://soundcloud.com/%s' % resolve_title
             info_json_url = self._resolv_url(url)
-        info_json = self._download_webpage(info_json_url, full_title, u'Downloading info JSON')
+        info_json = self._download_webpage(info_json_url, full_title, 'Downloading info JSON')
 
         info = json.loads(info_json)
         return self._extract_info_dict(info, full_title, secret_token=token)
 
 class SoundcloudSetIE(SoundcloudIE):
     _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)(?:[?].*)?$'
-    IE_NAME = u'soundcloud:set'
+    IE_NAME = 'soundcloud:set'
     # it's in tests/test_playlists.py
     _TESTS = []
 
@@ -254,7 +255,7 @@ class SoundcloudSetIE(SoundcloudIE):
 
 class SoundcloudUserIE(SoundcloudIE):
     _VALID_URL = r'https?://(www\.)?soundcloud\.com/(?P<user>[^/]+)(/?(tracks/)?)?(\?.*)?$'
-    IE_NAME = u'soundcloud:user'
+    IE_NAME = 'soundcloud:user'
 
     # it's in tests/test_playlists.py
     _TESTS = []
@@ -266,7 +267,7 @@ class SoundcloudUserIE(SoundcloudIE):
         url = 'http://soundcloud.com/%s/' % uploader
         resolv_url = self._resolv_url(url)
         user_json = self._download_webpage(resolv_url, uploader,
-            u'Downloading user info')
+            'Downloading user info')
         user = json.loads(user_json)
 
         tracks = []
@@ -276,7 +277,7 @@ class SoundcloudUserIE(SoundcloudIE):
                                                   })
             tracks_url = 'http://api.soundcloud.com/users/%s/tracks.json?' % user['id'] + data
             response = self._download_webpage(tracks_url, uploader, 
-                u'Downloading tracks page %s' % (i+1))
+                'Downloading tracks page %s' % (i+1))
             new_tracks = json.loads(response)
             tracks.extend(self._extract_info_dict(track, quiet=True) for track in new_tracks)
             if len(new_tracks) < 50:

youtube_dl/extractor/southparkstudios.py

@@ -18,14 +18,6 @@ class SouthParkStudiosIE(MTVServicesInfoExtractor):
         },
     }]
 
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        url = u'http://www.' + mobj.group(u'url')
-        video_id = mobj.group('id')
-        webpage = self._download_webpage(url, video_id)
-        mgid = self._search_regex(r'swfobject.embedSWF\(".*?(mgid:.*?)"',
-                                  webpage, u'mgid')
-        return self._get_videos_info(mgid)
 
 class SouthparkDeIE(SouthParkStudiosIE):
     IE_NAME = u'southpark.de'

youtube_dl/extractor/space.py

@@ -6,7 +6,7 @@ from ..utils import RegexNotFoundError, ExtractorError
 
 
 class SpaceIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.space\.com/\d+-(?P<title>[^/\.\?]*?)-video\.html'
+    _VALID_URL = r'https?://(?:(?:www|m)\.)?space\.com/\d+-(?P<title>[^/\.\?]*?)-video\.html'
     _TEST = {
         u'add_ie': ['Brightcove'],
         u'url': u'http://www.space.com/23373-huge-martian-landforms-detail-revealed-by-european-probe-video.html',

youtube_dl/extractor/spankwire.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import os
 import re
 
@@ -11,17 +13,18 @@ from ..aes import (
     aes_decrypt_text
 )
 
+
 class SpankwireIE(InfoExtractor):
     _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>spankwire\.com/[^/]*/video(?P<videoid>[0-9]+)/?)'
     _TEST = {
-        u'url': u'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/',
-        u'file': u'103545.mp4',
-        u'md5': u'1b3f55e345500552dbc252a3e9c1af43',
-        u'info_dict': {
-            u"uploader": u"oreusz", 
-            u"title": u"Buckcherry`s X Rated Music Video Crazy Bitch",
-            u"description": u"Crazy Bitch X rated music video.",
-            u"age_limit": 18,
+        'url': 'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/',
+        'file': '103545.mp4',
+        'md5': '1b3f55e345500552dbc252a3e9c1af43',
+        'info_dict': {
+            "uploader": "oreusz",
+            "title": "Buckcherry`s X Rated Music Video Crazy Bitch",
+            "description": "Crazy Bitch X rated music video.",
+            "age_limit": 18,
         }
     }
 
@@ -34,17 +37,17 @@ class SpankwireIE(InfoExtractor):
         req.add_header('Cookie', 'age_verified=1')
         webpage = self._download_webpage(req, video_id)
 
-        video_title = self._html_search_regex(r'<h1>([^<]+)', webpage, u'title')
+        video_title = self._html_search_regex(r'<h1>([^<]+)', webpage, 'title')
         video_uploader = self._html_search_regex(
-            r'by:\s*<a [^>]*>(.+?)</a>', webpage, u'uploader', fatal=False)
+            r'by:\s*<a [^>]*>(.+?)</a>', webpage, 'uploader', fatal=False)
         thumbnail = self._html_search_regex(
-            r'flashvars\.image_url = "([^"]+)', webpage, u'thumbnail', fatal=False)
+            r'flashvars\.image_url = "([^"]+)', webpage, 'thumbnail', fatal=False)
         description = self._html_search_regex(
-            r'<div\s+id="descriptionContent">([^<]+)<', webpage, u'description', fatal=False)
+            r'<div\s+id="descriptionContent">([^<]+)<', webpage, 'description', fatal=False)
 
         video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'flashvars\.quality_[0-9]{3}p = "([^"]+)', webpage)))
         if webpage.find('flashvars\.encrypted = "true"') != -1:
-            password = self._html_search_regex(r'flashvars\.video_title = "([^"]+)', webpage, u'password').replace('+', ' ')
+            password = self._html_search_regex(r'flashvars\.video_title = "([^"]+)', webpage, 'password').replace('+', ' ')
             video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
 
         formats = []
@@ -52,14 +55,21 @@ class SpankwireIE(InfoExtractor):
             path = compat_urllib_parse_urlparse(video_url).path
             extension = os.path.splitext(path)[1][1:]
             format = path.split('/')[4].split('_')[:2]
+            resolution, bitrate_str = format
             format = "-".join(format)
+            height = int(resolution.rstrip('P'))
+            tbr = int(bitrate_str.rstrip('K'))
+
             formats.append({
                 'url': video_url,
                 'ext': extension,
+                'resolution': resolution,
                 'format': format,
+                'tbr': tbr,
+                'height': height,
                 'format_id': format,
             })
-        formats.sort(key=lambda format: list(map(lambda s: s.zfill(6), format['format'].split('-'))))
+        self._sort_formats(formats)
 
         age_limit = self._rta_search(webpage)
 

youtube_dl/extractor/spike.py

@@ -0,0 +1,19 @@
+from __future__ import unicode_literals
+
+from .mtv import MTVServicesInfoExtractor
+
+
+class SpikeIE(MTVServicesInfoExtractor):
+    _VALID_URL = r'https?://www\.spike\.com/(video-clips|episodes)/.+'
+    _TEST = {
+        'url': 'http://www.spike.com/video-clips/lhtu8m/auction-hunters-can-allen-ride-a-hundred-year-old-motorcycle',
+        'md5': '1a9265f32b0c375793d6c4ce45255256',
+        'info_dict': {
+            'id': 'b9c8221a-4e50-479a-b86d-3333323e38ba',
+            'ext': 'mp4',
+            'title': 'Auction Hunters|Can Allen Ride A Hundred Year-Old Motorcycle?',
+            'description': 'md5:fbed7e82ed5fad493615b3094a9499cb',
+        },
+    }
+
+    _FEED_URL = 'http://www.spike.com/feeds/mrss/'

youtube_dl/extractor/teamcoco.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -9,61 +11,66 @@ from ..utils import (
 class TeamcocoIE(InfoExtractor):
     _VALID_URL = r'http://teamcoco\.com/video/(?P<url_title>.*)'
     _TEST = {
-        u'url': u'http://teamcoco.com/video/louis-ck-interview-george-w-bush',
-        u'file': u'19705.mp4',
-        u'md5': u'cde9ba0fa3506f5f017ce11ead928f9a',
-        u'info_dict': {
-            u"description": u"Louis C.K. got starstruck by George W. Bush, so what? Part one.", 
-            u"title": u"Louis C.K. Interview Pt. 1 11/3/11"
+        'url': 'http://teamcoco.com/video/louis-ck-interview-george-w-bush',
+        'file': '19705.mp4',
+        'md5': 'cde9ba0fa3506f5f017ce11ead928f9a',
+        'info_dict': {
+            "description": "Louis C.K. got starstruck by George W. Bush, so what? Part one.",
+            "title": "Louis C.K. Interview Pt. 1 11/3/11"
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
+            raise ExtractorError('Invalid URL: %s' % url)
         url_title = mobj.group('url_title')
         webpage = self._download_webpage(url, url_title)
 
-        video_id = self._html_search_regex(r'<article class="video" data-id="(\d+?)"',
-            webpage, u'video id')
+        video_id = self._html_search_regex(
+            r'<article class="video" data-id="(\d+?)"',
+            webpage, 'video id')
 
         self.report_extraction(video_id)
 
         data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
         data = self._download_xml(data_url, video_id, 'Downloading data webpage')
 
-
         qualities = ['500k', '480p', '1000k', '720p', '1080p']
         formats = []
-        for file in data.findall('files/file'):
-            if file.attrib.get('playmode') == 'all':
+        for filed in data.findall('files/file'):
+            if filed.attrib.get('playmode') == 'all':
                 # it just duplicates one of the entries
                 break
-            file_url = file.text
+            file_url = filed.text
             m_format = re.search(r'(\d+(k|p))\.mp4', file_url)
             if m_format is not None:
                 format_id = m_format.group(1)
             else:
-                format_id = file.attrib['bitrate']
+                format_id = filed.attrib['bitrate']
+            tbr = (
+                int(filed.attrib['bitrate'])
+                if filed.attrib['bitrate'].isdigit()
+                else None)
+
+            try:
+                quality = qualities.index(format_id)
+            except ValueError:
+                quality = -1
             formats.append({
                 'url': file_url,
                 'ext': 'mp4',
+                'tbr': tbr,
                 'format_id': format_id,
+                'quality': quality,
             })
-        def sort_key(f):
-            try:
-                return qualities.index(f['format_id'])
-            except ValueError:
-                return -1
-        formats.sort(key=sort_key)
-        if not formats:
-            raise ExtractorError(u'Unable to extract video URL')
+
+        self._sort_formats(formats)
 
         return {
-            'id':          video_id,
+            'id': video_id,
             'formats': formats,
-            'title':       self._og_search_title(webpage),
-            'thumbnail':   self._og_search_thumbnail(webpage),
+            'title': self._og_search_title(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
             'description': self._og_search_description(webpage),
         }

youtube_dl/extractor/ted.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import json
 import re
 
@@ -7,6 +9,7 @@ from ..utils import (
     RegexNotFoundError,
 )
 
+
 class TEDIE(SubtitlesInfoExtractor):
     _VALID_URL=r'''http://www\.ted\.com/
                    (
@@ -18,12 +21,12 @@ class TEDIE(SubtitlesInfoExtractor):
                    /(?P<name>\w+) # Here goes the name and then ".html"
                    '''
     _TEST = {
-        u'url': u'http://www.ted.com/talks/dan_dennett_on_our_consciousness.html',
-        u'file': u'102.mp4',
-        u'md5': u'2d76ee1576672e0bd8f187513267adf6',
-        u'info_dict': {
-            u"description": u"md5:c6fa72e6eedbd938c9caf6b2702f5922", 
-            u"title": u"Dan Dennett: The illusion of consciousness"
+        'url': 'http://www.ted.com/talks/dan_dennett_on_our_consciousness.html',
+        'file': '102.mp4',
+        'md5': '4ea1dada91e4174b53dac2bb8ace429d',
+        'info_dict': {
+            "description": "md5:c6fa72e6eedbd938c9caf6b2702f5922",
+            "title": "Dan Dennett: The illusion of consciousness"
         }
     }
 
@@ -47,7 +50,7 @@ class TEDIE(SubtitlesInfoExtractor):
         '''Returns the videos of the playlist'''
 
         webpage = self._download_webpage(
-            url, playlist_id, u'Downloading playlist webpage')
+            url, playlist_id, 'Downloading playlist webpage')
         matches = re.finditer(
             r'<p\s+class="talk-title[^"]*"><a\s+href="(?P<talk_url>/talks/[^"]+\.html)">[^<]*</a></p>',
             webpage)

youtube_dl/extractor/tumblr.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -9,11 +11,11 @@ from ..utils import (
 class TumblrIE(InfoExtractor):
     _VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\d*)/(.*?)'
     _TEST = {
-        u'url': u'http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes',
-        u'file': u'54196191430.mp4',
-        u'md5': u'479bb068e5b16462f5176a6828829767',
-        u'info_dict': {
-            u"title": u"tatiana maslany news"
+        'url': 'http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes',
+        'file': '54196191430.mp4',
+        'md5': '479bb068e5b16462f5176a6828829767',
+        'info_dict': {
+            "title": "tatiana maslany news"
         }
     }
 
@@ -28,18 +30,20 @@ class TumblrIE(InfoExtractor):
         re_video = r'src=\\x22(?P<video_url>http://%s\.tumblr\.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P<ext>.*?)\\x22' % (blog, video_id)
         video = re.search(re_video, webpage)
         if video is None:
-           raise ExtractorError(u'Unable to extract video')
+            raise ExtractorError('Unable to extract video')
         video_url = video.group('video_url')
         ext = video.group('ext')
 
-        video_thumbnail = self._search_regex(r'posters(.*?)\[\\x22(?P<thumb>.*?)\\x22',
-            webpage, u'thumbnail', fatal=False)  # We pick the first poster
-        if video_thumbnail: video_thumbnail = video_thumbnail.replace('\\', '')
+        video_thumbnail = self._search_regex(
+            r'posters.*?\[\\x22(.*?)\\x22',
+            webpage, 'thumbnail', fatal=False)  # We pick the first poster
+        if video_thumbnail:
+            video_thumbnail = video_thumbnail.replace('\\\\/', '/')
 
         # The only place where you can get a title, it's not complete,
         # but searching in other places doesn't work for all videos
         video_title = self._html_search_regex(r'<title>(?P<title>.*?)(?: \| Tumblr)?</title>',
-            webpage, u'title', flags=re.DOTALL)
+            webpage, 'title', flags=re.DOTALL)
 
         return [{'id': video_id,
                  'url': video_url,

youtube_dl/extractor/vimeo.py

@@ -291,7 +291,7 @@ class VimeoIE(InfoExtractor):
 
 class VimeoChannelIE(InfoExtractor):
     IE_NAME = 'vimeo:channel'
-    _VALID_URL = r'(?:https?://)?vimeo.\com/channels/(?P<id>[^/]+)'
+    _VALID_URL = r'(?:https?://)?vimeo\.com/channels/(?P<id>[^/]+)'
     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
 
@@ -327,7 +327,7 @@ class VimeoChannelIE(InfoExtractor):
 
 class VimeoUserIE(VimeoChannelIE):
     IE_NAME = 'vimeo:user'
-    _VALID_URL = r'(?:https?://)?vimeo.\com/(?P<name>[^/]+)(?:/videos|[#?]|$)'
+    _VALID_URL = r'(?:https?://)?vimeo\.com/(?P<name>[^/]+)(?:/videos|[#?]|$)'
     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
 
     @classmethod
@@ -344,7 +344,7 @@ class VimeoUserIE(VimeoChannelIE):
 
 class VimeoAlbumIE(VimeoChannelIE):
     IE_NAME = 'vimeo:album'
-    _VALID_URL = r'(?:https?://)?vimeo.\com/album/(?P<id>\d+)'
+    _VALID_URL = r'(?:https?://)?vimeo\.com/album/(?P<id>\d+)'
     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
 
     def _page_url(self, base_url, pagenum):
@@ -358,7 +358,7 @@ class VimeoAlbumIE(VimeoChannelIE):
 
 class VimeoGroupsIE(VimeoAlbumIE):
     IE_NAME = 'vimeo:group'
-    _VALID_URL = r'(?:https?://)?vimeo.\com/groups/(?P<name>[^/]+)'
+    _VALID_URL = r'(?:https?://)?vimeo\.com/groups/(?P<name>[^/]+)'
 
     def _extract_list_title(self, webpage):
         return self._og_search_title(webpage)
@@ -372,7 +372,7 @@ class VimeoGroupsIE(VimeoAlbumIE):
 class VimeoReviewIE(InfoExtractor):
     IE_NAME = 'vimeo:review'
     IE_DESC = 'Review pages on vimeo'
-    _VALID_URL = r'(?:https?://)?vimeo.\com/[^/]+/review/(?P<id>[^/]+)'
+    _VALID_URL = r'(?:https?://)?vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
     _TEST = {
         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
         'file': '75524534.mp4',

youtube_dl/extractor/vk.py

@@ -1,4 +1,6 @@
 # encoding: utf-8
+from __future__ import unicode_literals
+
 import re
 import json
 
@@ -10,19 +12,27 @@ from ..utils import (
 
 
 class VKIE(InfoExtractor):
-    IE_NAME = u'vk.com'
+    IE_NAME = 'vk.com'
     _VALID_URL = r'https?://vk\.com/(?:videos.*?\?.*?z=)?video(?P<id>.*?)(?:\?|%2F|$)'
 
-    _TEST = {
-        u'url': u'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
-        u'md5': u'0deae91935c54e00003c2a00646315f0',
-        u'info_dict': {
-            u'id': u'162222515',
-            u'ext': u'flv',
-            u'title': u'ProtivoGunz - Хуёвая песня',
-            u'uploader': u'Noize MC',
+    _TESTS = [{
+        'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
+        'file': '162222515.flv',
+        'md5': '0deae91935c54e00003c2a00646315f0',
+        'info_dict': {
+            'title': 'ProtivoGunz - Хуёвая песня',
+            'uploader': 'Noize MC',
         },
-    }
+    },
+    {
+        'url': 'http://vk.com/video4643923_163339118',
+        'file': '163339118.mp4',
+        'md5': 'f79bccb5cd182b1f43502ca5685b2b36',
+        'info_dict': {
+            'uploader': 'Elvira Dzhonik',
+            'title': 'Dream Theater - Hollow Years Live at Budokan 720*',
+        }
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -33,13 +43,21 @@ class VKIE(InfoExtractor):
         if m_yt is not None:
             self.to_screen(u'Youtube video detected')
             return self.url_result(m_yt.group(1), 'Youtube')
-        vars_json = self._search_regex(r'var vars = ({.*?});', info_page, u'vars')
-        vars = json.loads(vars_json)
+        data_json = self._search_regex(r'var vars = ({.*?});', info_page, 'vars')
+        data = json.loads(data_json)
+
+        formats = [{
+            'format_id': k,
+            'url': v,
+            'width': int(k[len('url'):]),
+        } for k, v in data.items()
+            if k.startswith('url')]
+        self._sort_formats(formats)
 
         return {
-            'id': compat_str(vars['vid']),
-            'url': vars['url240'],
-            'title': unescapeHTML(vars['md_title']),
-            'thumbnail': vars['jpg'],
-            'uploader': vars['md_author'],
+            'id': compat_str(data['vid']),
+            'formats': formats,
+            'title': unescapeHTML(data['md_title']),
+            'thumbnail': data.get('jpg'),
+            'uploader': data.get('md_author'),
         }

youtube_dl/extractor/websurg.py

@@ -1,59 +0,0 @@
-# coding: utf-8
-
-import re
-
-from ..utils import (
-    compat_urllib_request,
-    compat_urllib_parse
-)
-
-from .common import InfoExtractor
-
-class WeBSurgIE(InfoExtractor):
-    IE_NAME = u'websurg.com'
-    _VALID_URL = r'http://.*?\.websurg\.com/MEDIA/\?noheader=1&doi=(.*)'
-
-    _TEST = {
-        u'url': u'http://www.websurg.com/MEDIA/?noheader=1&doi=vd01en4012',
-        u'file': u'vd01en4012.mp4',
-        u'params': {
-            u'skip_download': True,
-        },
-        u'skip': u'Requires login information',
-    }
-    
-    _LOGIN_URL = 'http://www.websurg.com/inc/login/login_div.ajax.php?login=1'
-
-    def _real_initialize(self):
-
-        login_form = {
-            'username': self._downloader.params['username'],
-            'password': self._downloader.params['password'],
-            'Submit': 1
-        }
-        
-        request = compat_urllib_request.Request(
-            self._LOGIN_URL, compat_urllib_parse.urlencode(login_form))
-        request.add_header(
-            'Content-Type', 'application/x-www-form-urlencoded;charset=utf-8')
-        compat_urllib_request.urlopen(request).info()
-        webpage = self._download_webpage(self._LOGIN_URL, '', 'Logging in')
-        
-        if webpage != 'OK':
-            self._downloader.report_error(
-                u'Unable to log in: bad username/password')
-        
-    def _real_extract(self, url):
-        video_id = re.match(self._VALID_URL, url).group(1)
-        
-        webpage = self._download_webpage(url, video_id)
-        
-        url_info = re.search(r'streamer="(.*?)" src="(.*?)"', webpage)
-        
-        return {'id': video_id,
-                'title': self._og_search_title(webpage),
-                'description': self._og_search_description(webpage),
-                'ext' : 'mp4',
-                'url' : url_info.group(1) + '/' + url_info.group(2),
-                'thumbnail': self._og_search_thumbnail(webpage)
-                }

youtube_dl/extractor/wimp.py

@@ -1,5 +1,6 @@
+from __future__ import unicode_literals
+
 import re
-import base64
 
 from .common import InfoExtractor
 
@@ -7,12 +8,12 @@ from .common import InfoExtractor
 class WimpIE(InfoExtractor):
     _VALID_URL = r'(?:http://)?(?:www\.)?wimp\.com/([^/]+)/'
     _TEST = {
-        u'url': u'http://www.wimp.com/deerfence/',
-        u'file': u'deerfence.flv',
-        u'md5': u'8b215e2e0168c6081a1cf84b2846a2b5',
-        u'info_dict': {
-            u"title": u"Watch Till End: Herd of deer jump over a fence.",
-            u"description": u"These deer look as fluid as running water when they jump over this fence as a herd. This video is one that needs to be watched until the very end for the true majesty to be witnessed, but once it comes, it's sure to take your breath away.",
+        'url': 'http://www.wimp.com/deerfence/',
+        'file': 'deerfence.flv',
+        'md5': '8b215e2e0168c6081a1cf84b2846a2b5',
+        'info_dict': {
+            "title": "Watch Till End: Herd of deer jump over a fence.",
+            "description": "These deer look as fluid as running water when they jump over this fence as a herd. This video is one that needs to be watched until the very end for the true majesty to be witnessed, but once it comes, it's sure to take your breath away.",
         }
     }
 
@@ -20,13 +21,12 @@ class WimpIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group(1)
         webpage = self._download_webpage(url, video_id)
-        googleString = self._search_regex("googleCode = '(.*?)'", webpage, 'file url')
-        googleString = base64.b64decode(googleString).decode('ascii')
-        final_url = self._search_regex('","(.*?)"', googleString, u'final video url')
+        video_url = self._search_regex(
+            r's1\.addVariable\("file",\s*"([^"]+)"\);', webpage, 'video URL')
 
         return {
             'id': video_id,
-            'url': final_url,
+            'url': video_url,
             'title': self._og_search_title(webpage),
             'thumbnail': self._og_search_thumbnail(webpage),
             'description': self._og_search_description(webpage),

youtube_dl/extractor/xhamster.py

@@ -1,10 +1,11 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 from ..utils import (
     compat_urllib_parse,
     unescapeHTML,
-    determine_ext,
     ExtractorError,
 )
 
@@ -13,25 +14,25 @@ class XHamsterIE(InfoExtractor):
     """Information Extractor for xHamster"""
     _VALID_URL = r'(?:http://)?(?:www\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
     _TESTS = [{
-        u'url': u'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
-        u'file': u'1509445.flv',
-        u'md5': u'9f48e0e8d58e3076bb236ff412ab62fa',
-        u'info_dict': {
-            u"upload_date": u"20121014", 
-            u"uploader_id": u"Ruseful2011", 
-            u"title": u"FemaleAgent Shy beauty takes the bait",
-            u"age_limit": 18,
+        'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
+        'file': '1509445.mp4',
+        'md5': '8281348b8d3c53d39fffb377d24eac4e',
+        'info_dict': {
+            "upload_date": "20121014",
+            "uploader_id": "Ruseful2011",
+            "title": "FemaleAgent Shy beauty takes the bait",
+            "age_limit": 18,
         }
     },
     {
-        u'url': u'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
-        u'file': u'2221348.flv',
-        u'md5': u'e767b9475de189320f691f49c679c4c7',
-        u'info_dict': {
-            u"upload_date": u"20130914",
-            u"uploader_id": u"jojo747400",
-            u"title": u"Britney Spears  Sexy Booty",
-            u"age_limit": 18,
+        'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
+        'file': '2221348.flv',
+        'md5': 'e767b9475de189320f691f49c679c4c7',
+        'info_dict': {
+            "upload_date": "20130914",
+            "uploader_id": "jojo747400",
+            "title": "Britney Spears  Sexy Booty",
+            "age_limit": 18,
         }
     }]
 
@@ -39,14 +40,21 @@ class XHamsterIE(InfoExtractor):
         def extract_video_url(webpage):
             mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
             if mobj is None:
-                raise ExtractorError(u'Unable to extract media URL')
+                raise ExtractorError('Unable to extract media URL')
             if len(mobj.group('server')) == 0:
                 return compat_urllib_parse.unquote(mobj.group('file'))
             else:
                 return mobj.group('server')+'/key='+mobj.group('file')
 
+        def extract_mp4_video_url(webpage):
+            mp4 = re.search(r'<a href=\"(.+?)\" class=\"mp4Play\"',webpage)
+            if mp4 is None:
+                return None
+            else:
+                return mp4.group(1)
+
         def is_hd(webpage):
-            return webpage.find('<div class=\'icon iconHD\'') != -1
+            return '<div class=\'icon iconHD\'' in webpage
 
         mobj = re.match(self._VALID_URL, url)
 
@@ -55,50 +63,60 @@ class XHamsterIE(InfoExtractor):
         mrss_url = 'http://xhamster.com/movies/%s/%s.html' % (video_id, seo)
         webpage = self._download_webpage(mrss_url, video_id)
 
-        video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>',
-            webpage, u'title')
+        video_title = self._html_search_regex(
+            r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, 'title')
 
         # Only a few videos have an description
-        mobj = re.search('<span>Description: </span>(?P<description>[^<]+)', webpage)
-        if mobj:
-            video_description = unescapeHTML(mobj.group('description'))
-        else:
-            video_description = None
+        mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
+        video_description = mobj.group(1) if mobj else None
 
         mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage)
         if mobj:
             video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
         else:
             video_upload_date = None
-            self._downloader.report_warning(u'Unable to extract upload date')
+            self._downloader.report_warning('Unable to extract upload date')
 
-        video_uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
-            webpage, u'uploader id', default=u'anonymous')
+        video_uploader_id = self._html_search_regex(
+            r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
+            webpage, 'uploader id', default='anonymous')
 
-        video_thumbnail = self._search_regex(r'\'image\':\'(?P<thumbnail>[^\']+)\'',
-            webpage, u'thumbnail', fatal=False)
+        video_thumbnail = self._search_regex(
+            r'\'image\':\'(?P<thumbnail>[^\']+)\'',
+            webpage, 'thumbnail', fatal=False)
 
         age_limit = self._rta_search(webpage)
 
-        video_url = extract_video_url(webpage)
         hd = is_hd(webpage)
+        video_url = extract_video_url(webpage)
         formats = [{
             'url': video_url,
-            'ext': determine_ext(video_url),
-            'format': 'hd' if hd else 'sd',
             'format_id': 'hd' if hd else 'sd',
+            'preference': 0,
         }]
+
+        video_mp4_url = extract_mp4_video_url(webpage)
+        if video_mp4_url is not None:
+            formats.append({
+                'url': video_mp4_url,
+                'ext': 'mp4',
+                'format_id': 'mp4-hd' if hd else 'mp4-sd',
+                'preference': 1,
+            })
+
         if not hd:
-            webpage = self._download_webpage(mrss_url+'?hd', video_id)
+            webpage = self._download_webpage(
+                mrss_url + '?hd', video_id, note='Downloading HD webpage')
             if is_hd(webpage):
                 video_url = extract_video_url(webpage)
                 formats.append({
                     'url': video_url,
-                    'ext': determine_ext(video_url),
-                    'format': 'hd',
                     'format_id': 'hd',
+                    'preference': 2,
                 })
 
+        self._sort_formats(formats)
+
         return {
             'id': video_id,
             'title': video_title,

youtube_dl/extractor/xvideos.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -9,12 +11,12 @@ from ..utils import (
 class XVideosIE(InfoExtractor):
     _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
     _TEST = {
-        u'url': u'http://www.xvideos.com/video939581/funny_porns_by_s_-1',
-        u'file': u'939581.flv',
-        u'md5': u'1d0c835822f0a71a7bf011855db929d0',
-        u'info_dict': {
-            u"title": u"Funny Porns By >>>>S<<<<<< -1",
-            u"age_limit": 18,
+        'url': 'http://www.xvideos.com/video939581/funny_porns_by_s_-1',
+        'file': '939581.flv',
+        'md5': '1d0c835822f0a71a7bf011855db929d0',
+        'info_dict': {
+            "title": "Funny Porns By >>>>S<<<<<< -1",
+            "age_limit": 18,
         }
     }
 
@@ -27,18 +29,18 @@ class XVideosIE(InfoExtractor):
         self.report_extraction(video_id)
 
         # Extract video URL
-        video_url = compat_urllib_parse.unquote(self._search_regex(r'flv_url=(.+?)&',
-            webpage, u'video URL'))
+        video_url = compat_urllib_parse.unquote(
+            self._search_regex(r'flv_url=(.+?)&', webpage, 'video URL'))
 
         # Extract title
-        video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XVID',
-            webpage, u'title')
+        video_title = self._html_search_regex(
+            r'<title>(.*?)\s+-\s+XVID', webpage, 'title')
 
         # Extract video thumbnail
-        video_thumbnail = self._search_regex(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)',
-            webpage, u'thumbnail', fatal=False)
+        video_thumbnail = self._search_regex(
+            r'url_bigthumb=(.+?)&amp', webpage, 'thumbnail', fatal=False)
 
-        info = {
+        return {
             'id': video_id,
             'url': video_url,
             'uploader': None,
@@ -49,5 +51,3 @@ class XVideosIE(InfoExtractor):
             'description': None,
             'age_limit': 18,
         }
-
-        return [info]

youtube_dl/extractor/youtube.py

@@ -27,6 +27,9 @@ from ..utils import (
     get_element_by_id,
     get_element_by_attribute,
     ExtractorError,
+    int_or_none,
+    PagedList,
+    RegexNotFoundError,
     unescapeHTML,
     unified_strdate,
     orderedSet,
@@ -37,7 +40,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
     """Provide base functions for Youtube extractors"""
     _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
     _LANG_URL = r'https://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
-    _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
+    _AGE_URL = 'https://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
     _NETRC_MACHINE = 'youtube'
     # If True it will raise an error if no login info is provided
     _LOGIN_REQUIRED = False
@@ -108,7 +111,8 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
             'next_url': '/',
             'action_confirm': 'Confirm',
         }
-        req = compat_urllib_request.Request(self._AGE_URL, compat_urllib_parse.urlencode(age_form))
+        req = compat_urllib_request.Request(self._AGE_URL,
+            compat_urllib_parse.urlencode(age_form).encode('ascii'))
 
         self._download_webpage(
             req, None,
@@ -204,6 +208,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
         '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'vcodec': 'none', 'abr': 256, 'preference': -50},
 
         # Dash webm
+        '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'VP8', 'acodec': 'none', 'preference': -40},
+        '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'VP8', 'acodec': 'none', 'preference': -40},
+        '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'VP8', 'acodec': 'none', 'preference': -40},
+        '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'VP8', 'acodec': 'none', 'preference': -40},
+        '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'VP8', 'acodec': 'none', 'preference': -40},
+        '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'VP8', 'acodec': 'none', 'preference': -40},
         '242': {'ext': 'webm', 'height': 240, 'resolution': '240p', 'format_note': 'DASH webm', 'preference': -40},
         '243': {'ext': 'webm', 'height': 360, 'resolution': '360p', 'format_note': 'DASH webm', 'preference': -40},
         '244': {'ext': 'webm', 'height': 480, 'resolution': '480p', 'format_note': 'DASH webm', 'preference': -40},
@@ -269,6 +279,22 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                 u"uploader_id": u"setindia"
             }
         },
+        {
+            u"url": u"http://www.youtube.com/watch?v=a9LDPn-MO4I",
+            u"file": u"a9LDPn-MO4I.m4a",
+            u"note": u"256k DASH audio (format 141) via DASH manifest",
+            u"info_dict": {
+                u"upload_date": "20121002",
+                u"uploader_id": "8KVIDEO",
+                u"description": "No description available.",
+                u"uploader": "8KVIDEO",
+                u"title": "UHDTV TEST 8K VIDEO.mp4"
+            },
+            u"params": {
+                u"youtube_include_dash_manifest": True,
+                u"format": "141",
+            },
+        },
     ]
 
 
@@ -989,7 +1015,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
     def _get_available_subtitles(self, video_id, webpage):
         try:
             sub_list = self._download_webpage(
-                'http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
+                'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
                 video_id, note=False)
         except ExtractorError as err:
             self._downloader.report_warning(u'unable to download video subtitles: %s' % compat_str(err))
@@ -1005,7 +1031,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                 'fmt': self._downloader.params.get('subtitlesformat', 'srt'),
                 'name': unescapeHTML(l[0]).encode('utf-8'),
             })
-            url = u'http://www.youtube.com/api/timedtext?' + params
+            url = u'https://www.youtube.com/api/timedtext?' + params
             sub_lang_list[lang] = url
         if not sub_lang_list:
             self._downloader.report_warning(u'video doesn\'t have subtitles')
@@ -1066,18 +1092,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
         video_id = mobj.group(2)
         return video_id
 
-    def _get_video_url_list(self, url_map):
-        """
-        Transform a dictionary in the format {itag:url} to a list of (itag, url)
-        with the requested formats.
-        """
-        existing_formats = [x for x in self._formats if x in url_map]
-        if len(existing_formats) == 0:
-            raise ExtractorError(u'no known formats available for video')
-        video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
-        video_url_list.reverse() # order worst to best
-        return video_url_list
-
     def _extract_from_m3u8(self, manifest_url, video_id):
         url_map = {}
         def _get_urls(_manifest):
@@ -1251,7 +1265,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                 video_annotations = self._extract_annotations(video_id)
 
         # Decide which formats to download
-
         try:
             mobj = re.search(r';ytplayer.config = ({.*?});', video_webpage)
             if not mobj:
@@ -1276,9 +1289,27 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
         except ValueError:
             pass
 
+        def _map_to_format_list(urlmap):
+            formats = []
+            for itag, video_real_url in urlmap.items():
+                dct = {
+                    'format_id': itag,
+                    'url': video_real_url,
+                    'player_url': player_url,
+                }
+                if itag in self._formats:
+                    dct.update(self._formats[itag])
+                formats.append(dct)
+            return formats
+
         if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
             self.report_rtmp_download()
-            video_url_list = [('_rtmp', video_info['conn'][0])]
+            formats = [{
+                'format_id': '_rtmp',
+                'protocol': 'rtmp',
+                'url': video_info['conn'][0],
+                'player_url': player_url,
+            }]
         elif len(video_info.get('url_encoded_fmt_stream_map', [])) >= 1 or len(video_info.get('adaptive_fmts', [])) >= 1:
             encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts',[''])[0]
             if 'rtmpe%3Dyes' in encoded_url_map:
@@ -1323,23 +1354,50 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                     if 'ratebypass' not in url:
                         url += '&ratebypass=yes'
                     url_map[url_data['itag'][0]] = url
-            video_url_list = self._get_video_url_list(url_map)
+            formats = _map_to_format_list(url_map)
         elif video_info.get('hlsvp'):
             manifest_url = video_info['hlsvp'][0]
             url_map = self._extract_from_m3u8(manifest_url, video_id)
-            video_url_list = self._get_video_url_list(url_map)
+            formats = _map_to_format_list(url_map)
         else:
             raise ExtractorError(u'no conn, hlsvp or url_encoded_fmt_stream_map information found in video info')
 
-        formats = []
-        for itag, video_real_url in video_url_list:
-            dct = {
-                'format_id': itag,
-                'url': video_real_url,
-                'player_url': player_url,
-            }
-            dct.update(self._formats[itag])
-            formats.append(dct)
+        # Look for the DASH manifest
+        dash_manifest_url_lst = video_info.get('dashmpd')
+        if (dash_manifest_url_lst and dash_manifest_url_lst[0] and
+                self._downloader.params.get('youtube_include_dash_manifest', False)):
+            try:
+                dash_doc = self._download_xml(
+                    dash_manifest_url_lst[0], video_id,
+                    note=u'Downloading DASH manifest',
+                    errnote=u'Could not download DASH manifest')
+                for r in dash_doc.findall(u'.//{urn:mpeg:DASH:schema:MPD:2011}Representation'):
+                    url_el = r.find('{urn:mpeg:DASH:schema:MPD:2011}BaseURL')
+                    if url_el is None:
+                        continue
+                    format_id = r.attrib['id']
+                    video_url = url_el.text
+                    filesize = int_or_none(url_el.attrib.get('{http://youtube.com/yt/2012/10/10}contentLength'))
+                    f = {
+                        'format_id': format_id,
+                        'url': video_url,
+                        'width': int_or_none(r.attrib.get('width')),
+                        'tbr': int_or_none(r.attrib.get('bandwidth'), 1000),
+                        'asr': int_or_none(r.attrib.get('audioSamplingRate')),
+                        'filesize': filesize,
+                    }
+                    try:
+                        existing_format = next(
+                            fo for fo in formats
+                            if fo['format_id'] == format_id)
+                    except StopIteration:
+                        f.update(self._formats.get(format_id, {}))
+                        formats.append(f)
+                    else:
+                        existing_format.update(f)
+
+            except (ExtractorError, KeyError) as e:
+                self.report_warning(u'Skipping DASH manifest: %s' % e, video_id)
 
         self._sort_formats(formats)
 
@@ -1448,7 +1506,14 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
             if re.search(self._MORE_PAGES_INDICATOR, page) is None:
                 break
 
-        playlist_title = self._og_search_title(page)
+        try:
+            playlist_title = self._og_search_title(page)
+        except RegexNotFoundError:
+            self.report_warning(
+                u'Playlist page is missing OpenGraph title, falling back ...',
+                playlist_id)
+            playlist_title = self._html_search_regex(
+                r'<h1 class="pl-header-title">(.*?)</h1>', page, u'title')
 
         url_results = self._ids_to_results(ids)
         return self.playlist_result(url_results, playlist_id, playlist_title)
@@ -1465,7 +1530,7 @@ class YoutubeTopListIE(YoutubePlaylistIE):
         channel = mobj.group('chann')
         title = mobj.group('title')
         query = compat_urllib_parse.urlencode({'title': title})
-        playlist_re = 'href="([^"]+?%s[^"]+?)"' % re.escape(query)
+        playlist_re = 'href="([^"]+?%s.*?)"' % re.escape(query)
         channel_page = self._download_webpage('https://www.youtube.com/%s' % channel, title)
         link = self._html_search_regex(playlist_re, channel_page, u'list')
         url = compat_urlparse.urljoin('https://www.youtube.com/', link)
@@ -1490,7 +1555,7 @@ class YoutubeChannelIE(InfoExtractor):
     IE_DESC = u'YouTube.com channels'
     _VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)"
     _MORE_PAGES_INDICATOR = 'yt-uix-load-more'
-    _MORE_PAGES_URL = 'http://www.youtube.com/c4_browse_ajax?action_load_more_videos=1&flow=list&paging=%s&view=0&sort=da&channel_id=%s'
+    _MORE_PAGES_URL = 'https://www.youtube.com/c4_browse_ajax?action_load_more_videos=1&flow=list&paging=%s&view=0&sort=da&channel_id=%s'
     IE_NAME = u'youtube:channel'
 
     def extract_videos_from_page(self, page):
@@ -1546,9 +1611,9 @@ class YoutubeChannelIE(InfoExtractor):
 class YoutubeUserIE(InfoExtractor):
     IE_DESC = u'YouTube.com user videos (URL or "ytuser" keyword)'
     _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:user/)?(?!(?:attribution_link|watch)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)([A-Za-z0-9_-]+)'
-    _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
+    _TEMPLATE_URL = 'https://gdata.youtube.com/feeds/api/users/%s'
     _GDATA_PAGE_SIZE = 50
-    _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d&alt=json'
+    _GDATA_URL = 'https://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d&alt=json'
     IE_NAME = u'youtube:user'
 
     @classmethod
@@ -1572,44 +1637,35 @@ class YoutubeUserIE(InfoExtractor):
         # page by page until there are no video ids - it means we got
         # all of them.
 
-        url_results = []
-
-        for pagenum in itertools.count(0):
+        def download_page(pagenum):
             start_index = pagenum * self._GDATA_PAGE_SIZE + 1
 
             gdata_url = self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index)
-            page = self._download_webpage(gdata_url, username,
-                                          u'Downloading video ids from %d to %d' % (start_index, start_index + self._GDATA_PAGE_SIZE))
+            page = self._download_webpage(
+                gdata_url, username,
+                u'Downloading video ids from %d to %d' % (
+                    start_index, start_index + self._GDATA_PAGE_SIZE))
 
             try:
                 response = json.loads(page)
             except ValueError as err:
                 raise ExtractorError(u'Invalid JSON in API response: ' + compat_str(err))
             if 'entry' not in response['feed']:
-                # Number of videos is a multiple of self._MAX_RESULTS
-                break
+                return
 
             # Extract video identifiers
             entries = response['feed']['entry']
             for entry in entries:
                 title = entry['title']['$t']
                 video_id = entry['id']['$t'].split('/')[-1]
-                url_results.append({
+                yield {
                     '_type': 'url',
                     'url': video_id,
                     'ie_key': 'Youtube',
                     'id': 'video_id',
                     'title': title,
-                })
-
-            # A little optimization - if current page is not
-            # "full", ie. does not contain PAGE_SIZE video ids then
-            # we can assume that this page is the last one - there
-            # are no more ids on further pages - no need to query
-            # again.
-
-            if len(entries) < self._GDATA_PAGE_SIZE:
-                break
+                }
+        url_results = PagedList(download_page, self._GDATA_PAGE_SIZE)
 
         return self.playlist_result(url_results, playlist_title=username)
 
@@ -1688,7 +1744,7 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
         action = 'action_load_system_feed'
         if self._PERSONAL_FEED:
             action = 'action_load_personal_feed'
-        return 'http://www.youtube.com/feed_ajax?%s=1&feed_name=%s&paging=%%s' % (action, self._FEED_NAME)
+        return 'https://www.youtube.com/feed_ajax?%s=1&feed_name=%s&paging=%%s' % (action, self._FEED_NAME)
 
     @property
     def IE_NAME(self):
@@ -1757,7 +1813,10 @@ class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
 class YoutubeTruncatedURLIE(InfoExtractor):
     IE_NAME = 'youtube:truncated_url'
     IE_DESC = False  # Do not list
-    _VALID_URL = r'(?:https?://)?[^/]+/watch\?feature=[a-z_]+$'
+    _VALID_URL = r'''(?x)
+        (?:https?://)?[^/]+/watch\?feature=[a-z_]+$|
+        (?:https?://)?(?:www\.)?youtube\.com/attribution_link\?a=[^&]+$
+    '''
 
     def _real_extract(self, url):
         raise ExtractorError(

youtube_dl/postprocessor/ffmpeg.py

@@ -479,6 +479,7 @@ class FFmpegMergerPP(FFmpegPostProcessor):
     def run(self, info):
         filename = info['filepath']
         args = ['-c', 'copy']
+        self._downloader.to_screen(u'[ffmpeg] Merging formats into "%s"' % filename)
         self.run_ffmpeg_multiple_files(info['__files_to_merge'], filename, args)
         return True, info
 

youtube_dl/update.py

@@ -90,7 +90,7 @@ def update_self(to_screen, verbose):
         to_screen(u'youtube-dl is up to date (%s)' % __version__)
         return
 
-    to_screen(u'Updating to version ' + version_id + '...')
+    to_screen(u'Updating to version ' + version_id + ' ...')
     version = versions_info['versions'][version_id]
 
     print_notes(to_screen, versions_info['versions'])

youtube_dl/utils.py

@@ -6,6 +6,7 @@ import datetime
 import email.utils
 import errno
 import gzip
+import itertools
 import io
 import json
 import locale
@@ -224,7 +225,7 @@ if sys.version_info >= (2,7):
     def find_xpath_attr(node, xpath, key, val):
         """ Find the xpath xpath[@key=val] """
         assert re.match(r'^[a-zA-Z]+$', key)
-        assert re.match(r'^[a-zA-Z0-9@\s]*$', val)
+        assert re.match(r'^[a-zA-Z0-9@\s:._]*$', val)
         expr = xpath + u"[@%s='%s']" % (key, val)
         return node.find(expr)
 else:
@@ -1092,9 +1093,12 @@ def month_by_name(name):
         return None
 
 
-def fix_xml_all_ampersand(xml_str):
+def fix_xml_ampersands(xml_str):
     """Replace all the '&' by '&' in XML"""
-    return xml_str.replace(u'&', u'&')
+    return re.sub(
+        r'&(?!amp;|lt;|gt;|apos;|quot;|#x[0-9a-fA-F]{,4};|#[0-9]{,4};)',
+        u'&',
+        xml_str)
 
 
 def setproctitle(title):
@@ -1128,8 +1132,8 @@ class HEADRequest(compat_urllib_request.Request):
         return "HEAD"
 
 
-def int_or_none(v):
-    return v if v is None else int(v)
+def int_or_none(v, scale=1):
+    return v if v is None else (int(v) // scale)
 
 
 def parse_duration(s):
@@ -1161,3 +1165,50 @@ def check_executable(exe, args=[]):
     except OSError:
         return False
     return exe
+
+
+class PagedList(object):
+    def __init__(self, pagefunc, pagesize):
+        self._pagefunc = pagefunc
+        self._pagesize = pagesize
+
+    def __len__(self):
+        # This is only useful for tests
+        return len(self.getslice())
+
+    def getslice(self, start=0, end=None):
+        res = []
+        for pagenum in itertools.count(start // self._pagesize):
+            firstid = pagenum * self._pagesize
+            nextfirstid = pagenum * self._pagesize + self._pagesize
+            if start >= nextfirstid:
+                continue
+
+            page_results = list(self._pagefunc(pagenum))
+
+            startv = (
+                start % self._pagesize
+                if firstid <= start < nextfirstid
+                else 0)
+
+            endv = (
+                ((end - 1) % self._pagesize) + 1
+                if (end is not None and firstid <= end <= nextfirstid)
+                else None)
+
+            if startv != 0 or endv is not None:
+                page_results = page_results[startv:endv]
+            res.extend(page_results)
+
+            # A little optimization - if current page is not "full", ie. does
+            # not contain page_size videos then we can assume that this page
+            # is the last one - there are no more ids on further pages -
+            # i.e. no need to query again.
+            if len(page_results) + startv < self._pagesize:
+                break
+
+            # If we got the whole page, but the next page is not interesting,
+            # break out early as well
+            if end == nextfirstid:
+                break
+        return res

youtube_dl/version.py

@@ -1,2 +1,2 @@
 
-__version__ = '2013.01.17.1'
+__version__ = '2014.01.27.2'