release 2015.04.17

The QQMusic info extractor need forced encoding for correct working.

.travis.yml

@@ -2,6 +2,7 @@ language: python
 python:
   - "2.6"
   - "2.7"
+  - "3.2"
   - "3.3"
   - "3.4"
 before_install:

AUTHORS

@@ -113,3 +113,13 @@ Robin de Rooij
 Ryan Schmidt
 Leslie P. Polzer
 Duncan Keall
+Alexander Mamay
+Devin J. Pohly
+Eduardo Ferro Aldama
+Jeff Buchbinder
+Amish Bhadeshia
+Joram Schrijver
+Will W.
+Mohammad Teimori Pabandi
+Roman Le Négrate
+Matthias Küch

CONTRIBUTING.md

@@ -18,7 +18,9 @@ If your report is shorter than two lines, it is almost certainly missing some of
 
 For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the -v flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information.
 
-Site support requests **must contain an example URL**. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL.
+If your server has multiple IPs or you suspect censorship, adding --call-home may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/).
+
+**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL.
 
 ###  Are you using the latest version?
 

Makefile

@@ -2,7 +2,7 @@ all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bas
 
 clean:
 	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish *.dump *.part *.info.json *.mp4 *.flv *.mp3 *.avi CONTRIBUTING.md.tmp youtube-dl youtube-dl.exe
-	find -name "*.pyc" -delete
+	find . -name "*.pyc" -delete
 
 PREFIX ?= /usr/local
 BINDIR ?= $(PREFIX)/bin

README.md

@@ -45,21 +45,21 @@ which means you can modify it, redistribute it or use it however you like.
     youtube-dl [OPTIONS] URL [URL...]
 
 # OPTIONS
-    -h, --help                       print this help text and exit
-    --version                        print program version and exit
-    -U, --update                     update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed)
-    -i, --ignore-errors              continue on download errors, for example to skip unavailable videos in a playlist
+    -h, --help                       Print this help text and exit
+    --version                        Print program version and exit
+    -U, --update                     Update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed)
+    -i, --ignore-errors              Continue on download errors, for example to skip unavailable videos in a playlist
     --abort-on-error                 Abort downloading of further videos (in the playlist or the command line) if an error occurs
-    --dump-user-agent                display the current browser identification
+    --dump-user-agent                Display the current browser identification
     --list-extractors                List all supported extractors and the URLs they would handle
     --extractor-descriptions         Output descriptions of all supported extractors
-    --default-search PREFIX          Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for  youtube-dl "large apple".
+    --default-search PREFIX          Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large apple".
                                      Use the value "auto" to let youtube-dl guess ("auto_warning" to emit a warning when guessing). "error" just throws an error. The
                                      default value "fixup_error" repairs broken URLs, but emits an error if this is not possible instead of searching.
     --ignore-config                  Do not read configuration files. When given in the global configuration file /etc/youtube-dl.conf: Do not read the user configuration
                                      in ~/.config/youtube-dl/config (%APPDATA%/youtube-dl/config.txt on Windows)
     --flat-playlist                  Do not extract the videos of a playlist, only list them.
-    --no-color                       Do not emit color codes in output.
+    --no-color                       Do not emit color codes in output
 
 ## Network Options:
     --proxy URL                      Use the specified HTTP/HTTPS proxy. Pass in an empty string (--proxy "") for direct connection
@@ -71,70 +71,70 @@ which means you can modify it, redistribute it or use it however you like.
                                      not present) is used for the actual downloading. (experimental)
 
 ## Video Selection:
-    --playlist-start NUMBER          playlist video to start at (default is 1)
-    --playlist-end NUMBER            playlist video to end at (default is last)
-    --playlist-items ITEM_SPEC       playlist video items to download. Specify indices of the videos in the playlist seperated by commas like: "--playlist-items 1,2,5,8"
+    --playlist-start NUMBER          Playlist video to start at (default is 1)
+    --playlist-end NUMBER            Playlist video to end at (default is last)
+    --playlist-items ITEM_SPEC       Playlist video items to download. Specify indices of the videos in the playlist seperated by commas like: "--playlist-items 1,2,5,8"
                                      if you want to download videos indexed 1, 2, 5, 8 in the playlist. You can specify range: "--playlist-items 1-3,7,10-13", it will
                                      download the videos at index 1, 2, 3, 7, 10, 11, 12 and 13.
-    --match-title REGEX              download only matching titles (regex or caseless sub-string)
-    --reject-title REGEX             skip download for matching titles (regex or caseless sub-string)
+    --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)
+    --date DATE                      Download only videos uploaded in this date
+    --datebefore DATE                Download only videos uploaded on or before this date (i.e. inclusive)
+    --dateafter DATE                 Download only videos uploaded on or after this date (i.e. inclusive)
     --min-views COUNT                Do not download any videos with less than COUNT views
     --max-views COUNT                Do not download any videos with more than COUNT views
-    --match-filter FILTER            (Experimental) Generic video filter. Specify any key (see help for -o for a list of available keys) to match if the key is present,
+    --match-filter FILTER            Generic video filter (experimental). Specify any key (see help for -o for a list of available keys) to match if the key is present,
                                      !key to check if the key is not present,key > NUMBER (like "comment_count > 12", also works with >=, <, <=, !=, =) to compare against
                                      a number, and & to require multiple matches. Values which are not known are excluded unless you put a question mark (?) after the
                                      operator.For example, to only match videos that have been liked more than 100 times and disliked less than 50 times (or the dislike
                                      functionality is not available at the given service), but who also have a description, use  --match-filter "like_count > 100 &
                                      dislike_count <? 50 & description" .
-    --no-playlist                    If the URL refers to a video and a playlist, download only the video.
-    --yes-playlist                   If the URL refers to a video and a playlist, download the playlist.
-    --age-limit YEARS                download only videos suitable for the given age
+    --no-playlist                    Download only the video, if the URL refers to a video and a playlist.
+    --yes-playlist                   Download the playlist, if the URL refers to a video and a playlist.
+    --age-limit YEARS                Download only videos suitable for the given age
     --download-archive FILE          Download only videos not listed in the archive file. Record the IDs of all downloaded videos in it.
     --include-ads                    Download advertisements as well (experimental)
 
 ## Download Options:
-    -r, --rate-limit LIMIT           maximum download rate in bytes per second (e.g. 50K or 4.2M)
-    -R, --retries RETRIES            number of retries (default is 10), or "infinite".
-    --buffer-size SIZE               size of download buffer (e.g. 1024 or 16K) (default is 1024)
-    --no-resize-buffer               do not automatically adjust the buffer size. By default, the buffer size is automatically resized from an initial value of SIZE.
+    -r, --rate-limit LIMIT           Maximum download rate in bytes per second (e.g. 50K or 4.2M)
+    -R, --retries RETRIES            Number of retries (default is 10), or "infinite".
+    --buffer-size SIZE               Size of download buffer (e.g. 1024 or 16K) (default is 1024)
+    --no-resize-buffer               Do not automatically adjust the buffer size. By default, the buffer size is automatically resized from an initial value of SIZE.
     --playlist-reverse               Download playlist videos in reverse order
-    --xattr-set-filesize             (experimental) set file xattribute ytdl.filesize with expected filesize
-    --hls-prefer-native              (experimental) Use the native HLS downloader instead of ffmpeg.
+    --xattr-set-filesize             Set file xattribute ytdl.filesize with expected filesize (experimental)
+    --hls-prefer-native              Use the native HLS downloader instead of ffmpeg (experimental)
     --external-downloader COMMAND    Use the specified external downloader. Currently supports aria2c,curl,wget
-    --external-downloader-args ARGS  Give these arguments to the external downloader.
+    --external-downloader-args ARGS  Give these arguments to the external downloader
 
 ## Filesystem Options:
-    -a, --batch-file FILE            file containing URLs to download ('-' for stdin)
-    --id                             use only video ID in file name
-    -o, --output TEMPLATE            output filename template. Use %(title)s to get the title, %(uploader)s for the uploader name, %(uploader_id)s for the uploader
+    -a, --batch-file FILE            File containing URLs to download ('-' for stdin)
+    --id                             Use only video ID in file name
+    -o, --output TEMPLATE            Output filename template. Use %(title)s to get the title, %(uploader)s for the uploader name, %(uploader_id)s for the uploader
                                      nickname if different, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(format)s for
-                                     the format description (like "22 - 1280x720" or "HD"), %(format_id)s for the unique id of the format (like Youtube's itags: "137"),
+                                     the format description (like "22 - 1280x720" or "HD"), %(format_id)s for the unique id of the format (like YouTube's itags: "137"),
                                      %(upload_date)s for the upload date (YYYYMMDD), %(extractor)s for the provider (youtube, metacafe, etc), %(id)s for the video id,
                                      %(playlist_title)s, %(playlist_id)s, or %(playlist)s (=title if present, ID otherwise) for the playlist the video is in,
                                      %(playlist_index)s for the position in the playlist. %(height)s and %(width)s for the width and height of the video format.
                                      %(resolution)s for a textual description of the resolution of the video format. %% for a literal percent. Use - to output to stdout.
                                      Can also be used to download to a different directory, for example with -o '/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s' .
-    --autonumber-size NUMBER         Specifies the number of digits in %(autonumber)s when it is present in output filename template or --auto-number option is given
+    --autonumber-size NUMBER         Specify the number of digits in %(autonumber)s when it is present in output filename template or --auto-number option is given
     --restrict-filenames             Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames
-    -A, --auto-number                [deprecated; use  -o "%(autonumber)s-%(title)s.%(ext)s" ] number downloaded files starting from 00000
-    -t, --title                      [deprecated] use title in file name (default)
-    -l, --literal                    [deprecated] alias of --title
-    -w, --no-overwrites              do not overwrite files
-    -c, --continue                   force resume of partially downloaded files. By default, youtube-dl will resume downloads if possible.
-    --no-continue                    do not resume partially downloaded files (restart from beginning)
-    --no-part                        do not use .part files - write directly into output file
-    --no-mtime                       do not use the Last-modified header to set the file modification time
-    --write-description              write video description to a .description file
-    --write-info-json                write video metadata to a .info.json file
-    --write-annotations              write video annotations to a .annotation file
-    --load-info FILE                 json file containing the video information (created with the "--write-json" option)
-    --cookies FILE                   file to read cookies from and dump cookie jar in
+    -A, --auto-number                [deprecated; use  -o "%(autonumber)s-%(title)s.%(ext)s" ] Number downloaded files starting from 00000
+    -t, --title                      [deprecated] Use title in file name (default)
+    -l, --literal                    [deprecated] Alias of --title
+    -w, --no-overwrites              Do not overwrite files
+    -c, --continue                   Force resume of partially downloaded files. By default, youtube-dl will resume downloads if possible.
+    --no-continue                    Do not resume partially downloaded files (restart from beginning)
+    --no-part                        Do not use .part files - write directly into output file
+    --no-mtime                       Do not use the Last-modified header to set the file modification time
+    --write-description              Write video description to a .description file
+    --write-info-json                Write video metadata to a .info.json file
+    --write-annotations              Write video annotations to a .annotation file
+    --load-info FILE                 JSON file containing the video information (created with the "--write-info-json" option)
+    --cookies FILE                   File to read cookies from and dump cookie jar in
     --cache-dir DIR                  Location in the filesystem where youtube-dl can store some downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl
                                      or ~/.cache/youtube-dl . At the moment, only YouTube player files (for videos with obfuscated signatures) are cached, but that may
                                      change.
@@ -142,49 +142,49 @@ which means you can modify it, redistribute it or use it however you like.
     --rm-cache-dir                   Delete all filesystem cache files
 
 ## Thumbnail images:
-    --write-thumbnail                write thumbnail image to disk
-    --write-all-thumbnails           write all thumbnail image formats to disk
+    --write-thumbnail                Write thumbnail image to disk
+    --write-all-thumbnails           Write all thumbnail image formats to disk
     --list-thumbnails                Simulate and list all available thumbnail formats
 
 ## Verbosity / Simulation Options:
-    -q, --quiet                      activates quiet mode
+    -q, --quiet                      Activate quiet mode
     --no-warnings                    Ignore warnings
-    -s, --simulate                   do not download the video and do not write anything to disk
-    --skip-download                  do not download the video
-    -g, --get-url                    simulate, quiet but print URL
-    -e, --get-title                  simulate, quiet but print title
-    --get-id                         simulate, quiet but print id
-    --get-thumbnail                  simulate, quiet but print thumbnail URL
-    --get-description                simulate, quiet but print video description
-    --get-duration                   simulate, quiet but print video length
-    --get-filename                   simulate, quiet but print output filename
-    --get-format                     simulate, quiet but print output format
-    -j, --dump-json                  simulate, quiet but print JSON information. See --output for a description of available keys.
-    -J, --dump-single-json           simulate, quiet but print JSON information for each command-line argument. If the URL refers to a playlist, dump the whole playlist
+    -s, --simulate                   Do not download the video and do not write anything to disk
+    --skip-download                  Do not download the video
+    -g, --get-url                    Simulate, quiet but print URL
+    -e, --get-title                  Simulate, quiet but print title
+    --get-id                         Simulate, quiet but print id
+    --get-thumbnail                  Simulate, quiet but print thumbnail URL
+    --get-description                Simulate, quiet but print video description
+    --get-duration                   Simulate, quiet but print video length
+    --get-filename                   Simulate, quiet but print output filename
+    --get-format                     Simulate, quiet but print output format
+    -j, --dump-json                  Simulate, quiet but print JSON information. See --output for a description of available keys.
+    -J, --dump-single-json           Simulate, quiet but print JSON information for each command-line argument. If the URL refers to a playlist, dump the whole playlist
                                      information in a single line.
     --print-json                     Be quiet and print the video information as JSON (video is still being downloaded).
-    --newline                        output progress bar as new lines
-    --no-progress                    do not print progress bar
-    --console-title                  display progress in console titlebar
-    -v, --verbose                    print various debugging information
-    --dump-intermediate-pages        print downloaded pages to debug problems (very verbose)
+    --newline                        Output progress bar as new lines
+    --no-progress                    Do not print progress bar
+    --console-title                  Display progress in console titlebar
+    -v, --verbose                    Print various debugging information
+    --dump-pages                     Print downloaded pages to debug problems (very verbose)
     --write-pages                    Write downloaded intermediary pages to files in the current directory to debug problems
     --print-traffic                  Display sent and read HTTP traffic
-    -C, --call-home                  Contact the youtube-dl server for debugging.
-    --no-call-home                   Do NOT contact the youtube-dl server for debugging.
+    -C, --call-home                  Contact the youtube-dl server for debugging
+    --no-call-home                   Do NOT contact the youtube-dl server for debugging
 
 ## Workarounds:
     --encoding ENCODING              Force the specified encoding (experimental)
-    --no-check-certificate           Suppress HTTPS certificate validation.
+    --no-check-certificate           Suppress HTTPS certificate validation
     --prefer-insecure                Use an unencrypted connection to retrieve information about the video. (Currently supported only for YouTube)
-    --user-agent UA                  specify a custom user agent
-    --referer URL                    specify a custom referer, use if the video access is restricted to one domain
-    --add-header FIELD:VALUE         specify a custom HTTP header and its value, separated by a colon ':'. You can use this option multiple times
+    --user-agent UA                  Specify a custom user agent
+    --referer URL                    Specify a custom referer, use if the video access is restricted to one domain
+    --add-header FIELD:VALUE         Specify a custom HTTP header and its value, separated by a colon ':'. You can use this option multiple times
     --bidi-workaround                Work around terminals that lack bidirectional text support. Requires bidiv or fribidi executable in PATH
     --sleep-interval SECONDS         Number of seconds to sleep before each download.
 
 ## Video Format Options:
-    -f, --format FORMAT              video format code, specify the order of preference using slashes, as in -f 22/17/18 .  Instead of format codes, you can select by
+    -f, --format FORMAT              Video format code, specify the order of preference using slashes, as in -f 22/17/18 .  Instead of format codes, you can select by
                                      extension for the extensions aac, m4a, mp3, mp4, ogg, wav, webm. You can also use the special names "best", "bestvideo", "bestaudio",
                                      "worst".  You can filter the video results by putting a condition in brackets, as in -f "best[height=720]" (or -f "[filesize>10M]").
                                      This works for filesize, height, width, tbr, abr, vbr, asr, and fps and the comparisons <, <=, >, >=, =, != and for ext, acodec,
@@ -194,41 +194,44 @@ which means you can modify it, redistribute it or use it however you like.
                                      Use commas to download multiple audio formats, such as -f  136/137/mp4/bestvideo,140/m4a/bestaudio. You can merge the video and audio
                                      of two formats into a single file using -f <video-format>+<audio-format> (requires ffmpeg or avconv), for example -f
                                      bestvideo+bestaudio.
-    --all-formats                    download all available video formats
-    --prefer-free-formats            prefer free video formats unless a specific one is requested
-    --max-quality FORMAT             highest quality format to download
-    -F, --list-formats               list all available formats
+    --all-formats                    Download all available video formats
+    --prefer-free-formats            Prefer free video formats unless a specific one is requested
+    --max-quality FORMAT             Highest quality format to download
+    -F, --list-formats               List all available formats
     --youtube-skip-dash-manifest     Do not download the DASH manifest on YouTube videos
     --merge-output-format FORMAT     If a merge is required (e.g. bestvideo+bestaudio), output to given container format. One of mkv, mp4, ogg, webm, flv.Ignored if no
                                      merge is required
 
 ## Subtitle Options:
-    --write-sub                      write subtitle file
-    --write-auto-sub                 write automatic subtitle file (youtube only)
-    --all-subs                       downloads all the available subtitles of the video
-    --list-subs                      lists all available subtitles for the video
-    --sub-format FORMAT              subtitle format, accepts formats preference, for example: "ass/srt/best"
-    --sub-lang LANGS                 languages of the subtitles to download (optional) separated by commas, use IETF language tags like 'en,pt'
+    --write-sub                      Write subtitle file
+    --write-auto-sub                 Write automatic subtitle file (YouTube only)
+    --all-subs                       Download all the available subtitles of the video
+    --list-subs                      List all available subtitles for the video
+    --sub-format FORMAT              Subtitle format, accepts formats preference, for example: "srt" or "ass/srt/best"
+    --sub-lang LANGS                 Languages of the subtitles to download (optional) separated by commas, use IETF language tags like 'en,pt'
 
 ## Authentication Options:
-    -u, --username USERNAME          login with this account ID
-    -p, --password PASSWORD          account password. If this option is left out, youtube-dl will ask interactively.
-    -2, --twofactor TWOFACTOR        two-factor auth code
-    -n, --netrc                      use .netrc authentication data
-    --video-password PASSWORD        video password (vimeo, smotri)
+    -u, --username USERNAME          Login with this account ID
+    -p, --password PASSWORD          Account password. If this option is left out, youtube-dl will ask interactively.
+    -2, --twofactor TWOFACTOR        Two-factor auth code
+    -n, --netrc                      Use .netrc authentication data
+    --video-password PASSWORD        Video password (vimeo, smotri)
 
 ## Post-processing Options:
-    -x, --extract-audio              convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)
-    --audio-format FORMAT            "best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; "best" by default
-    --audio-quality QUALITY          ffmpeg/avconv audio quality specification, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K
-                                     (default 5)
+    -x, --extract-audio              Convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)
+    --audio-format FORMAT            Specify audio format: "best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; "best" by default
+    --audio-quality QUALITY          Specify ffmpeg/avconv audio quality, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default
+                                     5)
     --recode-video FORMAT            Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm|mkv)
-    -k, --keep-video                 keeps the video file on disk after the post-processing; the video is erased by default
-    --no-post-overwrites             do not overwrite post-processed files; the post-processed files are overwritten by default
-    --embed-subs                     embed subtitles in the video (only for mp4 videos)
-    --embed-thumbnail                embed thumbnail in the audio as cover art
-    --add-metadata                   write metadata to the video file
-    --xattrs                         write metadata to the video file's xattrs (using dublin core and xdg standards)
+    -k, --keep-video                 Keep the video file on disk after the post-processing; the video is erased by default
+    --no-post-overwrites             Do not overwrite post-processed files; the post-processed files are overwritten by default
+    --embed-subs                     Embed subtitles in the video (only for mp4 videos)
+    --embed-thumbnail                Embed thumbnail in the audio as cover art
+    --add-metadata                   Write metadata to the video file
+    --metadata-from-title FORMAT     Parse additional metadata like song title / artist from the video title. The format syntax is the same as --output, the parsed
+                                     parameters replace existing values. Additional templates: %(album), %(artist). Example: --metadata-from-title "%(artist)s -
+                                     %(title)s" matches a title like "Coldplay - Paradise"
+    --xattrs                         Write metadata to the video file's xattrs (using dublin core and xdg standards)
     --fixup POLICY                   Automatically correct known faults of the file. One of never (do nothing), warn (only emit a warning), detect_or_warn(the default;
                                      fix file if we can, warn otherwise)
     --prefer-avconv                  Prefer avconv over ffmpeg for running the postprocessors (default)
@@ -404,6 +407,18 @@ A note on the service that they don't host the infringing content, but just link
 
 Support requests for services that **do** purchase the rights to distribute their content are perfectly fine though. If in doubt, you can simply include a source that mentions the legitimate purchase of content.
 
+### How can I speed up work on my issue?
+
+(Also known as: Help, my important issue not being solved!) The youtube-dl core developer team is quite small. While we do our best to solve as many issues as possible, sometimes that can take quite a while. To speed up your issue, here's what you can do:
+
+First of all, please do report the issue [at our issue tracker](https://yt-dl.org/bugs). That allows us to coordinate all efforts by users and developers, and serves as a unified point. Unfortunately, the youtube-dl project has grown too large to use personal email as an effective communication channel.
+
+Please read the [bug reporting instructions](#bugs) below. A lot of bugs lack all the necessary information. If you can, offer proxy, VPN, or shell access to the youtube-dl developers. If you are able to, test the issue from multiple computers in multiple countries to exclude local censorship or misconfiguration issues.
+
+If nobody is interested in solving your issue, you are welcome to take matters into your own hands and submit a pull request (or coerce/pay somebody else to do so).
+
+Feel free to bump the issue from time to time by writing a small comment ("Issue is still present in youtube-dl version ...from France, but fixed from Belgium"), but please not more than once a month. Please do not declare your issue as `important` or `urgent`.
+
 ### How can I detect whether a given URL is supported by youtube-dl?
 
 For one, have a look at the [list of supported sites](docs/supportedsites.md). Note that it can sometimes happen that the site changes its URL scheme (say, from http://example.com/video/1234567 to http://example.com/v/1234567 ) and youtube-dl reports an URL of a service in that list as unsupported. In that case, simply report a bug.
@@ -503,6 +518,7 @@ youtube-dl makes the best effort to be a good command-line program, and thus sho
 From a Python program, you can embed youtube-dl in a more powerful fashion, like this:
 
 ```python
+from __future__ import unicode_literals
 import youtube_dl
 
 ydl_opts = {}
@@ -515,6 +531,7 @@ Most likely, you'll want to use various options. For a list of what can be done,
 Here's a more complete example of a program that outputs only errors (and a short message after the download is finished), and downloads/converts the video to an mp3 file:
 
 ```python
+from __future__ import unicode_literals
 import youtube_dl
 
 
@@ -572,7 +589,9 @@ If your report is shorter than two lines, it is almost certainly missing some of
 
 For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the -v flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information.
 
-Site support requests **must contain an example URL**. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL.
+If your server has multiple IPs or you suspect censorship, adding --call-home may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/).
+
+**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL.
 
 ###  Are you using the latest version?
 

devscripts/check-porn.py

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

devscripts/generate_aes_testdata.py

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

docs/supportedsites.md

@@ -2,6 +2,8 @@
  - **1tv**: Первый канал
  - **1up.com**
  - **220.ro**
+ - **22tracks:genre**
+ - **22tracks:track**
  - **24video**
  - **3sat**
  - **4tube**
@@ -47,6 +49,7 @@
  - **Bandcamp**
  - **Bandcamp:album**
  - **bbc.co.uk**: BBC iPlayer
+ - **BeatportPro**
  - **Beeg**
  - **BehindKink**
  - **Bet**
@@ -95,6 +98,7 @@
  - **CondeNast**: Condé Nast media group: Condé Nast, GQ, Glamour, Vanity Fair, Vogue, W Magazine, WIRED
  - **Cracked**
  - **Criterion**
+ - **CrooksAndLiars**
  - **Crunchyroll**
  - **crunchyroll:playlist**
  - **CSpan**: C-SPAN
@@ -108,15 +112,19 @@
  - **DctpTv**
  - **DeezerPlaylist**
  - **defense.gouv.fr**
+ - **DHM**: Filmarchiv - Deutsches Historisches Museum
  - **Discovery**
  - **divxstage**: DivxStage
  - **Dotsub**
+ - **DouyuTV**
  - **DRBonanza**
  - **Dropbox**
  - **DrTuber**
  - **DRTV**
  - **Dump**
+ - **Dumpert**
  - **dvtv**: http://video.aktualne.cz/
+ - **EaglePlatform**
  - **EbaumsWorld**
  - **EchoMsk**
  - **eHow**
@@ -144,6 +152,7 @@
  - **Firstpost**
  - **Flickr**
  - **Folketinget**: Folketinget (ft.dk; Danish parliament)
+ - **FootyRoom**
  - **Foxgay**
  - **FoxNews**
  - **france2.fr:generation-quoi**
@@ -158,9 +167,11 @@
  - **Gamekings**
  - **GameOne**
  - **gameone:playlist**
+ - **Gamersyde**
  - **GameSpot**
  - **GameStar**
  - **Gametrailers**
+ - **Gazeta**
  - **GDCVault**
  - **generic**: Generic downloader that works on some sites
  - **GiantBomb**
@@ -211,6 +222,7 @@
  - **jpopsuki.tv**
  - **Jukebox**
  - **Kaltura**
+ - **KanalPlay**: Kanal 5/9/11 Play
  - **Kankan**
  - **Karaoketv**
  - **keek**
@@ -225,6 +237,7 @@
  - **Letv**
  - **LetvPlaylist**
  - **LetvTv**
+ - **Libsyn**
  - **lifenews**: LIFE | NEWS
  - **LiveLeak**
  - **livestream**
@@ -244,6 +257,7 @@
  - **Mgoon**
  - **Minhateca**
  - **MinistryGrid**
+ - **miomio.tv**
  - **mitele.es**
  - **mixcloud**
  - **MLB**
@@ -277,6 +291,8 @@
  - **NBA**
  - **NBC**
  - **NBCNews**
+ - **NBCSports**
+ - **NBCSportsVPlayer**
  - **ndr**: NDR.de - Mediathek
  - **NDTV**
  - **NerdCubedFeed**
@@ -304,6 +320,7 @@
  - **npo.nl:radio**
  - **npo.nl:radio:fragment**
  - **NRK**
+ - **NRKPlaylist**
  - **NRKTV**
  - **ntv.ru**
  - **Nuvid**
@@ -315,6 +332,7 @@
  - **Ooyala**
  - **OpenFilm**
  - **orf:fm4**: radio FM4
+ - **orf:iptv**: iptv.ORF.at
  - **orf:oe1**: Radio Österreich 1
  - **orf:tvthek**: ORF TVthek
  - **parliamentlive.tv**: UK parliament videos
@@ -322,10 +340,12 @@
  - **PBS**
  - **Phoenix**
  - **Photobucket**
+ - **Pladform**
  - **PlanetaPlay**
  - **play.fm**
  - **played.to**
  - **Playvid**
+ - **Playwire**
  - **plus.google**: Google Plus
  - **pluzz.francetv.fr**
  - **podomatic**
@@ -333,16 +353,22 @@
  - **PornHub**
  - **PornHubPlaylist**
  - **Pornotube**
+ - **PornoVoisines**
  - **PornoXO**
+ - **PrimeShareTV**
  - **PromptFile**
  - **prosiebensat1**: ProSiebenSat.1 Digital
  - **Puls4**
  - **Pyvideo**
+ - **QQMusic**
+ - **QQMusicAlbum**
+ - **QQMusicSinger**
  - **QuickVid**
  - **R7**
  - **radio.de**
  - **radiobremen**
  - **radiofrance**
+ - **RadioJavan**
  - **Rai**
  - **RBMARadio**
  - **RedTube**
@@ -359,6 +385,7 @@
  - **RTP**
  - **RTS**: RTS.ch
  - **rtve.es:alacarta**: RTVE a la carta
+ - **rtve.es:infantil**: RTVE infantil
  - **rtve.es:live**: RTVE.es live streams
  - **RUHD**
  - **rutube**: Rutube videos
@@ -367,6 +394,8 @@
  - **rutube:movie**: Rutube movies
  - **rutube:person**: Rutube person videos
  - **RUTV**: RUTV.RU
+ - **safari**: safaribooksonline.com online video
+ - **safari:course**: safaribooksonline.com online courses
  - **Sandia**: Sandia National Laboratories
  - **Sapo**: SAPO Vídeos
  - **savefrom.net**
@@ -400,6 +429,7 @@
  - **southpark.cc.com**
  - **southpark.de**
  - **Space**
+ - **SpankBang**
  - **Spankwire**
  - **Spiegel**
  - **Spiegel:Article**: Articles on spiegel.de
@@ -408,7 +438,9 @@
  - **Sport5**
  - **SportBox**
  - **SportDeutschland**
+ - **Srf**
  - **SRMediathek**: Saarländischer Rundfunk
+ - **SSA**
  - **stanfordoc**: Stanford Open ClassRoom
  - **Steam**
  - **streamcloud.eu**
@@ -478,13 +510,17 @@
  - **Ubu**
  - **udemy**
  - **udemy:course**
+ - **UDNEmbed**
+ - **Ultimedia**
  - **Unistra**
  - **Urort**: NRK P3 Urørt
  - **ustream**
  - **ustream:channel**
+ - **Varzesh3**
  - **Vbox7**
  - **VeeHD**
  - **Veoh**
+ - **Vessel**
  - **Vesti**: Вести.Ru
  - **Vevo**
  - **VGTV**
@@ -505,6 +541,7 @@
  - **Vidzi**
  - **vier**
  - **vier:videos**
+ - **Viewster**
  - **viki**
  - **vimeo**
  - **vimeo:album**
@@ -551,6 +588,9 @@
  - **XXXYMovies**
  - **Yahoo**: Yahoo screen and movies
  - **Yam**
+ - **yandexmusic:album**: Яндекс.Музыка - Альбом
+ - **yandexmusic:playlist**: Яндекс.Музыка - Плейлист
+ - **yandexmusic:track**: Яндекс.Музыка - Трек
  - **YesJapan**
  - **Ynet**
  - **YouJizz**
@@ -569,7 +609,7 @@
  - **youtube:show**: YouTube.com (multi-season) shows
  - **youtube:subscriptions**: YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)
  - **youtube:user**: YouTube.com user videos (URL or "ytuser" keyword)
- - **youtube:watch_later**: Youtube watch later list, ":ytwatchlater" for short (requires authentication)
+ - **youtube:watchlater**: Youtube watch later list, ":ytwatchlater" for short (requires authentication)
  - **Zapiks**
  - **ZDF**
  - **ZDFChannel**

test/test_YoutubeDL.py

@@ -14,6 +14,9 @@ from test.helper import FakeYDL, assertRegexpMatches
 from youtube_dl import YoutubeDL
 from youtube_dl.extractor import YoutubeIE
 from youtube_dl.postprocessor.common import PostProcessor
+from youtube_dl.utils import match_filter_func
+
+TEST_URL = 'http://localhost/sample.mp4'
 
 
 class YDL(FakeYDL):
@@ -46,8 +49,8 @@ class TestFormatSelection(unittest.TestCase):
         ydl = YDL()
         ydl.params['prefer_free_formats'] = True
         formats = [
-            {'ext': 'webm', 'height': 460, 'url': 'x'},
-            {'ext': 'mp4', 'height': 460, 'url': 'y'},
+            {'ext': 'webm', 'height': 460, 'url': TEST_URL},
+            {'ext': 'mp4', 'height': 460, 'url': TEST_URL},
         ]
         info_dict = _make_result(formats)
         yie = YoutubeIE(ydl)
@@ -60,8 +63,8 @@ class TestFormatSelection(unittest.TestCase):
         ydl = YDL()
         ydl.params['prefer_free_formats'] = True
         formats = [
-            {'ext': 'webm', 'height': 720, 'url': 'a'},
-            {'ext': 'mp4', 'height': 1080, 'url': 'b'},
+            {'ext': 'webm', 'height': 720, 'url': TEST_URL},
+            {'ext': 'mp4', 'height': 1080, 'url': TEST_URL},
         ]
         info_dict['formats'] = formats
         yie = YoutubeIE(ydl)
@@ -74,9 +77,9 @@ class TestFormatSelection(unittest.TestCase):
         ydl = YDL()
         ydl.params['prefer_free_formats'] = False
         formats = [
-            {'ext': 'webm', 'height': 720, 'url': '_'},
-            {'ext': 'mp4', 'height': 720, 'url': '_'},
-            {'ext': 'flv', 'height': 720, 'url': '_'},
+            {'ext': 'webm', 'height': 720, 'url': TEST_URL},
+            {'ext': 'mp4', 'height': 720, 'url': TEST_URL},
+            {'ext': 'flv', 'height': 720, 'url': TEST_URL},
         ]
         info_dict['formats'] = formats
         yie = YoutubeIE(ydl)
@@ -88,8 +91,8 @@ class TestFormatSelection(unittest.TestCase):
         ydl = YDL()
         ydl.params['prefer_free_formats'] = False
         formats = [
-            {'ext': 'flv', 'height': 720, 'url': '_'},
-            {'ext': 'webm', 'height': 720, 'url': '_'},
+            {'ext': 'flv', 'height': 720, 'url': TEST_URL},
+            {'ext': 'webm', 'height': 720, 'url': TEST_URL},
         ]
         info_dict['formats'] = formats
         yie = YoutubeIE(ydl)
@@ -133,10 +136,10 @@ class TestFormatSelection(unittest.TestCase):
 
     def test_format_selection(self):
         formats = [
-            {'format_id': '35', 'ext': 'mp4', 'preference': 1, 'url': '_'},
-            {'format_id': '45', 'ext': 'webm', 'preference': 2, 'url': '_'},
-            {'format_id': '47', 'ext': 'webm', 'preference': 3, 'url': '_'},
-            {'format_id': '2', 'ext': 'flv', 'preference': 4, 'url': '_'},
+            {'format_id': '35', 'ext': 'mp4', 'preference': 1, 'url': TEST_URL},
+            {'format_id': '45', 'ext': 'webm', 'preference': 2, 'url': TEST_URL},
+            {'format_id': '47', 'ext': 'webm', 'preference': 3, 'url': TEST_URL},
+            {'format_id': '2', 'ext': 'flv', 'preference': 4, 'url': TEST_URL},
         ]
         info_dict = _make_result(formats)
 
@@ -167,10 +170,10 @@ class TestFormatSelection(unittest.TestCase):
 
     def test_format_selection_audio(self):
         formats = [
-            {'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none', 'url': '_'},
-            {'format_id': 'audio-mid', 'ext': 'webm', 'preference': 2, 'vcodec': 'none', 'url': '_'},
-            {'format_id': 'audio-high', 'ext': 'flv', 'preference': 3, 'vcodec': 'none', 'url': '_'},
-            {'format_id': 'vid', 'ext': 'mp4', 'preference': 4, 'url': '_'},
+            {'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none', 'url': TEST_URL},
+            {'format_id': 'audio-mid', 'ext': 'webm', 'preference': 2, 'vcodec': 'none', 'url': TEST_URL},
+            {'format_id': 'audio-high', 'ext': 'flv', 'preference': 3, 'vcodec': 'none', 'url': TEST_URL},
+            {'format_id': 'vid', 'ext': 'mp4', 'preference': 4, 'url': TEST_URL},
         ]
         info_dict = _make_result(formats)
 
@@ -185,8 +188,8 @@ class TestFormatSelection(unittest.TestCase):
         self.assertEqual(downloaded['format_id'], 'audio-low')
 
         formats = [
-            {'format_id': 'vid-low', 'ext': 'mp4', 'preference': 1, 'url': '_'},
-            {'format_id': 'vid-high', 'ext': 'mp4', 'preference': 2, 'url': '_'},
+            {'format_id': 'vid-low', 'ext': 'mp4', 'preference': 1, 'url': TEST_URL},
+            {'format_id': 'vid-high', 'ext': 'mp4', 'preference': 2, 'url': TEST_URL},
         ]
         info_dict = _make_result(formats)
 
@@ -228,9 +231,9 @@ class TestFormatSelection(unittest.TestCase):
 
     def test_format_selection_video(self):
         formats = [
-            {'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': '_'},
-            {'format_id': 'dash-video-high', 'ext': 'mp4', 'preference': 2, 'acodec': 'none', 'url': '_'},
-            {'format_id': 'vid', 'ext': 'mp4', 'preference': 3, 'url': '_'},
+            {'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': TEST_URL},
+            {'format_id': 'dash-video-high', 'ext': 'mp4', 'preference': 2, 'acodec': 'none', 'url': TEST_URL},
+            {'format_id': 'vid', 'ext': 'mp4', 'preference': 3, 'url': TEST_URL},
         ]
         info_dict = _make_result(formats)
 
@@ -337,6 +340,8 @@ class TestFormatSelection(unittest.TestCase):
         downloaded = ydl.downloaded_info_dicts[0]
         self.assertEqual(downloaded['format_id'], 'G')
 
+
+class TestYoutubeDL(unittest.TestCase):
     def test_subtitles(self):
         def s_formats(lang, autocaption=False):
             return [{
@@ -459,6 +464,73 @@ class TestFormatSelection(unittest.TestCase):
         self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
         os.unlink(audiofile)
 
+    def test_match_filter(self):
+        class FilterYDL(YDL):
+            def __init__(self, *args, **kwargs):
+                super(FilterYDL, self).__init__(*args, **kwargs)
+                self.params['simulate'] = True
+
+            def process_info(self, info_dict):
+                super(YDL, self).process_info(info_dict)
+
+            def _match_entry(self, info_dict, incomplete):
+                res = super(FilterYDL, self)._match_entry(info_dict, incomplete)
+                if res is None:
+                    self.downloaded_info_dicts.append(info_dict)
+                return res
+
+        first = {
+            'id': '1',
+            'url': TEST_URL,
+            'title': 'one',
+            'extractor': 'TEST',
+            'duration': 30,
+            'filesize': 10 * 1024,
+        }
+        second = {
+            'id': '2',
+            'url': TEST_URL,
+            'title': 'two',
+            'extractor': 'TEST',
+            'duration': 10,
+            'description': 'foo',
+            'filesize': 5 * 1024,
+        }
+        videos = [first, second]
+
+        def get_videos(filter_=None):
+            ydl = FilterYDL({'match_filter': filter_})
+            for v in videos:
+                ydl.process_ie_result(v, download=True)
+            return [v['id'] for v in ydl.downloaded_info_dicts]
+
+        res = get_videos()
+        self.assertEqual(res, ['1', '2'])
+
+        def f(v):
+            if v['id'] == '1':
+                return None
+            else:
+                return 'Video id is not 1'
+        res = get_videos(f)
+        self.assertEqual(res, ['1'])
+
+        f = match_filter_func('duration < 30')
+        res = get_videos(f)
+        self.assertEqual(res, ['2'])
+
+        f = match_filter_func('description = foo')
+        res = get_videos(f)
+        self.assertEqual(res, ['2'])
+
+        f = match_filter_func('description =? foo')
+        res = get_videos(f)
+        self.assertEqual(res, ['1', '2'])
+
+        f = match_filter_func('filesize > 5KiB')
+        res = get_videos(f)
+        self.assertEqual(res, ['1'])
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_aes.py

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

test/test_all_urls.py

@@ -59,7 +59,7 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertMatch('www.youtube.com/NASAgovVideo/videos', ['youtube:user'])
 
     def test_youtube_feeds(self):
-        self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:watch_later'])
+        self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:watchlater'])
         self.assertMatch('https://www.youtube.com/feed/subscriptions', ['youtube:subscriptions'])
         self.assertMatch('https://www.youtube.com/feed/recommended', ['youtube:recommended'])
         self.assertMatch('https://www.youtube.com/my_favorites', ['youtube:favorites'])
@@ -104,11 +104,11 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertMatch(':tds', ['ComedyCentralShows'])
 
     def test_vimeo_matching(self):
-        self.assertMatch('http://vimeo.com/channels/tributes', ['vimeo:channel'])
-        self.assertMatch('http://vimeo.com/channels/31259', ['vimeo:channel'])
-        self.assertMatch('http://vimeo.com/channels/31259/53576664', ['vimeo'])
-        self.assertMatch('http://vimeo.com/user7108434', ['vimeo:user'])
-        self.assertMatch('http://vimeo.com/user7108434/videos', ['vimeo:user'])
+        self.assertMatch('https://vimeo.com/channels/tributes', ['vimeo:channel'])
+        self.assertMatch('https://vimeo.com/channels/31259', ['vimeo:channel'])
+        self.assertMatch('https://vimeo.com/channels/31259/53576664', ['vimeo'])
+        self.assertMatch('https://vimeo.com/user7108434', ['vimeo:user'])
+        self.assertMatch('https://vimeo.com/user7108434/videos', ['vimeo:user'])
         self.assertMatch('https://vimeo.com/user21297594/review/75524534/3c257a1b5d', ['vimeo:review'])
 
     # https://github.com/rg3/youtube-dl/issues/1930

test/test_execution.py

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

test/test_http.py

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

test/test_postprocessors.py

@@ -0,0 +1,17 @@
+#!/usr/bin/env python
+
+from __future__ import unicode_literals
+
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from youtube_dl.postprocessor import MetadataFromTitlePP
+
+
+class TestMetadataFromTitle(unittest.TestCase):
+    def test_format_to_regex(self):
+        pp = MetadataFromTitlePP(None, '%(title)s - %(artist)s')
+        self.assertEqual(pp._titleregex, '(?P<title>.+)\ \-\ (?P<artist>.+)')

test/test_subtitles.py

@@ -26,6 +26,7 @@ from youtube_dl.extractor import (
     VikiIE,
     ThePlatformIE,
     RTVEALaCartaIE,
+    FunnyOrDieIE,
 )
 
 
@@ -320,5 +321,17 @@ class TestRtveSubtitles(BaseTestSubtitles):
         self.assertEqual(md5(subtitles['es']), '69e70cae2d40574fb7316f31d6eb7fca')
 
 
+class TestFunnyOrDieSubtitles(BaseTestSubtitles):
+    url = 'http://www.funnyordie.com/videos/224829ff6d/judd-apatow-will-direct-your-vine'
+    IE = FunnyOrDieIE
+
+    def test_allsubtitles(self):
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(set(subtitles.keys()), set(['en']))
+        self.assertEqual(md5(subtitles['en']), 'c5593c193eacd353596c11c2d4f9ecc4')
+
+
 if __name__ == '__main__':
     unittest.main()

test/test_unicode_literals.py

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

test/test_utils.py

@@ -24,6 +24,7 @@ from youtube_dl.utils import (
     encodeFilename,
     escape_rfc3986,
     escape_url,
+    ExtractorError,
     find_xpath_attr,
     fix_xml_ampersands,
     InAdvancePagedList,
@@ -38,6 +39,8 @@ from youtube_dl.utils import (
     parse_iso8601,
     read_batch_urls,
     sanitize_filename,
+    sanitize_path,
+    sanitize_url_path_consecutive_slashes,
     shell_quote,
     smuggle_url,
     str_to_int,
@@ -52,6 +55,7 @@ from youtube_dl.utils import (
     urlencode_postdata,
     version_tuple,
     xpath_with_ns,
+    xpath_text,
     render_table,
     match_str,
 )
@@ -131,6 +135,62 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
         self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
 
+    def test_sanitize_path(self):
+        if sys.platform != 'win32':
+            return
+
+        self.assertEqual(sanitize_path('abc'), 'abc')
+        self.assertEqual(sanitize_path('abc/def'), 'abc\\def')
+        self.assertEqual(sanitize_path('abc\\def'), 'abc\\def')
+        self.assertEqual(sanitize_path('abc|def'), 'abc#def')
+        self.assertEqual(sanitize_path('<>:"|?*'), '#######')
+        self.assertEqual(sanitize_path('C:/abc/def'), 'C:\\abc\\def')
+        self.assertEqual(sanitize_path('C?:/abc/def'), 'C##\\abc\\def')
+
+        self.assertEqual(sanitize_path('\\\\?\\UNC\\ComputerName\\abc'), '\\\\?\\UNC\\ComputerName\\abc')
+        self.assertEqual(sanitize_path('\\\\?\\UNC/ComputerName/abc'), '\\\\?\\UNC\\ComputerName\\abc')
+
+        self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
+        self.assertEqual(sanitize_path('\\\\?\\C:/abc'), '\\\\?\\C:\\abc')
+        self.assertEqual(sanitize_path('\\\\?\\C:\\ab?c\\de:f'), '\\\\?\\C:\\ab#c\\de#f')
+        self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
+
+        self.assertEqual(
+            sanitize_path('youtube/%(uploader)s/%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s'),
+            'youtube\\%(uploader)s\\%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s')
+
+        self.assertEqual(
+            sanitize_path('youtube/TheWreckingYard ./00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part'),
+            'youtube\\TheWreckingYard #\\00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part')
+        self.assertEqual(sanitize_path('abc/def...'), 'abc\\def..#')
+        self.assertEqual(sanitize_path('abc.../def'), 'abc..#\\def')
+        self.assertEqual(sanitize_path('abc.../def...'), 'abc..#\\def..#')
+
+        self.assertEqual(sanitize_path('../abc'), '..\\abc')
+        self.assertEqual(sanitize_path('../../abc'), '..\\..\\abc')
+        self.assertEqual(sanitize_path('./abc'), 'abc')
+        self.assertEqual(sanitize_path('./../abc'), '..\\abc')
+
+    def test_sanitize_url_path_consecutive_slashes(self):
+        self.assertEqual(
+            sanitize_url_path_consecutive_slashes('http://hostname/foo//bar/filename.html'),
+            'http://hostname/foo/bar/filename.html')
+        self.assertEqual(
+            sanitize_url_path_consecutive_slashes('http://hostname//foo/bar/filename.html'),
+            'http://hostname/foo/bar/filename.html')
+        self.assertEqual(
+            sanitize_url_path_consecutive_slashes('http://hostname//'),
+            'http://hostname/')
+        self.assertEqual(
+            sanitize_url_path_consecutive_slashes('http://hostname/foo/bar/filename.html'),
+            'http://hostname/foo/bar/filename.html')
+        self.assertEqual(
+            sanitize_url_path_consecutive_slashes('http://hostname/'),
+            'http://hostname/')
+        self.assertEqual(
+            sanitize_url_path_consecutive_slashes('http://hostname/abc//'),
+            'http://hostname/abc/')
+
     def test_ordered_set(self):
         self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
         self.assertEqual(orderedSet([]), [])
@@ -140,6 +200,8 @@ class TestUtil(unittest.TestCase):
 
     def test_unescape_html(self):
         self.assertEqual(unescapeHTML('%20;'), '%20;')
+        self.assertEqual(unescapeHTML('&#x2F;'), '/')
+        self.assertEqual(unescapeHTML('&#47;'), '/')
         self.assertEqual(
             unescapeHTML('&eacute;'), 'é')
 
@@ -165,6 +227,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(
             unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
             '20150202')
+        self.assertEqual(unified_strdate('25-09-2014'), '20140925')
 
     def test_find_xpath_attr(self):
         testxml = '''<root>
@@ -192,6 +255,17 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(find('media:song/media:author').text, 'The Author')
         self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
 
+    def test_xpath_text(self):
+        testxml = '''<root>
+            <div>
+                <p>Foo</p>
+            </div>
+        </root>'''
+        doc = xml.etree.ElementTree.fromstring(testxml)
+        self.assertEqual(xpath_text(doc, 'div/p'), 'Foo')
+        self.assertTrue(xpath_text(doc, 'div/bar') is None)
+        self.assertRaises(ExtractorError, xpath_text, doc, 'div/bar', fatal=True)
+
     def test_smuggle_url(self):
         data = {"ö": "ö", "abc": [3]}
         url = 'https://foo.bar/baz?x=y#a'
@@ -397,6 +471,12 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(d['x'], 1)
         self.assertEqual(d['y'], 'a')
 
+        on = js_to_json('["abc", "def",]')
+        self.assertEqual(json.loads(on), ['abc', 'def'])
+
+        on = js_to_json('{"abc": "def",}')
+        self.assertEqual(json.loads(on), {'abc': 'def'})
+
     def test_clean_html(self):
         self.assertEqual(clean_html('a:\nb'), 'a: b')
         self.assertEqual(clean_html('a:\n   "b"'), 'a:    "b"')

tox.ini

@@ -1,8 +1,11 @@
 [tox]
-envlist = py26,py27,py33
+envlist = py26,py27,py33,py34
 [testenv]
 deps =
    nose
    coverage
-commands = nosetests --verbose {posargs:test}  # --with-coverage --cover-package=youtube_dl --cover-html
+defaultargs = test --exclude test_download.py --exclude test_age_restriction.py
+    --exclude test_subtitles.py --exclude test_write_annotations.py
+    --exclude test_youtube_lists.py
+commands = nosetests --verbose {posargs:{[testenv]defaultargs}}  # --with-coverage --cover-package=youtube_dl --cover-html
                                                # test.test_download:TestDownload.test_NowVideo

youtube_dl/YoutubeDL.py

@@ -61,6 +61,7 @@ from .utils import (
     render_table,
     SameFileError,
     sanitize_filename,
+    sanitize_path,
     std_headers,
     subtitles_filename,
     takewhile_inclusive,
@@ -322,8 +323,10 @@ class YoutubeDL(object):
                 'Set the LC_ALL environment variable to fix this.')
             self.params['restrictfilenames'] = True
 
-        if '%(stitle)s' in self.params.get('outtmpl', ''):
-            self.report_warning('%(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.')
+        if isinstance(params.get('outtmpl'), bytes):
+            self.report_warning(
+                'Parameter outtmpl is bytes, but should be a unicode string. '
+                'Put  from __future__ import unicode_literals  at the top of your code file or consider switching to Python 3.x.')
 
         self._setup_opener()
 
@@ -562,7 +565,7 @@ class YoutubeDL(object):
                                  if v is not None)
             template_dict = collections.defaultdict(lambda: 'NA', template_dict)
 
-            outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
+            outtmpl = sanitize_path(self.params.get('outtmpl', DEFAULT_OUTTMPL))
             tmpl = compat_expanduser(outtmpl)
             filename = tmpl % template_dict
             # Temporary fix for #4787
@@ -629,7 +632,7 @@ class YoutubeDL(object):
         Returns a list with a dictionary for each video we find.
         If 'download', also downloads the videos.
         extra_info is a dict containing the extra values to add to each result
-         '''
+        '''
 
         if ie_key:
             ies = [self.get_info_extractor(ie_key)]
@@ -916,6 +919,11 @@ class YoutubeDL(object):
         if format_spec == 'best' or format_spec is None:
             return available_formats[-1]
         elif format_spec == 'worst':
+            audiovideo_formats = [
+                f for f in available_formats
+                if f.get('vcodec') != 'none' and f.get('acodec') != 'none']
+            if audiovideo_formats:
+                return audiovideo_formats[0]
             return available_formats[0]
         elif format_spec == 'bestaudio':
             audio_formats = [
@@ -1085,8 +1093,7 @@ class YoutubeDL(object):
         if req_format is None:
             req_format = 'best'
         formats_to_download = []
-        # The -1 is for supporting YoutubeIE
-        if req_format in ('-1', 'all'):
+        if req_format == 'all':
             formats_to_download = formats
         else:
             for rfstr in req_format.split(','):
@@ -1213,9 +1220,6 @@ class YoutubeDL(object):
         if len(info_dict['title']) > 200:
             info_dict['title'] = info_dict['title'][:197] + '...'
 
-        # Keep for backwards compatibility
-        info_dict['stitle'] = info_dict['title']
-
         if 'format' not in info_dict:
             info_dict['format'] = info_dict['ext']
 
@@ -1261,7 +1265,7 @@ class YoutubeDL(object):
             return
 
         try:
-            dn = os.path.dirname(encodeFilename(filename))
+            dn = os.path.dirname(sanitize_path(encodeFilename(filename)))
             if dn and not os.path.exists(dn):
                 os.makedirs(dn)
         except (OSError, IOError) as err:
@@ -1702,10 +1706,10 @@ class YoutubeDL(object):
             out = out.decode().strip()
             if re.match('[0-9a-f]+', out):
                 self._write_string('[debug] Git HEAD: ' + out + '\n')
-        except:
+        except Exception:
             try:
                 sys.exc_clear()
-            except:
+            except Exception:
                 pass
         self._write_string('[debug] Python version %s - %s\n' % (
             platform.python_version(), platform_name()))

youtube_dl/__init__.py

@@ -189,10 +189,6 @@ def _real_main(argv=None):
     if opts.allsubtitles and not opts.writeautomaticsub:
         opts.writesubtitles = True
 
-    if sys.version_info < (3,):
-        # In Python 2, sys.argv is a bytestring (also note http://bugs.python.org/issue2128 for Windows systems)
-        if opts.outtmpl is not None:
-            opts.outtmpl = opts.outtmpl.decode(preferredencoding())
     outtmpl = ((opts.outtmpl is not None and opts.outtmpl) or
                (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s') or
                (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s') or
@@ -213,6 +209,11 @@ def _real_main(argv=None):
     # PostProcessors
     postprocessors = []
     # Add the metadata pp first, the other pps will copy it
+    if opts.metafromtitle:
+        postprocessors.append({
+            'key': 'MetadataFromTitle',
+            'titleformat': opts.metafromtitle
+        })
     if opts.addmetadata:
         postprocessors.append({'key': 'FFmpegMetadata'})
     if opts.extractaudio:

youtube_dl/compat.py

@@ -389,7 +389,7 @@ else:
                 stdout=subprocess.PIPE, stderr=subprocess.PIPE)
             out, err = sp.communicate()
             lines, columns = map(int, out.split())
-        except:
+        except Exception:
             pass
         return _terminal_size(columns, lines)
 

youtube_dl/downloader/common.py

@@ -204,7 +204,7 @@ class FileDownloader(object):
             return
         try:
             os.utime(filename, (time.time(), filetime))
-        except:
+        except Exception:
             pass
         return filetime
 
@@ -318,7 +318,7 @@ class FileDownloader(object):
         )
 
         continuedl_and_exists = (
-            self.params.get('continuedl', False) and
+            self.params.get('continuedl', True) and
             os.path.isfile(encodeFilename(filename)) and
             not self.params.get('nopart', False)
         )

youtube_dl/downloader/f4m.py

@@ -281,7 +281,7 @@ class F4mFD(FileDownloader):
             boot_info = self._get_bootstrap_from_url(bootstrap_url)
         else:
             bootstrap_url = None
-            bootstrap = base64.b64decode(node.text)
+            bootstrap = base64.b64decode(node.text.encode('ascii'))
             boot_info = read_bootstrap_info(bootstrap)
         return (boot_info, bootstrap_url)
 
@@ -308,7 +308,7 @@ class F4mFD(FileDownloader):
         live = boot_info['live']
         metadata_node = media.find(_add_ns('metadata'))
         if metadata_node is not None:
-            metadata = base64.b64decode(metadata_node.text)
+            metadata = base64.b64decode(metadata_node.text.encode('ascii'))
         else:
             metadata = None
 

youtube_dl/downloader/http.py

@@ -49,7 +49,7 @@ class HttpFD(FileDownloader):
 
         open_mode = 'wb'
         if resume_len != 0:
-            if self.params.get('continuedl', False):
+            if self.params.get('continuedl', True):
                 self.report_resuming_byte(resume_len)
                 request.add_header('Range', 'bytes=%d-' % resume_len)
                 open_mode = 'ab'
@@ -92,6 +92,8 @@ class HttpFD(FileDownloader):
                             self._hook_progress({
                                 'filename': filename,
                                 'status': 'finished',
+                                'downloaded_bytes': resume_len,
+                                'total_bytes': resume_len,
                             })
                             return True
                         else:
@@ -218,12 +220,6 @@ class HttpFD(FileDownloader):
         if tmpfilename != '-':
             stream.close()
 
-        self._hook_progress({
-            'downloaded_bytes': byte_counter,
-            'total_bytes': data_len,
-            'tmpfilename': tmpfilename,
-            'status': 'error',
-        })
         if data_len is not None and byte_counter != data_len:
             raise ContentTooShortError(byte_counter, int(data_len))
         self.try_rename(tmpfilename, filename)

youtube_dl/downloader/rtmp.py

@@ -105,7 +105,7 @@ class RtmpFD(FileDownloader):
         protocol = info_dict.get('rtmp_protocol', None)
         real_time = info_dict.get('rtmp_real_time', False)
         no_resume = info_dict.get('no_resume', False)
-        continue_dl = info_dict.get('continuedl', False)
+        continue_dl = info_dict.get('continuedl', True)
 
         self.report_destination(filename)
         tmpfilename = self.temp_name(filename)

youtube_dl/extractor/__init__.py

@@ -37,6 +37,7 @@ from .bandcamp import BandcampIE, BandcampAlbumIE
 from .bbccouk import BBCCoUkIE
 from .beeg import BeegIE
 from .behindkink import BehindKinkIE
+from .beatportpro import BeatportProIE
 from .bet import BetIE
 from .bild import BildIE
 from .bilibili import BiliBiliIE
@@ -89,6 +90,7 @@ from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
 from .condenast import CondeNastIE
 from .cracked import CrackedIE
 from .criterion import CriterionIE
+from .crooksandliars import CrooksAndLiarsIE
 from .crunchyroll import (
     CrunchyrollIE,
     CrunchyrollShowPlaylistIE
@@ -105,17 +107,21 @@ from .dbtv import DBTVIE
 from .dctp import DctpTvIE
 from .deezer import DeezerPlaylistIE
 from .dfb import DFBIE
+from .dhm import DHMIE
 from .dotsub import DotsubIE
+from .douyutv import DouyuTVIE
 from .dreisat import DreiSatIE
 from .drbonanza import DRBonanzaIE
 from .drtuber import DrTuberIE
 from .drtv import DRTVIE
 from .dvtv import DVTVIE
 from .dump import DumpIE
+from .dumpert import DumpertIE
 from .defense import DefenseGouvFrIE
 from .discovery import DiscoveryIE
 from .divxstage import DivxStageIE
 from .dropbox import DropboxIE
+from .eagleplatform import EaglePlatformIE
 from .ebaumsworld import EbaumsWorldIE
 from .echomsk import EchoMskIE
 from .ehow import EHowIE
@@ -150,6 +156,7 @@ from .fktv import (
 )
 from .flickr import FlickrIE
 from .folketinget import FolketingetIE
+from .footyroom import FootyRoomIE
 from .fourtube import FourTubeIE
 from .foxgay import FoxgayIE
 from .foxnews import FoxNewsIE
@@ -171,9 +178,11 @@ from .gameone import (
     GameOneIE,
     GameOnePlaylistIE,
 )
+from .gamersyde import GamersydeIE
 from .gamespot import GameSpotIE
 from .gamestar import GameStarIE
 from .gametrailers import GametrailersIE
+from .gazeta import GazetaIE
 from .gdcvault import GDCVaultIE
 from .generic import GenericIE
 from .giantbomb import GiantBombIE
@@ -228,6 +237,7 @@ from .jove import JoveIE
 from .jukebox import JukeboxIE
 from .jpopsukitv import JpopsukiIE
 from .kaltura import KalturaIE
+from .kanalplay import KanalPlayIE
 from .kankan import KankanIE
 from .karaoketv import KaraoketvIE
 from .keezmovies import KeezMoviesIE
@@ -244,6 +254,7 @@ from .letv import (
     LetvTvIE,
     LetvPlaylistIE
 )
+from .libsyn import LibsynIE
 from .lifenews import LifeNewsIE
 from .liveleak import LiveLeakIE
 from .livestream import (
@@ -267,6 +278,7 @@ from .metacritic import MetacriticIE
 from .mgoon import MgoonIE
 from .minhateca import MinhatecaIE
 from .ministrygrid import MinistryGridIE
+from .miomio import MioMioIE
 from .mit import TechTVMITIE, MITIE, OCWMITIE
 from .mitele import MiTeleIE
 from .mixcloud import MixcloudIE
@@ -302,6 +314,8 @@ from .nba import NBAIE
 from .nbc import (
     NBCIE,
     NBCNewsIE,
+    NBCSportsIE,
+    NBCSportsVPlayerIE,
 )
 from .ndr import NDRIE
 from .ndtv import NDTVIE
@@ -340,6 +354,7 @@ from .npo import (
 )
 from .nrk import (
     NRKIE,
+    NRKPlaylistIE,
     NRKTVIE,
 )
 from .ntvde import NTVDeIE
@@ -354,6 +369,7 @@ from .orf import (
     ORFTVthekIE,
     ORFOE1IE,
     ORFFM4IE,
+    ORFIPTVIE,
 )
 from .parliamentliveuk import ParliamentLiveUKIE
 from .patreon import PatreonIE
@@ -361,9 +377,11 @@ from .pbs import PBSIE
 from .phoenix import PhoenixIE
 from .photobucket import PhotobucketIE
 from .planetaplay import PlanetaPlayIE
+from .pladform import PladformIE
 from .played import PlayedIE
 from .playfm import PlayFMIE
 from .playvid import PlayvidIE
+from .playwire import PlaywireIE
 from .podomatic import PodomaticIE
 from .pornhd import PornHdIE
 from .pornhub import (
@@ -371,14 +389,22 @@ from .pornhub import (
     PornHubPlaylistIE,
 )
 from .pornotube import PornotubeIE
+from .pornovoisines import PornoVoisinesIE
 from .pornoxo import PornoXOIE
+from .primesharetv import PrimeShareTVIE
 from .promptfile import PromptFileIE
 from .prosiebensat1 import ProSiebenSat1IE
 from .puls4 import Puls4IE
 from .pyvideo import PyvideoIE
+from .qqmusic import (
+    QQMusicIE,
+    QQMusicSingerIE,
+    QQMusicAlbumIE,
+)
 from .quickvid import QuickVidIE
 from .r7 import R7IE
 from .radiode import RadioDeIE
+from .radiojavan import RadioJavanIE
 from .radiobremen import RadioBremenIE
 from .radiofrance import RadioFranceIE
 from .rai import RaiIE
@@ -397,7 +423,7 @@ from .rtlnow import RTLnowIE
 from .rtl2 import RTL2IE
 from .rtp import RTPIE
 from .rts import RTSIE
-from .rtve import RTVEALaCartaIE, RTVELiveIE
+from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE
 from .ruhd import RUHDIE
 from .rutube import (
     RutubeIE,
@@ -408,6 +434,10 @@ from .rutube import (
 )
 from .rutv import RUTVIE
 from .sandia import SandiaIE
+from .safari import (
+    SafariIE,
+    SafariCourseIE,
+)
 from .sapo import SapoIE
 from .savefrom import SaveFromIE
 from .sbs import SBSIE
@@ -447,6 +477,7 @@ from .southpark import (
     SouthparkDeIE,
 )
 from .space import SpaceIE
+from .spankbang import SpankBangIE
 from .spankwire import SpankwireIE
 from .spiegel import SpiegelIE, SpiegelArticleIE
 from .spiegeltv import SpiegeltvIE
@@ -454,7 +485,9 @@ from .spike import SpikeIE
 from .sport5 import Sport5IE
 from .sportbox import SportBoxIE
 from .sportdeutschland import SportDeutschlandIE
+from .srf import SrfIE
 from .srmediathek import SRMediathekIE
+from .ssa import SSAIE
 from .stanfordoc import StanfordOpenClassroomIE
 from .steam import SteamIE
 from .streamcloud import StreamcloudIE
@@ -513,6 +546,10 @@ from .tvp import TvpIE, TvpSeriesIE
 from .tvplay import TVPlayIE
 from .tweakers import TweakersIE
 from .twentyfourvideo import TwentyFourVideoIE
+from .twentytwotracks import (
+    TwentyTwoTracksIE,
+    TwentyTwoTracksGenreIE
+)
 from .twitch import (
     TwitchVideoIE,
     TwitchChapterIE,
@@ -527,12 +564,16 @@ from .udemy import (
     UdemyIE,
     UdemyCourseIE
 )
+from .udn import UDNEmbedIE
+from .ultimedia import UltimediaIE
 from .unistra import UnistraIE
 from .urort import UrortIE
 from .ustream import UstreamIE, UstreamChannelIE
+from .varzesh3 import Varzesh3IE
 from .vbox7 import Vbox7IE
 from .veehd import VeeHDIE
 from .veoh import VeohIE
+from .vessel import VesselIE
 from .vesti import VestiIE
 from .vevo import VevoIE
 from .vgtv import VGTVIE
@@ -550,6 +591,7 @@ from .videoweed import VideoWeedIE
 from .vidme import VidmeIE
 from .vidzi import VidziIE
 from .vier import VierIE, VierVideosIE
+from .viewster import ViewsterIE
 from .vimeo import (
     VimeoIE,
     VimeoAlbumIE,
@@ -606,6 +648,11 @@ from .yahoo import (
     YahooSearchIE,
 )
 from .yam import YamIE
+from .yandexmusic import (
+    YandexMusicTrackIE,
+    YandexMusicAlbumIE,
+    YandexMusicPlaylistIE,
+)
 from .yesjapan import YesJapanIE
 from .ynet import YnetIE
 from .youjizz import YouJizzIE

youtube_dl/extractor/addanime.py

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

youtube_dl/extractor/adultswim.py

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

youtube_dl/extractor/aftenposten.py

@@ -14,10 +14,10 @@ from ..utils import (
 
 
 class AftenpostenIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?aftenposten\.no/webtv/([^/]+/)*(?P<id>[^/]+)-\d+\.html'
+    _VALID_URL = r'https?://(?:www\.)?aftenposten\.no/webtv/(?:#!/)?video/(?P<id>\d+)'
 
     _TEST = {
-        'url': 'http://www.aftenposten.no/webtv/serier-og-programmer/sweatshopenglish/TRAILER-SWEATSHOP---I-cant-take-any-more-7800835.html?paging=&section=webtv_serierogprogrammer_sweatshop_sweatshopenglish',
+        'url': 'http://www.aftenposten.no/webtv/#!/video/21039/trailer-sweatshop-i-can-t-take-any-more',
         'md5': 'fd828cd29774a729bf4d4425fe192972',
         'info_dict': {
             'id': '21039',
@@ -30,12 +30,7 @@ class AftenpostenIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        display_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, display_id)
-
-        video_id = self._html_search_regex(
-            r'data-xs-id="(\d+)"', webpage, 'video id')
+        video_id = self._match_id(url)
 
         data = self._download_xml(
             'http://frontend.xstream.dk/ap/feed/video/?platform=web&id=%s' % video_id, video_id)

youtube_dl/extractor/aftonbladet.py

@@ -2,10 +2,11 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..utils import int_or_none
 
 
 class AftonbladetIE(InfoExtractor):
-    _VALID_URL = r'^http://tv\.aftonbladet\.se/webbtv.+?(?P<video_id>article[0-9]+)\.ab(?:$|[?#])'
+    _VALID_URL = r'http://tv\.aftonbladet\.se/webbtv.+?(?P<id>article[0-9]+)\.ab(?:$|[?#])'
     _TEST = {
         'url': 'http://tv.aftonbladet.se/webbtv/nyheter/vetenskap/rymden/article36015.ab',
         'info_dict': {
@@ -43,9 +44,9 @@ class AftonbladetIE(InfoExtractor):
             formats.append({
                 'url': 'http://%s:%d/%s/%s' % (p['address'], p['port'], p['path'], p['filename']),
                 'ext': 'mp4',
-                'width': fmt['width'],
-                'height': fmt['height'],
-                'tbr': fmt['bitrate'],
+                'width': int_or_none(fmt.get('width')),
+                'height': int_or_none(fmt.get('height')),
+                'tbr': int_or_none(fmt.get('bitrate')),
                 'protocol': 'http',
             })
         self._sort_formats(formats)
@@ -54,9 +55,9 @@ class AftonbladetIE(InfoExtractor):
             'id': video_id,
             'title': internal_meta_json['title'],
             'formats': formats,
-            'thumbnail': internal_meta_json['imageUrl'],
-            'description': internal_meta_json['shortPreamble'],
-            'timestamp': internal_meta_json['timePublished'],
-            'duration': internal_meta_json['duration'],
-            'view_count': internal_meta_json['views'],
+            'thumbnail': internal_meta_json.get('imageUrl'),
+            'description': internal_meta_json.get('shortPreamble'),
+            'timestamp': int_or_none(internal_meta_json.get('timePublished')),
+            'duration': int_or_none(internal_meta_json.get('duration')),
+            'view_count': int_or_none(internal_meta_json.get('views')),
         }

youtube_dl/extractor/ard.py

@@ -50,6 +50,9 @@ class ARDMediathekIE(InfoExtractor):
         if '>Der gewünschte Beitrag ist nicht mehr verfügbar.<' in webpage:
             raise ExtractorError('Video %s is no longer available' % video_id, expected=True)
 
+        if 'Diese Sendung ist für Jugendliche unter 12 Jahren nicht geeignet. Der Clip ist deshalb nur von 20 bis 6 Uhr verfügbar.' in webpage:
+            raise ExtractorError('This program is only suitable for those aged 12 and older. Video %s is therefore only available between 20 pm and 6 am.' % video_id, expected=True)
+
         if re.search(r'[\?&]rss($|[=&])', url):
             doc = parse_xml(webpage)
             if doc.tag == 'rss':

youtube_dl/extractor/arte.py

@@ -146,6 +146,7 @@ class ArteTVPlus7IE(InfoExtractor):
 
             formats.append(format)
 
+        self._check_formats(formats, video_id)
         self._sort_formats(formats)
 
         info_dict['formats'] = formats

youtube_dl/extractor/beatportpro.py

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

youtube_dl/extractor/bliptv.py

@@ -172,6 +172,7 @@ class BlipTVIE(InfoExtractor):
                     'width': int_or_none(media_content.get('width')),
                     'height': int_or_none(media_content.get('height')),
                 })
+        self._check_formats(formats, video_id)
         self._sort_formats(formats)
 
         subtitles = self.extract_subtitles(video_id, subtitles_urls)

youtube_dl/extractor/bloomberg.py

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

youtube_dl/extractor/breakcom.py

@@ -41,7 +41,7 @@ class BreakIE(InfoExtractor):
             'tbr': media['bitRate'],
             'width': media['width'],
             'height': media['height'],
-        } for media in info['media']]
+        } for media in info['media'] if media.get('mediaPurpose') == 'play']
 
         if not formats:
             formats.append({

youtube_dl/extractor/brightcove.py

@@ -117,7 +117,10 @@ class BrightcoveIE(InfoExtractor):
         object_str = re.sub(r'(<object[^>]*)(xmlns=".*?")', r'\1', object_str)
         object_str = fix_xml_ampersands(object_str)
 
-        object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8'))
+        try:
+            object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8'))
+        except xml.etree.ElementTree.ParseError:
+            return
 
         fv_el = find_xpath_attr(object_doc, './param', 'name', 'flashVars')
         if fv_el is not None:
@@ -183,9 +186,9 @@ class BrightcoveIE(InfoExtractor):
             (?:
                 [^>]+?class=[\'"][^>]*?BrightcoveExperience.*?[\'"] |
                 [^>]*?>\s*<param\s+name="movie"\s+value="https?://[^/]*brightcove\.com/
-            ).+?</object>''',
+            ).+?>\s*</object>''',
             webpage)
-        return [cls._build_brighcove_url(m) for m in matches]
+        return list(filter(None, [cls._build_brighcove_url(m) for m in matches]))
 
     def _real_extract(self, url):
         url, smuggled_data = unsmuggle_url(url, {})

youtube_dl/extractor/cloudy.py

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

youtube_dl/extractor/cnn.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 class CNNIE(InfoExtractor):
     _VALID_URL = r'''(?x)https?://(?:(?:edition|www)\.)?cnn\.com/video/(?:data/.+?|\?)/
-        (?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:cnn|hln)(?:-ap)?|(?=&)))'''
+        (?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:[a-z]{3,5})(?:-ap)?|(?=&)))'''
 
     _TESTS = [{
         'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',
@@ -45,6 +45,12 @@ class CNNIE(InfoExtractor):
             'description': 'md5:e7223a503315c9f150acac52e76de086',
             'upload_date': '20141222',
         }
+    }, {
+        'url': 'http://cnn.com/video/?/video/politics/2015/03/27/pkg-arizona-senator-church-attendance-mandatory.ktvk',
+        'only_matching': True,
+    }, {
+        'url': 'http://cnn.com/video/?/video/us/2015/04/06/dnt-baker-refuses-anti-gay-order.wkmg',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/common.py

@@ -324,7 +324,7 @@ class InfoExtractor(object):
                 self._downloader.report_warning(errmsg)
                 return False
 
-    def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
+    def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None):
         """ Returns a tuple (page content as string, URL handle) """
         # Strip hashes from the URL (#1038)
         if isinstance(url_or_request, (compat_str, str)):
@@ -334,14 +334,11 @@ class InfoExtractor(object):
         if urlh is False:
             assert not fatal
             return False
-        content = self._webpage_read_content(urlh, url_or_request, video_id, note, errnote, fatal)
+        content = self._webpage_read_content(urlh, url_or_request, video_id, note, errnote, fatal, encoding=encoding)
         return (content, urlh)
 
-    def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None):
-        content_type = urlh.headers.get('Content-Type', '')
-        webpage_bytes = urlh.read()
-        if prefix is not None:
-            webpage_bytes = prefix + webpage_bytes
+    @staticmethod
+    def _guess_encoding_from_content(content_type, webpage_bytes):
         m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
         if m:
             encoding = m.group(1)
@@ -354,6 +351,16 @@ class InfoExtractor(object):
                 encoding = 'utf-16'
             else:
                 encoding = 'utf-8'
+
+        return encoding
+
+    def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None, encoding=None):
+        content_type = urlh.headers.get('Content-Type', '')
+        webpage_bytes = urlh.read()
+        if prefix is not None:
+            webpage_bytes = prefix + webpage_bytes
+        if not encoding:
+            encoding = self._guess_encoding_from_content(content_type, webpage_bytes)
         if self._downloader.params.get('dump_intermediate_pages', False):
             try:
                 url = url_or_request.get_full_url()
@@ -410,13 +417,13 @@ class InfoExtractor(object):
 
         return content
 
-    def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5):
+    def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None):
         """ Returns the data of the page as a string """
         success = False
         try_count = 0
         while success is False:
             try:
-                res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal)
+                res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal, encoding=encoding)
                 success = True
             except compat_http_client.IncompleteRead as e:
                 try_count += 1
@@ -431,10 +438,10 @@ class InfoExtractor(object):
 
     def _download_xml(self, url_or_request, video_id,
                       note='Downloading XML', errnote='Unable to download XML',
-                      transform_source=None, fatal=True):
+                      transform_source=None, fatal=True, encoding=None):
         """Return the xml as an xml.etree.ElementTree.Element"""
         xml_string = self._download_webpage(
-            url_or_request, video_id, note, errnote, fatal=fatal)
+            url_or_request, video_id, note, errnote, fatal=fatal, encoding=encoding)
         if xml_string is False:
             return xml_string
         if transform_source:
@@ -445,9 +452,10 @@ class InfoExtractor(object):
                        note='Downloading JSON metadata',
                        errnote='Unable to download JSON metadata',
                        transform_source=None,
-                       fatal=True):
+                       fatal=True, encoding=None):
         json_string = self._download_webpage(
-            url_or_request, video_id, note, errnote, fatal=fatal)
+            url_or_request, video_id, note, errnote, fatal=fatal,
+            encoding=encoding)
         if (not fatal) and json_string is False:
             return None
         return self._parse_json(
@@ -492,7 +500,7 @@ class InfoExtractor(object):
 
     # Methods for following #608
     @staticmethod
-    def url_result(url, ie=None, video_id=None):
+    def url_result(url, ie=None, video_id=None, video_title=None):
         """Returns a url that points to a page that should be processed"""
         # TODO: ie should be the class used for getting the info
         video_info = {'_type': 'url',
@@ -500,6 +508,8 @@ class InfoExtractor(object):
                       'ie_key': ie}
         if video_id is not None:
             video_info['id'] = video_id
+        if video_title is not None:
+            video_info['title'] = video_title
         return video_info
 
     @staticmethod
@@ -822,7 +832,7 @@ class InfoExtractor(object):
                                 (media_el.attrib.get('href') or media_el.attrib.get('url')))
             tbr = int_or_none(media_el.attrib.get('bitrate'))
             formats.append({
-                'format_id': '-'.join(filter(None, [f4m_id, 'f4m-%d' % (i if tbr is None else tbr)])),
+                'format_id': '-'.join(filter(None, [f4m_id, compat_str(i if tbr is None else tbr)])),
                 'url': manifest_url,
                 'ext': 'flv',
                 'tbr': tbr,
@@ -839,7 +849,7 @@ class InfoExtractor(object):
                               m3u8_id=None):
 
         formats = [{
-            'format_id': '-'.join(filter(None, [m3u8_id, 'm3u8-meta'])),
+            'format_id': '-'.join(filter(None, [m3u8_id, 'meta'])),
             'url': m3u8_url,
             'ext': ext,
             'protocol': 'm3u8',
@@ -883,8 +893,13 @@ class InfoExtractor(object):
                     formats.append({'url': format_url(line)})
                     continue
                 tbr = int_or_none(last_info.get('BANDWIDTH'), scale=1000)
+                format_id = []
+                if m3u8_id:
+                    format_id.append(m3u8_id)
+                last_media_name = last_media.get('NAME') if last_media else None
+                format_id.append(last_media_name if last_media_name else '%d' % (tbr if tbr else len(formats)))
                 f = {
-                    'format_id': '-'.join(filter(None, [m3u8_id, 'm3u8-%d' % (tbr if tbr else len(formats))])),
+                    'format_id': '-'.join(format_id),
                     'url': format_url(line.strip()),
                     'tbr': tbr,
                     'ext': ext,
@@ -1057,6 +1072,9 @@ class InfoExtractor(object):
     def _get_automatic_captions(self, *args, **kwargs):
         raise NotImplementedError("This method must be implemented by subclasses")
 
+    def _subtitles_timecode(self, seconds):
+        return '%02d:%02d:%02d.%03d' % (seconds / 3600, (seconds % 3600) / 60, seconds % 60, (seconds % 1) * 1000)
+
 
 class SearchInfoExtractor(InfoExtractor):
     """

youtube_dl/extractor/crooksandliars.py

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

youtube_dl/extractor/crunchyroll.py

@@ -23,7 +23,6 @@ from ..utils import (
 )
 from ..aes import (
     aes_cbc_decrypt,
-    inc,
 )
 
 
@@ -102,13 +101,6 @@ class CrunchyrollIE(InfoExtractor):
 
         key = obfuscate_key(id)
 
-        class Counter:
-            __value = iv
-
-            def next_value(self):
-                temp = self.__value
-                self.__value = inc(self.__value)
-                return temp
         decrypted_data = intlist_to_bytes(aes_cbc_decrypt(data, key, iv))
         return zlib.decompress(decrypted_data)
 

youtube_dl/extractor/dailymotion.py

@@ -25,8 +25,7 @@ class DailymotionBaseInfoExtractor(InfoExtractor):
     def _build_request(url):
         """Build a request with the family filter disabled"""
         request = compat_urllib_request.Request(url)
-        request.add_header('Cookie', 'family_filter=off')
-        request.add_header('Cookie', 'ff=off')
+        request.add_header('Cookie', 'family_filter=off; ff=off')
         return request
 
 
@@ -46,13 +45,13 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
 
     _TESTS = [
         {
-            'url': 'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech',
-            'md5': '392c4b85a60a90dc4792da41ce3144eb',
+            'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames',
+            'md5': '2137c41a8e78554bb09225b8eb322406',
             'info_dict': {
-                'id': 'x33vw9',
+                'id': 'x2iuewm',
                 'ext': 'mp4',
-                'uploader': 'Amphora Alex and Van .',
-                'title': 'Tutoriel de Youtubeur"DL DES VIDEO DE YOUTUBE"',
+                'uploader': 'IGN',
+                'title': 'Steam Machine Models, Pricing Listed on Steam Store - IGN News',
             }
         },
         # Vevo video
@@ -112,8 +111,9 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
             video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
 
         embed_url = 'http://www.dailymotion.com/embed/video/%s' % video_id
-        embed_page = self._download_webpage(embed_url, video_id,
-                                            'Downloading embed page')
+        embed_request = self._build_request(embed_url)
+        embed_page = self._download_webpage(
+            embed_request, video_id, 'Downloading embed page')
         info = self._search_regex(r'var info = ({.*?}),$', embed_page,
                                   'video info', flags=re.MULTILINE)
         info = json.loads(info)
@@ -224,7 +224,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
 
 class DailymotionUserIE(DailymotionPlaylistIE):
     IE_NAME = 'dailymotion:user'
-    _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?:old/)?user/(?P<user>[^/]+)'
     _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
     _TESTS = [{
         'url': 'https://www.dailymotion.com/user/nqtv',

youtube_dl/extractor/dhm.py

@@ -0,0 +1,73 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    xpath_text,
+    parse_duration,
+)
+
+
+class DHMIE(InfoExtractor):
+    IE_DESC = 'Filmarchiv - Deutsches Historisches Museum'
+    _VALID_URL = r'https?://(?:www\.)?dhm\.de/filmarchiv/(?:[^/]+/)+(?P<id>[^/]+)'
+
+    _TESTS = [{
+        'url': 'http://www.dhm.de/filmarchiv/die-filme/the-marshallplan-at-work-in-west-germany/',
+        'md5': '11c475f670209bf6acca0b2b7ef51827',
+        'info_dict': {
+            'id': 'the-marshallplan-at-work-in-west-germany',
+            'ext': 'flv',
+            'title': 'MARSHALL PLAN AT WORK IN WESTERN GERMANY, THE',
+            'description': 'md5:1fabd480c153f97b07add61c44407c82',
+            'duration': 660,
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+    }, {
+        'url': 'http://www.dhm.de/filmarchiv/02-mapping-the-wall/peter-g/rolle-1/',
+        'md5': '09890226332476a3e3f6f2cb74734aa5',
+        'info_dict': {
+            'id': 'rolle-1',
+            'ext': 'flv',
+            'title': 'ROLLE 1',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        playlist_url = self._search_regex(
+            r"file\s*:\s*'([^']+)'", webpage, 'playlist url')
+
+        playlist = self._download_xml(playlist_url, video_id)
+
+        track = playlist.find(
+            './{http://xspf.org/ns/0/}trackList/{http://xspf.org/ns/0/}track')
+
+        video_url = xpath_text(
+            track, './{http://xspf.org/ns/0/}location',
+            'video url', fatal=True)
+        thumbnail = xpath_text(
+            track, './{http://xspf.org/ns/0/}image',
+            'thumbnail')
+
+        title = self._search_regex(
+            [r'dc:title="([^"]+)"', r'<title> &raquo;([^<]+)</title>'],
+            webpage, 'title').strip()
+        description = self._html_search_regex(
+            r'<p><strong>Description:</strong>(.+?)</p>',
+            webpage, 'description', default=None)
+        duration = parse_duration(self._search_regex(
+            r'<em>Length\s*</em>\s*:\s*</strong>([^<]+)',
+            webpage, 'duration', default=None))
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/douyutv.py

@@ -0,0 +1,112 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import hashlib
+import time
+from .common import InfoExtractor
+from ..utils import (ExtractorError, unescapeHTML)
+from ..compat import (compat_str, compat_basestring)
+
+
+class DouyuTVIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?douyutv\.com/(?P<id>[A-Za-z0-9]+)'
+    _TESTS = [{
+        'url': 'http://www.douyutv.com/iseven',
+        'info_dict': {
+            'id': '17732',
+            'display_id': 'iseven',
+            'ext': 'flv',
+            'title': 're:^清晨醒脑！T-ara根本停不下来！ [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'description': 'md5:c93d6692dde6fe33809a46edcbecca44',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': '7师傅',
+            'uploader_id': '431925',
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        'url': 'http://www.douyutv.com/85982',
+        'info_dict': {
+            'id': '85982',
+            'display_id': '85982',
+            'ext': 'flv',
+            'title': 're:^小漠从零单排记！——CSOL2躲猫猫 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'description': 'md5:746a2f7a253966a06755a912f0acc0d2',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': 'douyu小漠',
+            'uploader_id': '3769985',
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        if video_id.isdigit():
+            room_id = video_id
+        else:
+            page = self._download_webpage(url, video_id)
+            room_id = self._html_search_regex(
+                r'"room_id"\s*:\s*(\d+),', page, 'room id')
+
+        prefix = 'room/%s?aid=android&client_sys=android&time=%d' % (
+            room_id, int(time.time()))
+
+        auth = hashlib.md5((prefix + '1231').encode('ascii')).hexdigest()
+        config = self._download_json(
+            'http://www.douyutv.com/api/v1/%s&auth=%s' % (prefix, auth),
+            video_id)
+
+        data = config['data']
+
+        error_code = config.get('error', 0)
+        if error_code is not 0:
+            error_desc = 'Server reported error %i' % error_code
+            if isinstance(data, (compat_str, compat_basestring)):
+                error_desc += ': ' + data
+            raise ExtractorError(error_desc, expected=True)
+
+        show_status = data.get('show_status')
+        # 1 = live, 2 = offline
+        if show_status == '2':
+            raise ExtractorError(
+                'Live stream is offline', expected=True)
+
+        base_url = data['rtmp_url']
+        live_path = data['rtmp_live']
+
+        title = self._live_title(unescapeHTML(data['room_name']))
+        description = data.get('show_details')
+        thumbnail = data.get('room_src')
+
+        uploader = data.get('nickname')
+        uploader_id = data.get('owner_uid')
+
+        multi_formats = data.get('rtmp_multi_bitrate')
+        if not isinstance(multi_formats, dict):
+            multi_formats = {}
+        multi_formats['live'] = live_path
+
+        formats = [{
+            'url': '%s/%s' % (base_url, format_path),
+            'format_id': format_id,
+            'preference': 1 if format_id == 'live' else 0,
+        } for format_id, format_path in multi_formats.items()]
+        self._sort_formats(formats)
+
+        return {
+            'id': room_id,
+            'display_id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'formats': formats,
+            'is_live': True,
+        }

youtube_dl/extractor/dreisat.py

@@ -3,22 +3,25 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import unified_strdate
+from ..utils import (
+    ExtractorError,
+    unified_strdate,
+)
 
 
 class DreiSatIE(InfoExtractor):
     IE_NAME = '3sat'
     _VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/(?:index\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
     _TEST = {
-        'url': 'http://www.3sat.de/mediathek/index.php?obj=36983',
-        'md5': '9dcfe344732808dbfcc901537973c922',
+        'url': 'http://www.3sat.de/mediathek/index.php?mode=play&obj=45918',
+        'md5': 'be37228896d30a88f315b638900a026e',
         'info_dict': {
-            'id': '36983',
+            'id': '45918',
             'ext': 'mp4',
-            'title': 'Kaffeeland Schweiz',
-            'description': 'md5:cc4424b18b75ae9948b13929a0814033',
+            'title': 'Waidmannsheil',
+            'description': 'md5:cce00ca1d70e21425e72c86a98a56817',
             'uploader': '3sat',
-            'upload_date': '20130622'
+            'upload_date': '20140913'
         }
     }
 
@@ -28,6 +31,15 @@ class DreiSatIE(InfoExtractor):
         details_url = 'http://www.3sat.de/mediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
         details_doc = self._download_xml(details_url, video_id, 'Downloading video details')
 
+        status_code = details_doc.find('./status/statuscode')
+        if status_code is not None and status_code.text != 'ok':
+            code = status_code.text
+            if code == 'notVisibleAnymore':
+                message = 'Video %s is not available' % video_id
+            else:
+                message = '%s returned error: %s' % (self.IE_NAME, code)
+            raise ExtractorError(message, expected=True)
+
         thumbnail_els = details_doc.findall('.//teaserimage')
         thumbnails = [{
             'width': int(te.attrib['key'].partition('x')[0]),

youtube_dl/extractor/drtv.py

@@ -1,3 +1,4 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor, ExtractorError
@@ -8,16 +9,16 @@ class DRTVIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
 
     _TEST = {
-        'url': 'http://www.dr.dk/tv/se/partiets-mand/partiets-mand-7-8',
-        'md5': '4a7e1dd65cdb2643500a3f753c942f25',
+        'url': 'https://www.dr.dk/tv/se/boern/ultra/panisk-paske/panisk-paske-5',
+        'md5': 'dc515a9ab50577fa14cc4e4b0265168f',
         'info_dict': {
-            'id': 'partiets-mand-7-8',
+            'id': 'panisk-paske-5',
             'ext': 'mp4',
-            'title': 'Partiets mand (7:8)',
-            'description': 'md5:a684b90a8f9336cd4aab94b7647d7862',
-            'timestamp': 1403047940,
-            'upload_date': '20140617',
-            'duration': 1299.040,
+            'title': 'Panisk Påske (5)',
+            'description': 'md5:ca14173c5ab24cd26b0fcc074dff391c',
+            'timestamp': 1426984612,
+            'upload_date': '20150322',
+            'duration': 1455,
         },
     }
 
@@ -26,6 +27,10 @@ class DRTVIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
+        if '>Programmet er ikke længere tilgængeligt' in webpage:
+            raise ExtractorError(
+                'Video %s is not available' % video_id, expected=True)
+
         video_id = self._search_regex(
             r'data-(?:material-identifier|episode-slug)="([^"]+)"',
             webpage, 'video id')

youtube_dl/extractor/dump.py

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

youtube_dl/extractor/dumpert.py

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

youtube_dl/extractor/eagleplatform.py

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

youtube_dl/extractor/eighttracks.py

@@ -3,7 +3,6 @@ from __future__ import unicode_literals
 
 import json
 import random
-import re
 
 from .common import InfoExtractor
 from ..compat import (
@@ -103,20 +102,23 @@ class EightTracksIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        playlist_id = mobj.group('id')
+        playlist_id = self._match_id(url)
 
         webpage = self._download_webpage(url, playlist_id)
 
-        json_like = self._search_regex(
-            r"(?s)PAGE.mix = (.*?);\n", webpage, 'trax information')
-        data = json.loads(json_like)
+        data = self._parse_json(
+            self._search_regex(
+                r"(?s)PAGE\.mix\s*=\s*({.+?});\n", webpage, 'trax information'),
+            playlist_id)
 
         session = str(random.randint(0, 1000000000))
         mix_id = data['id']
         track_count = data['tracks_count']
         duration = data['duration']
         avg_song_duration = float(duration) / track_count
+        # duration is sometimes negative, use predefined avg duration
+        if avg_song_duration <= 0:
+            avg_song_duration = 300
         first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id)
         next_url = first_url
         entries = []

youtube_dl/extractor/ellentv.py

@@ -13,15 +13,15 @@ from ..utils import (
 class EllenTVIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)'
     _TESTS = [{
-        'url': 'http://www.ellentv.com/videos/0-7jqrsr18/',
-        'md5': 'e4af06f3bf0d5f471921a18db5764642',
+        'url': 'http://www.ellentv.com/videos/0-ipq1gsai/',
+        'md5': '8e3c576bf2e9bfff4d76565f56f94c9c',
         'info_dict': {
-            'id': '0-7jqrsr18',
+            'id': '0-ipq1gsai',
             'ext': 'mp4',
-            'title': 'What\'s Wrong with These Photos? A Whole Lot',
-            'description': 'md5:35f152dc66b587cf13e6d2cf4fa467f6',
-            'timestamp': 1406876400,
-            'upload_date': '20140801',
+            'title': 'Fast Fingers of Fate',
+            'description': 'md5:686114ced0a032926935e9015ee794ac',
+            'timestamp': 1428033600,
+            'upload_date': '20150403',
         }
     }, {
         'url': 'http://ellentube.com/videos/0-dvzmabd5/',
@@ -40,14 +40,15 @@ class EllenTVIE(InfoExtractor):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
-        video_url = self._html_search_meta('VideoURL', webpage, 'url')
+
+        video_url = self._html_search_meta('VideoURL', webpage, 'url', fatal=True)
         title = self._og_search_title(webpage, default=None) or self._search_regex(
             r'pageName\s*=\s*"([^"]+)"', webpage, 'title')
         description = self._html_search_meta(
             'description', webpage, 'description') or self._og_search_description(webpage)
         timestamp = parse_iso8601(self._search_regex(
             r'<span class="publish-date"><time datetime="([^"]+)">',
-            webpage, 'timestamp'))
+            webpage, 'timestamp', fatal=False))
 
         return {
             'id': video_id,

youtube_dl/extractor/eroprofile.py

@@ -1,11 +1,17 @@
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
+from ..compat import compat_urllib_parse
+from ..utils import ExtractorError
 
 
 class EroProfileIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?eroprofile\.com/m/videos/view/(?P<id>[^/]+)'
-    _TEST = {
+    _LOGIN_URL = 'http://www.eroprofile.com/auth/auth.php?'
+    _NETRC_MACHINE = 'eroprofile'
+    _TESTS = [{
         'url': 'http://www.eroprofile.com/m/videos/view/sexy-babe-softcore',
         'md5': 'c26f351332edf23e1ea28ce9ec9de32f',
         'info_dict': {
@@ -16,13 +22,55 @@ class EroProfileIE(InfoExtractor):
             'thumbnail': 're:https?://.*\.jpg',
             'age_limit': 18,
         }
-    }
+    }, {
+        'url': 'http://www.eroprofile.com/m/videos/view/Try-It-On-Pee_cut_2-wmv-4shared-com-file-sharing-download-movie-file',
+        'md5': '1baa9602ede46ce904c431f5418d8916',
+        'info_dict': {
+            'id': '1133519',
+            'ext': 'm4v',
+            'title': 'Try It On Pee_cut_2.wmv - 4shared.com - file sharing - download movie file',
+            'thumbnail': 're:https?://.*\.jpg',
+            'age_limit': 18,
+        },
+        'skip': 'Requires login',
+    }]
+
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            return
+
+        query = compat_urllib_parse.urlencode({
+            'username': username,
+            'password': password,
+            'url': 'http://www.eroprofile.com/',
+        })
+        login_url = self._LOGIN_URL + query
+        login_page = self._download_webpage(login_url, None, False)
+
+        m = re.search(r'Your username or password was incorrect\.', login_page)
+        if m:
+            raise ExtractorError(
+                'Wrong username and/or password.', expected=True)
+
+        self.report_login()
+        redirect_url = self._search_regex(
+            r'<script[^>]+?src="([^"]+)"', login_page, 'login redirect url')
+        self._download_webpage(redirect_url, None, False)
+
+    def _real_initialize(self):
+        self._login()
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
 
         webpage = self._download_webpage(url, display_id)
 
+        m = re.search(r'You must be logged in to view this video\.', webpage)
+        if m:
+            raise ExtractorError(
+                'This video requires login. Please specify a username and password and try again.', expected=True)
+
         video_id = self._search_regex(
             [r"glbUpdViews\s*\('\d*','(\d+)'", r'p/report/video/(\d+)'],
             webpage, 'video id', default=None)

youtube_dl/extractor/extremetube.py

@@ -4,11 +4,11 @@ import re
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_urllib_parse_urlparse,
+    compat_parse_qs,
     compat_urllib_request,
-    compat_urllib_parse,
 )
 from ..utils import (
+    qualities,
     str_to_int,
 )
 
@@ -17,7 +17,7 @@ class ExtremeTubeIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<id>[0-9]+))(?:[/?&]|$)'
     _TESTS = [{
         'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
-        'md5': '1fb9228f5e3332ec8c057d6ac36f33e0',
+        'md5': '344d0c6d50e2f16b06e49ca011d8ac69',
         'info_dict': {
             'id': '652431',
             'ext': 'mp4',
@@ -49,19 +49,27 @@ class ExtremeTubeIE(InfoExtractor):
             r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>',
             webpage, 'view count', fatal=False))
 
-        video_url = compat_urllib_parse.unquote(self._html_search_regex(
-            r'video_url=(.+?)&amp;', webpage, 'video_url'))
-        path = compat_urllib_parse_urlparse(video_url).path
-        format = path.split('/')[5].split('_')[:2]
-        format = "-".join(format)
+        flash_vars = compat_parse_qs(self._search_regex(
+            r'<param[^>]+?name="flashvars"[^>]+?value="([^"]+)"', webpage, 'flash vars'))
+
+        formats = []
+        quality = qualities(['180p', '240p', '360p', '480p', '720p', '1080p'])
+        for k, vals in flash_vars.items():
+            m = re.match(r'quality_(?P<quality>[0-9]+p)$', k)
+            if m is not None:
+                formats.append({
+                    'format_id': m.group('quality'),
+                    'quality': quality(m.group('quality')),
+                    'url': vals[0],
+                })
+
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
             'title': video_title,
+            'formats': formats,
             'uploader': uploader,
             'view_count': view_count,
-            'url': video_url,
-            'format': format,
-            'format_id': format,
             'age_limit': 18,
         }

youtube_dl/extractor/footyroom.py

@@ -0,0 +1,49 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class FootyRoomIE(InfoExtractor):
+    _VALID_URL = r'http://footyroom\.com/(?P<id>[^/]+)'
+    _TESTS = [{
+        'url': 'http://footyroom.com/schalke-04-0-2-real-madrid-2015-02/',
+        'info_dict': {
+            'id': 'schalke-04-0-2-real-madrid-2015-02',
+            'title': 'Schalke 04 0 – 2 Real Madrid',
+        },
+        'playlist_count': 3,
+    }, {
+        'url': 'http://footyroom.com/georgia-0-2-germany-2015-03/',
+        'info_dict': {
+            'id': 'georgia-0-2-germany-2015-03',
+            'title': 'Georgia 0 – 2 Germany',
+        },
+        'playlist_count': 1,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        playlist = self._parse_json(
+            self._search_regex(
+                r'VideoSelector\.load\((\[.+?\])\);', webpage, 'video selector'),
+            playlist_id)
+
+        playlist_title = self._og_search_title(webpage)
+
+        entries = []
+        for video in playlist:
+            payload = video.get('payload')
+            if not payload:
+                continue
+            playwire_url = self._search_regex(
+                r'data-config="([^"]+)"', payload,
+                'playwire url', default=None)
+            if playwire_url:
+                entries.append(self.url_result(self._proto_relative_url(
+                    playwire_url, 'http:'), 'Playwire'))
+
+        return self.playlist_result(entries, playlist_id, playlist_title)

youtube_dl/extractor/francetv.py

@@ -14,7 +14,9 @@ from ..utils import (
     clean_html,
     ExtractorError,
     int_or_none,
+    float_or_none,
     parse_duration,
+    determine_ext,
 )
 
 
@@ -50,7 +52,8 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
             if not video_url:
                 continue
             format_id = video['format']
-            if video_url.endswith('.f4m'):
+            ext = determine_ext(video_url)
+            if ext == 'f4m':
                 if georestricted:
                     # See https://github.com/rg3/youtube-dl/issues/3963
                     # m3u8 urls work fine
@@ -60,12 +63,9 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
                     'http://hdfauth.francetv.fr/esi/urltokengen2.html?url=%s' % video_url_parsed.path,
                     video_id, 'Downloading f4m manifest token', fatal=False)
                 if f4m_url:
-                    f4m_formats = self._extract_f4m_formats(f4m_url, video_id)
-                    for f4m_format in f4m_formats:
-                        f4m_format['preference'] = 1
-                    formats.extend(f4m_formats)
-            elif video_url.endswith('.m3u8'):
-                formats.extend(self._extract_m3u8_formats(video_url, video_id, 'mp4'))
+                    formats.extend(self._extract_f4m_formats(f4m_url, video_id, 1, format_id))
+            elif ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(video_url, video_id, 'mp4', m3u8_id=format_id))
             elif video_url.startswith('rtmp'):
                 formats.append({
                     'url': video_url,
@@ -86,7 +86,7 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
             'title': info['titre'],
             'description': clean_html(info['synopsis']),
             'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']),
-            'duration': parse_duration(info['duree']),
+            'duration': float_or_none(info.get('real_duration'), 1000) or parse_duration(info['duree']),
             'timestamp': int_or_none(info['diffusion']['timestamp']),
             'formats': formats,
         }
@@ -260,22 +260,28 @@ class CultureboxIE(FranceTVBaseInfoExtractor):
     _VALID_URL = r'https?://(?:m\.)?culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)'
 
     _TEST = {
-        'url': 'http://culturebox.francetvinfo.fr/festivals/dans-les-jardins-de-william-christie/dans-les-jardins-de-william-christie-le-camus-162553',
-        'md5': '5ad6dec1ffb2a3fbcb20cc4b744be8d6',
+        'url': 'http://culturebox.francetvinfo.fr/live/musique/musique-classique/le-livre-vermeil-de-montserrat-a-la-cathedrale-delne-214511',
+        'md5': '9b88dc156781c4dbebd4c3e066e0b1d6',
         'info_dict': {
-            'id': 'EV_22853',
+            'id': 'EV_50111',
             'ext': 'flv',
-            'title': 'Dans les jardins de William Christie - Le Camus',
-            'description': 'md5:4710c82315c40f0c865ca8b9a68b5299',
-            'upload_date': '20140829',
-            'timestamp': 1409317200,
+            'title': "Le Livre Vermeil de Montserrat à la Cathédrale d'Elne",
+            'description': 'md5:f8a4ad202e8fe533e2c493cc12e739d9',
+            'upload_date': '20150320',
+            'timestamp': 1426892400,
+            'duration': 2760.9,
         },
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         name = mobj.group('name')
+
         webpage = self._download_webpage(url, name)
+
+        if ">Ce live n'est plus disponible en replay<" in webpage:
+            raise ExtractorError('Video %s is not available' % name, expected=True)
+
         video_id, catalogue = self._search_regex(
             r'"http://videos\.francetv\.fr/video/([^@]+@[^"]+)"', webpage, 'video id').split('@')
 

youtube_dl/extractor/funnyordie.py

@@ -50,7 +50,6 @@ class FunnyOrDieIE(InfoExtractor):
         bitrates.sort()
 
         formats = []
-
         for bitrate in bitrates:
             for link in links:
                 formats.append({
@@ -59,6 +58,13 @@ class FunnyOrDieIE(InfoExtractor):
                     'vbr': bitrate,
                 })
 
+        subtitles = {}
+        for src, src_lang in re.findall(r'<track kind="captions" src="([^"]+)" srclang="([^"]+)"', webpage):
+            subtitles[src_lang] = [{
+                'ext': src.split('/')[-1],
+                'url': 'http://www.funnyordie.com%s' % src,
+            }]
+
         post_json = self._search_regex(
             r'fb_post\s*=\s*(\{.*?\});', webpage, 'post details')
         post = json.loads(post_json)
@@ -69,4 +75,5 @@ class FunnyOrDieIE(InfoExtractor):
             'description': post.get('description'),
             'thumbnail': post.get('picture'),
             'formats': formats,
+            'subtitles': subtitles,
         }

youtube_dl/extractor/gamersyde.py

@@ -0,0 +1,70 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    js_to_json,
+    parse_duration,
+    remove_start,
+)
+
+
+class GamersydeIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?gamersyde\.com/hqstream_(?P<display_id>[\da-z_]+)-(?P<id>\d+)_[a-z]{2}\.html'
+    _TEST = {
+        'url': 'http://www.gamersyde.com/hqstream_bloodborne_birth_of_a_hero-34371_en.html',
+        'md5': 'f38d400d32f19724570040d5ce3a505f',
+        'info_dict': {
+            'id': '34371',
+            'ext': 'mp4',
+            'duration': 372,
+            'title': 'Bloodborne - Birth of a hero',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        playlist = self._parse_json(
+            self._search_regex(
+                r'(?s)playlist: \[({.+?})\]\s*}\);', webpage, 'files'),
+            display_id, transform_source=js_to_json)
+
+        formats = []
+        for source in playlist['sources']:
+            video_url = source.get('file')
+            if not video_url:
+                continue
+            format_id = source.get('label')
+            f = {
+                'url': video_url,
+                'format_id': format_id,
+            }
+            m = re.search(r'^(?P<height>\d+)[pP](?P<fps>\d+)fps', format_id)
+            if m:
+                f.update({
+                    'height': int(m.group('height')),
+                    'fps': int(m.group('fps')),
+                })
+            formats.append(f)
+        self._sort_formats(formats)
+
+        title = remove_start(playlist['title'], '%s - ' % video_id)
+        thumbnail = playlist.get('image')
+        duration = parse_duration(self._search_regex(
+            r'Length:</label>([^<]+)<', webpage, 'duration', fatal=False))
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/gazeta.py

@@ -0,0 +1,38 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class GazetaIE(InfoExtractor):
+    _VALID_URL = r'(?P<url>https?://(?:www\.)?gazeta\.ru/(?:[^/]+/)?video/(?:(?:main|\d{4}/\d{2}/\d{2})/)?(?P<id>[A-Za-z0-9-_.]+)\.s?html)'
+    _TESTS = [{
+        'url': 'http://www.gazeta.ru/video/main/zadaite_vopros_vladislavu_yurevichu.shtml',
+        'md5': 'd49c9bdc6e5a7888f27475dc215ee789',
+        'info_dict': {
+            'id': '205566',
+            'ext': 'mp4',
+            'title': '«70–80 процентов гражданских в Донецке на грани голода»',
+            'description': 'md5:38617526050bd17b234728e7f9620a71',
+            'thumbnail': 're:^https?://.*\.jpg',
+        },
+    }, {
+        'url': 'http://www.gazeta.ru/lifestyle/video/2015/03/08/master-klass_krasivoi_byt._delaem_vesennii_makiyazh.shtml',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+
+        display_id = mobj.group('id')
+        embed_url = '%s?p=embed' % mobj.group('url')
+        embed_page = self._download_webpage(
+            embed_url, display_id, 'Downloading embed page')
+
+        video_id = self._search_regex(
+            r'<div[^>]*?class="eagleplayer"[^>]*?data-id="([^"]+)"', embed_page, 'video id')
+
+        return self.url_result(
+            'eagleplatform:gazeta.media.eagleplatform.com:%s' % video_id, 'EaglePlatform')

youtube_dl/extractor/generic.py

@@ -29,10 +29,12 @@ from ..utils import (
     xpath_text,
 )
 from .brightcove import BrightcoveIE
+from .nbc import NBCSportsVPlayerIE
 from .ooyala import OoyalaIE
 from .rutv import RUTVIE
 from .smotri import SmotriIE
 from .condenast import CondeNastIE
+from .udn import UDNEmbedIE
 
 
 class GenericIE(InfoExtractor):
@@ -527,6 +529,17 @@ class GenericIE(InfoExtractor):
             },
             'add_ie': ['Viddler'],
         },
+        # Libsyn embed
+        {
+            'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
+            'info_dict': {
+                'id': '3377616',
+                'ext': 'mp3',
+                'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
+                'description': 'md5:601cb790edd05908957dae8aaa866465',
+                'upload_date': '20150220',
+            },
+        },
         # jwplayer YouTube
         {
             'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
@@ -570,6 +583,66 @@ class GenericIE(InfoExtractor):
                 'title': 'John Carlson Postgame 2/25/15',
             },
         },
+        # Eagle.Platform embed (generic URL)
+        {
+            'url': 'http://lenta.ru/news/2015/03/06/navalny/',
+            'info_dict': {
+                'id': '227304',
+                'ext': 'mp4',
+                'title': 'Навальный вышел на свободу',
+                'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'duration': 87,
+                'view_count': int,
+                'age_limit': 0,
+            },
+        },
+        # ClipYou (Eagle.Platform) embed (custom URL)
+        {
+            'url': 'http://muz-tv.ru/play/7129/',
+            'info_dict': {
+                'id': '12820',
+                'ext': 'mp4',
+                'title': "'O Sole Mio",
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'duration': 216,
+                'view_count': int,
+            },
+        },
+        # Pladform embed
+        {
+            'url': 'http://muz-tv.ru/kinozal/view/7400/',
+            'info_dict': {
+                'id': '100183293',
+                'ext': 'mp4',
+                'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
+                'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'duration': 694,
+                'age_limit': 0,
+            },
+        },
+        # Playwire embed
+        {
+            'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
+            'info_dict': {
+                'id': '3519514',
+                'ext': 'mp4',
+                'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
+                'thumbnail': 're:^https?://.*\.png$',
+                'duration': 45.115,
+            },
+        },
+        # 5min embed
+        {
+            'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
+            'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
+            'info_dict': {
+                'id': '518726732',
+                'ext': 'mp4',
+                'title': 'Facebook Creates "On This Day" | Crunch Report',
+            },
+        },
         # RSS feed with enclosure
         {
             'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
@@ -579,6 +652,81 @@ class GenericIE(InfoExtractor):
                 'upload_date': '20150228',
                 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
             }
+        },
+        # Crooks and Liars embed
+        {
+            'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
+            'info_dict': {
+                'id': '8RUoRhRi',
+                'ext': 'mp4',
+                'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
+                'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
+                'timestamp': 1428207000,
+                'upload_date': '20150405',
+                'uploader': 'Heather',
+            },
+        },
+        # Crooks and Liars external embed
+        {
+            'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
+            'info_dict': {
+                'id': 'MTE3MjUtMzQ2MzA',
+                'ext': 'mp4',
+                'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
+                'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
+                'timestamp': 1265032391,
+                'upload_date': '20100201',
+                'uploader': 'Heather',
+            },
+        },
+        # NBC Sports vplayer embed
+        {
+            'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
+            'info_dict': {
+                'id': 'ln7x1qSThw4k',
+                'ext': 'flv',
+                'title': "PFT Live: New leader in the 'new-look' defense",
+                'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
+            },
+        },
+        # UDN embed
+        {
+            'url': 'http://www.udn.com/news/story/7314/822787',
+            'md5': 'fd2060e988c326991037b9aff9df21a6',
+            'info_dict': {
+                'id': '300346',
+                'ext': 'mp4',
+                'title': '中一中男師變性 全校師生力挺',
+                'thumbnail': 're:^https?://.*\.jpg$',
+            }
+        },
+        # Ooyala embed
+        {
+            'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
+            'info_dict': {
+                'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
+                'ext': 'mp4',
+                'description': 'VIDEO: Index/Match versus VLOOKUP.',
+                'title': 'This is what separates the Excel masters from the wannabes',
+            },
+            'params': {
+                # m3u8 downloads
+                'skip_download': True,
+            }
+        },
+        # Contains a SMIL manifest
+        {
+            'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
+            'info_dict': {
+                'id': 'file',
+                'ext': 'flv',
+                'title': '+ Football: Lottery Champions League Europe',
+                'uploader': 'www.telewebion.com',
+            },
+            'params': {
+                # rtmpe downloads
+                'skip_download': True,
+            }
         }
     ]
 
@@ -967,10 +1115,24 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(mobj.group('url'))
 
+        # Look for NYTimes player
+        mobj = re.search(
+            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
+            webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'))
+
+        # Look for Libsyn player
+        mobj = re.search(
+            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'))
+
         # Look for Ooyala videos
         mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
                 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
-                re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage))
+                re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
+                re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
         if mobj is not None:
             return OoyalaIE._build_url_result(mobj.group('ec'))
 
@@ -1155,6 +1317,54 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
 
+        # Look for Eagle.Platform embeds
+        mobj = re.search(
+            r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'EaglePlatform')
+
+        # Look for ClipYou (uses Eagle.Platform) embeds
+        mobj = re.search(
+            r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
+        if mobj is not None:
+            return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
+
+        # Look for Pladform embeds
+        mobj = re.search(
+            r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'Pladform')
+
+        # Look for Playwire embeds
+        mobj = re.search(
+            r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'))
+
+        # Look for 5min embeds
+        mobj = re.search(
+            r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
+        if mobj is not None:
+            return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
+
+        # Look for Crooks and Liars embeds
+        mobj = re.search(
+            r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'))
+
+        # Look for NBC Sports VPlayer embeds
+        nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
+        if nbc_sports_url:
+            return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
+
+        # Look for UDN embeds
+        mobj = re.search(
+            r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
+        if mobj is not None:
+            return self.url_result(
+                compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
+
         def check_video(vurl):
             if YoutubeIE.suitable(vurl):
                 return True
@@ -1211,10 +1421,16 @@ class GenericIE(InfoExtractor):
             # HTML5 video
             found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
         if not found:
+            REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
             found = re.search(
                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
-                r'(?:[a-z-]+="[^"]+"\s+)*?content="[0-9]{,2};url=\'?([^\'"]+)',
+                r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
                 webpage)
+            if not found:
+                # Look also in Refresh HTTP header
+                refresh_header = head_response.headers.get('Refresh')
+                if refresh_header:
+                    found = re.search(REDIRECT_REGEX, refresh_header)
             if found:
                 new_url = found.group(1)
                 self.report_following_redirect(new_url)
@@ -1238,13 +1454,22 @@ class GenericIE(InfoExtractor):
             # here's a fun little line of code for you:
             video_id = os.path.splitext(video_id)[0]
 
-            entries.append({
-                'id': video_id,
-                'url': video_url,
-                'uploader': video_uploader,
-                'title': video_title,
-                'age_limit': age_limit,
-            })
+            if determine_ext(video_url) == 'smil':
+                entries.append({
+                    'id': video_id,
+                    'formats': self._extract_smil_formats(video_url, video_id),
+                    'uploader': video_uploader,
+                    'title': video_title,
+                    'age_limit': age_limit,
+                })
+            else:
+                entries.append({
+                    'id': video_id,
+                    'url': video_url,
+                    'uploader': video_uploader,
+                    'title': video_title,
+                    'age_limit': age_limit,
+                })
 
         if len(entries) == 1:
             return entries[0]

youtube_dl/extractor/globo.py

@@ -20,7 +20,7 @@ class GloboIE(InfoExtractor):
     _VALID_URL = 'https?://.+?\.globo\.com/(?P<id>.+)'
 
     _API_URL_TEMPLATE = 'http://api.globovideos.com/videos/%s/playlist'
-    _SECURITY_URL_TEMPLATE = 'http://security.video.globo.com/videos/%s/hash?player=flash&version=2.9.9.50&resource_id=%s'
+    _SECURITY_URL_TEMPLATE = 'http://security.video.globo.com/videos/%s/hash?player=flash&version=17.0.0.132&resource_id=%s'
 
     _VIDEOID_REGEXES = [
         r'\bdata-video-id="(\d+)"',

youtube_dl/extractor/grooveshark.py

@@ -140,9 +140,9 @@ class GroovesharkIE(InfoExtractor):
 
         if webpage is not None:
             o = GroovesharkHtmlParser.extract_object_tags(webpage)
-            return (webpage, [x for x in o if x['attrs']['id'] == 'jsPlayerEmbed'])
+            return webpage, [x for x in o if x['attrs']['id'] == 'jsPlayerEmbed']
 
-        return (webpage, None)
+        return webpage, None
 
     def _real_initialize(self):
         self.ts = int(time.time() * 1000)  # timestamp in millis
@@ -154,7 +154,7 @@ class GroovesharkIE(InfoExtractor):
         swf_referer = None
         if self.do_playerpage_request:
             (_, player_objs) = self._get_playerpage(url)
-            if player_objs is not None:
+            if player_objs:
                 swf_referer = self._build_swf_referer(url, player_objs[0])
                 self.to_screen('SWF Referer: %s' % swf_referer)
 

youtube_dl/extractor/hitbox.py

@@ -10,6 +10,7 @@ from ..utils import (
     float_or_none,
     int_or_none,
     compat_str,
+    determine_ext,
 )
 
 
@@ -147,12 +148,27 @@ class HitboxLiveIE(HitboxIE):
                 servers.append(base_url)
                 for stream in cdn.get('bitrates'):
                     label = stream.get('label')
-                    if label != 'Auto':
+                    if label == 'Auto':
+                        continue
+                    stream_url = stream.get('url')
+                    if not stream_url:
+                        continue
+                    bitrate = int_or_none(stream.get('bitrate'))
+                    if stream.get('provider') == 'hls' or determine_ext(stream_url) == 'm3u8':
+                        if not stream_url.startswith('http'):
+                            continue
                         formats.append({
-                            'url': '%s/%s' % (base_url, stream.get('url')),
+                            'url': stream_url,
                             'ext': 'mp4',
-                            'vbr': stream.get('bitrate'),
-                            'resolution': label,
+                            'tbr': bitrate,
+                            'format_note': label,
+                            'rtmp_live': True,
+                        })
+                    else:
+                        formats.append({
+                            'url': '%s/%s' % (base_url, stream_url),
+                            'ext': 'mp4',
+                            'tbr': bitrate,
                             'rtmp_live': True,
                             'format_note': host,
                             'page_url': url,

youtube_dl/extractor/jeuxvideo.py

@@ -2,7 +2,6 @@
 
 from __future__ import unicode_literals
 
-import json
 import re
 
 from .common import InfoExtractor
@@ -15,10 +14,10 @@ class JeuxVideoIE(InfoExtractor):
         'url': 'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
         'md5': '046e491afb32a8aaac1f44dd4ddd54ee',
         'info_dict': {
-            'id': '5182',
+            'id': '114765',
             'ext': 'mp4',
-            'title': 'GC 2013 : Tearaway nous présente ses papiers d\'identité',
-            'description': 'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.\n',
+            'title': 'Tearaway : GC 2013 : Tearaway nous présente ses papiers d\'identité',
+            'description': 'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.',
         },
     }
 
@@ -26,26 +25,29 @@ class JeuxVideoIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         title = mobj.group(1)
         webpage = self._download_webpage(url, title)
-        xml_link = self._html_search_regex(
-            r'<param name="flashvars" value="config=(.*?)" />',
+        title = self._html_search_meta('name', webpage)
+        config_url = self._html_search_regex(
+            r'data-src="(/contenu/medias/video.php.*?)"',
             webpage, 'config URL')
+        config_url = 'http://www.jeuxvideo.com' + config_url
 
         video_id = self._search_regex(
-            r'http://www\.jeuxvideo\.com/config/\w+/\d+/(.*?)/\d+_player\.xml',
-            xml_link, 'video ID')
+            r'id=(\d+)',
+            config_url, 'video ID')
 
-        config = self._download_xml(
-            xml_link, title, 'Downloading XML config')
-        info_json = config.find('format.json').text
-        info = json.loads(info_json)['versions'][0]
+        config = self._download_json(
+            config_url, title, 'Downloading JSON config')
 
-        video_url = 'http://video720.jeuxvideo.com/' + info['file']
+        formats = [{
+            'url': source['file'],
+            'format_id': source['label'],
+            'resolution': source['label'],
+        } for source in reversed(config['sources'])]
 
         return {
             'id': video_id,
-            'title': config.find('titre_video').text,
-            'ext': 'mp4',
-            'url': video_url,
+            'title': title,
+            'formats': formats,
             'description': self._og_search_description(webpage),
-            'thumbnail': config.find('image').text,
+            'thumbnail': config.get('image'),
         }

youtube_dl/extractor/kanalplay.py

@@ -0,0 +1,96 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    float_or_none,
+)
+
+
+class KanalPlayIE(InfoExtractor):
+    IE_DESC = 'Kanal 5/9/11 Play'
+    _VALID_URL = r'https?://(?:www\.)?kanal(?P<channel_id>5|9|11)play\.se/(?:#!/)?(?:play/)?program/\d+/video/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://www.kanal5play.se/#!/play/program/3060212363/video/3270012277',
+        'info_dict': {
+            'id': '3270012277',
+            'ext': 'flv',
+            'title': 'Saknar både dusch och avlopp',
+            'description': 'md5:6023a95832a06059832ae93bc3c7efb7',
+            'duration': 2636.36,
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }, {
+        'url': 'http://www.kanal9play.se/#!/play/program/335032/video/246042',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.kanal11play.se/#!/play/program/232835958/video/367135199',
+        'only_matching': True,
+    }]
+
+    def _fix_subtitles(self, subs):
+        return '\r\n\r\n'.join(
+            '%s\r\n%s --> %s\r\n%s'
+            % (
+                num,
+                self._subtitles_timecode(item['startMillis'] / 1000.0),
+                self._subtitles_timecode(item['endMillis'] / 1000.0),
+                item['text'],
+            ) for num, item in enumerate(subs, 1))
+
+    def _get_subtitles(self, channel_id, video_id):
+        subs = self._download_json(
+            'http://www.kanal%splay.se/api/subtitles/%s' % (channel_id, video_id),
+            video_id, 'Downloading subtitles JSON', fatal=False)
+        return {'se': [{'ext': 'srt', 'data': self._fix_subtitles(subs)}]} if subs else {}
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        channel_id = mobj.group('channel_id')
+
+        video = self._download_json(
+            'http://www.kanal%splay.se/api/getVideo?format=FLASH&videoId=%s' % (channel_id, video_id),
+            video_id)
+
+        reasons_for_no_streams = video.get('reasonsForNoStreams')
+        if reasons_for_no_streams:
+            raise ExtractorError(
+                '%s returned error: %s' % (self.IE_NAME, '\n'.join(reasons_for_no_streams)),
+                expected=True)
+
+        title = video['title']
+        description = video.get('description')
+        duration = float_or_none(video.get('length'), 1000)
+        thumbnail = video.get('posterUrl')
+
+        stream_base_url = video['streamBaseUrl']
+
+        formats = [{
+            'url': stream_base_url,
+            'play_path': stream['source'],
+            'ext': 'flv',
+            'tbr': float_or_none(stream.get('bitrate'), 1000),
+            'rtmp_real_time': True,
+        } for stream in video['streams']]
+        self._sort_formats(formats)
+
+        subtitles = {}
+        if video.get('hasSubtitle'):
+            subtitles = self.extract_subtitles(channel_id, video_id)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+            'subtitles': subtitles,
+        }

youtube_dl/extractor/krasview.py

@@ -40,8 +40,10 @@ class KrasViewIE(InfoExtractor):
         description = self._og_search_description(webpage, default=None)
         thumbnail = flashvars.get('image') or self._og_search_thumbnail(webpage)
         duration = int_or_none(flashvars.get('duration'))
-        width = int_or_none(self._og_search_property('video:width', webpage, 'video width'))
-        height = int_or_none(self._og_search_property('video:height', webpage, 'video height'))
+        width = int_or_none(self._og_search_property(
+            'video:width', webpage, 'video width', default=None))
+        height = int_or_none(self._og_search_property(
+            'video:height', webpage, 'video height', default=None))
 
         return {
             'id': video_id,

youtube_dl/extractor/letv.py

@@ -88,12 +88,13 @@ class LetvIE(InfoExtractor):
         play_json_req = compat_urllib_request.Request(
             'http://api.letv.com/mms/out/video/playJson?' + compat_urllib_parse.urlencode(params)
         )
-        play_json_req.add_header(
-            'Ytdl-request-proxy',
-            self._downloader.params.get('cn_verification_proxy'))
+        cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
+        if cn_verification_proxy:
+            play_json_req.add_header('Ytdl-request-proxy', cn_verification_proxy)
+
         play_json = self._download_json(
             play_json_req,
-            media_id, 'playJson data')
+            media_id, 'Downloading playJson data')
 
         # Check for errors
         playstatus = play_json['playstatus']

youtube_dl/extractor/libsyn.py

@@ -0,0 +1,59 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import unified_strdate
+
+
+class LibsynIE(InfoExtractor):
+    _VALID_URL = r'https?://html5-player\.libsyn\.com/embed/episode/id/(?P<id>[0-9]+)'
+
+    _TEST = {
+        'url': 'http://html5-player.libsyn.com/embed/episode/id/3377616/',
+        'md5': '443360ee1b58007bc3dcf09b41d093bb',
+        'info_dict': {
+            'id': '3377616',
+            'ext': 'mp3',
+            'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
+            'description': 'md5:601cb790edd05908957dae8aaa866465',
+            'upload_date': '20150220',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        formats = [{
+            'url': media_url,
+        } for media_url in set(re.findall('var\s+mediaURL(?:Libsyn)?\s*=\s*"([^"]+)"', webpage))]
+
+        podcast_title = self._search_regex(
+            r'<h2>([^<]+)</h2>', webpage, 'title')
+        episode_title = self._search_regex(
+            r'<h3>([^<]+)</h3>', webpage, 'title', default=None)
+
+        title = '%s - %s' % (podcast_title, episode_title) if podcast_title else episode_title
+
+        description = self._html_search_regex(
+            r'<div id="info_text_body">(.+?)</div>', webpage,
+            'description', fatal=False)
+
+        thumbnail = self._search_regex(
+            r'<img[^>]+class="info-show-icon"[^>]+src="([^"]+)"',
+            webpage, 'thumbnail', fatal=False)
+
+        release_date = unified_strdate(self._search_regex(
+            r'<div class="release_date">Released: ([^<]+)<', webpage, 'release date', fatal=False))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'upload_date': release_date,
+            'formats': formats,
+        }

youtube_dl/extractor/livestream.py

@@ -2,6 +2,7 @@ from __future__ import unicode_literals
 
 import re
 import json
+import itertools
 
 from .common import InfoExtractor
 from ..compat import (
@@ -20,7 +21,7 @@ from ..utils import (
 
 class LivestreamIE(InfoExtractor):
     IE_NAME = 'livestream'
-    _VALID_URL = r'https?://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>[0-9]+)(?:/player)?)?/?(?:$|[?#])'
+    _VALID_URL = r'https?://(?:new\.)?livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>[0-9]+)(?:/player)?)?/?(?:$|[?#])'
     _TESTS = [{
         'url': 'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
         'md5': '53274c76ba7754fb0e8d072716f2292b',
@@ -40,9 +41,19 @@ class LivestreamIE(InfoExtractor):
             'id': '2245590',
         },
         'playlist_mincount': 4,
+    }, {
+        'url': 'http://new.livestream.com/chess24/tatasteelchess',
+        'info_dict': {
+            'title': 'Tata Steel Chess',
+            'id': '3705884',
+        },
+        'playlist_mincount': 60,
     }, {
         'url': 'https://new.livestream.com/accounts/362/events/3557232/videos/67864563/player?autoPlay=false&height=360&mute=false&width=640',
         'only_matching': True,
+    }, {
+        'url': 'http://livestream.com/bsww/concacafbeachsoccercampeonato2015',
+        'only_matching': True,
     }]
 
     def _parse_smil(self, video_id, smil_url):
@@ -117,6 +128,30 @@ class LivestreamIE(InfoExtractor):
             'view_count': video_data.get('views'),
         }
 
+    def _extract_event(self, info):
+        event_id = compat_str(info['id'])
+        account = compat_str(info['owner_account_id'])
+        root_url = (
+            'https://new.livestream.com/api/accounts/{account}/events/{event}/'
+            'feed.json'.format(account=account, event=event_id))
+
+        def _extract_videos():
+            last_video = None
+            for i in itertools.count(1):
+                if last_video is None:
+                    info_url = root_url
+                else:
+                    info_url = '{root}?&id={id}&newer=-1&type=video'.format(
+                        root=root_url, id=last_video)
+                videos_info = self._download_json(info_url, event_id, 'Downloading page {0}'.format(i))['data']
+                videos_info = [v['data'] for v in videos_info if v['type'] == 'video']
+                if not videos_info:
+                    break
+                for v in videos_info:
+                    yield self._extract_video_info(v)
+                last_video = videos_info[-1]['id']
+        return self.playlist_result(_extract_videos(), event_id, info['full_name'])
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
@@ -144,14 +179,13 @@ class LivestreamIE(InfoExtractor):
                 result = result and compat_str(vdata['data']['id']) == vid
             return result
 
-        videos = [self._extract_video_info(video_data['data'])
-                  for video_data in info['feed']['data']
-                  if is_relevant(video_data, video_id)]
         if video_id is None:
             # This is an event page:
-            return self.playlist_result(
-                videos, '%s' % info['id'], info['full_name'])
+            return self._extract_event(info)
         else:
+            videos = [self._extract_video_info(video_data['data'])
+                      for video_data in info['feed']['data']
+                      if is_relevant(video_data, video_id)]
             if not videos:
                 raise ExtractorError('Cannot find video %s' % video_id)
             return videos[0]

youtube_dl/extractor/lrt.py

@@ -52,6 +52,7 @@ class LRTIE(InfoExtractor):
                     'url': data['streamer'],
                     'play_path': 'mp4:%s' % data['file'],
                     'preference': -1,
+                    'rtmp_real_time': True,
                 })
             else:
                 formats.extend(

youtube_dl/extractor/miomio.py

@@ -0,0 +1,98 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import random
+
+from .common import InfoExtractor
+from ..utils import (
+    xpath_text,
+    int_or_none,
+    ExtractorError,
+)
+
+
+class MioMioIE(InfoExtractor):
+    IE_NAME = 'miomio.tv'
+    _VALID_URL = r'https?://(?:www\.)?miomio\.tv/watch/cc(?P<id>[0-9]+)'
+    _TESTS = [{
+        # "type=video" in flashvars
+        'url': 'http://www.miomio.tv/watch/cc88912/',
+        'md5': '317a5f7f6b544ce8419b784ca8edae65',
+        'info_dict': {
+            'id': '88912',
+            'ext': 'flv',
+            'title': '【SKY】字幕 铠武昭和VS平成 假面骑士大战FEAT战队 魔星字幕组 字幕',
+            'duration': 5923,
+        },
+    }, {
+        'url': 'http://www.miomio.tv/watch/cc184024/',
+        'info_dict': {
+            'id': '43729',
+            'title': '《动漫同人插画绘制》',
+        },
+        'playlist_mincount': 86,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_meta(
+            'description', webpage, 'title', fatal=True)
+
+        mioplayer_path = self._search_regex(
+            r'src="(/mioplayer/[^"]+)"', webpage, 'ref_path')
+
+        xml_config = self._search_regex(
+            r'flashvars="type=(?:sina|video)&amp;(.+?)&amp;',
+            webpage, 'xml config')
+
+        # skipping the following page causes lags and eventually connection drop-outs
+        self._request_webpage(
+            'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/xml.php?id=%s&r=%s' % (id, random.randint(100, 999)),
+            video_id)
+
+        # the following xml contains the actual configuration information on the video file(s)
+        vid_config = self._download_xml(
+            'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/sina.php?{0}'.format(xml_config),
+            video_id)
+
+        http_headers = {
+            'Referer': 'http://www.miomio.tv%s' % mioplayer_path,
+        }
+
+        if not int_or_none(xpath_text(vid_config, 'timelength')):
+            raise ExtractorError('Unable to load videos!', expected=True)
+
+        entries = []
+        for f in vid_config.findall('./durl'):
+            segment_url = xpath_text(f, 'url', 'video url')
+            if not segment_url:
+                continue
+            order = xpath_text(f, 'order', 'order')
+            segment_id = video_id
+            segment_title = title
+            if order:
+                segment_id += '-%s' % order
+                segment_title += ' part %s' % order
+            entries.append({
+                'id': segment_id,
+                'url': segment_url,
+                'title': segment_title,
+                'duration': int_or_none(xpath_text(f, 'length', 'duration'), 1000),
+                'http_headers': http_headers,
+            })
+
+        if len(entries) == 1:
+            segment = entries[0]
+            segment['id'] = video_id
+            segment['title'] = title
+            return segment
+
+        return {
+            '_type': 'multi_video',
+            'id': video_id,
+            'entries': entries,
+            'title': title,
+            'http_headers': http_headers,
+        }

youtube_dl/extractor/mixcloud.py

@@ -1,6 +1,7 @@
 from __future__ import unicode_literals
 
 import re
+import itertools
 
 from .common import InfoExtractor
 from ..compat import (
@@ -10,7 +11,6 @@ from ..utils import (
     ExtractorError,
     HEADRequest,
     str_to_int,
-    parse_iso8601,
 )
 
 
@@ -27,8 +27,6 @@ class MixcloudIE(InfoExtractor):
             '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',
-            'timestamp': 1321359578,
             'thumbnail': 're:https?://.*\.jpg',
             'view_count': int,
             'like_count': int,
@@ -37,31 +35,30 @@ class MixcloudIE(InfoExtractor):
         'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/',
         'info_dict': {
             'id': 'gillespeterson-caribou-7-inch-vinyl-mix-chat',
-            'ext': 'm4a',
-            'title': 'Electric Relaxation vol. 3',
+            'ext': 'mp3',
+            'title': 'Caribou 7 inch Vinyl Mix & Chat',
             'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
-            'uploader': 'Daniel Drumz',
+            'uploader': 'Gilles Peterson Worldwide',
             'uploader_id': 'gillespeterson',
-            'thumbnail': 're:https?://.*\.jpg',
+            'thumbnail': 're:https?://.*/images/',
             'view_count': int,
             'like_count': int,
         },
     }]
 
-    def _get_url(self, track_id, template_url):
-        server_count = 30
-        for i in range(server_count):
-            url = template_url % i
+    def _get_url(self, track_id, template_url, server_number):
+        boundaries = (1, 30)
+        for nr in server_numbers(server_number, boundaries):
+            url = template_url % nr
             try:
                 # We only want to know if the request succeed
                 # don't download the whole file
                 self._request_webpage(
                     HEADRequest(url), track_id,
-                    'Checking URL %d/%d ...' % (i + 1, server_count + 1))
+                    'Checking URL %d/%d ...' % (nr, boundaries[-1]))
                 return url
             except ExtractorError:
                 pass
-
         return None
 
     def _real_extract(self, url):
@@ -75,17 +72,18 @@ class MixcloudIE(InfoExtractor):
         preview_url = self._search_regex(
             r'\s(?:data-preview-url|m-preview)="([^"]+)"', webpage, 'preview url')
         song_url = preview_url.replace('/previews/', '/c/originals/')
+        server_number = int(self._search_regex(r'stream(\d+)', song_url, 'server number'))
         template_url = re.sub(r'(stream\d*)', 'stream%d', song_url)
-        final_song_url = self._get_url(track_id, template_url)
+        final_song_url = self._get_url(track_id, template_url, server_number)
         if final_song_url is None:
             self.to_screen('Trying with m4a extension')
             template_url = template_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/')
-            final_song_url = self._get_url(track_id, template_url)
+            final_song_url = self._get_url(track_id, template_url, server_number)
         if final_song_url is None:
             raise ExtractorError('Unable to extract track url')
 
         PREFIX = (
-            r'<span class="play-button[^"]*?"'
+            r'm-play-on-spacebar[^>]+'
             r'(?:\s+[a-zA-Z0-9-]+(?:="[^"]+")?)*?\s+')
         title = self._html_search_regex(
             PREFIX + r'm-title="([^"]+)"', webpage, 'title')
@@ -99,16 +97,12 @@ class MixcloudIE(InfoExtractor):
             r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
         description = self._og_search_description(webpage)
         like_count = str_to_int(self._search_regex(
-            [r'<meta itemprop="interactionCount" content="UserLikes:([0-9]+)"',
-             r'/favorites/?">([0-9]+)<'],
+            r'\bbutton-favorite\b[^>]+m-ajax-toggle-count="([^"]+)"',
             webpage, 'like count', fatal=False))
         view_count = str_to_int(self._search_regex(
             [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
              r'/listeners/?">([0-9,.]+)</a>'],
             webpage, 'play count', fatal=False))
-        timestamp = parse_iso8601(self._search_regex(
-            r'<time itemprop="dateCreated" datetime="([^"]+)">',
-            webpage, 'upload date', default=None))
 
         return {
             'id': track_id,
@@ -118,7 +112,38 @@ class MixcloudIE(InfoExtractor):
             'thumbnail': thumbnail,
             'uploader': uploader,
             'uploader_id': uploader_id,
-            'timestamp': timestamp,
             'view_count': view_count,
             'like_count': like_count,
         }
+
+
+def server_numbers(first, boundaries):
+    """ Server numbers to try in descending order of probable availability.
+    Starting from first (i.e. the number of the server hosting the preview file)
+    and going further and further up to the higher boundary and down to the
+    lower one in an alternating fashion. Namely:
+
+        server_numbers(2, (1, 5))
+
+        # Where the preview server is 2, min number is 1 and max is 5.
+        # Yields: 2, 3, 1, 4, 5
+
+    Why not random numbers or increasing sequences? Since from what I've seen,
+    full length files seem to be hosted on servers whose number is closer to
+    that of the preview; to be confirmed.
+    """
+    zip_longest = getattr(itertools, 'zip_longest', None)
+    if zip_longest is None:
+        # python 2.x
+        zip_longest = itertools.izip_longest
+
+    if len(boundaries) != 2:
+        raise ValueError("boundaries should be a two-element tuple")
+    min, max = boundaries
+    highs = range(first + 1, max + 1)
+    lows = range(first - 1, min - 1, -1)
+    rest = filter(
+        None, itertools.chain.from_iterable(zip_longest(highs, lows)))
+    yield first
+    for n in rest:
+        yield n

youtube_dl/extractor/mlb.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 
 class MLBIE(InfoExtractor):
-    _VALID_URL = r'https?://m(?:lb)?\.mlb\.com/(?:(?:.*?/)?video/(?:topic/[\da-z_-]+/)?v|(?:shared/video/embed/embed\.html|[^/]+/video/play\.jsp)\?.*?\bcontent_id=)(?P<id>n?\d+)'
+    _VALID_URL = r'https?://m(?:lb)?\.(?:[\da-z_-]+\.)?mlb\.com/(?:(?:.*?/)?video/(?:topic/[\da-z_-]+/)?v|(?:shared/video/embed/embed\.html|[^/]+/video/play\.jsp)\?.*?\bcontent_id=)(?P<id>n?\d+)'
     _TESTS = [
         {
             'url': 'http://m.mlb.com/sea/video/topic/51231442/v34698933/nymsea-ackley-robs-a-home-run-with-an-amazing-catch/?c_id=sea',
@@ -80,6 +80,10 @@ class MLBIE(InfoExtractor):
             'url': 'http://mlb.mlb.com/es/video/play.jsp?content_id=36599553',
             'only_matching': True,
         },
+        {
+            'url': 'http://m.cardinals.mlb.com/stl/video/v51175783/atlstl-piscotty-makes-great-sliding-catch-on-line/?partnerId=as_mlb_20150321_42500876&adbid=579409712979910656&adbpl=tw&adbpr=52847728',
+            'only_matching': True,
+        }
     ]
 
     def _real_extract(self, url):

youtube_dl/extractor/mtv.py

@@ -118,6 +118,14 @@ class MTVServicesInfoExtractor(InfoExtractor):
         mediagen_doc = self._download_xml(mediagen_url, video_id,
                                           'Downloading video urls')
 
+        item = mediagen_doc.find('./video/item')
+        if item is not None and item.get('type') == 'text':
+            message = '%s returned error: ' % self.IE_NAME
+            if item.get('code') is not None:
+                message += '%s - ' % item.get('code')
+            message += item.text
+            raise ExtractorError(message, expected=True)
+
         description_node = itemdoc.find('description')
         if description_node is not None:
             description = description_node.text.strip()

youtube_dl/extractor/nbc.py

@@ -14,7 +14,7 @@ from ..utils import (
 
 
 class NBCIE(InfoExtractor):
-    _VALID_URL = r'http://www\.nbc\.com/(?:[^/]+/)+(?P<id>n?\d+)'
+    _VALID_URL = r'https?://www\.nbc\.com/(?:[^/]+/)+(?P<id>n?\d+)'
 
     _TESTS = [
         {
@@ -50,6 +50,57 @@ class NBCIE(InfoExtractor):
         return self.url_result(theplatform_url)
 
 
+class NBCSportsVPlayerIE(InfoExtractor):
+    _VALID_URL = r'https?://vplayer\.nbcsports\.com/(?:[^/]+/)+(?P<id>[0-9a-zA-Z_]+)'
+
+    _TESTS = [{
+        'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_share/select/9CsDKds0kvHI',
+        'info_dict': {
+            'id': '9CsDKds0kvHI',
+            'ext': 'flv',
+            'description': 'md5:df390f70a9ba7c95ff1daace988f0d8d',
+            'title': 'Tyler Kalinoski hits buzzer-beater to lift Davidson',
+        }
+    }, {
+        'url': 'http://vplayer.nbcsports.com/p/BxmELC/nbc_embedshare/select/_hqLjQ95yx8Z',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_url(webpage):
+        iframe_m = re.search(
+            r'<iframe[^>]+src="(?P<url>https?://vplayer\.nbcsports\.com/[^"]+)"', webpage)
+        if iframe_m:
+            return iframe_m.group('url')
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        theplatform_url = self._og_search_video_url(webpage)
+        return self.url_result(theplatform_url, 'ThePlatform')
+
+
+class NBCSportsIE(InfoExtractor):
+    # Does not include https becuase its certificate is invalid
+    _VALID_URL = r'http://www\.nbcsports\.com//?(?:[^/]+/)+(?P<id>[0-9a-z-]+)'
+
+    _TEST = {
+        'url': 'http://www.nbcsports.com//college-basketball/ncaab/tom-izzo-michigan-st-has-so-much-respect-duke',
+        'info_dict': {
+            'id': 'PHJSaFWbrTY9',
+            'ext': 'flv',
+            'title': 'Tom Izzo, Michigan St. has \'so much respect\' for Duke',
+            'description': 'md5:ecb459c9d59e0766ac9c7d5d0eda8113',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        return self.url_result(
+            NBCSportsVPlayerIE._extract_url(webpage), 'NBCSportsVPlayer')
+
+
 class NBCNewsIE(InfoExtractor):
     _VALID_URL = r'''(?x)https?://(?:www\.)?nbcnews\.com/
         (?:video/.+?/(?P<id>\d+)|

youtube_dl/extractor/niconico.py

@@ -22,7 +22,7 @@ class NiconicoIE(InfoExtractor):
     IE_NAME = 'niconico'
     IE_DESC = 'ニコニコ動画'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.nicovideo.jp/watch/sm22312215',
         'md5': 'd1a75c0823e2f629128c43e1212760f9',
         'info_dict': {
@@ -39,9 +39,26 @@ class NiconicoIE(InfoExtractor):
             'username': 'ydl.niconico@gmail.com',
             'password': 'youtube-dl',
         },
-    }
+    }, {
+        'url': 'http://www.nicovideo.jp/watch/nm14296458',
+        'md5': '8db08e0158457cf852a31519fceea5bc',
+        'info_dict': {
+            'id': 'nm14296458',
+            'ext': 'swf',
+            'title': '【鏡音リン】Dance on media【オリジナル】take2!',
+            'description': 'md5:',
+            'uploader': 'りょうた',
+            'uploader_id': '18822557',
+            'upload_date': '20110429',
+            'duration': 209,
+        },
+        'params': {
+            'username': 'ydl.niconico@gmail.com',
+            'password': 'youtube-dl',
+        },
+    }]
 
-    _VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/((?:[a-z]{2})?[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/(?P<id>(?:[a-z]{2})?[0-9]+)'
     _NETRC_MACHINE = 'niconico'
     # Determine whether the downloader used authentication to download video
     _AUTHENTICATED = False
@@ -76,8 +93,7 @@ class NiconicoIE(InfoExtractor):
         return True
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
+        video_id = self._match_id(url)
 
         # Get video webpage. We are not actually interested in it, but need
         # the cookies in order to be able to download the info webpage
@@ -90,7 +106,7 @@ class NiconicoIE(InfoExtractor):
         if self._AUTHENTICATED:
             # Get flv info
             flv_info_webpage = self._download_webpage(
-                'http://flapi.nicovideo.jp/api/getflv?v=' + video_id,
+                'http://flapi.nicovideo.jp/api/getflv/' + video_id + '?as3=1',
                 video_id, 'Downloading flv info')
         else:
             # Get external player info

youtube_dl/extractor/npo.py

@@ -219,7 +219,8 @@ class NPOLiveIE(NPOBaseIE):
         if streams:
             for stream in streams:
                 stream_type = stream.get('type').lower()
-                if stream_type == 'ss':
+                # smooth streaming is not supported
+                if stream_type in ['ss', 'ms']:
                     continue
                 stream_info = self._download_json(
                     'http://ida.omroep.nl/aapi/?stream=%s&token=%s&type=jsonp'
@@ -230,7 +231,10 @@ class NPOLiveIE(NPOBaseIE):
                 stream_url = self._download_json(
                     stream_info['stream'], display_id,
                     'Downloading %s URL' % stream_type,
-                    transform_source=strip_jsonp)
+                    'Unable to download %s URL' % stream_type,
+                    transform_source=strip_jsonp, fatal=False)
+                if not stream_url:
+                    continue
                 if stream_type == 'hds':
                     f4m_formats = self._extract_f4m_formats(stream_url, display_id)
                     # f4m downloader downloads only piece of live stream
@@ -242,6 +246,7 @@ class NPOLiveIE(NPOBaseIE):
                 else:
                     formats.append({
                         'url': stream_url,
+                        'preference': -10,
                     })
 
         self._sort_formats(formats)

youtube_dl/extractor/nrk.py

@@ -14,46 +14,48 @@ from ..utils import (
 
 
 class NRKIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?nrk\.no/(?:video|lyd)/[^/]+/(?P<id>[\dA-F]{16})'
+    _VALID_URL = r'(?:nrk:|http://(?:www\.)?nrk\.no/video/PS\*)(?P<id>\d+)'
 
     _TESTS = [
         {
-            'url': 'http://www.nrk.no/video/dompap_og_andre_fugler_i_piip_show/D0FA54B5C8B6CE59/emne/piipshow/',
-            'md5': 'a6eac35052f3b242bb6bb7f43aed5886',
+            'url': 'http://www.nrk.no/video/PS*150533',
+            'md5': 'bccd850baebefe23b56d708a113229c2',
             'info_dict': {
                 'id': '150533',
                 'ext': 'flv',
                 'title': 'Dompap og andre fugler i Piip-Show',
-                'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f'
+                'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
+                'duration': 263,
             }
         },
         {
-            'url': 'http://www.nrk.no/lyd/lyd_av_oppleser_for_blinde/AEFDDD5473BA0198/',
-            'md5': '3471f2a51718195164e88f46bf427668',
+            'url': 'http://www.nrk.no/video/PS*154915',
+            'md5': '0b1493ba1aae7d9579a5ad5531bc395a',
             'info_dict': {
                 'id': '154915',
                 'ext': 'flv',
                 'title': 'Slik høres internett ut når du er blind',
                 'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
+                'duration': 20,
             }
         },
     ]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
-        page = self._download_webpage(url, video_id)
-
-        video_id = self._html_search_regex(r'<div class="nrk-video" data-nrk-id="(\d+)">', page, 'video id')
+        video_id = self._match_id(url)
 
         data = self._download_json(
-            'http://v7.psapi.nrk.no/mediaelement/%s' % video_id, video_id, 'Downloading media JSON')
+            'http://v8.psapi.nrk.no/mediaelement/%s' % video_id,
+            video_id, 'Downloading media JSON')
 
         if data['usageRights']['isGeoBlocked']:
-            raise ExtractorError('NRK har ikke rettig-heter til å vise dette programmet utenfor Norge', expected=True)
+            raise ExtractorError(
+                'NRK har ikke rettig-heter til å vise dette programmet utenfor Norge',
+                expected=True)
 
-        video_url = data['mediaUrl'] + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124'
+        video_url = data['mediaUrl'] + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81'
+
+        duration = parse_duration(data.get('duration'))
 
         images = data.get('images')
         if images:
@@ -69,10 +71,51 @@ class NRKIE(InfoExtractor):
             'ext': 'flv',
             'title': data['title'],
             'description': data['description'],
+            'duration': duration,
             'thumbnail': thumbnail,
         }
 
 
+class NRKPlaylistIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?nrk\.no/(?!video)(?:[^/]+/)+(?P<id>[^/]+)'
+
+    _TESTS = [{
+        'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
+        'info_dict': {
+            'id': 'gjenopplev-den-historiske-solformorkelsen-1.12270763',
+            'title': 'Gjenopplev den historiske solformørkelsen',
+            'description': 'md5:c2df8ea3bac5654a26fc2834a542feed',
+        },
+        'playlist_count': 2,
+    }, {
+        'url': 'http://www.nrk.no/kultur/bok/rivertonprisen-til-karin-fossum-1.12266449',
+        'info_dict': {
+            'id': 'rivertonprisen-til-karin-fossum-1.12266449',
+            'title': 'Rivertonprisen til Karin Fossum',
+            'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.',
+        },
+        'playlist_count': 5,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        entries = [
+            self.url_result('nrk:%s' % video_id, 'NRK')
+            for video_id in re.findall(
+                r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"',
+                webpage)
+        ]
+
+        playlist_title = self._og_search_title(webpage)
+        playlist_description = self._og_search_description(webpage)
+
+        return self.playlist_result(
+            entries, playlist_id, playlist_title, playlist_description)
+
+
 class NRKTVIE(InfoExtractor):
     _VALID_URL = r'(?P<baseurl>http://tv\.nrk(?:super)?\.no/)(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?'
 
@@ -149,9 +192,6 @@ class NRKTVIE(InfoExtractor):
         }
     ]
 
-    def _seconds2str(self, s):
-        return '%02d:%02d:%02d.%03d' % (s / 3600, (s % 3600) / 60, s % 60, (s % 1) * 1000)
-
     def _debug_print(self, txt):
         if self._downloader.params.get('verbose', False):
             self.to_screen('[debug] %s' % txt)
@@ -168,8 +208,8 @@ class NRKTVIE(InfoExtractor):
         for pos, p in enumerate(ps):
             begin = parse_duration(p.get('begin'))
             duration = parse_duration(p.get('dur'))
-            starttime = self._seconds2str(begin)
-            endtime = self._seconds2str(begin + duration)
+            starttime = self._subtitles_timecode(begin)
+            endtime = self._subtitles_timecode(begin + duration)
             srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (compat_str(pos), starttime, endtime, p.text)
         return {lang: [
             {'ext': 'ttml', 'url': url},

youtube_dl/extractor/nytimes.py

@@ -1,15 +1,17 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..utils import parse_iso8601
+from ..utils import (
+    float_or_none,
+    int_or_none,
+    parse_iso8601,
+)
 
 
 class NYTimesIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?nytimes\.com/video/(?:[^/]+/)+(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:(?:www\.)?nytimes\.com/video/(?:[^/]+/)+?|graphics8\.nytimes\.com/bcvideo/\d+(?:\.\d+)?/iframe/embed\.html\?videoId=)(?P<id>\d+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.nytimes.com/video/opinion/100000002847155/verbatim-what-is-a-photocopier.html?playlistId=100000001150263',
         'md5': '18a525a510f942ada2720db5f31644c0',
         'info_dict': {
@@ -22,18 +24,21 @@ class NYTimesIE(InfoExtractor):
             'uploader': 'Brett Weiner',
             'duration': 419,
         }
-    }
+    }, {
+        'url': 'http://www.nytimes.com/video/travel/100000003550828/36-hours-in-dubai.html',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         video_data = self._download_json(
-            'http://www.nytimes.com/svc/video/api/v2/video/%s' % video_id, video_id, 'Downloading video JSON')
+            'http://www.nytimes.com/svc/video/api/v2/video/%s' % video_id,
+            video_id, 'Downloading video JSON')
 
         title = video_data['headline']
-        description = video_data['summary']
-        duration = video_data['duration'] / 1000.0
+        description = video_data.get('summary')
+        duration = float_or_none(video_data.get('duration'), 1000)
 
         uploader = video_data['byline']
         timestamp = parse_iso8601(video_data['publication_date'][:-8])
@@ -49,11 +54,11 @@ class NYTimesIE(InfoExtractor):
         formats = [
             {
                 'url': video['url'],
-                'format_id': video['type'],
-                'vcodec': video['video_codec'],
-                'width': video['width'],
-                'height': video['height'],
-                'filesize': get_file_size(video['fileSize']),
+                'format_id': video.get('type'),
+                'vcodec': video.get('video_codec'),
+                'width': int_or_none(video.get('width')),
+                'height': int_or_none(video.get('height')),
+                'filesize': get_file_size(video.get('fileSize')),
             } for video in video_data['renditions']
         ]
         self._sort_formats(formats)
@@ -61,7 +66,8 @@ class NYTimesIE(InfoExtractor):
         thumbnails = [
             {
                 'url': 'http://www.nytimes.com/%s' % image['url'],
-                'resolution': '%dx%d' % (image['width'], image['height']),
+                'width': int_or_none(image.get('width')),
+                'height': int_or_none(image.get('height')),
             } for image in video_data['images']
         ]
 

youtube_dl/extractor/orf.py

@@ -11,6 +11,11 @@ from ..utils import (
     HEADRequest,
     unified_strdate,
     ExtractorError,
+    strip_jsonp,
+    int_or_none,
+    float_or_none,
+    determine_ext,
+    remove_end,
 )
 
 
@@ -197,3 +202,92 @@ class ORFFM4IE(InfoExtractor):
             'description': data['subtitle'],
             'entries': entries
         }
+
+
+class ORFIPTVIE(InfoExtractor):
+    IE_NAME = 'orf:iptv'
+    IE_DESC = 'iptv.ORF.at'
+    _VALID_URL = r'http://iptv\.orf\.at/(?:#/)?stories/(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://iptv.orf.at/stories/2267952',
+        'md5': '26ffa4bab6dbce1eee78bbc7021016cd',
+        'info_dict': {
+            'id': '339775',
+            'ext': 'flv',
+            'title': 'Kreml-Kritiker Nawalny wieder frei',
+            'description': 'md5:6f24e7f546d364dacd0e616a9e409236',
+            'duration': 84.729,
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'upload_date': '20150306',
+        },
+    }
+
+    def _real_extract(self, url):
+        story_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            'http://iptv.orf.at/stories/%s' % story_id, story_id)
+
+        video_id = self._search_regex(
+            r'data-video(?:id)?="(\d+)"', webpage, 'video id')
+
+        data = self._download_json(
+            'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id,
+            video_id)[0]
+
+        duration = float_or_none(data['duration'], 1000)
+
+        video = data['sources']['default']
+        load_balancer_url = video['loadBalancerUrl']
+        abr = int_or_none(video.get('audioBitrate'))
+        vbr = int_or_none(video.get('bitrate'))
+        fps = int_or_none(video.get('videoFps'))
+        width = int_or_none(video.get('videoWidth'))
+        height = int_or_none(video.get('videoHeight'))
+        thumbnail = video.get('preview')
+
+        rendition = self._download_json(
+            load_balancer_url, video_id, transform_source=strip_jsonp)
+
+        f = {
+            'abr': abr,
+            'vbr': vbr,
+            'fps': fps,
+            'width': width,
+            'height': height,
+        }
+
+        formats = []
+        for format_id, format_url in rendition['redirect'].items():
+            if format_id == 'rtmp':
+                ff = f.copy()
+                ff.update({
+                    'url': format_url,
+                    'format_id': format_id,
+                })
+                formats.append(ff)
+            elif determine_ext(format_url) == 'f4m':
+                formats.extend(self._extract_f4m_formats(
+                    format_url, video_id, f4m_id=format_id))
+            elif determine_ext(format_url) == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, video_id, 'mp4', m3u8_id=format_id))
+            else:
+                continue
+        self._sort_formats(formats)
+
+        title = remove_end(self._og_search_title(webpage), ' - iptv.ORF.at')
+        description = self._og_search_description(webpage)
+        upload_date = unified_strdate(self._html_search_meta(
+            'dc.date', webpage, 'upload date'))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'thumbnail': thumbnail,
+            'upload_date': upload_date,
+            'formats': formats,
+        }

youtube_dl/extractor/phoenix.py

@@ -5,19 +5,33 @@ from .zdf import extract_from_xml_url
 
 
 class PhoenixIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?phoenix\.de/content/(?P<id>[0-9]+)'
-    _TEST = {
-        'url': 'http://www.phoenix.de/content/884301',
-        'md5': 'ed249f045256150c92e72dbb70eadec6',
-        'info_dict': {
-            'id': '884301',
-            'ext': 'mp4',
-            'title': 'Michael Krons mit Hans-Werner Sinn',
-            'description': 'Im Dialog - Sa. 25.10.14, 00.00 - 00.35 Uhr',
-            'upload_date': '20141025',
-            'uploader': 'Im Dialog',
-        }
-    }
+    _VALID_URL = r'''(?x)https?://(?:www\.)?phoenix\.de/content/
+        (?:
+            phoenix/die_sendungen/(?:[^/]+/)?
+        )?
+        (?P<id>[0-9]+)'''
+    _TESTS = [
+        {
+            'url': 'http://www.phoenix.de/content/884301',
+            'md5': 'ed249f045256150c92e72dbb70eadec6',
+            'info_dict': {
+                'id': '884301',
+                'ext': 'mp4',
+                'title': 'Michael Krons mit Hans-Werner Sinn',
+                'description': 'Im Dialog - Sa. 25.10.14, 00.00 - 00.35 Uhr',
+                'upload_date': '20141025',
+                'uploader': 'Im Dialog',
+            }
+        },
+        {
+            'url': 'http://www.phoenix.de/content/phoenix/die_sendungen/869815',
+            'only_matching': True,
+        },
+        {
+            'url': 'http://www.phoenix.de/content/phoenix/die_sendungen/diskussionen/928234',
+            'only_matching': True,
+        },
+    ]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

youtube_dl/extractor/pladform.py

@@ -0,0 +1,90 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    xpath_text,
+    qualities,
+)
+
+
+class PladformIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:
+                            (?:
+                                out\.pladform\.ru/player|
+                                static\.pladform\.ru/player\.swf
+                            )
+                            \?.*\bvideoid=|
+                            video\.pladform\.ru/catalog/video/videoid/
+                        )
+                        (?P<id>\d+)
+                    '''
+    _TESTS = [{
+        # http://muz-tv.ru/kinozal/view/7400/
+        'url': 'http://out.pladform.ru/player?pl=24822&videoid=100183293',
+        'md5': '61f37b575dd27f1bb2e1854777fe31f4',
+        'info_dict': {
+            'id': '100183293',
+            'ext': 'mp4',
+            'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
+            'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 694,
+            'age_limit': 0,
+        },
+    }, {
+        'url': 'http://static.pladform.ru/player.swf?pl=21469&videoid=100183293&vkcid=0',
+        'only_matching': True,
+    }, {
+        'url': 'http://video.pladform.ru/catalog/video/videoid/100183293/vkcid/0',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        video = self._download_xml(
+            'http://out.pladform.ru/getVideo?pl=1&videoid=%s' % video_id,
+            video_id)
+
+        if video.tag == 'error':
+            raise ExtractorError(
+                '%s returned error: %s' % (self.IE_NAME, video.text),
+                expected=True)
+
+        quality = qualities(('ld', 'sd', 'hd'))
+
+        formats = [{
+            'url': src.text,
+            'format_id': src.get('quality'),
+            'quality': quality(src.get('quality')),
+        } for src in video.findall('./src')]
+        self._sort_formats(formats)
+
+        webpage = self._download_webpage(
+            'http://video.pladform.ru/catalog/video/videoid/%s' % video_id,
+            video_id)
+
+        title = self._og_search_title(webpage, fatal=False) or xpath_text(
+            video, './/title', 'title', fatal=True)
+        description = self._search_regex(
+            r'</h3>\s*<p>([^<]+)</p>', webpage, 'description', fatal=False)
+        thumbnail = self._og_search_thumbnail(webpage) or xpath_text(
+            video, './/cover', 'cover')
+
+        duration = int_or_none(xpath_text(video, './/time', 'duration'))
+        age_limit = int_or_none(xpath_text(video, './/age18', 'age limit'))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'age_limit': age_limit,
+            'formats': formats,
+        }

youtube_dl/extractor/playfm.py

@@ -4,85 +4,72 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse,
-    compat_urllib_request,
-)
+from ..compat import compat_str
 from ..utils import (
     ExtractorError,
-    float_or_none,
     int_or_none,
-    str_to_int,
+    parse_iso8601,
 )
 
 
 class PlayFMIE(InfoExtractor):
     IE_NAME = 'play.fm'
-    _VALID_URL = r'https?://(?:www\.)?play\.fm/[^?#]*(?P<upload_date>[0-9]{8})(?P<id>[0-9]{6})(?:$|[?#])'
+    _VALID_URL = r'https?://(?:www\.)?play\.fm/(?P<slug>(?:[^/]+/)+(?P<id>[^/]+))/?(?:$|[?#])'
 
     _TEST = {
-        'url': 'http://www.play.fm/recording/leipzigelectronicmusicbatofarparis_fr20140712137220',
+        'url': 'https://www.play.fm/dan-drastic/sven-tasnadi-leipzig-electronic-music-batofar-paris-fr-2014-07-12',
         'md5': 'c505f8307825a245d0c7ad1850001f22',
         'info_dict': {
-            'id': '137220',
+            'id': '71276',
             'ext': 'mp3',
-            'title': 'LEIPZIG ELECTRONIC MUSIC @ Batofar (Paris,FR) - 2014-07-12',
-            'uploader': 'Sven Tasnadi',
-            'uploader_id': 'sventasnadi',
-            'duration': 5627.428,
-            'upload_date': '20140712',
+            'title': 'Sven Tasnadi - LEIPZIG ELECTRONIC MUSIC @ Batofar (Paris,FR) - 2014-07-12',
+            'description': '',
+            'duration': 5627,
+            'timestamp': 1406033781,
+            'upload_date': '20140722',
+            'uploader': 'Dan Drastic',
+            'uploader_id': '71170',
             'view_count': int,
             'comment_count': int,
-            'thumbnail': 're:^https?://.*\.jpg$',
         },
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        upload_date = mobj.group('upload_date')
+        slug = mobj.group('slug')
 
-        rec_data = compat_urllib_parse.urlencode({'rec_id': video_id})
-        req = compat_urllib_request.Request(
-            'http://www.play.fm/flexRead/recording', data=rec_data)
-        req.add_header('Content-Type', 'application/x-www-form-urlencoded')
-        rec_doc = self._download_xml(req, video_id)
+        recordings = self._download_json(
+            'http://v2api.play.fm/recordings/slug/%s' % slug, video_id)
 
-        error_node = rec_doc.find('./error')
-        if error_node is not None:
-            raise ExtractorError('An error occured: %s (code %s)' % (
-                error_node.text, rec_doc.find('./status').text))
+        error = recordings.get('error')
+        if isinstance(error, dict):
+            raise ExtractorError(
+                '%s returned error: %s' % (self.IE_NAME, error.get('message')),
+                expected=True)
 
-        recording = rec_doc.find('./recording')
-        title = recording.find('./title').text
-        view_count = str_to_int(recording.find('./stats/playcount').text)
-        comment_count = str_to_int(recording.find('./stats/comments').text)
-        duration = float_or_none(recording.find('./duration').text, scale=1000)
-        thumbnail = recording.find('./image').text
-
-        artist = recording.find('./artists/artist')
-        uploader = artist.find('./name').text
-        uploader_id = artist.find('./slug').text
-
-        video_url = '%s//%s/%s/%s/offset/0/sh/%s/rec/%s/jingle/%s/loc/%s' % (
-            'http:', recording.find('./url').text,
-            recording.find('./_class').text, recording.find('./file_id').text,
-            rec_doc.find('./uuid').text, video_id,
-            rec_doc.find('./jingle/file_id').text,
-            'http%3A%2F%2Fwww.play.fm%2Fplayer',
-        )
+        audio_url = recordings['audio']
+        video_id = compat_str(recordings.get('id') or video_id)
+        title = recordings['title']
+        description = recordings.get('description')
+        duration = int_or_none(recordings.get('recordingDuration'))
+        timestamp = parse_iso8601(recordings.get('created_at'))
+        uploader = recordings.get('page', {}).get('title')
+        uploader_id = compat_str(recordings.get('page', {}).get('id'))
+        view_count = int_or_none(recordings.get('playCount'))
+        comment_count = int_or_none(recordings.get('commentCount'))
+        categories = [tag['name'] for tag in recordings.get('tags', []) if tag.get('name')]
 
         return {
             'id': video_id,
-            'url': video_url,
-            'ext': 'mp3',
-            'filesize': int_or_none(recording.find('./size').text),
+            'url': audio_url,
             'title': title,
-            'upload_date': upload_date,
-            'view_count': view_count,
-            'comment_count': comment_count,
+            'description': description,
             'duration': duration,
-            'thumbnail': thumbnail,
+            'timestamp': timestamp,
             'uploader': uploader,
             'uploader_id': uploader_id,
+            'view_count': view_count,
+            'comment_count': comment_count,
+            'categories': categories,
         }

youtube_dl/extractor/playwire.py

@@ -0,0 +1,78 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    xpath_text,
+    float_or_none,
+    int_or_none,
+)
+
+
+class PlaywireIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:config|cdn)\.playwire\.com(?:/v2)?/(?P<publisher_id>\d+)/(?:videos/v2|embed|config)/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://config.playwire.com/14907/videos/v2/3353705/player.json',
+        'md5': 'e6398701e3595888125729eaa2329ed9',
+        'info_dict': {
+            'id': '3353705',
+            'ext': 'mp4',
+            'title': 'S04_RM_UCL_Rus',
+            'thumbnail': 're:^http://.*\.png$',
+            'duration': 145.94,
+        },
+    }, {
+        'url': 'http://cdn.playwire.com/11625/embed/85228.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://config.playwire.com/12421/videos/v2/3389892/zeus.json',
+        'only_matching': True,
+    }, {
+        'url': 'http://cdn.playwire.com/v2/12342/config/1532636.json',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        publisher_id, video_id = mobj.group('publisher_id'), mobj.group('id')
+
+        player = self._download_json(
+            'http://config.playwire.com/%s/videos/v2/%s/zeus.json' % (publisher_id, video_id),
+            video_id)
+
+        title = player['settings']['title']
+        duration = float_or_none(player.get('duration'), 1000)
+
+        content = player['content']
+        thumbnail = content.get('poster')
+        src = content['media']['f4m']
+
+        f4m = self._download_xml(src, video_id)
+        base_url = xpath_text(f4m, './{http://ns.adobe.com/f4m/1.0}baseURL', 'base url', fatal=True)
+        formats = []
+        for media in f4m.findall('./{http://ns.adobe.com/f4m/1.0}media'):
+            media_url = media.get('url')
+            if not media_url:
+                continue
+            tbr = int_or_none(media.get('bitrate'))
+            width = int_or_none(media.get('width'))
+            height = int_or_none(media.get('height'))
+            f = {
+                'url': '%s/%s' % (base_url, media.attrib['url']),
+                'tbr': tbr,
+                'width': width,
+                'height': height,
+            }
+            if not (tbr or width or height):
+                f['quality'] = 1 if '-hd.' in media_url else 0
+            formats.append(f)
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/pornhub.py

@@ -33,10 +33,8 @@ class PornHubIE(InfoExtractor):
     }
 
     def _extract_count(self, pattern, webpage, name):
-        count = self._html_search_regex(pattern, webpage, '%s count' % name, fatal=False)
-        if count:
-            count = str_to_int(count)
-        return count
+        return str_to_int(self._search_regex(
+            pattern, webpage, '%s count' % name, fatal=False))
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -62,11 +60,14 @@ class PornHubIE(InfoExtractor):
         if thumbnail:
             thumbnail = compat_urllib_parse.unquote(thumbnail)
 
-        view_count = self._extract_count(r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
-        like_count = self._extract_count(r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like')
-        dislike_count = self._extract_count(r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike')
+        view_count = self._extract_count(
+            r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
+        like_count = self._extract_count(
+            r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like')
+        dislike_count = self._extract_count(
+            r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike')
         comment_count = self._extract_count(
-            r'All comments \(<var class="videoCommentCount">([\d,\.]+)</var>', webpage, 'comment')
+            r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
 
         video_urls = list(map(compat_urllib_parse.unquote, re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage)))
         if webpage.find('"encrypted":true') != -1:

youtube_dl/extractor/pornovoisines.py

@@ -0,0 +1,96 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+import random
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    float_or_none,
+    unified_strdate,
+)
+
+
+class PornoVoisinesIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?pornovoisines\.com/showvideo/(?P<id>\d+)/(?P<display_id>[^/]+)'
+
+    _VIDEO_URL_TEMPLATE = 'http://stream%d.pornovoisines.com' \
+        '/static/media/video/transcoded/%s-640x360-1000-trscded.mp4'
+
+    _SERVER_NUMBERS = (1, 2)
+
+    _TEST = {
+        'url': 'http://www.pornovoisines.com/showvideo/1285/recherche-appartement/',
+        'md5': '5ac670803bc12e9e7f9f662ce64cf1d1',
+        'info_dict': {
+            'id': '1285',
+            'display_id': 'recherche-appartement',
+            'ext': 'mp4',
+            'title': 'Recherche appartement',
+            'description': 'md5:819ea0b785e2a04667a1a01cdc89594e',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'upload_date': '20140925',
+            'duration': 120,
+            'view_count': int,
+            'average_rating': float,
+            'categories': ['Débutante', 'Scénario', 'Sodomie'],
+            'age_limit': 18,
+        }
+    }
+
+    @classmethod
+    def build_video_url(cls, num):
+        return cls._VIDEO_URL_TEMPLATE % (random.choice(cls._SERVER_NUMBERS), num)
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_url = self.build_video_url(video_id)
+
+        title = self._html_search_regex(
+            r'<h1>(.+?)</h1>', webpage, 'title', flags=re.DOTALL)
+        description = self._html_search_regex(
+            r'<article id="descriptif">(.+?)</article>',
+            webpage, "description", fatal=False, flags=re.DOTALL)
+
+        thumbnail = self._search_regex(
+            r'<div id="mediaspace%s">\s*<img src="/?([^"]+)"' % video_id,
+            webpage, 'thumbnail', fatal=False)
+        if thumbnail:
+            thumbnail = 'http://www.pornovoisines.com/%s' % thumbnail
+
+        upload_date = unified_strdate(self._search_regex(
+            r'Publié le ([\d-]+)', webpage, 'upload date', fatal=False))
+        duration = int_or_none(self._search_regex(
+            'Durée (\d+)', webpage, 'duration', fatal=False))
+        view_count = int_or_none(self._search_regex(
+            r'(\d+) vues', webpage, 'view count', fatal=False))
+        average_rating = self._search_regex(
+            r'Note : (\d+,\d+)', webpage, 'average rating', fatal=False)
+        if average_rating:
+            average_rating = float_or_none(average_rating.replace(',', '.'))
+
+        categories = self._html_search_meta(
+            'keywords', webpage, 'categories', fatal=False)
+        if categories:
+            categories = [category.strip() for category in categories.split(',')]
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'url': video_url,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'upload_date': upload_date,
+            'duration': duration,
+            'view_count': view_count,
+            'average_rating': average_rating,
+            'categories': categories,
+            'age_limit': 18,
+        }

youtube_dl/extractor/primesharetv.py

@@ -0,0 +1,69 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_parse,
+    compat_urllib_request,
+)
+from ..utils import ExtractorError
+
+
+class PrimeShareTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?primeshare\.tv/download/(?P<id>[\da-zA-Z]+)'
+
+    _TEST = {
+        'url': 'http://primeshare.tv/download/238790B611',
+        'md5': 'b92d9bf5461137c36228009f31533fbc',
+        'info_dict': {
+            'id': '238790B611',
+            'ext': 'mp4',
+            'title': 'Public Domain - 1960s Commercial - Crest Toothpaste-YKsuFona',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        if '>File not exist<' in webpage:
+            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+
+        fields = dict(re.findall(r'''(?x)<input\s+
+            type="hidden"\s+
+            name="([^"]+)"\s+
+            (?:id="[^"]+"\s+)?
+            value="([^"]*)"
+            ''', webpage))
+
+        headers = {
+            'Referer': url,
+            'Content-Type': 'application/x-www-form-urlencoded',
+        }
+
+        wait_time = int(self._search_regex(
+            r'var\s+cWaitTime\s*=\s*(\d+)',
+            webpage, 'wait time', default=7)) + 1
+        self._sleep(wait_time, video_id)
+
+        req = compat_urllib_request.Request(
+            url, compat_urllib_parse.urlencode(fields), headers)
+        video_page = self._download_webpage(
+            req, video_id, 'Downloading video page')
+
+        video_url = self._search_regex(
+            r"url\s*:\s*'([^']+\.primeshare\.tv(?::443)?/file/[^']+)'",
+            video_page, 'video url')
+
+        title = self._html_search_regex(
+            r'<h1>Watch\s*(?:&nbsp;)?\s*\((.+?)(?:\s*\[\.\.\.\])?\)\s*(?:&nbsp;)?\s*<strong>',
+            video_page, 'title')
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'ext': 'mp4',
+        }

youtube_dl/extractor/prosiebensat1.py

@@ -10,6 +10,7 @@ from ..compat import (
 )
 from ..utils import (
     unified_strdate,
+    int_or_none,
 )
 
 
@@ -24,7 +25,7 @@ class ProSiebenSat1IE(InfoExtractor):
             'info_dict': {
                 'id': '2104602',
                 'ext': 'mp4',
-                'title': 'Staffel 2, Episode 18 - Jahresrückblick',
+                'title': 'Episode 18 - Staffel 2',
                 'description': 'md5:8733c81b702ea472e069bc48bb658fc1',
                 'upload_date': '20131231',
                 'duration': 5845.04,
@@ -266,6 +267,9 @@ class ProSiebenSat1IE(InfoExtractor):
             urls_sources = urls_sources.values()
 
         def fix_bitrate(bitrate):
+            bitrate = int_or_none(bitrate)
+            if not bitrate:
+                return None
             return (bitrate // 1000) if bitrate % 1000 == 0 else bitrate
 
         for source in urls_sources:

youtube_dl/extractor/qqmusic.py

@@ -0,0 +1,170 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import random
+import time
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    strip_jsonp,
+    unescapeHTML,
+)
+from ..compat import compat_urllib_request
+
+
+class QQMusicIE(InfoExtractor):
+    _VALID_URL = r'http://y.qq.com/#type=song&mid=(?P<id>[0-9A-Za-z]+)'
+    _TESTS = [{
+        'url': 'http://y.qq.com/#type=song&mid=004295Et37taLD',
+        'md5': 'bed90b6db2a7a7a7e11bc585f471f63a',
+        'info_dict': {
+            'id': '004295Et37taLD',
+            'ext': 'm4a',
+            'title': '可惜没如果',
+            'upload_date': '20141227',
+            'creator': '林俊杰',
+            'description': 'md5:4348ff1dd24036906baa7b6f973f8d30',
+        }
+    }]
+
+    # Reference: m_r_GetRUin() in top_player.js
+    # http://imgcache.gtimg.cn/music/portal_v3/y/top_player.js
+    @staticmethod
+    def m_r_get_ruin():
+        curMs = int(time.time() * 1000) % 1000
+        return int(round(random.random() * 2147483647) * curMs % 1E10)
+
+    def _real_extract(self, url):
+        mid = self._match_id(url)
+
+        detail_info_page = self._download_webpage(
+            'http://s.plcloud.music.qq.com/fcgi-bin/fcg_yqq_song_detail_info.fcg?songmid=%s&play=0' % mid,
+            mid, note='Download song detail info',
+            errnote='Unable to get song detail info', encoding='gbk')
+
+        song_name = self._html_search_regex(
+            r"songname:\s*'([^']+)'", detail_info_page, 'song name')
+
+        publish_time = self._html_search_regex(
+            r'发行时间：(\d{4}-\d{2}-\d{2})', detail_info_page,
+            'publish time', default=None)
+        if publish_time:
+            publish_time = publish_time.replace('-', '')
+
+        singer = self._html_search_regex(
+            r"singer:\s*'([^']+)", detail_info_page, 'singer', default=None)
+
+        lrc_content = self._html_search_regex(
+            r'<div class="content" id="lrc_content"[^<>]*>([^<>]+)</div>',
+            detail_info_page, 'LRC lyrics', default=None)
+
+        guid = self.m_r_get_ruin()
+
+        vkey = self._download_json(
+            'http://base.music.qq.com/fcgi-bin/fcg_musicexpress.fcg?json=3&guid=%s' % guid,
+            mid, note='Retrieve vkey', errnote='Unable to get vkey',
+            transform_source=strip_jsonp)['key']
+        song_url = 'http://cc.stream.qqmusic.qq.com/C200%s.m4a?vkey=%s&guid=%s&fromtag=0' % (mid, vkey, guid)
+
+        return {
+            'id': mid,
+            'url': song_url,
+            'title': song_name,
+            'upload_date': publish_time,
+            'creator': singer,
+            'description': lrc_content,
+        }
+
+
+class QQPlaylistBaseIE(InfoExtractor):
+    @staticmethod
+    def qq_static_url(category, mid):
+        return 'http://y.qq.com/y/static/%s/%s/%s/%s.html' % (category, mid[-2], mid[-1], mid)
+
+    @classmethod
+    def get_entries_from_page(cls, page):
+        entries = []
+
+        for item in re.findall(r'class="data"[^<>]*>([^<>]+)</', page):
+            song_mid = unescapeHTML(item).split('|')[-5]
+            entries.append(cls.url_result(
+                'http://y.qq.com/#type=song&mid=' + song_mid, 'QQMusic',
+                song_mid))
+
+        return entries
+
+
+class QQMusicSingerIE(QQPlaylistBaseIE):
+    _VALID_URL = r'http://y.qq.com/#type=singer&mid=(?P<id>[0-9A-Za-z]+)'
+    _TEST = {
+        'url': 'http://y.qq.com/#type=singer&mid=001BLpXF2DyJe2',
+        'info_dict': {
+            'id': '001BLpXF2DyJe2',
+            'title': '林俊杰',
+            'description': 'md5:2a222d89ba4455a3af19940c0481bb78',
+        },
+        'playlist_count': 12,
+    }
+
+    def _real_extract(self, url):
+        mid = self._match_id(url)
+
+        singer_page = self._download_webpage(
+            self.qq_static_url('singer', mid), mid, 'Download singer page')
+
+        entries = self.get_entries_from_page(singer_page)
+
+        singer_name = self._html_search_regex(
+            r"singername\s*:\s*'([^']+)'", singer_page, 'singer name',
+            default=None)
+
+        singer_id = self._html_search_regex(
+            r"singerid\s*:\s*'([0-9]+)'", singer_page, 'singer id',
+            default=None)
+
+        singer_desc = None
+
+        if singer_id:
+            req = compat_urllib_request.Request(
+                'http://s.plcloud.music.qq.com/fcgi-bin/fcg_get_singer_desc.fcg?utf8=1&outCharset=utf-8&format=xml&singerid=%s' % singer_id)
+            req.add_header(
+                'Referer', 'http://s.plcloud.music.qq.com/xhr_proxy_utf8.html')
+            singer_desc_page = self._download_xml(
+                req, mid, 'Donwload singer description XML')
+
+            singer_desc = singer_desc_page.find('./data/info/desc').text
+
+        return self.playlist_result(entries, mid, singer_name, singer_desc)
+
+
+class QQMusicAlbumIE(QQPlaylistBaseIE):
+    _VALID_URL = r'http://y.qq.com/#type=album&mid=(?P<id>[0-9A-Za-z]+)'
+
+    _TEST = {
+        'url': 'http://y.qq.com/#type=album&mid=000gXCTb2AhRR1&play=0',
+        'info_dict': {
+            'id': '000gXCTb2AhRR1',
+            'title': '我们都是这样长大的',
+            'description': 'md5:d216c55a2d4b3537fe4415b8767d74d6',
+        },
+        'playlist_count': 4,
+    }
+
+    def _real_extract(self, url):
+        mid = self._match_id(url)
+
+        album_page = self._download_webpage(
+            self.qq_static_url('album', mid), mid, 'Download album page')
+
+        entries = self.get_entries_from_page(album_page)
+
+        album_name = self._html_search_regex(
+            r"albumname\s*:\s*'([^']+)',", album_page, 'album name',
+            default=None)
+
+        album_detail = self._html_search_regex(
+            r'<div class="album_detail close_detail">\s*<p>((?:[^<>]+(?:<br />)?)+)</p>',
+            album_page, 'album details', default=None)
+
+        return self.playlist_result(entries, mid, album_name, album_detail)

youtube_dl/extractor/radiojavan.py

@@ -0,0 +1,67 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import(
+    unified_strdate,
+    str_to_int,
+)
+
+
+class RadioJavanIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?radiojavan\.com/videos/video/(?P<id>[^/]+)/?'
+    _TEST = {
+        'url': 'http://www.radiojavan.com/videos/video/chaartaar-ashoobam',
+        'md5': 'e85208ffa3ca8b83534fca9fe19af95b',
+        'info_dict': {
+            'id': 'chaartaar-ashoobam',
+            'ext': 'mp4',
+            'title': 'Chaartaar - Ashoobam',
+            'thumbnail': 're:^https?://.*\.jpe?g$',
+            'upload_date': '20150215',
+            'view_count': int,
+            'like_count': int,
+            'dislike_count': int,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        formats = [{
+            'url': 'https://media.rdjavan.com/media/music_video/%s' % video_path,
+            'format_id': '%sp' % height,
+            'height': int(height),
+        } for height, video_path in re.findall(r"RJ\.video(\d+)p\s*=\s*'/?([^']+)'", webpage)]
+        self._sort_formats(formats)
+
+        title = self._og_search_title(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        upload_date = unified_strdate(self._search_regex(
+            r'class="date_added">Date added: ([^<]+)<',
+            webpage, 'upload date', fatal=False))
+
+        view_count = str_to_int(self._search_regex(
+            r'class="views">Plays: ([\d,]+)',
+            webpage, 'view count', fatal=False))
+        like_count = str_to_int(self._search_regex(
+            r'class="rating">([\d,]+) likes',
+            webpage, 'like count', fatal=False))
+        dislike_count = str_to_int(self._search_regex(
+            r'class="rating">([\d,]+) dislikes',
+            webpage, 'dislike count', fatal=False))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'upload_date': upload_date,
+            'view_count': view_count,
+            'like_count': like_count,
+            'dislike_count': dislike_count,
+            'formats': formats,
+        }

youtube_dl/extractor/rai.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 
 class RaiIE(InfoExtractor):
-    _VALID_URL = r'(?P<url>http://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it)/dl/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html)'
+    _VALID_URL = r'(?P<url>(?P<host>http://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it))/dl/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html)'
     _TESTS = [
         {
             'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
@@ -62,34 +62,78 @@ class RaiIE(InfoExtractor):
                 'description': 'Edizione delle ore 20:30 ',
             }
         },
+        {
+            'url': 'http://www.ilcandidato.rai.it/dl/ray/media/Il-Candidato---Primo-episodio-Le-Primarie-28e5525a-b495-45e8-a7c3-bc48ba45d2b6.html',
+            'md5': '02b64456f7cc09f96ff14e7dd489017e',
+            'info_dict': {
+                'id': '28e5525a-b495-45e8-a7c3-bc48ba45d2b6',
+                'ext': 'flv',
+                'title': 'Il Candidato - Primo episodio: "Le Primarie"',
+                'description': 'Primo appuntamento con "Il candidato" con Filippo Timi, alias Piero Zucca presidente!',
+                'uploader': 'RaiTre',
+            }
+        }
     ]
 
+    def _extract_relinker_url(self, webpage):
+        return self._proto_relative_url(self._search_regex(
+            [r'name="videourl" content="([^"]+)"', r'var\s+videoURL(?:_MP4)?\s*=\s*"([^"]+)"'],
+            webpage, 'relinker url', default=None))
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
+        host = mobj.group('host')
 
-        media = self._download_json('%s?json' % mobj.group('url'), video_id, 'Downloading video JSON')
+        webpage = self._download_webpage(url, video_id)
 
-        title = media.get('name')
-        description = media.get('desc')
-        thumbnail = media.get('image_300') or media.get('image_medium') or media.get('image')
-        duration = parse_duration(media.get('length'))
-        uploader = media.get('author')
-        upload_date = unified_strdate(media.get('date'))
+        relinker_url = self._extract_relinker_url(webpage)
 
-        formats = []
+        if not relinker_url:
+            iframe_path = self._search_regex(
+                r'<iframe[^>]+src="/?(dl/[^"]+\?iframe\b[^"]*)"',
+                webpage, 'iframe')
+            webpage = self._download_webpage(
+                '%s/%s' % (host, iframe_path), video_id)
+            relinker_url = self._extract_relinker_url(webpage)
 
-        for format_id in ['wmv', 'm3u8', 'mediaUri', 'h264']:
-            media_url = media.get(format_id)
-            if not media_url:
-                continue
-            formats.append({
+        relinker = self._download_json(
+            '%s&output=47' % relinker_url, video_id)
+
+        media_url = relinker['video'][0]
+        ct = relinker.get('ct')
+        if ct == 'f4m':
+            formats = self._extract_f4m_formats(
+                media_url + '&hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id)
+        else:
+            formats = [{
                 'url': media_url,
-                'format_id': format_id,
-                'ext': 'mp4',
-            })
+                'format_id': ct,
+            }]
 
-        subtitles = self.extract_subtitles(video_id, url)
+        json_link = self._html_search_meta(
+            'jsonlink', webpage, 'JSON link', default=None)
+        if json_link:
+            media = self._download_json(
+                host + json_link, video_id, 'Downloading video JSON')
+            title = media.get('name')
+            description = media.get('desc')
+            thumbnail = media.get('image_300') or media.get('image_medium') or media.get('image')
+            duration = parse_duration(media.get('length'))
+            uploader = media.get('author')
+            upload_date = unified_strdate(media.get('date'))
+        else:
+            title = (self._search_regex(
+                r'var\s+videoTitolo\s*=\s*"(.+?)";',
+                webpage, 'title', default=None) or self._og_search_title(webpage)).replace('\\"', '"')
+            description = self._og_search_description(webpage)
+            thumbnail = self._og_search_thumbnail(webpage)
+            duration = None
+            uploader = self._html_search_meta('Editore', webpage, 'uploader')
+            upload_date = unified_strdate(self._html_search_meta(
+                'item-date', webpage, 'upload date', default=None))
+
+        subtitles = self.extract_subtitles(video_id, webpage)
 
         return {
             'id': video_id,
@@ -103,8 +147,7 @@ class RaiIE(InfoExtractor):
             'subtitles': subtitles,
         }
 
-    def _get_subtitles(self, video_id, url):
-        webpage = self._download_webpage(url, video_id)
+    def _get_subtitles(self, video_id, webpage):
         subtitles = {}
         m = re.search(r'<meta name="closedcaption" content="(?P<captions>[^"]+)"', webpage)
         if m:

youtube_dl/extractor/redtube.py

@@ -1,17 +1,19 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..utils import ExtractorError
 
 
 class RedTubeIE(InfoExtractor):
     _VALID_URL = r'http://(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
     _TEST = {
         'url': 'http://www.redtube.com/66418',
+        'md5': '7b8c22b5e7098a3e1c09709df1126d2d',
         'info_dict': {
             'id': '66418',
             'ext': 'mp4',
-            "title": "Sucked on a toilet",
-            "age_limit": 18,
+            'title': 'Sucked on a toilet',
+            'age_limit': 18,
         }
     }
 
@@ -19,6 +21,9 @@ class RedTubeIE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
+        if any(s in webpage for s in ['video-deleted-info', '>This video has been removed']):
+            raise ExtractorError('Video %s has been removed' % video_id, expected=True)
+
         video_url = self._html_search_regex(
             r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL')
         video_title = self._html_search_regex(

youtube_dl/extractor/rtve.py

@@ -8,8 +8,10 @@ import time
 from .common import InfoExtractor
 from ..compat import compat_urlparse
 from ..utils import (
+    ExtractorError,
     float_or_none,
     remove_end,
+    std_headers,
     struct_unpack,
 )
 
@@ -84,13 +86,22 @@ class RTVEALaCartaIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    def _real_initialize(self):
+        user_agent_b64 = base64.b64encode(std_headers['User-Agent'].encode('utf-8')).decode('utf-8')
+        manager_info = self._download_json(
+            'http://www.rtve.es/odin/loki/' + user_agent_b64,
+            None, 'Fetching manager info')
+        self._manager = manager_info['manager']
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         info = self._download_json(
             'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
             video_id)['page']['items'][0]
-        png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % video_id
+        if info['state'] == 'DESPU':
+            raise ExtractorError('The video is no longer available', expected=True)
+        png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id)
         png = self._download_webpage(png_url, video_id, 'Downloading url information')
         video_url = _decrypt_url(png)
         if not video_url.endswith('.f4m'):
@@ -127,6 +138,47 @@ class RTVEALaCartaIE(InfoExtractor):
             for s in subs)
 
 
+class RTVEInfantilIE(InfoExtractor):
+    IE_NAME = 'rtve.es:infantil'
+    IE_DESC = 'RTVE infantil'
+    _VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/(?P<show>[^/]*)/video/(?P<short_title>[^/]*)/(?P<id>[0-9]+)/'
+
+    _TESTS = [{
+        'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/',
+        'md5': '915319587b33720b8e0357caaa6617e6',
+        'info_dict': {
+            'id': '3040283',
+            'ext': 'mp4',
+            'title': 'Maneras de vivir',
+            'thumbnail': 'http://www.rtve.es/resources/jpg/6/5/1426182947956.JPG',
+            'duration': 357.958,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        info = self._download_json(
+            'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
+            video_id)['page']['items'][0]
+
+        webpage = self._download_webpage(url, video_id)
+        vidplayer_id = self._search_regex(
+            r' id="vidplayer([0-9]+)"', webpage, 'internal video ID')
+
+        png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id
+        png = self._download_webpage(png_url, video_id, 'Downloading url information')
+        video_url = _decrypt_url(png)
+
+        return {
+            'id': video_id,
+            'ext': 'mp4',
+            'title': info['title'],
+            'url': video_url,
+            'thumbnail': info.get('image'),
+            'duration': float_or_none(info.get('duration'), scale=1000),
+        }
+
+
 class RTVELiveIE(InfoExtractor):
     IE_NAME = 'rtve.es:live'
     IE_DESC = 'RTVE.es live streams'

youtube_dl/extractor/safari.py

@@ -0,0 +1,157 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from .brightcove import BrightcoveIE
+
+from ..compat import (
+    compat_urllib_parse,
+    compat_urllib_request,
+)
+from ..utils import (
+    ExtractorError,
+    smuggle_url,
+    std_headers,
+)
+
+
+class SafariBaseIE(InfoExtractor):
+    _LOGIN_URL = 'https://www.safaribooksonline.com/accounts/login/'
+    _SUCCESSFUL_LOGIN_REGEX = r'<a href="/accounts/logout/"[^>]*>Sign Out</a>'
+    _ACCOUNT_CREDENTIALS_HINT = 'Use --username and --password options to supply credentials for safaribooksonline.com'
+    _NETRC_MACHINE = 'safari'
+
+    _API_BASE = 'https://www.safaribooksonline.com/api/v1/book'
+    _API_FORMAT = 'json'
+
+    LOGGED_IN = False
+
+    def _real_initialize(self):
+        # We only need to log in once for courses or individual videos
+        if not self.LOGGED_IN:
+            self._login()
+            SafariBaseIE.LOGGED_IN = True
+
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            raise ExtractorError(
+                self._ACCOUNT_CREDENTIALS_HINT,
+                expected=True)
+
+        headers = std_headers
+        if 'Referer' not in headers:
+            headers['Referer'] = self._LOGIN_URL
+
+        login_page = self._download_webpage(
+            self._LOGIN_URL, None,
+            'Downloading login form')
+
+        csrf = self._html_search_regex(
+            r"name='csrfmiddlewaretoken'\s+value='([^']+)'",
+            login_page, 'csrf token')
+
+        login_form = {
+            'csrfmiddlewaretoken': csrf,
+            'email': username,
+            'password1': password,
+            'login': 'Sign In',
+            'next': '',
+        }
+
+        request = compat_urllib_request.Request(
+            self._LOGIN_URL, compat_urllib_parse.urlencode(login_form), headers=headers)
+        login_page = self._download_webpage(
+            request, None, 'Logging in as %s' % username)
+
+        if re.search(self._SUCCESSFUL_LOGIN_REGEX, login_page) is None:
+            raise ExtractorError(
+                'Login failed; make sure your credentials are correct and try again.',
+                expected=True)
+
+        self.to_screen('Login successful')
+
+
+class SafariIE(SafariBaseIE):
+    IE_NAME = 'safari'
+    IE_DESC = 'safaribooksonline.com online video'
+    _VALID_URL = r'''(?x)https?://
+                            (?:www\.)?safaribooksonline\.com/
+                                (?:
+                                    library/view/[^/]+|
+                                    api/v1/book
+                                )/
+                                (?P<course_id>\d+)/
+                                    (?:chapter(?:-content)?/)?
+                                (?P<part>part\d+)\.html
+    '''
+
+    _TESTS = [{
+        'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
+        'md5': '5b0c4cc1b3c1ba15dda7344085aa5592',
+        'info_dict': {
+            'id': '2842601850001',
+            'ext': 'mp4',
+            'title': 'Introduction',
+        },
+        'skip': 'Requires safaribooksonline account credentials',
+    }, {
+        'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        course_id = mobj.group('course_id')
+        part = mobj.group('part')
+
+        webpage = self._download_webpage(
+            '%s/%s/chapter-content/%s.html' % (self._API_BASE, course_id, part),
+            part)
+
+        bc_url = BrightcoveIE._extract_brightcove_url(webpage)
+        if not bc_url:
+            raise ExtractorError('Could not extract Brightcove URL from %s' % url, expected=True)
+
+        return self.url_result(smuggle_url(bc_url, {'Referer': url}), 'Brightcove')
+
+
+class SafariCourseIE(SafariBaseIE):
+    IE_NAME = 'safari:course'
+    IE_DESC = 'safaribooksonline.com online courses'
+
+    _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)/(?P<id>\d+)/?(?:[#?]|$)'
+
+    _TESTS = [{
+        'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
+        'info_dict': {
+            'id': '9780133392838',
+            'title': 'Hadoop Fundamentals LiveLessons',
+        },
+        'playlist_count': 22,
+        'skip': 'Requires safaribooksonline account credentials',
+    }, {
+        'url': 'https://www.safaribooksonline.com/api/v1/book/9781449396459/?override_format=json',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        course_id = self._match_id(url)
+
+        course_json = self._download_json(
+            '%s/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT),
+            course_id, 'Downloading course JSON')
+
+        if 'chapters' not in course_json:
+            raise ExtractorError(
+                'No chapters found for course %s' % course_id, expected=True)
+
+        entries = [
+            self.url_result(chapter, 'Safari')
+            for chapter in course_json['chapters']]
+
+        course_title = course_json['title']
+
+        return self.playlist_result(entries, course_id, course_title)

youtube_dl/extractor/slideshare.py

@@ -30,7 +30,7 @@ class SlideshareIE(InfoExtractor):
         page_title = mobj.group('title')
         webpage = self._download_webpage(url, page_title)
         slideshare_obj = self._search_regex(
-            r'var\s+slideshare_object\s*=\s*({.*?});\s*var\s+user_info\s*=',
+            r'\$\.extend\(slideshare_object,\s*(\{.*?\})\);',
             webpage, 'slideshare object')
         info = json.loads(slideshare_obj)
         if info['slideshow']['type'] != 'video':

youtube_dl/extractor/sohu.py

@@ -4,22 +4,87 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from .common import compat_str
+from ..compat import (
+    compat_str,
+    compat_urllib_request
+)
+from ..utils import sanitize_url_path_consecutive_slashes
 
 
 class SohuIE(InfoExtractor):
     _VALID_URL = r'https?://(?P<mytv>my\.)?tv\.sohu\.com/.+?/(?(mytv)|n)(?P<id>\d+)\.shtml.*?'
 
-    _TEST = {
+    _TESTS = [{
+        'note': 'This video is available only in Mainland China',
         'url': 'http://tv.sohu.com/20130724/n382479172.shtml#super',
-        'md5': 'bde8d9a6ffd82c63a1eefaef4eeefec7',
+        'md5': '29175c8cadd8b5cc4055001e85d6b372',
         'info_dict': {
             'id': '382479172',
             'ext': 'mp4',
             'title': 'MV：Far East Movement《The Illest》',
         },
-        'skip': 'Only available from China',
-    }
+        'params': {
+            'cn_verification_proxy': 'proxy.uku.im:8888'
+        }
+    }, {
+        'url': 'http://tv.sohu.com/20150305/n409385080.shtml',
+        'md5': '699060e75cf58858dd47fb9c03c42cfb',
+        'info_dict': {
+            'id': '409385080',
+            'ext': 'mp4',
+            'title': '《2015湖南卫视羊年元宵晚会》唐嫣《花好月圆》',
+        }
+    }, {
+        'url': 'http://my.tv.sohu.com/us/232799889/78693464.shtml',
+        'md5': '9bf34be48f2f4dadcb226c74127e203c',
+        'info_dict': {
+            'id': '78693464',
+            'ext': 'mp4',
+            'title': '【爱范品】第31期：MWC见不到的奇葩手机',
+        }
+    }, {
+        'note': 'Multipart video',
+        'url': 'http://my.tv.sohu.com/pl/8384802/78910339.shtml',
+        'info_dict': {
+            'id': '78910339',
+        },
+        'playlist': [{
+            'md5': 'bdbfb8f39924725e6589c146bc1883ad',
+            'info_dict': {
+                'id': '78910339_part1',
+                'ext': 'mp4',
+                'duration': 294,
+                'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
+            }
+        }, {
+            'md5': '3e1f46aaeb95354fd10e7fca9fc1804e',
+            'info_dict': {
+                'id': '78910339_part2',
+                'ext': 'mp4',
+                'duration': 300,
+                'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
+            }
+        }, {
+            'md5': '8407e634175fdac706766481b9443450',
+            'info_dict': {
+                'id': '78910339_part3',
+                'ext': 'mp4',
+                'duration': 150,
+                'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
+            }
+        }]
+    }, {
+        'note': 'Video with title containing dash',
+        'url': 'http://my.tv.sohu.com/us/249884221/78932792.shtml',
+        'info_dict': {
+            'id': '78932792',
+            'ext': 'mp4',
+            'title': 'youtube-dl testing video',
+        },
+        'params': {
+            'skip_download': True
+        }
+    }]
 
     def _real_extract(self, url):
 
@@ -29,8 +94,14 @@ class SohuIE(InfoExtractor):
             else:
                 base_data_url = 'http://hot.vrs.sohu.com/vrs_flash.action?vid='
 
+            req = compat_urllib_request.Request(base_data_url + vid_id)
+
+            cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
+            if cn_verification_proxy:
+                req.add_header('Ytdl-request-proxy', cn_verification_proxy)
+
             return self._download_json(
-                base_data_url + vid_id, video_id,
+                req, video_id,
                 'Downloading JSON data for %s' % vid_id)
 
         mobj = re.match(self._VALID_URL, url)
@@ -38,10 +109,8 @@ class SohuIE(InfoExtractor):
         mytv = mobj.group('mytv') is not None
 
         webpage = self._download_webpage(url, video_id)
-        raw_title = self._html_search_regex(
-            r'(?s)<title>(.+?)</title>',
-            webpage, 'video title')
-        title = raw_title.partition('-')[0].strip()
+
+        title = self._og_search_title(webpage)
 
         vid = self._html_search_regex(
             r'var vid ?= ?["\'](\d+)["\']',
@@ -77,7 +146,9 @@ class SohuIE(InfoExtractor):
                     % (format_id, i + 1, part_count))
 
                 part_info = part_str.split('|')
-                video_url = '%s%s?key=%s' % (part_info[0], su[i], part_info[3])
+
+                video_url = sanitize_url_path_consecutive_slashes(
+                    '%s%s?key=%s' % (part_info[0], su[i], part_info[3]))
 
                 formats.append({
                     'url': video_url,

youtube_dl/extractor/soundcloud.py

@@ -221,7 +221,12 @@ class SoundcloudIE(InfoExtractor):
                 info_json_url += "&secret_token=" + token
         elif mobj.group('player'):
             query = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
-            return self.url_result(query['url'][0])
+            real_url = query['url'][0]
+            # If the token is in the query of the original url we have to
+            # manually add it
+            if 'secret_token' in query:
+                real_url += '?secret_token=' + query['secret_token'][0]
+            return self.url_result(real_url)
         else:
             # extract uploader (which is in the url)
             uploader = mobj.group('uploader')
@@ -242,7 +247,7 @@ class SoundcloudIE(InfoExtractor):
 
 
 class SoundcloudSetIE(SoundcloudIE):
-    _VALID_URL = r'https?://(?:www\.)?soundcloud\.com/(?P<uploader>[\w\d-]+)/sets/(?P<slug_title>[\w\d-]+)(?:/(?P<token>[^?/]+))?'
+    _VALID_URL = r'https?://(?:(?:www|m)\.)?soundcloud\.com/(?P<uploader>[\w\d-]+)/sets/(?P<slug_title>[\w\d-]+)(?:/(?P<token>[^?/]+))?'
     IE_NAME = 'soundcloud:set'
     _TESTS = [{
         'url': 'https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep',
@@ -287,7 +292,7 @@ class SoundcloudSetIE(SoundcloudIE):
 
 
 class SoundcloudUserIE(SoundcloudIE):
-    _VALID_URL = r'https?://(www\.)?soundcloud\.com/(?P<user>[^/]+)/?((?P<rsrc>tracks|likes)/?)?(\?.*)?$'
+    _VALID_URL = r'https?://(?:(?:www|m)\.)?soundcloud\.com/(?P<user>[^/]+)/?((?P<rsrc>tracks|likes)/?)?(\?.*)?$'
     IE_NAME = 'soundcloud:user'
     _TESTS = [{
         'url': 'https://soundcloud.com/the-concept-band',

youtube_dl/extractor/spankbang.py

@@ -0,0 +1,60 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class SpankBangIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:(?:www|[a-z]{2})\.)?spankbang\.com/(?P<id>[\da-z]+)/video'
+    _TEST = {
+        'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
+        'md5': '1cc433e1d6aa14bc376535b8679302f7',
+        'info_dict': {
+            'id': '3vvn',
+            'ext': 'mp4',
+            'title': 'fantasy solo',
+            'description': 'dillion harper masturbates on a bed',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': 'silly2587',
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        stream_key = self._html_search_regex(
+            r'''var\s+stream_key\s*=\s*['"](.+?)['"]''',
+            webpage, 'stream key')
+
+        formats = [{
+            'url': 'http://spankbang.com/_%s/%s/title/%sp__mp4' % (video_id, stream_key, height),
+            'ext': 'mp4',
+            'format_id': '%sp' % height,
+            'height': int(height),
+        } for height in re.findall(r'<span[^>]+q_(\d+)p', webpage)]
+        self._sort_formats(formats)
+
+        title = self._html_search_regex(
+            r'(?s)<h1>(.+?)</h1>', webpage, 'title')
+        description = self._search_regex(
+            r'class="desc"[^>]*>([^<]+)',
+            webpage, 'description', default=None)
+        thumbnail = self._og_search_thumbnail(webpage)
+        uploader = self._search_regex(
+            r'class="user"[^>]*>([^<]+)',
+            webpage, 'uploader', fatal=False)
+
+        age_limit = self._rta_search(webpage)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'formats': formats,
+            'age_limit': age_limit,
+        }

youtube_dl/extractor/spike.py

@@ -5,7 +5,7 @@ from .mtv import MTVServicesInfoExtractor
 
 class SpikeIE(MTVServicesInfoExtractor):
     _VALID_URL = r'''(?x)https?://
-        (?:www\.spike\.com/(?:video-clips|(?:full-)?episodes)/.+|
+        (?:www\.spike\.com/(?:video-(?:clips|playlists)|(?:full-)?episodes)/.+|
          m\.spike\.com/videos/video\.rbml\?id=(?P<id>[^&]+))
         '''
     _TEST = {

youtube_dl/extractor/srf.py

@@ -0,0 +1,104 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    parse_iso8601,
+    xpath_text,
+)
+
+
+class SrfIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.srf\.ch/play(?:er)?/tv/[^/]+/video/(?P<display_id>[^?]+)\?id=|tp\.srgssr\.ch/p/flash\?urn=urn:srf:ais:video:)(?P<id>[0-9a-f\-]{36})'
+    _TESTS = [{
+        'url': 'http://www.srf.ch/play/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5',
+        'md5': '4cd93523723beff51bb4bee974ee238d',
+        'info_dict': {
+            'id': '28e1a57d-5b76-4399-8ab3-9097f071e6c5',
+            'display_id': 'snowden-beantragt-asyl-in-russland',
+            'ext': 'm4v',
+            'upload_date': '20130701',
+            'title': 'Snowden beantragt Asyl in Russland',
+            'timestamp': 1372713995,
+        }
+    }, {
+        # No Speichern (Save) button
+        'url': 'http://www.srf.ch/play/tv/top-gear/video/jaguar-xk120-shadow-und-tornado-dampflokomotive?id=677f5829-e473-4823-ac83-a1087fe97faa',
+        'md5': 'd97e236e80d1d24729e5d0953d276a4f',
+        'info_dict': {
+            'id': '677f5829-e473-4823-ac83-a1087fe97faa',
+            'display_id': 'jaguar-xk120-shadow-und-tornado-dampflokomotive',
+            'ext': 'flv',
+            'upload_date': '20130710',
+            'title': 'Jaguar XK120, Shadow und Tornado-Dampflokomotive',
+            'timestamp': 1373493600,
+        },
+    }, {
+        'url': 'http://www.srf.ch/player/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5',
+        'only_matching': True,
+    }, {
+        'url': 'https://tp.srgssr.ch/p/flash?urn=urn:srf:ais:video:28e1a57d-5b76-4399-8ab3-9097f071e6c5',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        display_id = re.match(self._VALID_URL, url).group('display_id') or video_id
+
+        video_data = self._download_xml(
+            'http://il.srgssr.ch/integrationlayer/1.0/ue/srf/video/play/%s.xml' % video_id,
+            display_id)
+
+        title = xpath_text(
+            video_data, './AssetMetadatas/AssetMetadata/title', fatal=True)
+        thumbnails = [{
+            'url': s.text
+        } for s in video_data.findall('.//ImageRepresentation/url')]
+        timestamp = parse_iso8601(xpath_text(video_data, './createdDate'))
+        # The <duration> field in XML is different from the exact duration, skipping
+
+        formats = []
+        for item in video_data.findall('./Playlists/Playlist') + video_data.findall('./Downloads/Download'):
+            for url_node in item.findall('url'):
+                quality = url_node.attrib['quality']
+                full_url = url_node.text
+                original_ext = determine_ext(full_url)
+                format_id = '%s-%s' % (quality, item.attrib['protocol'])
+                if original_ext == 'f4m':
+                    formats.extend(self._extract_f4m_formats(
+                        full_url + '?hdcore=3.4.0', display_id, f4m_id=format_id))
+                elif original_ext == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        full_url, display_id, 'mp4', m3u8_id=format_id))
+                else:
+                    formats.append({
+                        'url': full_url,
+                        'ext': original_ext,
+                        'format_id': format_id,
+                        'quality': 0 if 'HD' in quality else -1,
+                        'preference': 1,
+                    })
+
+        self._sort_formats(formats)
+
+        subtitles = {}
+        subtitles_data = video_data.find('Subtitles')
+        if subtitles_data is not None:
+            subtitles_list = [{
+                'url': sub.text,
+                'ext': determine_ext(sub.text),
+            } for sub in subtitles_data]
+            if subtitles_list:
+                subtitles['de'] = subtitles_list
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'formats': formats,
+            'title': title,
+            'thumbnails': thumbnails,
+            'timestamp': timestamp,
+            'subtitles': subtitles,
+        }