release 2015.05.04

The video url still redirects to an http url, but it doesn't explicitly contain the video id.

AUTHORS

@@ -120,3 +120,7 @@ Jeff Buchbinder
 Amish Bhadeshia
 Joram Schrijver
 Will W.
+Mohammad Teimori Pabandi
+Roman Le Négrate
+Matthias Küch
+Julian Richen

README.md

@@ -5,6 +5,7 @@ youtube-dl - download videos from youtube.com or other video platforms
 - [OPTIONS](#options)
 - [CONFIGURATION](#configuration)
 - [OUTPUT TEMPLATE](#output-template)
+- [FORMAT SELECTION](#format-selection)
 - [VIDEO SELECTION](#video-selection)
 - [FAQ](#faq)
 - [DEVELOPER INSTRUCTIONS](#developer-instructions)
@@ -45,21 +46,21 @@ 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 +72,70 @@ 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 .annotations.xml file
+    --load-info FILE                 JSON file containing the video information (created with the "--write-info-json" option)
+    --cookies FILE                   File to read cookies from and dump cookie jar in
     --cache-dir DIR                  Location in the filesystem where youtube-dl can store some downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl
                                      or ~/.cache/youtube-dl . At the moment, only YouTube player files (for videos with obfuscated signatures) are cached, but that may
                                      change.
@@ -142,96 +143,86 @@ 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-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
-                                     extension for the extensions aac, m4a, mp3, mp4, ogg, wav, webm. You can also use the special names "best", "bestvideo", "bestaudio",
-                                     "worst".  You can filter the video results by putting a condition in brackets, as in -f "best[height=720]" (or -f "[filesize>10M]").
-                                     This works for filesize, height, width, tbr, abr, vbr, asr, and fps and the comparisons <, <=, >, >=, =, != and for ext, acodec,
-                                     vcodec, container, and protocol and the comparisons =, != . Formats for which the value is not known are excluded unless you put a
-                                     question mark (?) after the operator. You can combine format filters, so  -f "[height <=? 720][tbr>500]" selects up to 720p videos
-                                     (or videos where the height is not known) with a bitrate of at least 500 KBit/s. By default, youtube-dl will pick the best quality.
-                                     Use commas to download multiple audio formats, such as -f  136/137/mp4/bestvideo,140/m4a/bestaudio. You can merge the video and audio
-                                     of two formats into a single file using -f <video-format>+<audio-format> (requires ffmpeg or avconv), for example -f
-                                     bestvideo+bestaudio.
-    --all-formats                    download all available video formats
-    --prefer-free-formats            prefer free video formats unless a specific one is requested
-    --max-quality FORMAT             highest quality format to download
-    -F, --list-formats               list all available formats
+    -f, --format FORMAT              Video format code, see the "FORMAT SELECTION" for all the info
+    --all-formats                    Download all available video formats
+    --prefer-free-formats            Prefer free video formats unless a specific one is requested
+    -F, --list-formats               List all available formats
     --youtube-skip-dash-manifest     Do not download the DASH 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
-    --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
+    -k, --keep-video                 Keep the video file on disk after the post-processing; the video is erased by default
+    --no-post-overwrites             Do not overwrite post-processed files; the post-processed files are overwritten by default
+    --embed-subs                     Embed subtitles in the video (only for mkv and mp4 videos)
+    --embed-thumbnail                Embed thumbnail in the audio as cover art
+    --add-metadata                   Write metadata to the video file
+    --metadata-from-title FORMAT     Parse additional metadata like song title / artist from the video title. The format syntax is the same as --output, the parsed
                                      parameters replace existing values. Additional templates: %(album), %(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)
+    --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)
@@ -271,6 +262,17 @@ $ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc --restrict-filena
 youtube-dl_test_video_.mp4          # A simple file name
 ```
 
+# FORMAT SELECTION
+
+By default youtube-dl tries to download the best quality, but sometimes you may want to download other format.
+The simplest case is requesting a specific format, for example `-f 22`. You can get the list of available formats using `--list-formats`, you can also use a file extension (currently it supports aac, m4a, mp3, mp4, ogg, wav, webm) or the special names `best`, `bestvideo`, `bestaudio` and `worst`.
+
+If you want to download multiple videos and they don't have the same formats available, you can specify the order of preference using slashes, as in `-f 22/17/18`. You can also filter the video results by putting a condition in brackets, as in `-f "best[height=720]"` (or `-f "[filesize>10M]"`).  This works for filesize, height, width, tbr, abr, vbr, asr, and fps and the comparisons <, <=, >, >=, =, != and for ext, acodec, vcodec, container, and protocol and the comparisons =, != . Formats for which the value is not known are excluded unless you put a question mark (?) after the operator. You can combine format filters, so  `-f "[height <=? 720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s. Use commas to download multiple formats, such as `-f 136/137/mp4/bestvideo,140/m4a/bestaudio`. You can merge the video and audio of two formats into a single file using `-f <video-format>+<audio-format>` (requires ffmpeg or avconv), for example `-f bestvideo+bestaudio`.
+
+Since the end of April 2015 and version 2015.04.26 youtube-dl uses `-f bestvideo+bestaudio/best` as default format selection (see #5447, #5456). If ffmpeg or avconv are installed this results in downloading `bestvideo` and `bestaudio` separately and muxing them together into a single file giving the best overall quality available. Otherwise it falls back to `best` and results in downloading best available quality served as a single file. `best` is also needed for videos that don't come from YouTube because they don't provide the audio and video in two different files. If you want to only download some dash formats (for example if you are not interested in getting videos with a resolution higher than 1080p), you can add `-f bestvideo[height<=?1080]+bestaudio/best` to your configuration file.
+
+If you want to preserve the old format selection behavior (prior to youtube-dl 2015.04.26), i.e. you want to download best available quality media served as a single file, you should explicitly specify your choice with `-f best`. You may want to add it to the [configuration file](#configuration) in order not to type it every time you run youtube-dl.
+
 # VIDEO SELECTION
 
 Videos can be filtered by their upload date using the options `--date`, `--datebefore` or `--dateafter`, they accept dates in two formats:
@@ -321,9 +323,9 @@ YouTube changed their playlist format in March 2014 and later on, so you'll need
 
 If you have installed youtube-dl with a package manager, pip, setup.py or a tarball, please use that to update. Note that Ubuntu packages do not seem to get updated anymore. Since we are not affiliated with Ubuntu, there is little we can do. Feel free to [report bugs](https://bugs.launchpad.net/ubuntu/+source/youtube-dl/+filebug) to the [Ubuntu packaging guys](mailto:ubuntu-motu@lists.ubuntu.com?subject=outdated%20version%20of%20youtube-dl) - all they have to do is update the package to a somewhat recent version. See above for a way to update.
 
-### Do I always have to pass in `--max-quality FORMAT`, or `-citw`?
+### Do I always have to pass `-citw`?
 
-By default, youtube-dl intends to have the best options (incidentally, if you have a convincing case that these should be different, [please file an issue where you explain that](https://yt-dl.org/bug)). Therefore, it is unnecessary and sometimes harmful to copy long option strings from webpages. In particular, `--max-quality` *limits* the video quality (so if you want the best quality, do NOT pass it in), and the only option out of `-citw` that is regularly useful is `-i`.
+By default, youtube-dl intends to have the best options (incidentally, if you have a convincing case that these should be different, [please file an issue where you explain that](https://yt-dl.org/bug)). Therefore, it is unnecessary and sometimes harmful to copy long option strings from webpages. In particular, the only option out of `-citw` that is regularly useful is `-i`.
 
 ### Can you please put the -b option back?
 
@@ -355,6 +357,22 @@ YouTube has switched to a new video info format in July 2011 which is not suppor
 
 YouTube requires an additional signature since September 2012 which is not supported by old versions of youtube-dl. See [above](#how-do-i-update-youtube-dl) for how to update youtube-dl.
 
+### Video URL contains an ampersand and I'm getting some strange output `[1] 2839` or `'v' is not recognized as an internal or external command` ###
+
+That's actually the output from your shell. Since ampersand is one of the special shell characters it's interpreted by shell preventing you from passing the whole URL to youtube-dl. To disable your shell from interpreting the ampersands (or any other special characters) you have to either put the whole URL in quotes or escape them with a backslash (which approach will work depends on your shell).
+
+For example if your URL is https://www.youtube.com/watch?t=4&v=BaW_jenozKc you should end up with following command:
+
+```youtube-dl 'https://www.youtube.com/watch?t=4&v=BaW_jenozKc'```
+
+or
+
+```youtube-dl https://www.youtube.com/watch?t=4\&v=BaW_jenozKc```
+
+For Windows you have to use the double quotes:
+
+```youtube-dl "https://www.youtube.com/watch?t=4&v=BaW_jenozKc"```
+
 ### ExtractorError: Could not find JS function u'OF'
 
 In February 2015, the new YouTube player contained a character sequence in a string that was misinterpreted by old versions of youtube-dl. See [above](#how-do-i-update-youtube-dl) for how to update youtube-dl.

docs/supportedsites.md

@@ -44,6 +44,7 @@
  - **audiomack**
  - **audiomack:album**
  - **Azubu**
+ - **BaiduVideo**
  - **bambuser**
  - **bambuser:channel**
  - **Bandcamp**
@@ -98,6 +99,7 @@
  - **CondeNast**: Condé Nast media group: Condé Nast, GQ, Glamour, Vanity Fair, Vogue, W Magazine, WIRED
  - **Cracked**
  - **Criterion**
+ - **CrooksAndLiars**
  - **Crunchyroll**
  - **crunchyroll:playlist**
  - **CSpan**: C-SPAN
@@ -154,6 +156,7 @@
  - **FootyRoom**
  - **Foxgay**
  - **FoxNews**
+ - **FoxSports**
  - **france2.fr:generation-quoi**
  - **FranceCulture**
  - **FranceInter**
@@ -166,12 +169,14 @@
  - **Gamekings**
  - **GameOne**
  - **gameone:playlist**
+ - **Gamersyde**
  - **GameSpot**
  - **GameStar**
  - **Gametrailers**
  - **Gazeta**
  - **GDCVault**
  - **generic**: Generic downloader that works on some sites
+ - **Gfycat**
  - **GiantBomb**
  - **Giga**
  - **Glide**: Glide mobile video messages (glide.me)
@@ -179,9 +184,8 @@
  - **GodTube**
  - **GoldenMoustache**
  - **Golem**
- - **GorillaVid**: GorillaVid.in, daclips.in, movpod.in and fastvideo.in
+ - **GorillaVid**: GorillaVid.in, daclips.in, movpod.in, fastvideo.in and realvid.net
  - **Goshgay**
- - **Grooveshark**
  - **Groupon**
  - **Hark**
  - **HearThisAt**
@@ -250,6 +254,7 @@
  - **Malemotion**
  - **MDR**
  - **media.ccc.de**
+ - **MegaVideoz**
  - **metacafe**
  - **Metacritic**
  - **Mgoon**
@@ -336,6 +341,7 @@
  - **parliamentlive.tv**: UK parliament videos
  - **Patreon**
  - **PBS**
+ - **PhilharmonieDeParis**: Philharmonie de Paris
  - **Phoenix**
  - **Photobucket**
  - **Pladform**
@@ -351,17 +357,22 @@
  - **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**
@@ -398,6 +409,7 @@
  - **Screencast**
  - **ScreencastOMatic**
  - **ScreenwaveMedia**
+ - **SenateISVP**
  - **ServingSys**
  - **Sexu**
  - **SexyKarma**: Sexy Karma and Watch Indian Porn
@@ -420,8 +432,10 @@
  - **soundgasm**
  - **soundgasm:profile**
  - **southpark.cc.com**
+ - **southpark.cc.com:español**
  - **southpark.de**
  - **Space**
+ - **SpankBang**
  - **Spankwire**
  - **Spiegel**
  - **Spiegel:Article**: Articles on spiegel.de
@@ -430,6 +444,7 @@
  - **Sport5**
  - **SportBox**
  - **SportDeutschland**
+ - **Srf**
  - **SRMediathek**: Saarländischer Rundfunk
  - **SSA**
  - **stanfordoc**: Stanford Open ClassRoom
@@ -452,7 +467,7 @@
  - **TeamFour**
  - **TechTalks**
  - **techtv.mit.edu**
- - **TED**
+ - **ted**
  - **tegenlicht.vpro.nl**
  - **TeleBruxelles**
  - **telecinco.es**
@@ -501,6 +516,7 @@
  - **Ubu**
  - **udemy**
  - **udemy:course**
+ - **UDNEmbed**
  - **Ultimedia**
  - **Unistra**
  - **Urort**: NRK P3 Urørt
@@ -541,7 +557,7 @@
  - **vimeo:review**: Review pages on vimeo
  - **vimeo:user**
  - **vimeo:watchlater**: Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)
- - **Vimple**: Vimple.ru
+ - **Vimple**: Vimple - one-click video hosting
  - **Vine**
  - **vine:user**
  - **vk.com**

test/helper.py

@@ -150,7 +150,7 @@ def expect_info_dict(self, got_dict, expected_dict):
                              'invalid value for field %s, expected %r, got %r' % (info_field, expected, got))
 
     # Check for the presence of mandatory fields
-    if got_dict.get('_type') != 'playlist':
+    if got_dict.get('_type') not in ('playlist', 'multi_video'):
         for key in ('id', 'url', 'title', 'ext'):
             self.assertTrue(got_dict.get(key), 'Missing mandatory field %s' % key)
     # Check for mandatory fields that are automatically set by YoutubeDL

test/parameters.json

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

test/test_YoutubeDL.py

@@ -101,39 +101,6 @@ class TestFormatSelection(unittest.TestCase):
         downloaded = ydl.downloaded_info_dicts[0]
         self.assertEqual(downloaded['ext'], 'flv')
 
-    def test_format_limit(self):
-        formats = [
-            {'format_id': 'meh', 'url': 'http://example.com/meh', 'preference': 1},
-            {'format_id': 'good', 'url': 'http://example.com/good', 'preference': 2},
-            {'format_id': 'great', 'url': 'http://example.com/great', 'preference': 3},
-            {'format_id': 'excellent', 'url': 'http://example.com/exc', 'preference': 4},
-        ]
-        info_dict = _make_result(formats)
-
-        ydl = YDL()
-        ydl.process_ie_result(info_dict)
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], 'excellent')
-
-        ydl = YDL({'format_limit': 'good'})
-        assert ydl.params['format_limit'] == 'good'
-        ydl.process_ie_result(info_dict.copy())
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], 'good')
-
-        ydl = YDL({'format_limit': 'great', 'format': 'all'})
-        ydl.process_ie_result(info_dict.copy())
-        self.assertEqual(ydl.downloaded_info_dicts[0]['format_id'], 'meh')
-        self.assertEqual(ydl.downloaded_info_dicts[1]['format_id'], 'good')
-        self.assertEqual(ydl.downloaded_info_dicts[2]['format_id'], 'great')
-        self.assertTrue('3' in ydl.msgs[0])
-
-        ydl = YDL()
-        ydl.params['format_limit'] = 'excellent'
-        ydl.process_ie_result(info_dict.copy())
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], 'excellent')
-
     def test_format_selection(self):
         formats = [
             {'format_id': '35', 'ext': 'mp4', 'preference': 1, 'url': TEST_URL},
@@ -270,7 +237,7 @@ class TestFormatSelection(unittest.TestCase):
             f2['url'] = 'url:' + f2id
 
             info_dict = _make_result([f1, f2], extractor='youtube')
-            ydl = YDL()
+            ydl = YDL({'format': 'best/bestvideo'})
             yie = YoutubeIE(ydl)
             yie._sort_formats(info_dict['formats'])
             ydl.process_ie_result(info_dict)
@@ -278,7 +245,7 @@ class TestFormatSelection(unittest.TestCase):
             self.assertEqual(downloaded['format_id'], f1id)
 
             info_dict = _make_result([f2, f1], extractor='youtube')
-            ydl = YDL()
+            ydl = YDL({'format': 'best/bestvideo'})
             yie = YoutubeIE(ydl)
             yie._sort_formats(info_dict['formats'])
             ydl.process_ie_result(info_dict)
@@ -443,27 +410,36 @@ class TestYoutubeDL(unittest.TestCase):
             def run(self, info):
                 with open(audiofile, 'wt') as f:
                     f.write('EXAMPLE')
-                info['filepath']
-                return False, info
+                return [info['filepath']], info
 
-        def run_pp(params):
+        def run_pp(params, PP):
             with open(filename, 'wt') as f:
                 f.write('EXAMPLE')
             ydl = YoutubeDL(params)
-            ydl.add_post_processor(SimplePP())
+            ydl.add_post_processor(PP())
             ydl.post_process(filename, {'filepath': filename})
 
-        run_pp({'keepvideo': True})
+        run_pp({'keepvideo': True}, SimplePP)
         self.assertTrue(os.path.exists(filename), '%s doesn\'t exist' % filename)
         self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
         os.unlink(filename)
         os.unlink(audiofile)
 
-        run_pp({'keepvideo': False})
+        run_pp({'keepvideo': False}, SimplePP)
         self.assertFalse(os.path.exists(filename), '%s exists' % filename)
         self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
         os.unlink(audiofile)
 
+        class ModifierPP(PostProcessor):
+            def run(self, info):
+                with open(info['filepath'], 'wt') as f:
+                    f.write('MODIFIED')
+                return [], info
+
+        run_pp({'keepvideo': False}, ModifierPP)
+        self.assertTrue(os.path.exists(filename), '%s doesn\'t exist' % filename)
+        os.unlink(filename)
+
     def test_match_filter(self):
         class FilterYDL(YDL):
             def __init__(self, *args, **kwargs):

test/test_download.py

@@ -153,7 +153,7 @@ def generator(test_case):
                     break
 
             if is_playlist:
-                self.assertEqual(res_dict['_type'], 'playlist')
+                self.assertTrue(res_dict['_type'] in ['playlist', 'multi_video'])
                 self.assertTrue('entries' in res_dict)
                 expect_info_dict(self, res_dict, test_case.get('info_dict', {}))
 

test/test_execution.py

@@ -8,6 +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__)))
 
@@ -31,7 +34,7 @@ class TestExecution(unittest.TestCase):
 
     def test_cmdline_umlauts(self):
         p = subprocess.Popen(
-            [sys.executable, 'youtube_dl/__main__.py', 'ä', '--version'],
+            [sys.executable, 'youtube_dl/__main__.py', encodeArgument('ä'), '--version'],
             cwd=rootDir, stdout=_DEV_NULL, stderr=subprocess.PIPE)
         _, stderr = p.communicate()
         self.assertFalse(stderr)

test/test_utils.py

@@ -41,6 +41,8 @@ from youtube_dl.utils import (
     sanitize_filename,
     sanitize_path,
     sanitize_url_path_consecutive_slashes,
+    prepend_extension,
+    replace_extension,
     shell_quote,
     smuggle_url,
     str_to_int,
@@ -58,6 +60,8 @@ from youtube_dl.utils import (
     xpath_text,
     render_table,
     match_str,
+    parse_dfxp_time_expr,
+    dfxp2srt,
 )
 
 
@@ -191,6 +195,22 @@ class TestUtil(unittest.TestCase):
             sanitize_url_path_consecutive_slashes('http://hostname/abc//'),
             'http://hostname/abc/')
 
+    def test_prepend_extension(self):
+        self.assertEqual(prepend_extension('abc.ext', 'temp'), 'abc.temp.ext')
+        self.assertEqual(prepend_extension('abc.ext', 'temp', 'ext'), 'abc.temp.ext')
+        self.assertEqual(prepend_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
+        self.assertEqual(prepend_extension('abc', 'temp'), 'abc.temp')
+        self.assertEqual(prepend_extension('.abc', 'temp'), '.abc.temp')
+        self.assertEqual(prepend_extension('.abc.ext', 'temp'), '.abc.temp.ext')
+
+    def test_replace_extension(self):
+        self.assertEqual(replace_extension('abc.ext', 'temp'), 'abc.temp')
+        self.assertEqual(replace_extension('abc.ext', 'temp', 'ext'), 'abc.temp')
+        self.assertEqual(replace_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
+        self.assertEqual(replace_extension('abc', 'temp'), 'abc.temp')
+        self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
+        self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
+
     def test_ordered_set(self):
         self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
         self.assertEqual(orderedSet([]), [])
@@ -227,6 +247,7 @@ 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>
@@ -470,6 +491,12 @@ 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"')
@@ -574,6 +601,42 @@ ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
             'like_count > 100 & dislike_count <? 50 & description',
             {'like_count': 190, 'dislike_count': 10}))
 
+    def test_parse_dfxp_time_expr(self):
+        self.assertEqual(parse_dfxp_time_expr(None), 0.0)
+        self.assertEqual(parse_dfxp_time_expr(''), 0.0)
+        self.assertEqual(parse_dfxp_time_expr('0.1'), 0.1)
+        self.assertEqual(parse_dfxp_time_expr('0.1s'), 0.1)
+        self.assertEqual(parse_dfxp_time_expr('00:00:01'), 1.0)
+        self.assertEqual(parse_dfxp_time_expr('00:00:01.100'), 1.1)
+
+    def test_dfxp2srt(self):
+        dfxp_data = '''<?xml version="1.0" encoding="UTF-8"?>
+            <tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
+            <body>
+                <div xml:lang="en">
+                    <p begin="0" end="1">The following line contains Chinese characters and special symbols</p>
+                    <p begin="1" end="2">第二行<br/>♪♪</p>
+                    <p begin="2" end="3"><span>Third<br/>Line</span></p>
+                </div>
+            </body>
+            </tt>'''
+        srt_data = '''1
+00:00:00,000 --> 00:00:01,000
+The following line contains Chinese characters and special symbols
+
+2
+00:00:01,000 --> 00:00:02,000
+第二行
+♪♪
+
+3
+00:00:02,000 --> 00:00:03,000
+Third
+Line
+
+'''
+        self.assertEqual(dfxp2srt(dfxp_data), srt_data)
+
 
 if __name__ == '__main__':
     unittest.main()

youtube_dl/YoutubeDL.py

@@ -64,7 +64,6 @@ from .utils import (
     sanitize_path,
     std_headers,
     subtitles_filename,
-    takewhile_inclusive,
     UnavailableVideoError,
     url_basename,
     version_tuple,
@@ -72,6 +71,7 @@ from .utils import (
     write_string,
     YoutubeDLHandler,
     prepend_extension,
+    replace_extension,
     args_to_str,
     age_restricted,
 )
@@ -135,7 +135,6 @@ class YoutubeDL(object):
                        (or video) as a single JSON line.
     simulate:          Do not download the video files.
     format:            Video format code. See options.py for more information.
-    format_limit:      Highest quality format to try.
     outtmpl:           Template for output names.
     restrictfilenames: Do not allow "&" and spaces in file names
     ignoreerrors:      Do not stop on download errors.
@@ -916,10 +915,16 @@ class YoutubeDL(object):
         if not available_formats:
             return None
 
-        if format_spec == 'best' or format_spec is None:
-            return available_formats[-1]
-        elif format_spec == 'worst':
-            return available_formats[0]
+        if format_spec in ['best', 'worst', None]:
+            format_idx = 0 if format_spec == 'worst' else -1
+            audiovideo_formats = [
+                f for f in available_formats
+                if f.get('vcodec') != 'none' and f.get('acodec') != 'none']
+            if audiovideo_formats:
+                return audiovideo_formats[format_idx]
+            # for audio only urls, select the best/worst audio format
+            elif all(f.get('acodec') != 'none' for f in available_formats):
+                return available_formats[format_idx]
         elif format_spec == 'bestaudio':
             audio_formats = [
                 f for f in available_formats
@@ -1063,12 +1068,6 @@ class YoutubeDL(object):
             full_format_info.update(format)
             format['http_headers'] = self._calc_headers(full_format_info)
 
-        format_limit = self.params.get('format_limit', None)
-        if format_limit:
-            formats = list(takewhile_inclusive(
-                lambda f: f['format_id'] != format_limit, formats
-            ))
-
         # TODO Central sorting goes here
 
         if formats[0] is not info_dict:
@@ -1086,7 +1085,11 @@ class YoutubeDL(object):
 
         req_format = self.params.get('format')
         if req_format is None:
-            req_format = 'best'
+            req_format_list = []
+            if info_dict['extractor'] in ['youtube', 'ted'] and FFmpegMergerPP(self).available:
+                req_format_list.append('bestvideo+bestaudio')
+            req_format_list.append('best')
+            req_format = '/'.join(req_format_list)
         formats_to_download = []
         if req_format == 'all':
             formats_to_download = formats
@@ -1268,7 +1271,7 @@ class YoutubeDL(object):
             return
 
         if self.params.get('writedescription', False):
-            descfn = filename + '.description'
+            descfn = replace_extension(filename, 'description', info_dict.get('ext'))
             if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(descfn)):
                 self.to_screen('[info] Video description is already present')
             elif info_dict.get('description') is None:
@@ -1283,7 +1286,7 @@ class YoutubeDL(object):
                     return
 
         if self.params.get('writeannotations', False):
-            annofn = filename + '.annotations.xml'
+            annofn = replace_extension(filename, 'annotations.xml', info_dict.get('ext'))
             if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(annofn)):
                 self.to_screen('[info] Video annotations are already present')
             else:
@@ -1330,13 +1333,13 @@ class YoutubeDL(object):
                     return
 
         if self.params.get('writeinfojson', False):
-            infofn = os.path.splitext(filename)[0] + '.info.json'
+            infofn = replace_extension(filename, 'info.json', info_dict.get('ext'))
             if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(infofn)):
                 self.to_screen('[info] Video description metadata is already present')
             else:
                 self.to_screen('[info] Writing video description metadata as JSON to: ' + infofn)
                 try:
-                    write_json_file(info_dict, infofn)
+                    write_json_file(self.filter_requested_info(info_dict), infofn)
                 except (OSError, IOError):
                     self.report_error('Cannot write metadata to JSON file ' + infofn)
                     return
@@ -1356,7 +1359,7 @@ class YoutubeDL(object):
                 if info_dict.get('requested_formats') is not None:
                     downloaded = []
                     success = True
-                    merger = FFmpegMergerPP(self, not self.params.get('keepvideo'))
+                    merger = FFmpegMergerPP(self)
                     if not merger.available:
                         postprocessors = []
                         self.report_warning('You have requested multiple '
@@ -1364,16 +1367,49 @@ class YoutubeDL(object):
                                             ' The formats won\'t be merged')
                     else:
                         postprocessors = [merger]
-                    for f in info_dict['requested_formats']:
-                        new_info = dict(info_dict)
-                        new_info.update(f)
-                        fname = self.prepare_filename(new_info)
-                        fname = prepend_extension(fname, 'f%s' % f['format_id'])
-                        downloaded.append(fname)
-                        partial_success = dl(fname, new_info)
-                        success = success and partial_success
-                    info_dict['__postprocessors'] = postprocessors
-                    info_dict['__files_to_merge'] = downloaded
+
+                    def compatible_formats(formats):
+                        video, audio = formats
+                        # Check extension
+                        video_ext, audio_ext = audio.get('ext'), video.get('ext')
+                        if video_ext and audio_ext:
+                            COMPATIBLE_EXTS = (
+                                ('mp3', 'mp4', 'm4a', 'm4p', 'm4b', 'm4r', 'm4v'),
+                                ('webm')
+                            )
+                            for exts in COMPATIBLE_EXTS:
+                                if video_ext in exts and audio_ext in exts:
+                                    return True
+                        # TODO: Check acodec/vcodec
+                        return False
+
+                    filename_real_ext = os.path.splitext(filename)[1][1:]
+                    filename_wo_ext = (
+                        os.path.splitext(filename)[0]
+                        if filename_real_ext == info_dict['ext']
+                        else filename)
+                    requested_formats = info_dict['requested_formats']
+                    if self.params.get('merge_output_format') is None and not compatible_formats(requested_formats):
+                        info_dict['ext'] = 'mkv'
+                        self.report_warning('You have requested formats incompatible for merge. '
+                                            'The formats will be merged into mkv')
+                    # Ensure filename always has a correct extension for successful merge
+                    filename = '%s.%s' % (filename_wo_ext, info_dict['ext'])
+                    if os.path.exists(encodeFilename(filename)):
+                        self.to_screen(
+                            '[download] %s has already been downloaded and '
+                            'merged' % filename)
+                    else:
+                        for f in requested_formats:
+                            new_info = dict(info_dict)
+                            new_info.update(f)
+                            fname = self.prepare_filename(new_info)
+                            fname = prepend_extension(fname, 'f%s' % f['format_id'], new_info['ext'])
+                            downloaded.append(fname)
+                            partial_success = dl(fname, new_info)
+                            success = success and partial_success
+                        info_dict['__postprocessors'] = postprocessors
+                        info_dict['__files_to_merge'] = downloaded
                 else:
                     # Just a single file
                     success = dl(filename, info_dict)
@@ -1460,7 +1496,7 @@ class YoutubeDL(object):
                 [info_filename], mode='r',
                 openhook=fileinput.hook_encoded('utf-8'))) as f:
             # FileInput doesn't have a read method, we can't call json.load
-            info = json.loads('\n'.join(f))
+            info = self.filter_requested_info(json.loads('\n'.join(f)))
         try:
             self.process_ie_result(info, download=True)
         except DownloadError:
@@ -1472,6 +1508,12 @@ class YoutubeDL(object):
                 raise
         return self._download_retcode
 
+    @staticmethod
+    def filter_requested_info(info_dict):
+        return dict(
+            (k, v) for k, v in info_dict.items()
+            if k not in ['requested_formats', 'requested_subtitles'])
+
     def post_process(self, filename, ie_info):
         """Run all the postprocessors on the given file."""
         info = dict(ie_info)
@@ -1481,24 +1523,17 @@ class YoutubeDL(object):
             pps_chain.extend(ie_info['__postprocessors'])
         pps_chain.extend(self._pps)
         for pp in pps_chain:
-            keep_video = None
-            old_filename = info['filepath']
             try:
-                keep_video_wish, info = pp.run(info)
-                if keep_video_wish is not None:
-                    if keep_video_wish:
-                        keep_video = keep_video_wish
-                    elif keep_video is None:
-                        # No clear decision yet, let IE decide
-                        keep_video = keep_video_wish
+                files_to_delete, info = pp.run(info)
             except PostProcessingError as e:
                 self.report_error(e.msg)
-            if keep_video is False and not self.params.get('keepvideo', False):
-                try:
+            if files_to_delete and not self.params.get('keepvideo', False):
+                for old_filename in files_to_delete:
                     self.to_screen('Deleting original file %s (pass -k to keep)' % old_filename)
-                    os.remove(encodeFilename(old_filename))
-                except (IOError, OSError):
-                    self.report_warning('Unable to remove downloaded video file')
+                    try:
+                        os.remove(encodeFilename(old_filename))
+                    except (IOError, OSError):
+                        self.report_warning('Unable to remove downloaded original file')
 
     def _make_archive_id(self, info_dict):
         # Future-proof against any change in case
@@ -1768,14 +1803,6 @@ class YoutubeDL(object):
 
         debuglevel = 1 if self.params.get('debug_printtraffic') else 0
         https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel)
-        # The ssl context is only available in python 2.7.9 and 3.x
-        if hasattr(https_handler, '_context'):
-            ctx = https_handler._context
-            # get_ca_certs is unavailable prior to python 3.4
-            if hasattr(ctx, 'get_ca_certs') and len(ctx.get_ca_certs()) == 0:
-                self.report_warning(
-                    'No ssl certificates were loaded, urls that use https '
-                    'won\'t work')
         ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel)
         opener = compat_urllib_request.build_opener(
             proxy_handler, https_handler, cookie_processor, ydlh)

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
@@ -244,9 +240,7 @@ def _real_main(argv=None):
     if opts.xattrs:
         postprocessors.append({'key': 'XAttrMetadata'})
     if opts.embedthumbnail:
-        if not opts.addmetadata:
-            postprocessors.append({'key': 'FFmpegAudioFix'})
-        postprocessors.append({'key': 'AtomicParsley'})
+        postprocessors.append({'key': 'EmbedThumbnail'})
     # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
     # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
     if opts.exec_cmd:
@@ -289,7 +283,6 @@ def _real_main(argv=None):
         'simulate': opts.simulate or any_getting,
         'skip_download': opts.skip_download,
         'format': opts.format,
-        'format_limit': opts.format_limit,
         'listformats': opts.listformats,
         'outtmpl': outtmpl,
         'autonumber_size': opts.autonumber_size,

youtube_dl/compat.py

@@ -46,11 +46,6 @@ try:
 except ImportError:  # Python 2
     import htmlentitydefs as compat_html_entities
 
-try:
-    import html.parser as compat_html_parser
-except ImportError:  # Python 2
-    import HTMLParser as compat_html_parser
-
 try:
     import http.client as compat_http_client
 except ImportError:  # Python 2
@@ -404,7 +399,6 @@ __all__ = [
     'compat_getenv',
     'compat_getpass',
     'compat_html_entities',
-    'compat_html_parser',
     'compat_http_client',
     'compat_http_server',
     'compat_kwargs',

youtube_dl/downloader/__init__.py

@@ -6,7 +6,7 @@ from .f4m import F4mFD
 from .hls import HlsFD
 from .hls import NativeHlsFD
 from .http import HttpFD
-from .mplayer import MplayerFD
+from .rtsp import RtspFD
 from .rtmp import RtmpFD
 
 from ..utils import (
@@ -17,8 +17,8 @@ PROTOCOL_MAP = {
     'rtmp': RtmpFD,
     'm3u8_native': NativeHlsFD,
     'm3u8': HlsFD,
-    'mms': MplayerFD,
-    'rtsp': MplayerFD,
+    'mms': RtspFD,
+    'rtsp': RtspFD,
     'f4m': F4mFD,
 }
 

youtube_dl/downloader/common.py

@@ -8,6 +8,7 @@ import time
 from ..compat import compat_str
 from ..utils import (
     encodeFilename,
+    decodeArgument,
     format_bytes,
     timeconvert,
 )
@@ -353,19 +354,15 @@ class FileDownloader(object):
         # this interface
         self._progress_hooks.append(ph)
 
-    def _debug_cmd(self, args, subprocess_encoding, exe=None):
+    def _debug_cmd(self, args, exe=None):
         if not self.params.get('verbose', False):
             return
 
-        if exe is None:
-            exe = os.path.basename(args[0])
+        str_args = [decodeArgument(a) for a in args]
+
+        if exe is None:
+            exe = os.path.basename(str_args[0])
 
-        if subprocess_encoding:
-            str_args = [
-                a.decode(subprocess_encoding) if isinstance(a, bytes) else a
-                for a in args]
-        else:
-            str_args = args
         try:
             import pipes
             shell_quote = lambda args: ' '.join(map(pipes.quote, str_args))

youtube_dl/downloader/external.py

@@ -2,11 +2,11 @@ from __future__ import unicode_literals
 
 import os.path
 import subprocess
-import sys
 
 from .common import FileDownloader
 from ..utils import (
     encodeFilename,
+    encodeArgument,
 )
 
 
@@ -60,17 +60,9 @@ class ExternalFD(FileDownloader):
 
     def _call_downloader(self, tmpfilename, info_dict):
         """ Either overwrite this or implement _make_cmd """
-        cmd = self._make_cmd(tmpfilename, info_dict)
+        cmd = [encodeArgument(a) for a in self._make_cmd(tmpfilename, info_dict)]
 
-        if sys.platform == 'win32' and sys.version_info < (3, 0):
-            # Windows subprocess module does not actually support Unicode
-            # on Python 2.x
-            # See http://stackoverflow.com/a/9951851/35070
-            subprocess_encoding = sys.getfilesystemencoding()
-            cmd = [a.encode(subprocess_encoding, 'ignore') for a in cmd]
-        else:
-            subprocess_encoding = None
-        self._debug_cmd(cmd, subprocess_encoding)
+        self._debug_cmd(cmd)
 
         p = subprocess.Popen(
             cmd, stderr=subprocess.PIPE)

youtube_dl/downloader/f4m.py

@@ -389,6 +389,8 @@ class F4mFD(FileDownloader):
             url = base_url + name
             if akamai_pv:
                 url += '?' + akamai_pv.strip(';')
+            if info_dict.get('extra_param_to_segment_url'):
+                url += info_dict.get('extra_param_to_segment_url')
             frag_filename = '%s-%s' % (tmpfilename, name)
             try:
                 success = http_dl.download(frag_filename, {'url': url})

youtube_dl/downloader/http.py

@@ -28,13 +28,8 @@ class HttpFD(FileDownloader):
         add_headers = info_dict.get('http_headers')
         if add_headers:
             headers.update(add_headers)
-        data = info_dict.get('http_post_data')
-        http_method = info_dict.get('http_method')
-        basic_request = compat_urllib_request.Request(url, data, headers)
-        request = compat_urllib_request.Request(url, data, headers)
-        if http_method is not None:
-            basic_request.get_method = lambda: http_method
-            request.get_method = lambda: http_method
+        basic_request = compat_urllib_request.Request(url, None, headers)
+        request = compat_urllib_request.Request(url, None, headers)
 
         is_test = self.params.get('test', False)
 

youtube_dl/downloader/rtmp.py

@@ -3,7 +3,6 @@ from __future__ import unicode_literals
 import os
 import re
 import subprocess
-import sys
 import time
 
 from .common import FileDownloader
@@ -11,6 +10,7 @@ from ..compat import compat_str
 from ..utils import (
     check_executable,
     encodeFilename,
+    encodeArgument,
     get_exe_version,
 )
 
@@ -121,7 +121,7 @@ class RtmpFD(FileDownloader):
         # possible. This is part of rtmpdump's normal usage, AFAIK.
         basic_args = [
             'rtmpdump', '--verbose', '-r', url,
-            '-o', encodeFilename(tmpfilename, True)]
+            '-o', tmpfilename]
         if player_url is not None:
             basic_args += ['--swfVfy', player_url]
         if page_url is not None:
@@ -154,16 +154,9 @@ class RtmpFD(FileDownloader):
         if not live and continue_dl:
             args += ['--skip', '1']
 
-        if sys.platform == 'win32' and sys.version_info < (3, 0):
-            # Windows subprocess module does not actually support Unicode
-            # on Python 2.x
-            # See http://stackoverflow.com/a/9951851/35070
-            subprocess_encoding = sys.getfilesystemencoding()
-            args = [a.encode(subprocess_encoding, 'ignore') for a in args]
-        else:
-            subprocess_encoding = None
+        args = [encodeArgument(a) for a in args]
 
-        self._debug_cmd(args, subprocess_encoding, exe='rtmpdump')
+        self._debug_cmd(args, exe='rtmpdump')
 
         RD_SUCCESS = 0
         RD_FAILED = 1
@@ -180,7 +173,11 @@ class RtmpFD(FileDownloader):
             prevsize = os.path.getsize(encodeFilename(tmpfilename))
             self.to_screen('[rtmpdump] %s bytes' % prevsize)
             time.sleep(5.0)  # This seems to be needed
-            retval = run_rtmpdump(basic_args + ['-e'] + [[], ['-k', '1']][retval == RD_FAILED])
+            args = basic_args + ['--resume']
+            if retval == RD_FAILED:
+                args += ['--skip', '1']
+            args = [encodeArgument(a) for a in args]
+            retval = run_rtmpdump(args)
             cursize = os.path.getsize(encodeFilename(tmpfilename))
             if prevsize == cursize and retval == RD_FAILED:
                 break

youtube_dl/downloader/rtsp.py

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

youtube_dl/extractor/__init__.py

@@ -32,6 +32,7 @@ from .atresplayer import AtresPlayerIE
 from .atttechchannel import ATTTechChannelIE
 from .audiomack import AudiomackIE, AudiomackAlbumIE
 from .azubu import AzubuIE
+from .baidu import BaiduVideoIE
 from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE
 from .bbccouk import BBCCoUkIE
@@ -70,6 +71,7 @@ from .chirbit import (
     ChirbitProfileIE,
 )
 from .cinchcast import CinchcastIE
+from .cinemassacre import CinemassacreIE
 from .clipfish import ClipfishIE
 from .cliphunter import CliphunterIE
 from .clipsyndicate import ClipsyndicateIE
@@ -90,6 +92,7 @@ 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
@@ -159,6 +162,7 @@ from .footyroom import FootyRoomIE
 from .fourtube import FourTubeIE
 from .foxgay import FoxgayIE
 from .foxnews import FoxNewsIE
+from .foxsports import FoxSportsIE
 from .franceculture import FranceCultureIE
 from .franceinter import FranceInterIE
 from .francetv import (
@@ -177,12 +181,14 @@ from .gameone import (
     GameOneIE,
     GameOnePlaylistIE,
 )
+from .gamersyde import GamersydeIE
 from .gamespot import GameSpotIE
 from .gamestar import GameStarIE
 from .gametrailers import GametrailersIE
 from .gazeta import GazetaIE
 from .gdcvault import GDCVaultIE
 from .generic import GenericIE
+from .gfycat import GfycatIE
 from .giantbomb import GiantBombIE
 from .giga import GigaIE
 from .glide import GlideIE
@@ -194,7 +200,6 @@ from .googleplus import GooglePlusIE
 from .googlesearch import GoogleSearchIE
 from .gorillavid import GorillaVidIE
 from .goshgay import GoshgayIE
-from .grooveshark import GroovesharkIE
 from .groupon import GrouponIE
 from .hark import HarkIE
 from .hearthisat import HearThisAtIE
@@ -271,6 +276,7 @@ from .macgamestore import MacGameStoreIE
 from .mailru import MailRuIE
 from .malemotion import MalemotionIE
 from .mdr import MDRIE
+from .megavideoz import MegaVideozIE
 from .metacafe import MetacafeIE
 from .metacritic import MetacriticIE
 from .mgoon import MgoonIE
@@ -372,6 +378,7 @@ from .orf import (
 from .parliamentliveuk import ParliamentLiveUKIE
 from .patreon import PatreonIE
 from .pbs import PBSIE
+from .philharmoniedeparis import PhilharmonieDeParisIE
 from .phoenix import PhoenixIE
 from .photobucket import PhotobucketIE
 from .planetaplay import PlanetaPlayIE
@@ -387,15 +394,22 @@ 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
@@ -435,7 +449,8 @@ from .sbs import SBSIE
 from .scivee import SciVeeIE
 from .screencast import ScreencastIE
 from .screencastomatic import ScreencastOMaticIE
-from .screenwavemedia import CinemassacreIE, ScreenwaveMediaIE, TeamFourIE
+from .screenwavemedia import ScreenwaveMediaIE, TeamFourIE
+from .senateisvp import SenateISVPIE
 from .servingsys import ServingSysIE
 from .sexu import SexuIE
 from .sexykarma import SexyKarmaIE
@@ -465,9 +480,11 @@ from .soundgasm import (
 )
 from .southpark import (
     SouthParkIE,
+    SouthParkEsIE,
     SouthparkDeIE,
 )
 from .space import SpaceIE
+from .spankbang import SpankBangIE
 from .spankwire import SpankwireIE
 from .spiegel import SpiegelIE, SpiegelArticleIE
 from .spiegeltv import SpiegeltvIE
@@ -475,6 +492,7 @@ 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
@@ -553,6 +571,7 @@ from .udemy import (
     UdemyIE,
     UdemyCourseIE
 )
+from .udn import UDNEmbedIE
 from .ultimedia import UltimediaIE
 from .unistra import UnistraIE
 from .urort import UrortIE

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/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/baidu.py

@@ -0,0 +1,68 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_urlparse
+
+
+class BaiduVideoIE(InfoExtractor):
+    _VALID_URL = r'http://v\.baidu\.com/(?P<type>[a-z]+)/(?P<id>\d+)\.htm'
+    _TESTS = [{
+        'url': 'http://v.baidu.com/comic/1069.htm?frp=bdbrand&q=%E4%B8%AD%E5%8D%8E%E5%B0%8F%E5%BD%93%E5%AE%B6',
+        'info_dict': {
+            'id': '1069',
+            'title': '中华小当家 TV版 (全52集)',
+            'description': 'md5:395a419e41215e531c857bb037bbaf80',
+        },
+        'playlist_count': 52,
+    }, {
+        'url': 'http://v.baidu.com/show/11595.htm?frp=bdbrand',
+        'info_dict': {
+            'id': '11595',
+            'title': 're:^奔跑吧兄弟',
+            'description': 'md5:1bf88bad6d850930f542d51547c089b8',
+        },
+        'playlist_mincount': 3,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        playlist_id = mobj.group('id')
+        category = category2 = mobj.group('type')
+        if category == 'show':
+            category2 = 'tvshow'
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        playlist_title = self._html_search_regex(
+            r'title\s*:\s*(["\'])(?P<title>[^\']+)\1', webpage,
+            'playlist title', group='title')
+        playlist_description = self._html_search_regex(
+            r'<input[^>]+class="j-data-intro"[^>]+value="([^"]+)"/>', webpage,
+            playlist_id, 'playlist description')
+
+        site = self._html_search_regex(
+            r'filterSite\s*:\s*["\']([^"]*)["\']', webpage,
+            'primary provider site')
+        api_result = self._download_json(
+            'http://v.baidu.com/%s_intro/?dtype=%sPlayUrl&id=%s&site=%s' % (
+                category, category2, playlist_id, site),
+            playlist_id, 'Get playlist links')
+
+        entries = []
+        for episode in api_result[0]['episodes']:
+            episode_id = '%s_%s' % (playlist_id, episode['episode'])
+
+            redirect_page = self._download_webpage(
+                compat_urlparse.urljoin(url, episode['url']), episode_id,
+                note='Download Baidu redirect page')
+            real_url = self._html_search_regex(
+                r'location\.replace\("([^"]+)"\)', redirect_page, 'real URL')
+
+            entries.append(self.url_result(
+                real_url, video_title=episode['single_title']))
+
+        return self.playlist_result(
+            entries, playlist_id, playlist_title, playlist_description)

youtube_dl/extractor/bambuser.py

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

youtube_dl/extractor/bandcamp.py

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

youtube_dl/extractor/bbccouk.py

@@ -3,7 +3,10 @@ from __future__ import unicode_literals
 import xml.etree.ElementTree
 
 from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+)
 from ..compat import compat_HTTPError
 
 
@@ -112,6 +115,20 @@ class BBCCoUkIE(InfoExtractor):
                 # rtmp download
                 'skip_download': True,
             }
+        }, {
+            'url': 'http://www.bbc.co.uk/iplayer/episode/b054fn09/ad/natural-world-20152016-2-super-powered-owls',
+            'info_dict': {
+                'id': 'p02n76xf',
+                'ext': 'flv',
+                'title': 'Natural World, 2015-2016: 2. Super Powered Owls',
+                'description': 'md5:e4db5c937d0e95a7c6b5e654d429183d',
+                'duration': 3540,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+            'skip': 'geolocation',
         }, {
             'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
             'only_matching': True,
@@ -326,16 +343,27 @@ class BBCCoUkIE(InfoExtractor):
 
         webpage = self._download_webpage(url, group_id, 'Downloading video page')
 
-        programme_id = self._search_regex(
-            r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None)
+        programme_id = None
+
+        tviplayer = self._search_regex(
+            r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById',
+            webpage, 'player', default=None)
+
+        if tviplayer:
+            player = self._parse_json(tviplayer, group_id).get('player', {})
+            duration = int_or_none(player.get('duration'))
+            programme_id = player.get('vpid')
+
+        if not programme_id:
+            programme_id = self._search_regex(
+                r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None)
+
         if programme_id:
-            player = self._download_json(
-                'http://www.bbc.co.uk/iplayer/episode/%s.json' % group_id,
-                group_id)['jsConf']['player']
-            title = player['title']
-            description = player['subtitle']
-            duration = player['duration']
             formats, subtitles = self._download_media_selector(programme_id)
+            title = self._og_search_title(webpage)
+            description = self._search_regex(
+                r'<p class="medium-description">([^<]+)</p>',
+                webpage, 'description', fatal=False)
         else:
             programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
 
@@ -345,6 +373,7 @@ class BBCCoUkIE(InfoExtractor):
             'id': programme_id,
             'title': title,
             'description': description,
+            'thumbnail': self._og_search_thumbnail(webpage, default=None),
             'duration': duration,
             'formats': formats,
             'subtitles': subtitles,

youtube_dl/extractor/bilibili.py

@@ -2,34 +2,45 @@
 from __future__ import unicode_literals
 
 import re
+import itertools
 
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
     unified_strdate,
+    ExtractorError,
 )
 
 
 class BiliBiliIE(InfoExtractor):
     _VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>[0-9]+)/'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.bilibili.tv/video/av1074402/',
         'md5': '2c301e4dab317596e837c3e7633e7d86',
         'info_dict': {
-            'id': '1074402',
+            'id': '1074402_part1',
             'ext': 'flv',
             'title': '【金坷垃】金泡沫',
             'duration': 308,
             'upload_date': '20140420',
             'thumbnail': 're:^https?://.+\.jpg',
         },
-    }
+    }, {
+        'url': 'http://www.bilibili.com/video/av1041170/',
+        'info_dict': {
+            'id': '1041170',
+            'title': '【BD1080P】刀语【诸神&异域】',
+        },
+        'playlist_count': 9,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
+        if self._search_regex(r'(此视频不存在或被删除)', webpage, 'error message', default=None):
+            raise ExtractorError('The video does not exist or was deleted', expected=True)
         video_code = self._search_regex(
             r'(?s)<div itemprop="video".*?>(.*?)</div>', webpage, 'video code')
 
@@ -54,19 +65,14 @@ class BiliBiliIE(InfoExtractor):
 
         cid = self._search_regex(r'cid=(\d+)', webpage, 'cid')
 
+        entries = []
+
         lq_doc = self._download_xml(
             'http://interface.bilibili.com/v_cdn_play?appkey=1&cid=%s' % cid,
             video_id,
             note='Downloading LQ video info'
         )
-        lq_durl = lq_doc.find('./durl')
-        formats = [{
-            'format_id': 'lq',
-            'quality': 1,
-            'url': lq_durl.find('./url').text,
-            'filesize': int_or_none(
-                lq_durl.find('./size'), get_attr='text'),
-        }]
+        lq_durls = lq_doc.findall('./durl')
 
         hq_doc = self._download_xml(
             'http://interface.bilibili.com/playurl?appkey=1&cid=%s' % cid,
@@ -74,23 +80,44 @@ class BiliBiliIE(InfoExtractor):
             note='Downloading HQ video info',
             fatal=False,
         )
-        if hq_doc is not False:
-            hq_durl = hq_doc.find('./durl')
-            formats.append({
-                'format_id': 'hq',
-                'quality': 2,
-                'ext': 'flv',
-                'url': hq_durl.find('./url').text,
+        hq_durls = hq_doc.findall('./durl') if hq_doc is not False else itertools.repeat(None)
+
+        assert len(lq_durls) == len(hq_durls)
+
+        i = 1
+        for lq_durl, hq_durl in zip(lq_durls, hq_durls):
+            formats = [{
+                'format_id': 'lq',
+                'quality': 1,
+                'url': lq_durl.find('./url').text,
                 'filesize': int_or_none(
-                    hq_durl.find('./size'), get_attr='text'),
+                    lq_durl.find('./size'), get_attr='text'),
+            }]
+            if hq_durl:
+                formats.append({
+                    'format_id': 'hq',
+                    'quality': 2,
+                    'ext': 'flv',
+                    'url': hq_durl.find('./url').text,
+                    'filesize': int_or_none(
+                        hq_durl.find('./size'), get_attr='text'),
+                })
+            self._sort_formats(formats)
+
+            entries.append({
+                'id': '%s_part%d' % (video_id, i),
+                'title': title,
+                'formats': formats,
+                'duration': duration,
+                'upload_date': upload_date,
+                'thumbnail': thumbnail,
             })
 
-        self._sort_formats(formats)
+            i += 1
+
         return {
+            '_type': 'multi_video',
+            'entries': entries,
             'id': video_id,
-            'title': title,
-            'formats': formats,
-            'duration': duration,
-            'upload_date': upload_date,
-            'thumbnail': thumbnail,
+            'title': title
         }

youtube_dl/extractor/bliptv.py

@@ -102,6 +102,15 @@ class BlipTVIE(InfoExtractor):
         },
     ]
 
+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage)
+        if mobj:
+            return 'http://blip.tv/a/a-' + mobj.group(1)
+        mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage)
+        if mobj:
+            return mobj.group(1)
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         lookup_id = mobj.group('lookup_id')
@@ -172,6 +181,7 @@ 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/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/cinemassacre.py

@@ -0,0 +1,99 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+from .bliptv import BlipTVIE
+
+
+class CinemassacreIE(InfoExtractor):
+    _VALID_URL = 'https?://(?:www\.)?cinemassacre\.com/(?P<date_y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/(?P<display_id>[^?#/]+)'
+    _TESTS = [
+        {
+            'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
+            'md5': 'fde81fbafaee331785f58cd6c0d46190',
+            'info_dict': {
+                'id': 'Cinemassacre-19911',
+                'ext': 'mp4',
+                'upload_date': '20121110',
+                'title': '“Angry Video Game Nerd: The Movie” – Trailer',
+                'description': 'md5:fb87405fcb42a331742a0dce2708560b',
+            },
+        },
+        {
+            'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
+            'md5': 'd72f10cd39eac4215048f62ab477a511',
+            'info_dict': {
+                'id': 'Cinemassacre-521be8ef82b16',
+                'ext': 'mp4',
+                'upload_date': '20131002',
+                'title': 'The Mummy’s Hand (1940)',
+            },
+        },
+        {
+            # blip.tv embedded video
+            'url': 'http://cinemassacre.com/2006/12/07/chronologically-confused-about-bad-movie-and-video-game-sequel-titles/',
+            'md5': 'ca9b3c8dd5a66f9375daeb5135f5a3de',
+            'info_dict': {
+                'id': '4065369',
+                'ext': 'flv',
+                'title': 'AVGN: Chronologically Confused about Bad Movie and Video Game Sequel Titles',
+                'upload_date': '20061207',
+                'uploader': 'cinemassacre',
+                'uploader_id': '250778',
+                'timestamp': 1283233867,
+                'description': 'md5:0a108c78d130676b207d0f6d029ecffd',
+            }
+        },
+        {
+            # Youtube embedded video
+            'url': 'http://cinemassacre.com/2006/09/01/mckids/',
+            'md5': '6eb30961fa795fedc750eac4881ad2e1',
+            'info_dict': {
+                'id': 'FnxsNhuikpo',
+                'ext': 'mp4',
+                'upload_date': '20060901',
+                'uploader': 'Cinemassacre Extras',
+                'description': 'md5:de9b751efa9e45fbaafd9c8a1123ed53',
+                'uploader_id': 'Cinemassacre',
+                'title': 'AVGN: McKids',
+            }
+        }
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('display_id')
+        video_date = mobj.group('date_y') + mobj.group('date_m') + mobj.group('date_d')
+
+        webpage = self._download_webpage(url, display_id)
+
+        playerdata_url = self._search_regex(
+            [
+                r'src="(http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
+                r'<iframe[^>]+src="((?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"',
+            ],
+            webpage, 'player data URL', default=None)
+        if not playerdata_url:
+            playerdata_url = BlipTVIE._extract_url(webpage)
+        if not playerdata_url:
+            raise ExtractorError('Unable to find player data')
+
+        video_title = self._html_search_regex(
+            r'<title>(?P<title>.+?)\|', webpage, 'title')
+        video_description = self._html_search_regex(
+            r'<div class="entry-content">(?P<description>.+?)</div>',
+            webpage, 'description', flags=re.DOTALL, fatal=False)
+        video_thumbnail = self._og_search_thumbnail(webpage)
+
+        return {
+            '_type': 'url_transparent',
+            'display_id': display_id,
+            'title': video_title,
+            'description': video_description,
+            'upload_date': video_date,
+            'thumbnail': video_thumbnail,
+            'url': playerdata_url,
+        }

youtube_dl/extractor/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|ktvk)(?:-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',
@@ -48,6 +48,9 @@ class CNNIE(InfoExtractor):
     }, {
         '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/comedycentral.py

@@ -201,7 +201,7 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
 
         uri = mMovieParams[0][1]
         # Correct cc.com in uri
-        uri = re.sub(r'(episode:[^.]+)(\.cc)?\.com', r'\1.cc.com', uri)
+        uri = re.sub(r'(episode:[^.]+)(\.cc)?\.com', r'\1.com', uri)
 
         index_url = 'http://%s.cc.com/feeds/mrss?%s' % (show_name, compat_urllib_parse.urlencode({'uri': uri}))
         idoc = self._download_xml(

youtube_dl/extractor/common.py

@@ -23,6 +23,7 @@ from ..compat import (
 )
 from ..utils import (
     age_restricted,
+    bug_reports_message,
     clean_html,
     compiled_regex_type,
     ExtractorError,
@@ -46,7 +47,7 @@ class InfoExtractor(object):
     information possibly downloading the video to the file system, among
     other possible outcomes.
 
-    The type field determines the the type of the result.
+    The type field determines the type of the result.
     By far the most common value (and the default if _type is missing) is
     "video", which indicates a single video.
 
@@ -110,11 +111,8 @@ class InfoExtractor(object):
                                   (quality takes higher priority)
                                  -1 for default (order by other properties),
                                  -2 or smaller for less than default.
-                    * http_method  HTTP method to use for the download.
                     * http_headers  A dictionary of additional HTTP headers
                                  to add to the request.
-                    * http_post_data  Additional data to send with a POST
-                                 request.
                     * stretched_ratio  If given and not 1, indicates that the
                                  video's pixels are not square.
                                  width : height ratio as float.
@@ -324,7 +322,7 @@ 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 +332,11 @@ 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 +349,16 @@ 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 +415,13 @@ 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 +436,10 @@ 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 +450,10 @@ 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 +498,7 @@ 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 +506,8 @@ 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
@@ -546,8 +554,7 @@ class InfoExtractor(object):
         elif fatal:
             raise RegexNotFoundError('Unable to extract %s' % _name)
         else:
-            self._downloader.report_warning('unable to extract %s; '
-                                            'please report this issue on http://yt-dl.org/bug' % _name)
+            self._downloader.report_warning('unable to extract %s' % _name + bug_reports_message())
             return None
 
     def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None):
@@ -562,7 +569,7 @@ class InfoExtractor(object):
 
     def _get_login_info(self):
         """
-        Get the the login info as (username, password)
+        Get the login info as (username, password)
         It will look in the netrc file using the _NETRC_MACHINE value
         If there's no info available, return (None, None)
         """
@@ -698,7 +705,7 @@ class InfoExtractor(object):
         return self._html_search_meta('twitter:player', html,
                                       'twitter card player')
 
-    def _sort_formats(self, formats):
+    def _sort_formats(self, formats, field_preference=None):
         if not formats:
             raise ExtractorError('No video formats found')
 
@@ -708,6 +715,9 @@ class InfoExtractor(object):
             if not f.get('ext') and 'url' in f:
                 f['ext'] = determine_ext(f['url'])
 
+            if isinstance(field_preference, (list, tuple)):
+                return tuple(f.get(field) if f.get(field) is not None else -1 for field in field_preference)
+
             preference = f.get('preference')
             if preference is None:
                 proto = f.get('protocol')
@@ -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,

youtube_dl/extractor/cracked.py

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

youtube_dl/extractor/crooksandliars.py

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

youtube_dl/extractor/crunchyroll.py

@@ -263,8 +263,8 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             streamdata = self._download_xml(
                 streamdata_req, video_id,
                 note='Downloading media info for %s' % video_format)
-            video_url = streamdata.find('.//host').text
-            video_play_path = streamdata.find('.//file').text
+            video_url = streamdata.find('./host').text
+            video_play_path = streamdata.find('./file').text
             formats.append({
                 'url': video_url,
                 'play_path': video_play_path,

youtube_dl/extractor/cspan.py

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

youtube_dl/extractor/dailymotion.py

@@ -85,7 +85,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        url = 'http://www.dailymotion.com/video/%s' % video_id
+        url = 'https://www.dailymotion.com/video/%s' % video_id
 
         # Retrieve video webpage to extract further information
         request = self._build_request(url)
@@ -110,7 +110,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
         if mobj is not None:
             video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
 
-        embed_url = 'http://www.dailymotion.com/embed/video/%s' % video_id
+        embed_url = 'https://www.dailymotion.com/embed/video/%s' % video_id
         embed_request = self._build_request(embed_url)
         embed_page = self._download_webpage(
             embed_request, video_id, 'Downloading embed page')
@@ -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/dotsub.py

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

youtube_dl/extractor/dreisat.py

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

youtube_dl/extractor/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

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import base64
 
 from .common import InfoExtractor
+from ..compat import compat_urllib_request
 from ..utils import qualities
 
 
@@ -23,7 +24,10 @@ class DumpertIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+
+        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')

youtube_dl/extractor/eagleplatform.py

@@ -45,6 +45,7 @@ class EaglePlatformIE(InfoExtractor):
             'duration': 216,
             'view_count': int,
         },
+        'skip': 'Georestricted',
     }]
 
     def _handle_error(self, response):

youtube_dl/extractor/ellentv.py

@@ -6,56 +6,42 @@ import json
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
-    parse_iso8601,
 )
 
 
 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',
+    _TEST = {
+        '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': 'md5:587e79fbbd0d73b148bc596d99ce48e6',
+            'timestamp': 1428035648,
+            'upload_date': '20150403',
+            'uploader_id': 'batchUser',
         }
-    }, {
-        'url': 'http://ellentube.com/videos/0-dvzmabd5/',
-        'md5': '98238118eaa2bbdf6ad7f708e3e4f4eb',
-        'info_dict': {
-            'id': '0-dvzmabd5',
-            'ext': 'mp4',
-            'title': '1 year old twin sister makes her brother laugh',
-            'description': '1 year old twin sister makes her brother laugh',
-            'timestamp': 1419542075,
-            'upload_date': '20141225',
-        }
-    }]
+    }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
-        video_url = self._html_search_meta('VideoURL', webpage, 'url')
-        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 = self._download_webpage(
+            'http://widgets.ellentube.com/videos/%s' % video_id,
+            video_id)
 
-        return {
-            'id': video_id,
-            'url': video_url,
-            'title': title,
-            'description': description,
-            'timestamp': timestamp,
-        }
+        partner_id = self._search_regex(
+            r"var\s+partnerId\s*=\s*'([^']+)", webpage, 'partner id')
+
+        kaltura_id = self._search_regex(
+            [r'id="kaltura_player_([^"]+)"',
+             r"_wb_entry_id\s*:\s*'([^']+)",
+             r'data-kaltura-entry-id="([^"]+)'],
+            webpage, 'kaltura id')
+
+        return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura')
 
 
 class EllenTVClipsIE(InfoExtractor):
@@ -67,7 +53,7 @@ class EllenTVClipsIE(InfoExtractor):
             'id': 'meryl-streep-vanessa-hudgens',
             'title': 'Meryl Streep, Vanessa Hudgens',
         },
-        'playlist_mincount': 9,
+        'playlist_mincount': 7,
     }
 
     def _real_extract(self, url):
@@ -91,4 +77,8 @@ class EllenTVClipsIE(InfoExtractor):
             raise ExtractorError('Failed to download JSON', cause=ve)
 
     def _extract_entries(self, playlist):
-        return [self.url_result(item['url'], 'EllenTV') for item in playlist]
+        return [
+            self.url_result(
+                'kaltura:%s:%s' % (item['kaltura_partner_id'], item['kaltura_entry_id']),
+                'Kaltura')
+            for item in playlist]

youtube_dl/extractor/escapist.py

@@ -1,128 +1,107 @@
 from __future__ import unicode_literals
 
+import json
+
 from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse,
-    compat_urllib_request,
-)
+from ..compat import compat_urllib_request
+
 from ..utils import (
-    ExtractorError,
-    js_to_json,
-    parse_duration,
+    determine_ext,
+    clean_html,
+    int_or_none,
+    float_or_none,
 )
 
 
+def _decrypt_config(key, string):
+    a = ''
+    i = ''
+    r = ''
+
+    while len(a) < (len(string) / 2):
+        a += key
+
+    a = a[0:int(len(string) / 2)]
+
+    t = 0
+    while t < len(string):
+        i += chr(int(string[t] + string[t + 1], 16))
+        t += 2
+
+    icko = [s for s in i]
+
+    for t, c in enumerate(a):
+        r += chr(ord(c) ^ ord(icko[t]))
+
+    return r
+
+
 class EscapistIE(InfoExtractor):
-    _VALID_URL = r'https?://?(www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P<id>[0-9]+)-[^/?#]*(?:$|[?#])'
-    _USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko'
-    _TEST = {
+    _VALID_URL = r'https?://?(?:www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P<id>[0-9]+)-[^/?#]*(?:$|[?#])'
+    _TESTS = [{
         'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
         'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
         'info_dict': {
             'id': '6618',
             'ext': 'mp4',
             'description': "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
-            'uploader_id': 'the-escapist-presents',
-            'uploader': 'The Escapist Presents',
             'title': "Breaking Down Baldur's Gate",
             'thumbnail': 're:^https?://.*\.jpg$',
             'duration': 264,
+            'uploader': 'The Escapist',
         }
-    }
+    }, {
+        'url': 'http://www.escapistmagazine.com/videos/view/zero-punctuation/10044-Evolve-One-vs-Multiplayer',
+        'md5': '9e8c437b0dbb0387d3bd3255ca77f6bf',
+        'info_dict': {
+            'id': '10044',
+            'ext': 'mp4',
+            'description': 'This week, Zero Punctuation reviews Evolve.',
+            'title': 'Evolve - One vs Multiplayer',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 304,
+            'uploader': 'The Escapist',
+        }
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage_req = compat_urllib_request.Request(url)
-        webpage_req.add_header('User-Agent', self._USER_AGENT)
-        webpage = self._download_webpage(webpage_req, video_id)
+        webpage = self._download_webpage(url, video_id)
 
-        uploader_id = self._html_search_regex(
-            r"<h1\s+class='headline'>\s*<a\s+href='/videos/view/(.*?)'",
-            webpage, 'uploader ID', fatal=False)
-        uploader = self._html_search_regex(
-            r"<h1\s+class='headline'>(.*?)</a>",
-            webpage, 'uploader', fatal=False)
-        description = self._html_search_meta('description', webpage)
-        duration = parse_duration(self._html_search_meta('duration', webpage))
+        ims_video = self._parse_json(
+            self._search_regex(
+                r'imsVideo\.play\(({.+?})\);', webpage, 'imsVideo'),
+            video_id)
+        video_id = ims_video['videoID']
+        key = ims_video['hash']
 
-        raw_title = self._html_search_meta('title', webpage, fatal=True)
-        title = raw_title.partition(' : ')[2]
+        config_req = compat_urllib_request.Request(
+            'http://www.escapistmagazine.com/videos/'
+            'vidconfig.php?videoID=%s&hash=%s' % (video_id, key))
+        config_req.add_header('Referer', url)
+        config = self._download_webpage(config_req, video_id, 'Downloading video config')
 
-        config_url = compat_urllib_parse.unquote(self._html_search_regex(
-            r'''(?x)
-            (?:
-                <param\s+name="flashvars".*?\s+value="config=|
-                flashvars=&quot;config=
-            )
-            (https?://[^"&]+)
-            ''',
-            webpage, 'config URL'))
+        data = json.loads(_decrypt_config(key, config))
 
-        formats = []
-        ad_formats = []
+        video_data = data['videoData']
 
-        def _add_format(name, cfg_url, quality):
-            cfg_req = compat_urllib_request.Request(cfg_url)
-            cfg_req.add_header('User-Agent', self._USER_AGENT)
-            config = self._download_json(
-                cfg_req, video_id,
-                'Downloading ' + name + ' configuration',
-                'Unable to download ' + name + ' configuration',
-                transform_source=js_to_json)
+        title = clean_html(video_data['title'])
+        duration = float_or_none(video_data.get('duration'), 1000)
+        uploader = video_data.get('publisher')
 
-            playlist = config['playlist']
-            for p in playlist:
-                if p.get('eventCategory') == 'Video':
-                    ar = formats
-                elif p.get('eventCategory') == 'Video Postroll':
-                    ar = ad_formats
-                else:
-                    continue
-
-                ar.append({
-                    'url': p['url'],
-                    'format_id': name,
-                    'quality': quality,
-                    'http_headers': {
-                        'User-Agent': self._USER_AGENT,
-                    },
-                })
-
-        _add_format('normal', config_url, quality=0)
-        hq_url = (config_url +
-                  ('&hq=1' if '?' in config_url else config_url + '?hq=1'))
-        try:
-            _add_format('hq', hq_url, quality=1)
-        except ExtractorError:
-            pass  # That's fine, we'll just use normal quality
+        formats = [{
+            'url': video['src'],
+            'format_id': '%s-%sp' % (determine_ext(video['src']), video['res']),
+            'height': int_or_none(video.get('res')),
+        } for video in data['files']['videos']]
         self._sort_formats(formats)
 
-        if '/escapist/sales-marketing/' in formats[-1]['url']:
-            raise ExtractorError('This IP address has been blocked by The Escapist', expected=True)
-
-        res = {
+        return {
             'id': video_id,
             'formats': formats,
-            'uploader': uploader,
-            'uploader_id': uploader_id,
             'title': title,
             'thumbnail': self._og_search_thumbnail(webpage),
-            'description': description,
+            'description': self._og_search_description(webpage),
             'duration': duration,
+            'uploader': uploader,
         }
-
-        if self._downloader.params.get('include_ads') and ad_formats:
-            self._sort_formats(ad_formats)
-            ad_res = {
-                'id': '%s-ad' % video_id,
-                'title': '%s (Postroll)' % title,
-                'formats': ad_formats,
-            }
-            return {
-                '_type': 'playlist',
-                'entries': [res, ad_res],
-                'title': title,
-                'id': video_id,
-            }
-
-        return res

youtube_dl/extractor/facebook.py

@@ -24,8 +24,12 @@ class FacebookIE(InfoExtractor):
     _VALID_URL = r'''(?x)
         https?://(?:\w+\.)?facebook\.com/
         (?:[^#]*?\#!/)?
-        (?:video/video\.php|photo\.php|video\.php|video/embed)\?(?:.*?)
-        (?:v|video_id)=(?P<id>[0-9]+)
+        (?:
+            (?:video/video\.php|photo\.php|video\.php|video/embed)\?(?:.*?)
+            (?:v|video_id)=|
+            [^/]+/videos/(?:[^/]+/)?
+        )
+        (?P<id>[0-9]+)
         (?:.*)'''
     _LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1'
     _CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1'
@@ -50,6 +54,12 @@ class FacebookIE(InfoExtractor):
     }, {
         'url': 'https://www.facebook.com/video.php?v=10204634152394104',
         'only_matching': True,
+    }, {
+        'url': 'https://www.facebook.com/amogood/videos/1618742068337349/?fref=nf',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.facebook.com/ChristyClarkForBC/videos/vb.22819070941/10153870694020942/?type=2&theater',
+        'only_matching': True,
     }]
 
     def _login(self):

youtube_dl/extractor/flickr.py

@@ -3,9 +3,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_urllib_request
 from ..utils import (
     ExtractorError,
-    unescapeHTML,
+    find_xpath_attr,
 )
 
 
@@ -29,25 +30,31 @@ class FlickrIE(InfoExtractor):
         video_id = mobj.group('id')
         video_uploader_id = mobj.group('uploader_id')
         webpage_url = 'http://www.flickr.com/photos/' + video_uploader_id + '/' + video_id
-        webpage = self._download_webpage(webpage_url, video_id)
+        req = compat_urllib_request.Request(webpage_url)
+        req.add_header(
+            'User-Agent',
+            # it needs a more recent version
+            'Mozilla/5.0 (X11; Linux x86_64; rv:38.0) Gecko/20150101 Firefox/38.0 (Chrome)')
+        webpage = self._download_webpage(req, video_id)
 
-        secret = self._search_regex(r"photo_secret: '(\w+)'", webpage, 'secret')
+        secret = self._search_regex(r'secret"\s*:\s*"(\w+)"', webpage, 'secret')
 
         first_url = 'https://secure.flickr.com/apps/video/video_mtl_xml.gne?v=x&photo_id=' + video_id + '&secret=' + secret + '&bitrate=700&target=_self'
-        first_xml = self._download_webpage(first_url, video_id, 'Downloading first data webpage')
+        first_xml = self._download_xml(first_url, video_id, 'Downloading first data webpage')
 
-        node_id = self._html_search_regex(r'<Item id="id">(\d+-\d+)</Item>',
-                                          first_xml, 'node_id')
+        node_id = find_xpath_attr(
+            first_xml, './/{http://video.yahoo.com/YEP/1.0/}Item', 'id',
+            'id').text
 
         second_url = 'https://secure.flickr.com/video_playlist.gne?node_id=' + node_id + '&tech=flash&mode=playlist&bitrate=700&secret=' + secret + '&rd=video.yahoo.com&noad=1'
-        second_xml = self._download_webpage(second_url, video_id, 'Downloading second data webpage')
+        second_xml = self._download_xml(second_url, video_id, 'Downloading second data webpage')
 
         self.report_extraction(video_id)
 
-        mobj = re.search(r'<STREAM APP="(.+?)" FULLPATH="(.+?)"', second_xml)
-        if mobj is None:
+        stream = second_xml.find('.//STREAM')
+        if stream is None:
             raise ExtractorError('Unable to extract video url')
-        video_url = mobj.group(1) + unescapeHTML(mobj.group(2))
+        video_url = stream.attrib['APP'] + stream.attrib['FULLPATH']
 
         return {
             'id': video_id,

youtube_dl/extractor/footyroom.py

@@ -6,14 +6,21 @@ from .common import InfoExtractor
 
 class FootyRoomIE(InfoExtractor):
     _VALID_URL = r'http://footyroom\.com/(?P<id>[^/]+)'
-    _TEST = {
+    _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)
@@ -36,6 +43,7 @@ class FootyRoomIE(InfoExtractor):
                 r'data-config="([^"]+)"', payload,
                 'playwire url', default=None)
             if playwire_url:
-                entries.append(self.url_result(playwire_url, 'Playwire'))
+                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/foxsports.py

@@ -0,0 +1,32 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import smuggle_url
+
+
+class FoxSportsIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?foxsports\.com/video\?vid=(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://www.foxsports.com/video?vid=432609859715',
+        'info_dict': {
+            'id': 'gA0bHB3Ladz3',
+            'ext': 'flv',
+            'title': 'Courtney Lee on going up 2-0 in series vs. Blazers',
+            'description': 'Courtney Lee talks about Memphis being focused.',
+        },
+        'add_ie': ['ThePlatform'],
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        config = self._parse_json(
+            self._search_regex(
+                r"data-player-config='([^']+)'", webpage, 'data player config'),
+            video_id)
+
+        return self.url_result(smuggle_url(
+            config['releaseURL'] + '&manifest=f4m', {'force_smil_url': True}))

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/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/gdcvault.py

@@ -11,7 +11,7 @@ from ..utils import remove_end
 
 
 class GDCVaultIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P<id>\d+)/(?P<name>(\w|-)+)'
+    _VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P<id>\d+)/(?P<name>(\w|-)+)?'
     _NETRC_MACHINE = 'gdcvault'
     _TESTS = [
         {
@@ -19,6 +19,7 @@ class GDCVaultIE(InfoExtractor):
             'md5': '7ce8388f544c88b7ac11c7ab1b593704',
             'info_dict': {
                 'id': '1019721',
+                'display_id': 'Doki-Doki-Universe-Sweet-Simple',
                 'ext': 'mp4',
                 'title': 'Doki-Doki Universe: Sweet, Simple and Genuine (GDC Next 10)'
             }
@@ -27,6 +28,7 @@ class GDCVaultIE(InfoExtractor):
             'url': 'http://www.gdcvault.com/play/1015683/Embracing-the-Dark-Art-of',
             'info_dict': {
                 'id': '1015683',
+                'display_id': 'Embracing-the-Dark-Art-of',
                 'ext': 'flv',
                 'title': 'Embracing the Dark Art of Mathematical Modeling in AI'
             },
@@ -39,10 +41,15 @@ class GDCVaultIE(InfoExtractor):
             'md5': 'a5eb77996ef82118afbbe8e48731b98e',
             'info_dict': {
                 'id': '1015301',
+                'display_id': 'Thexder-Meets-Windows-95-or',
                 'ext': 'flv',
                 'title': 'Thexder Meets Windows 95, or Writing Great Games in the Windows 95 Environment',
             },
             'skip': 'Requires login',
+        },
+        {
+            'url': 'http://gdcvault.com/play/1020791/',
+            'only_matching': True,
         }
     ]
 
@@ -90,7 +97,7 @@ class GDCVaultIE(InfoExtractor):
         })
         return video_formats
 
-    def _login(self, webpage_url, video_id):
+    def _login(self, webpage_url, display_id):
         (username, password) = self._get_login_info()
         if username is None or password is None:
             self.report_warning('It looks like ' + webpage_url + ' requires a login. Try specifying a username and password and try again.')
@@ -107,9 +114,9 @@ class GDCVaultIE(InfoExtractor):
 
         request = compat_urllib_request.Request(login_url, compat_urllib_parse.urlencode(login_form))
         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
-        self._download_webpage(request, video_id, 'Logging in')
-        start_page = self._download_webpage(webpage_url, video_id, 'Getting authenticated video page')
-        self._download_webpage(logout_url, video_id, 'Logging out')
+        self._download_webpage(request, display_id, 'Logging in')
+        start_page = self._download_webpage(webpage_url, display_id, 'Getting authenticated video page')
+        self._download_webpage(logout_url, display_id, 'Logging out')
 
         return start_page
 
@@ -117,8 +124,10 @@ class GDCVaultIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
 
         video_id = mobj.group('id')
+        display_id = mobj.group('name') or video_id
+
         webpage_url = 'http://www.gdcvault.com/play/' + video_id
-        start_page = self._download_webpage(webpage_url, video_id)
+        start_page = self._download_webpage(webpage_url, display_id)
 
         direct_url = self._search_regex(
             r's1\.addVariable\("file",\s*encodeURIComponent\("(/[^"]+)"\)\);',
@@ -131,6 +140,7 @@ class GDCVaultIE(InfoExtractor):
 
             return {
                 'id': video_id,
+                'display_id': display_id,
                 'url': video_url,
                 'ext': 'flv',
                 'title': title,
@@ -141,7 +151,7 @@ class GDCVaultIE(InfoExtractor):
             start_page, 'xml root', default=None)
         if xml_root is None:
             # Probably need to authenticate
-            login_res = self._login(webpage_url, video_id)
+            login_res = self._login(webpage_url, display_id)
             if login_res is None:
                 self.report_warning('Could not login.')
             else:
@@ -159,7 +169,7 @@ class GDCVaultIE(InfoExtractor):
             xml_name = self._html_search_regex(r'<iframe src=".*?\?xmlURL=xml/(?P<xml_file>.+?\.xml).*?".*?</iframe>', start_page, 'xml filename')
 
         xml_decription_url = xml_root + 'xml/' + xml_name
-        xml_description = self._download_xml(xml_decription_url, video_id)
+        xml_description = self._download_xml(xml_decription_url, display_id)
 
         video_title = xml_description.find('./metadata/title').text
         video_formats = self._parse_mp4(xml_description)
@@ -168,6 +178,7 @@ class GDCVaultIE(InfoExtractor):
 
         return {
             'id': video_id,
+            'display_id': display_id,
             'title': video_title,
             'formats': video_formats,
         }

youtube_dl/extractor/generic.py

@@ -34,6 +34,9 @@ from .ooyala import OoyalaIE
 from .rutv import RUTVIE
 from .smotri import SmotriIE
 from .condenast import CondeNastIE
+from .udn import UDNEmbedIE
+from .senateisvp import SenateISVPIE
+from .bliptv import BlipTVIE
 
 
 class GenericIE(InfoExtractor):
@@ -410,6 +413,19 @@ class GenericIE(InfoExtractor):
                 'thumbnail': 're:^https?://.*\.jpg$',
             },
         },
+        # MLB articles
+        {
+            'url': 'http://m.mlb.com/news/article/118550098/blue-jays-kevin-pillar-goes-spidey-up-the-wall-to-rob-tim-beckham-of-a-homer',
+            'md5': 'b190e70141fb9a1552a85426b4da1b5d',
+            'info_dict': {
+                'id': '75609783',
+                'ext': 'mp4',
+                'title': 'Must C: Pillar climbs for catch',
+                'description': '4/15/15: Blue Jays outfielder Kevin Pillar continues his defensive dominance by climbing the wall in left to rob Tim Beckham of a home run',
+                'timestamp': 1429124820,
+                'upload_date': '20150415',
+            }
+        },
         # Wistia embed
         {
             'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
@@ -614,13 +630,24 @@ class GenericIE(InfoExtractor):
             'info_dict': {
                 'id': '100183293',
                 'ext': 'mp4',
-                'title': 'Тайны перевала Дятлова • Тайна перевала Дятлова 1 серия 2 часть',
+                'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
                 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
                 'thumbnail': 're:^https?://.*\.jpg$',
                 '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/',
@@ -641,6 +668,32 @@ class GenericIE(InfoExtractor):
                 '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',
@@ -650,6 +703,45 @@ class GenericIE(InfoExtractor):
                 '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,
+            }
         }
     ]
 
@@ -995,12 +1087,9 @@ class GenericIE(InfoExtractor):
             }
 
         # Look for embedded blip.tv player
-        mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage)
-        if mobj:
-            return self.url_result('http://blip.tv/a/a-' + mobj.group(1), 'BlipTV')
-        mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage)
-        if mobj:
-            return self.url_result(mobj.group(1), 'BlipTV')
+        bliptv_url = BlipTVIE._extract_url(webpage)
+        if bliptv_url:
+            return self.url_result(bliptv_url, 'BlipTV')
 
         # Look for embedded condenast player
         matches = re.findall(
@@ -1054,7 +1143,8 @@ class GenericIE(InfoExtractor):
         # 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'))
 
@@ -1212,6 +1302,10 @@ class GenericIE(InfoExtractor):
         mobj = re.search(
             r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
             webpage)
+        if not mobj:
+            mobj = re.search(
+                r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
+                webpage)
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'MLB')
 
@@ -1257,17 +1351,41 @@ class GenericIE(InfoExtractor):
         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')
+
+        # Look for Senate ISVP iframe
+        senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
+        if senate_isvp_url:
+            return self.url_result(surl, 'SenateISVP')
+
         def check_video(vurl):
             if YoutubeIE.suitable(vurl):
                 return True
@@ -1357,13 +1475,22 @@ 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/gfycat.py

@@ -0,0 +1,90 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    float_or_none,
+    qualities,
+)
+
+
+class GfycatIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?gfycat\.com/(?P<id>[^/?#]+)'
+    _TEST = {
+        'url': 'http://gfycat.com/DeadlyDecisiveGermanpinscher',
+        'info_dict': {
+            'id': 'DeadlyDecisiveGermanpinscher',
+            'ext': 'mp4',
+            'title': 'Ghost in the Shell',
+            'timestamp': 1410656006,
+            'upload_date': '20140914',
+            'uploader': 'anonymous',
+            'duration': 10.4,
+            'view_count': int,
+            'like_count': int,
+            'dislike_count': int,
+            'categories': list,
+            'age_limit': 0,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        gfy = self._download_json(
+            'http://gfycat.com/cajax/get/%s' % video_id,
+            video_id, 'Downloading video info')['gfyItem']
+
+        title = gfy.get('title') or gfy['gfyName']
+        description = gfy.get('description')
+        timestamp = int_or_none(gfy.get('createDate'))
+        uploader = gfy.get('userName')
+        view_count = int_or_none(gfy.get('views'))
+        like_count = int_or_none(gfy.get('likes'))
+        dislike_count = int_or_none(gfy.get('dislikes'))
+        age_limit = 18 if gfy.get('nsfw') == '1' else 0
+
+        width = int_or_none(gfy.get('width'))
+        height = int_or_none(gfy.get('height'))
+        fps = int_or_none(gfy.get('frameRate'))
+        num_frames = int_or_none(gfy.get('numFrames'))
+
+        duration = float_or_none(num_frames, fps) if num_frames and fps else None
+
+        categories = gfy.get('tags') or gfy.get('extraLemmas') or []
+
+        FORMATS = ('gif', 'webm', 'mp4')
+        quality = qualities(FORMATS)
+
+        formats = []
+        for format_id in FORMATS:
+            video_url = gfy.get('%sUrl' % format_id)
+            if not video_url:
+                continue
+            filesize = gfy.get('%sSize' % format_id)
+            formats.append({
+                'url': video_url,
+                'format_id': format_id,
+                'width': width,
+                'height': height,
+                'fps': fps,
+                'filesize': filesize,
+                'quality': quality(format_id),
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'timestamp': timestamp,
+            'uploader': uploader,
+            'duration': duration,
+            'view_count': view_count,
+            'like_count': like_count,
+            'dislike_count': dislike_count,
+            'categories': categories,
+            'age_limit': age_limit,
+            'formats': formats,
+        }

youtube_dl/extractor/gorillavid.py

@@ -15,10 +15,10 @@ from ..utils import (
 
 
 class GorillaVidIE(InfoExtractor):
-    IE_DESC = 'GorillaVid.in, daclips.in, movpod.in and fastvideo.in'
+    IE_DESC = 'GorillaVid.in, daclips.in, movpod.in, fastvideo.in and realvid.net'
     _VALID_URL = r'''(?x)
         https?://(?P<host>(?:www\.)?
-            (?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in))/
+            (?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in|realvid\.net))/
         (?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?
     '''
 
@@ -61,6 +61,15 @@ class GorillaVidIE(InfoExtractor):
             'title': 'Man of Steel - Trailer',
             'thumbnail': 're:http://.*\.jpg',
         },
+    }, {
+        'url': 'http://realvid.net/ctn2y6p2eviw',
+        'md5': 'b2166d2cf192efd6b6d764c18fd3710e',
+        'info_dict': {
+            'id': 'ctn2y6p2eviw',
+            'ext': 'flv',
+            'title': 'rdx 1955',
+            'thumbnail': 're:http://.*\.jpg',
+        },
     }, {
         'url': 'http://movpod.in/0wguyyxi1yca',
         'only_matching': True,
@@ -97,7 +106,7 @@ class GorillaVidIE(InfoExtractor):
             webpage = self._download_webpage(req, video_id, 'Downloading video page')
 
         title = self._search_regex(
-            r'style="z-index: [0-9]+;">([^<]+)</span>',
+            [r'style="z-index: [0-9]+;">([^<]+)</span>', r'>Watch (.+) '],
             webpage, 'title', default=None) or self._og_search_title(webpage)
         video_url = self._search_regex(
             r'file\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'file url')

youtube_dl/extractor/grooveshark.py

@@ -1,191 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import time
-import math
-import os.path
-import re
-
-
-from .common import InfoExtractor
-from ..compat import (
-    compat_html_parser,
-    compat_urllib_parse,
-    compat_urllib_request,
-    compat_urlparse,
-)
-from ..utils import ExtractorError
-
-
-class GroovesharkHtmlParser(compat_html_parser.HTMLParser):
-    def __init__(self):
-        self._current_object = None
-        self.objects = []
-        compat_html_parser.HTMLParser.__init__(self)
-
-    def handle_starttag(self, tag, attrs):
-        attrs = dict((k, v) for k, v in attrs)
-        if tag == 'object':
-            self._current_object = {'attrs': attrs, 'params': []}
-        elif tag == 'param':
-            self._current_object['params'].append(attrs)
-
-    def handle_endtag(self, tag):
-        if tag == 'object':
-            self.objects.append(self._current_object)
-            self._current_object = None
-
-    @classmethod
-    def extract_object_tags(cls, html):
-        p = cls()
-        p.feed(html)
-        p.close()
-        return p.objects
-
-
-class GroovesharkIE(InfoExtractor):
-    _VALID_URL = r'https?://(www\.)?grooveshark\.com/#!/s/([^/]+)/([^/]+)'
-    _TEST = {
-        'url': 'http://grooveshark.com/#!/s/Jolene+Tenth+Key+Remix+Ft+Will+Sessions/6SS1DW?src=5',
-        'md5': '7ecf8aefa59d6b2098517e1baa530023',
-        'info_dict': {
-            'id': '6SS1DW',
-            'title': 'Jolene (Tenth Key Remix ft. Will Sessions)',
-            'ext': 'mp3',
-            'duration': 227,
-        }
-    }
-
-    do_playerpage_request = True
-    do_bootstrap_request = True
-
-    def _parse_target(self, target):
-        uri = compat_urlparse.urlparse(target)
-        hash = uri.fragment[1:].split('?')[0]
-        token = os.path.basename(hash.rstrip('/'))
-        return (uri, hash, token)
-
-    def _build_bootstrap_url(self, target):
-        (uri, hash, token) = self._parse_target(target)
-        query = 'getCommunicationToken=1&hash=%s&%d' % (compat_urllib_parse.quote(hash, safe=''), self.ts)
-        return (compat_urlparse.urlunparse((uri.scheme, uri.netloc, '/preload.php', None, query, None)), token)
-
-    def _build_meta_url(self, target):
-        (uri, hash, token) = self._parse_target(target)
-        query = 'hash=%s&%d' % (compat_urllib_parse.quote(hash, safe=''), self.ts)
-        return (compat_urlparse.urlunparse((uri.scheme, uri.netloc, '/preload.php', None, query, None)), token)
-
-    def _build_stream_url(self, meta):
-        return compat_urlparse.urlunparse(('http', meta['streamKey']['ip'], '/stream.php', None, None, None))
-
-    def _build_swf_referer(self, target, obj):
-        (uri, _, _) = self._parse_target(target)
-        return compat_urlparse.urlunparse((uri.scheme, uri.netloc, obj['attrs']['data'], None, None, None))
-
-    def _transform_bootstrap(self, js):
-        return re.split('(?m)^\s*try\s*\{', js)[0] \
-                 .split(' = ', 1)[1].strip().rstrip(';')
-
-    def _transform_meta(self, js):
-        return js.split('\n')[0].split('=')[1].rstrip(';')
-
-    def _get_meta(self, target):
-        (meta_url, token) = self._build_meta_url(target)
-        self.to_screen('Metadata URL: %s' % meta_url)
-
-        headers = {'Referer': compat_urlparse.urldefrag(target)[0]}
-        req = compat_urllib_request.Request(meta_url, headers=headers)
-        res = self._download_json(req, token,
-                                  transform_source=self._transform_meta)
-
-        if 'getStreamKeyWithSong' not in res:
-            raise ExtractorError(
-                'Metadata not found. URL may be malformed, or Grooveshark API may have changed.')
-
-        if res['getStreamKeyWithSong'] is None:
-            raise ExtractorError(
-                'Metadata download failed, probably due to Grooveshark anti-abuse throttling. Wait at least an hour before retrying from this IP.',
-                expected=True)
-
-        return res['getStreamKeyWithSong']
-
-    def _get_bootstrap(self, target):
-        (bootstrap_url, token) = self._build_bootstrap_url(target)
-
-        headers = {'Referer': compat_urlparse.urldefrag(target)[0]}
-        req = compat_urllib_request.Request(bootstrap_url, headers=headers)
-        res = self._download_json(req, token, fatal=False,
-                                  note='Downloading player bootstrap data',
-                                  errnote='Unable to download player bootstrap data',
-                                  transform_source=self._transform_bootstrap)
-        return res
-
-    def _get_playerpage(self, target):
-        (_, _, token) = self._parse_target(target)
-
-        webpage = self._download_webpage(
-            target, token,
-            note='Downloading player page',
-            errnote='Unable to download player page',
-            fatal=False)
-
-        if webpage is not None:
-            # Search (for example German) error message
-            error_msg = self._html_search_regex(
-                r'<div id="content">\s*<h2>(.*?)</h2>', webpage,
-                'error message', default=None)
-            if error_msg is not None:
-                error_msg = error_msg.replace('\n', ' ')
-                raise ExtractorError('Grooveshark said: %s' % error_msg)
-
-        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, None
-
-    def _real_initialize(self):
-        self.ts = int(time.time() * 1000)  # timestamp in millis
-
-    def _real_extract(self, url):
-        (target_uri, _, token) = self._parse_target(url)
-
-        # 1. Fill cookiejar by making a request to the player page
-        swf_referer = None
-        if self.do_playerpage_request:
-            (_, player_objs) = self._get_playerpage(url)
-            if player_objs:
-                swf_referer = self._build_swf_referer(url, player_objs[0])
-                self.to_screen('SWF Referer: %s' % swf_referer)
-
-        # 2. Ask preload.php for swf bootstrap data to better mimic webapp
-        if self.do_bootstrap_request:
-            bootstrap = self._get_bootstrap(url)
-            self.to_screen('CommunicationToken: %s' % bootstrap['getCommunicationToken'])
-
-        # 3. Ask preload.php for track metadata.
-        meta = self._get_meta(url)
-
-        # 4. Construct stream request for track.
-        stream_url = self._build_stream_url(meta)
-        duration = int(math.ceil(float(meta['streamKey']['uSecs']) / 1000000))
-        post_dict = {'streamKey': meta['streamKey']['streamKey']}
-        post_data = compat_urllib_parse.urlencode(post_dict).encode('utf-8')
-        headers = {
-            'Content-Length': len(post_data),
-            'Content-Type': 'application/x-www-form-urlencoded'
-        }
-        if swf_referer is not None:
-            headers['Referer'] = swf_referer
-
-        return {
-            'id': token,
-            'title': meta['song']['Name'],
-            'http_method': 'POST',
-            'url': stream_url,
-            'ext': 'mp3',
-            'format': 'mp3 audio',
-            'duration': duration,
-            'http_post_data': post_data,
-            'http_headers': headers,
-        }

youtube_dl/extractor/hitbox.py

@@ -10,6 +10,7 @@ from ..utils import (
     float_or_none,
     int_or_none,
     compat_str,
+    determine_ext,
 )
 
 
@@ -42,7 +43,8 @@ class HitboxIE(InfoExtractor):
     def _extract_metadata(self, url, video_id):
         thumb_base = 'https://edge.sf.hitbox.tv'
         metadata = self._download_json(
-            '%s/%s' % (url, video_id), video_id)
+            '%s/%s' % (url, video_id), video_id,
+            'Downloading metadata JSON')
 
         date = 'media_live_since'
         media_type = 'livestream'
@@ -87,21 +89,41 @@ class HitboxIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
+        player_config = self._download_json(
+            'https://www.hitbox.tv/api/player/config/video/%s' % video_id,
+            video_id, 'Downloading video JSON')
+
+        formats = []
+        for video in player_config['clip']['bitrates']:
+            label = video.get('label')
+            if label == 'Auto':
+                continue
+            video_url = video.get('url')
+            if not video_url:
+                continue
+            bitrate = int_or_none(video.get('bitrate'))
+            if determine_ext(video_url) == 'm3u8':
+                if not video_url.startswith('http'):
+                    continue
+                formats.append({
+                    'url': video_url,
+                    'ext': 'mp4',
+                    'tbr': bitrate,
+                    'format_note': label,
+                    'protocol': 'm3u8_native',
+                })
+            else:
+                formats.append({
+                    'url': video_url,
+                    'tbr': bitrate,
+                    'format_note': label,
+                })
+        self._sort_formats(formats)
+
         metadata = self._extract_metadata(
             'https://www.hitbox.tv/api/media/video',
             video_id)
-
-        player_config = self._download_json(
-            'https://www.hitbox.tv/api/player/config/video/%s' % video_id,
-            video_id)
-
-        clip = player_config.get('clip')
-        video_url = clip.get('url')
-        res = clip.get('bitrates', [])[0].get('label')
-
-        metadata['resolution'] = res
-        metadata['url'] = video_url
-        metadata['protocol'] = 'm3u8'
+        metadata['formats'] = formats
 
         return metadata
 
@@ -129,10 +151,6 @@ class HitboxLiveIE(HitboxIE):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        metadata = self._extract_metadata(
-            'https://www.hitbox.tv/api/media/live',
-            video_id)
-
         player_config = self._download_json(
             'https://www.hitbox.tv/api/player/config/live/%s' % video_id,
             video_id)
@@ -147,20 +165,39 @@ 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,
                             'player_url': 'http://www.hitbox.tv/static/player/flowplayer/flowplayer.commercial-3.2.16.swf',
                         })
-
         self._sort_formats(formats)
+
+        metadata = self._extract_metadata(
+            'https://www.hitbox.tv/api/media/live',
+            video_id)
         metadata['formats'] = formats
         metadata['is_live'] = True
         metadata['title'] = self._live_title(metadata.get('title'))
+
         return metadata

youtube_dl/extractor/iconosquare.py

@@ -1,36 +1,75 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..utils import int_or_none
 
 
 class IconosquareIE(InfoExtractor):
-    _VALID_URL = r'https?://(www\.)?(?:iconosquare\.com|statigr\.am)/p/(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:iconosquare\.com|statigr\.am)/p/(?P<id>[^/]+)'
     _TEST = {
         'url': 'http://statigr.am/p/522207370455279102_24101272',
         'md5': '6eb93b882a3ded7c378ee1d6884b1814',
         'info_dict': {
             'id': '522207370455279102_24101272',
             'ext': 'mp4',
-            'uploader_id': 'aguynamedpatrick',
-            'title': 'Instagram photo by @aguynamedpatrick (Patrick Janelle)',
+            'title': 'Instagram media by @aguynamedpatrick (Patrick Janelle)',
             'description': 'md5:644406a9ec27457ed7aa7a9ebcd4ce3d',
+            'timestamp': 1376471991,
+            'upload_date': '20130814',
+            'uploader': 'aguynamedpatrick',
+            'uploader_id': '24101272',
+            'comment_count': int,
+            'like_count': int,
         },
     }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
+
         webpage = self._download_webpage(url, video_id)
+
+        media = self._parse_json(
+            self._search_regex(
+                r'window\.media\s*=\s*({.+?});\n', webpage, 'media'),
+            video_id)
+
+        formats = [{
+            'url': f['url'],
+            'format_id': format_id,
+            'width': int_or_none(f.get('width')),
+            'height': int_or_none(f.get('height'))
+        } for format_id, f in media['videos'].items()]
+        self._sort_formats(formats)
+
         title = self._html_search_regex(
             r'<title>(.+?)(?: *\(Videos?\))? \| (?:Iconosquare|Statigram)</title>',
             webpage, 'title')
-        uploader_id = self._html_search_regex(
-            r'@([^ ]+)', title, 'uploader name', fatal=False)
+
+        timestamp = int_or_none(media.get('created_time') or media.get('caption', {}).get('created_time'))
+        description = media.get('caption', {}).get('text')
+
+        uploader = media.get('user', {}).get('username')
+        uploader_id = media.get('user', {}).get('id')
+
+        comment_count = int_or_none(media.get('comments', {}).get('count'))
+        like_count = int_or_none(media.get('likes', {}).get('count'))
+
+        thumbnails = [{
+            'url': t['url'],
+            'id': thumbnail_id,
+            'width': int_or_none(t.get('width')),
+            'height': int_or_none(t.get('height'))
+        } for thumbnail_id, t in media.get('images', {}).items()]
 
         return {
             'id': video_id,
-            'url': self._og_search_video_url(webpage),
             'title': title,
-            'description': self._og_search_description(webpage),
-            'thumbnail': self._og_search_thumbnail(webpage),
-            'uploader_id': uploader_id
+            'description': description,
+            'thumbnails': thumbnails,
+            'timestamp': timestamp,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'comment_count': comment_count,
+            'like_count': like_count,
+            'formats': formats,
         }

youtube_dl/extractor/ign.py

@@ -61,7 +61,7 @@ class IGNIE(InfoExtractor):
         },
         {
             'url': 'http://www.ign.com/articles/2014/08/15/rewind-theater-wild-trailer-gamescom-2014?watch',
-            'md5': '4e9a0bda1e5eebd31ddcf86ec0b9b3c7',
+            'md5': '618fedb9c901fd086f6f093564ef8558',
             'info_dict': {
                 'id': '078fdd005f6d3c02f63d795faa1b984f',
                 'ext': 'mp4',
@@ -77,10 +77,10 @@ class IGNIE(InfoExtractor):
     def _find_video_id(self, webpage):
         res_id = [
             r'"video_id"\s*:\s*"(.*?)"',
+            r'class="hero-poster[^"]*?"[^>]*id="(.+?)"',
             r'data-video-id="(.+?)"',
             r'<object id="vid_(.+?)"',
             r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"',
-            r'class="hero-poster[^"]*?"[^>]*id="(.+?)"',
         ]
         return self._search_regex(res_id, webpage, 'video id')
 

youtube_dl/extractor/instagram.py

@@ -3,13 +3,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-)
+from ..utils import int_or_none
 
 
 class InstagramIE(InfoExtractor):
-    _VALID_URL = r'http://instagram\.com/p/(?P<id>.*?)/'
+    _VALID_URL = r'https?://instagram\.com/p/(?P<id>[\da-zA-Z]+)'
     _TEST = {
         'url': 'http://instagram.com/p/aye83DjauH/?foo=bar#abc',
         'md5': '0d2da106a9d2631273e192b372806516',
@@ -23,8 +21,8 @@ class InstagramIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
+
         webpage = self._download_webpage(url, video_id)
         uploader_id = self._search_regex(r'"owner":{"username":"(.+?)"',
                                          webpage, 'uploader id', fatal=False)

youtube_dl/extractor/lifenews.py

@@ -16,7 +16,7 @@ class LifeNewsIE(InfoExtractor):
     IE_DESC = 'LIFE | NEWS'
     _VALID_URL = r'http://lifenews\.ru/(?:mobile/)?news/(?P<id>\d+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://lifenews.ru/news/126342',
         'md5': 'e1b50a5c5fb98a6a544250f2e0db570a',
         'info_dict': {
@@ -27,7 +27,19 @@ class LifeNewsIE(InfoExtractor):
             'thumbnail': 're:http://.*\.jpg',
             'upload_date': '20140130',
         }
-    }
+    }, {
+        # video in <iframe>
+        'url': 'http://lifenews.ru/news/152125',
+        'md5': '77d19a6f0886cd76bdbf44b4d971a273',
+        'info_dict': {
+            'id': '152125',
+            'ext': 'mp4',
+            'title': 'В Сети появилось видео захвата «Правым сектором» колхозных полей ',
+            'description': 'Жители двух поселков Днепропетровской области не простили радикалам угрозу лишения плодородных земель и пошли в лобовую. ',
+            'upload_date': '20150402',
+            'uploader': 'embed.life.ru',
+        }
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -36,7 +48,9 @@ class LifeNewsIE(InfoExtractor):
         webpage = self._download_webpage('http://lifenews.ru/news/%s' % video_id, video_id, 'Downloading page')
 
         videos = re.findall(r'<video.*?poster="(?P<poster>[^"]+)".*?src="(?P<video>[^"]+)".*?></video>', webpage)
-        if not videos:
+        iframe_link = self._html_search_regex(
+            '<iframe[^>]+src="([^"]+)', webpage, 'iframe link', default=None)
+        if not videos and not iframe_link:
             raise ExtractorError('No media links available for %s' % video_id)
 
         title = self._og_search_title(webpage)
@@ -47,26 +61,41 @@ class LifeNewsIE(InfoExtractor):
         description = self._og_search_description(webpage)
 
         view_count = self._html_search_regex(
-            r'<div class=\'views\'>(\d+)</div>', webpage, 'view count', fatal=False)
+            r'<div class=\'views\'>\s*(\d+)\s*</div>', webpage, 'view count', fatal=False)
         comment_count = self._html_search_regex(
-            r'<div class=\'comments\'>\s*<span class=\'counter\'>(\d+)</span>', webpage, 'comment count', fatal=False)
+            r'<div class=\'comments\'>\s*<span class=\'counter\'>\s*(\d+)\s*</span>', webpage, 'comment count', fatal=False)
 
         upload_date = self._html_search_regex(
             r'<time datetime=\'([^\']+)\'>', webpage, 'upload date', fatal=False)
         if upload_date is not None:
             upload_date = unified_strdate(upload_date)
 
+        common_info = {
+            'description': description,
+            'view_count': int_or_none(view_count),
+            'comment_count': int_or_none(comment_count),
+            'upload_date': upload_date,
+        }
+
         def make_entry(video_id, media, video_number=None):
-            return {
+            cur_info = dict(common_info)
+            cur_info.update({
                 'id': video_id,
                 'url': media[1],
                 'thumbnail': media[0],
                 'title': title if video_number is None else '%s-video%s' % (title, video_number),
-                'description': description,
-                'view_count': int_or_none(view_count),
-                'comment_count': int_or_none(comment_count),
-                'upload_date': upload_date,
-            }
+            })
+            return cur_info
+
+        if iframe_link:
+            cur_info = dict(common_info)
+            cur_info.update({
+                '_type': 'url_transparent',
+                'id': video_id,
+                'title': title,
+                'url': iframe_link,
+            })
+            return cur_info
 
         if len(videos) == 1:
             return make_entry(video_id, videos[0])

youtube_dl/extractor/livestream.py

@@ -21,7 +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',
@@ -51,6 +51,9 @@ class LivestreamIE(InfoExtractor):
     }, {
         '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):

youtube_dl/extractor/megavideoz.py

@@ -0,0 +1,56 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    float_or_none,
+    xpath_text,
+)
+
+
+class MegaVideozIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?megavideoz\.eu/video/(?P<id>[^/]+)(?:/(?P<display_id>[^/]+))?'
+    _TEST = {
+        'url': 'http://megavideoz.eu/video/WM6UB919XMXH/SMPTE-Universal-Film-Leader',
+        'info_dict': {
+            'id': '48723',
+            'display_id': 'SMPTE-Universal-Film-Leader',
+            'ext': 'mp4',
+            'title': 'SMPTE Universal Film Leader',
+            'thumbnail': 're:https?://.*?\.jpg',
+            'duration': 10.93,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id') or video_id
+
+        webpage = self._download_webpage(url, display_id)
+
+        if any(p in webpage for p in ('>Video Not Found<', '>404 Error<')):
+            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+
+        config = self._download_xml(
+            self._search_regex(
+                r"var\s+cnf\s*=\s*'([^']+)'", webpage, 'cnf url'),
+            display_id)
+
+        video_url = xpath_text(config, './file', 'video url', fatal=True)
+        title = xpath_text(config, './title', 'title', fatal=True)
+        thumbnail = xpath_text(config, './image', 'thumbnail')
+        duration = float_or_none(xpath_text(config, './duration', 'duration'))
+        video_id = xpath_text(config, './mediaid', 'video id') or video_id
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'url': video_url,
+            'title': title,
+            'thumbnail': thumbnail,
+            'duration': duration
+        }

youtube_dl/extractor/miomio.py

@@ -7,6 +7,7 @@ from .common import InfoExtractor
 from ..utils import (
     xpath_text,
     int_or_none,
+    ExtractorError,
 )
 
 
@@ -14,13 +15,14 @@ class MioMioIE(InfoExtractor):
     IE_NAME = 'miomio.tv'
     _VALID_URL = r'https?://(?:www\.)?miomio\.tv/watch/cc(?P<id>[0-9]+)'
     _TESTS = [{
-        'url': 'http://www.miomio.tv/watch/cc179734/',
-        'md5': '48de02137d0739c15b440a224ad364b9',
+        # "type=video" in flashvars
+        'url': 'http://www.miomio.tv/watch/cc88912/',
+        'md5': '317a5f7f6b544ce8419b784ca8edae65',
         'info_dict': {
-            'id': '179734',
+            'id': '88912',
             'ext': 'flv',
-            'title': '手绘动漫鬼泣但丁全程画法',
-            'duration': 354,
+            '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/',
@@ -29,6 +31,14 @@ class MioMioIE(InfoExtractor):
             'title': '《动漫同人插画绘制》',
         },
         'playlist_mincount': 86,
+        'skip': 'This video takes time too long for retrieving the URL',
+    }, {
+        'url': 'http://www.miomio.tv/watch/cc173113/',
+        'info_dict': {
+            'id': '173113',
+            'title': 'The New Macbook 2015 上手试玩与简评'
+        },
+        'playlist_mincount': 2,
     }]
 
     def _real_extract(self, url):
@@ -42,9 +52,9 @@ class MioMioIE(InfoExtractor):
             r'src="(/mioplayer/[^"]+)"', webpage, 'ref_path')
 
         xml_config = self._search_regex(
-            r'flashvars="type=sina&amp;(.+?)&amp;',
+            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)),
@@ -59,6 +69,9 @@ class MioMioIE(InfoExtractor):
             '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')

youtube_dl/extractor/mixcloud.py

@@ -1,7 +1,6 @@
 from __future__ import unicode_literals
 
 import re
-import itertools
 
 from .common import InfoExtractor
 from ..compat import (
@@ -46,20 +45,16 @@ class MixcloudIE(InfoExtractor):
         },
     }]
 
-    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 ...' % (nr, boundaries[-1]))
-                return url
-            except ExtractorError:
-                pass
-        return None
+    def _check_url(self, url, track_id, ext):
+        try:
+            # We only want to know if the request succeed
+            # don't download the whole file
+            self._request_webpage(
+                HEADRequest(url), track_id,
+                'Trying %s URL' % ext)
+            return True
+        except ExtractorError:
+            return False
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -72,15 +67,10 @@ 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, 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, server_number)
-        if final_song_url is None:
-            raise ExtractorError('Unable to extract track url')
+        if not self._check_url(song_url, track_id, 'mp3'):
+            song_url = song_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/')
+            if not self._check_url(song_url, track_id, 'm4a'):
+                raise ExtractorError('Unable to extract track url')
 
         PREFIX = (
             r'm-play-on-spacebar[^>]+'
@@ -97,7 +87,7 @@ 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'\bbutton-favorite\b.+m-ajax-toggle-count="([^"]+)"',
+            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]+)"',
@@ -107,7 +97,7 @@ class MixcloudIE(InfoExtractor):
         return {
             'id': track_id,
             'title': title,
-            'url': final_song_url,
+            'url': song_url,
             'description': description,
             'thumbnail': thumbnail,
             'uploader': uploader,
@@ -115,35 +105,3 @@ class MixcloudIE(InfoExtractor):
             '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)?\.(?:[\da-z_-]+\.)?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|m-internal-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',
@@ -83,6 +83,11 @@ class MLBIE(InfoExtractor):
         {
             '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,
+        },
+        {
+            # From http://m.mlb.com/news/article/118550098/blue-jays-kevin-pillar-goes-spidey-up-the-wall-to-rob-tim-beckham-of-a-homer
+            'url': 'http://mlb.mlb.com/shared/video/embed/m-internal-embed.html?content_id=75609783&property=mlb&autoplay=true&hashmode=false&siteSection=mlb/multimedia/article_118550098/article_embed&club=mlb',
+            'only_matching': True,
         }
     ]
 

youtube_dl/extractor/moniker.py

@@ -9,6 +9,7 @@ from ..compat import (
     compat_urllib_parse,
     compat_urllib_request,
 )
+from ..utils import ExtractorError
 
 
 class MonikerIE(InfoExtractor):
@@ -40,6 +41,15 @@ class MonikerIE(InfoExtractor):
         video_id = self._match_id(url)
         orig_webpage = self._download_webpage(url, video_id)
 
+        if '>File Not Found<' in orig_webpage:
+            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+
+        error = self._search_regex(
+            r'class="err">([^<]+)<', orig_webpage, 'error', default=None)
+        if error:
+            raise ExtractorError(
+                '%s returned error: %s' % (self.IE_NAME, error), expected=True)
+
         fields = re.findall(r'type="hidden" name="(.+?)"\s* value="?(.+?)">', orig_webpage)
         data = dict(fields)
 

youtube_dl/extractor/mtv.py

@@ -25,6 +25,7 @@ def _media_xml_tag(tag):
 
 class MTVServicesInfoExtractor(InfoExtractor):
     _MOBILE_TEMPLATE = None
+    _LANG = None
 
     @staticmethod
     def _id_from_uri(uri):
@@ -118,6 +119,14 @@ 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()
@@ -161,8 +170,12 @@ class MTVServicesInfoExtractor(InfoExtractor):
         video_id = self._id_from_uri(uri)
         feed_url = self._get_feed_url(uri)
         data = compat_urllib_parse.urlencode({'uri': uri})
+        info_url = feed_url + '?'
+        if self._LANG:
+            info_url += 'lang=%s&' % self._LANG
+        info_url += data
         idoc = self._download_xml(
-            feed_url + '?' + data, video_id,
+            info_url, video_id,
             'Downloading info', transform_source=fix_xml_ampersands)
         return self.playlist_result(
             [self._get_video_info(item) for item in idoc.findall('.//item')])

youtube_dl/extractor/nbc.py

@@ -37,13 +37,26 @@ class NBCIE(InfoExtractor):
             },
             'skip': 'Only works from US',
         },
+        {
+            'url': 'http://www.nbc.com/saturday-night-live/video/star-wars-teaser/2832821',
+            'info_dict': {
+                'id': '8iUuyzWDdYUZ',
+                'ext': 'flv',
+                'title': 'Star Wars Teaser',
+                'description': 'md5:0b40f9cbde5b671a7ff62fceccc4f442',
+            },
+            'skip': 'Only works from US',
+        }
     ]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
         theplatform_url = self._search_regex(
-            '(?:class="video-player video-player-full" data-mpx-url|class="player" src)="(.*?)"',
+            [
+                r'(?:class="video-player video-player-full" data-mpx-url|class="player" src)="(.*?)"',
+                r'"embedURL"\s*:\s*"([^"]+)"'
+            ],
             webpage, 'theplatform url').replace('_no_endcard', '')
         if theplatform_url.startswith('//'):
             theplatform_url = 'http:' + theplatform_url

youtube_dl/extractor/niconico.py

@@ -3,6 +3,7 @@ from __future__ import unicode_literals
 
 import re
 import json
+import datetime
 
 from .common import InfoExtractor
 from ..compat import (
@@ -14,7 +15,9 @@ from ..utils import (
     ExtractorError,
     int_or_none,
     parse_duration,
-    unified_strdate,
+    parse_iso8601,
+    xpath_text,
+    determine_ext,
 )
 
 
@@ -32,30 +35,50 @@ class NiconicoIE(InfoExtractor):
             'uploader': 'takuya0301',
             'uploader_id': '2698420',
             'upload_date': '20131123',
+            'timestamp': 1385182762,
             'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
             'duration': 33,
         },
-        'params': {
-            'username': 'ydl.niconico@gmail.com',
-            'password': 'youtube-dl',
-        },
     }, {
+        # File downloaded with and without credentials are different, so omit
+        # the md5 field
         '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:',
+            'description': 'md5:689f066d74610b3b22e0f1739add0f58',
             'uploader': 'りょうた',
             'uploader_id': '18822557',
             'upload_date': '20110429',
+            'timestamp': 1304065916,
             'duration': 209,
         },
-        'params': {
-            'username': 'ydl.niconico@gmail.com',
-            'password': 'youtube-dl',
+    }, {
+        # 'video exists but is marked as "deleted"
+        # md5 is unstable
+        'url': 'http://www.nicovideo.jp/watch/sm10000',
+        'info_dict': {
+            'id': 'sm10000',
+            'ext': 'unknown_video',
+            'description': 'deleted',
+            'title': 'ドラえもんエターナル第3話「決戦第3新東京市」＜前編＞',
+            'upload_date': '20071224',
+            'timestamp': 1198527840,  # timestamp field has different value if logged in
+            'duration': 304,
         },
+    }, {
+        'url': 'http://www.nicovideo.jp/watch/so22543406',
+        'info_dict': {
+            'id': '1388129933',
+            'ext': 'mp4',
+            'title': '【第1回】RADIOアニメロミックス ラブライブ！～のぞえりRadio Garden～',
+            'description': 'md5:b27d224bb0ff53d3c8269e9f8b561cf1',
+            'timestamp': 1388851200,
+            'upload_date': '20140104',
+            'uploader': 'アニメロチャンネル',
+            'uploader_id': '312',
+        }
     }]
 
     _VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/(?P<id>(?:[a-z]{2})?[0-9]+)'
@@ -95,9 +118,13 @@ class NiconicoIE(InfoExtractor):
     def _real_extract(self, url):
         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
-        self._download_webpage('http://www.nicovideo.jp/watch/' + video_id, video_id)
+        # Get video webpage. We are not actually interested in it for normal
+        # cases, but need the cookies in order to be able to download the
+        # info webpage
+        webpage, handle = self._download_webpage_handle(
+            'http://www.nicovideo.jp/watch/' + video_id, video_id)
+        if video_id.startswith('so'):
+            video_id = self._match_id(handle.geturl())
 
         video_info = self._download_xml(
             'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id,
@@ -127,22 +154,78 @@ class NiconicoIE(InfoExtractor):
                 flv_info_request, video_id,
                 note='Downloading flv info', errnote='Unable to download flv info')
 
-        if 'deleted=' in flv_info_webpage:
-            raise ExtractorError('The video has been deleted.',
-                                 expected=True)
-        video_real_url = compat_urlparse.parse_qs(flv_info_webpage)['url'][0]
+        flv_info = compat_urlparse.parse_qs(flv_info_webpage)
+        if 'url' not in flv_info:
+            if 'deleted' in flv_info:
+                raise ExtractorError('The video has been deleted.',
+                                     expected=True)
+            else:
+                raise ExtractorError('Unable to find video URL')
+
+        video_real_url = flv_info['url'][0]
 
         # Start extracting information
-        title = video_info.find('.//title').text
-        extension = video_info.find('.//movie_type').text
+        title = xpath_text(video_info, './/title')
+        if not title:
+            title = self._og_search_title(webpage, default=None)
+        if not title:
+            title = self._html_search_regex(
+                r'<span[^>]+class="videoHeaderTitle"[^>]*>([^<]+)</span>',
+                webpage, 'video title')
+
+        watch_api_data_string = self._html_search_regex(
+            r'<div[^>]+id="watchAPIDataContainer"[^>]+>([^<]+)</div>',
+            webpage, 'watch api data', default=None)
+        watch_api_data = self._parse_json(watch_api_data_string, video_id) if watch_api_data_string else {}
+        video_detail = watch_api_data.get('videoDetail', {})
+
+        extension = xpath_text(video_info, './/movie_type')
+        if not extension:
+            extension = determine_ext(video_real_url)
         video_format = extension.upper()
-        thumbnail = video_info.find('.//thumbnail_url').text
-        description = video_info.find('.//description').text
-        upload_date = unified_strdate(video_info.find('.//first_retrieve').text.split('+')[0])
-        view_count = int_or_none(video_info.find('.//view_counter').text)
-        comment_count = int_or_none(video_info.find('.//comment_num').text)
-        duration = parse_duration(video_info.find('.//length').text)
-        webpage_url = video_info.find('.//watch_url').text
+
+        thumbnail = (
+            xpath_text(video_info, './/thumbnail_url') or
+            self._html_search_meta('image', webpage, 'thumbnail', default=None) or
+            video_detail.get('thumbnail'))
+
+        description = xpath_text(video_info, './/description')
+
+        timestamp = parse_iso8601(xpath_text(video_info, './/first_retrieve'))
+        if not timestamp:
+            match = self._html_search_meta('datePublished', webpage, 'date published', default=None)
+            if match:
+                timestamp = parse_iso8601(match.replace('+', ':00+'))
+        if not timestamp and video_detail.get('postedAt'):
+            timestamp = parse_iso8601(
+                video_detail['postedAt'].replace('/', '-'),
+                delimiter=' ', timezone=datetime.timedelta(hours=9))
+
+        view_count = int_or_none(xpath_text(video_info, './/view_counter'))
+        if not view_count:
+            match = self._html_search_regex(
+                r'>Views: <strong[^>]*>([^<]+)</strong>',
+                webpage, 'view count', default=None)
+            if match:
+                view_count = int_or_none(match.replace(',', ''))
+        view_count = view_count or video_detail.get('viewCount')
+
+        comment_count = int_or_none(xpath_text(video_info, './/comment_num'))
+        if not comment_count:
+            match = self._html_search_regex(
+                r'>Comments: <strong[^>]*>([^<]+)</strong>',
+                webpage, 'comment count', default=None)
+            if match:
+                comment_count = int_or_none(match.replace(',', ''))
+        comment_count = comment_count or video_detail.get('commentCount')
+
+        duration = (parse_duration(
+            xpath_text(video_info, './/length') or
+            self._html_search_meta(
+                'video:duration', webpage, 'video duration', default=None)) or
+            video_detail.get('length'))
+
+        webpage_url = xpath_text(video_info, './/watch_url') or url
 
         if video_info.find('.//ch_id') is not None:
             uploader_id = video_info.find('.//ch_id').text
@@ -162,7 +245,7 @@ class NiconicoIE(InfoExtractor):
             'thumbnail': thumbnail,
             'description': description,
             'uploader': uploader,
-            'upload_date': upload_date,
+            'timestamp': timestamp,
             'uploader_id': uploader_id,
             'view_count': view_count,
             'comment_count': comment_count,

youtube_dl/extractor/orf.py

@@ -210,16 +210,16 @@ class ORFIPTVIE(InfoExtractor):
     _VALID_URL = r'http://iptv\.orf\.at/(?:#/)?stories/(?P<id>\d+)'
 
     _TEST = {
-        'url': 'http://iptv.orf.at/stories/2267952',
-        'md5': '26ffa4bab6dbce1eee78bbc7021016cd',
+        'url': 'http://iptv.orf.at/stories/2275236/',
+        'md5': 'c8b22af4718a4b4af58342529453e3e5',
         'info_dict': {
-            'id': '339775',
+            'id': '350612',
             'ext': 'flv',
-            'title': 'Kreml-Kritiker Nawalny wieder frei',
-            'description': 'md5:6f24e7f546d364dacd0e616a9e409236',
-            'duration': 84.729,
+            'title': 'Weitere Evakuierungen um Vulkan Calbuco',
+            'description': 'md5:d689c959bdbcf04efeddedbf2299d633',
+            'duration': 68.197,
             'thumbnail': 're:^https?://.*\.jpg$',
-            'upload_date': '20150306',
+            'upload_date': '20150425',
         },
     }
 

youtube_dl/extractor/pbs.py

@@ -5,6 +5,8 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
+    determine_ext,
+    int_or_none,
     unified_strdate,
     US_RATINGS,
 )
@@ -149,21 +151,44 @@ class PBSIE(InfoExtractor):
                 for vid_id in video_id]
             return self.playlist_result(entries, display_id)
 
-        info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id
-        info = self._download_json(info_url, display_id)
+        info = self._download_json(
+            'http://video.pbs.org/videoInfo/%s?format=json&type=partner' % video_id,
+            display_id)
 
-        redirect_url = info['alternate_encoding']['url']
-        redirect_info = self._download_json(
-            redirect_url + '?format=json', display_id,
-            'Downloading video url info')
-        if redirect_info['status'] == 'error':
-            if redirect_info['http_code'] == 403:
-                message = (
-                    'The video is not available in your region due to '
-                    'right restrictions')
+        formats = []
+        for encoding_name in ('recommended_encoding', 'alternate_encoding'):
+            redirect = info.get(encoding_name)
+            if not redirect:
+                continue
+            redirect_url = redirect.get('url')
+            if not redirect_url:
+                continue
+
+            redirect_info = self._download_json(
+                redirect_url + '?format=json', display_id,
+                'Downloading %s video url info' % encoding_name)
+
+            if redirect_info['status'] == 'error':
+                if redirect_info['http_code'] == 403:
+                    message = (
+                        'The video is not available in your region due to '
+                        'right restrictions')
+                else:
+                    message = redirect_info['message']
+                raise ExtractorError(message, expected=True)
+
+            format_url = redirect_info.get('url')
+            if not format_url:
+                continue
+
+            if determine_ext(format_url) == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, display_id, 'mp4', preference=1, m3u8_id='hls'))
             else:
-                message = redirect_info['message']
-            raise ExtractorError(message, expected=True)
+                formats.append({
+                    'url': format_url,
+                })
+        self._sort_formats(formats)
 
         rating_str = info.get('rating')
         if rating_str is not None:
@@ -174,11 +199,10 @@ class PBSIE(InfoExtractor):
             'id': video_id,
             'display_id': display_id,
             'title': info['title'],
-            'url': redirect_info['url'],
-            'ext': 'mp4',
             'description': info['program'].get('description'),
             'thumbnail': info.get('image_url'),
-            'duration': info.get('duration'),
+            'duration': int_or_none(info.get('duration')),
             'age_limit': age_limit,
             'upload_date': upload_date,
+            'formats': formats,
         }

youtube_dl/extractor/philharmoniedeparis.py

@@ -0,0 +1,78 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    float_or_none,
+    int_or_none,
+    parse_iso8601,
+    xpath_text,
+)
+
+
+class PhilharmonieDeParisIE(InfoExtractor):
+    IE_DESC = 'Philharmonie de Paris'
+    _VALID_URL = r'http://live\.philharmoniedeparis\.fr/(?:[Cc]oncert/|misc/Playlist\.ashx\?id=)(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://live.philharmoniedeparis.fr/concert/1032066.html',
+        'info_dict': {
+            'id': '1032066',
+            'ext': 'flv',
+            'title': 'md5:d1f5585d87d041d07ce9434804bc8425',
+            'timestamp': 1428179400,
+            'upload_date': '20150404',
+            'duration': 6592.278,
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }, {
+        'url': 'http://live.philharmoniedeparis.fr/Concert/1030324.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://live.philharmoniedeparis.fr/misc/Playlist.ashx?id=1030324&track=&lang=fr',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        concert = self._download_xml(
+            'http://live.philharmoniedeparis.fr/misc/Playlist.ashx?id=%s' % video_id,
+            video_id).find('./concert')
+
+        formats = []
+        info_dict = {
+            'id': video_id,
+            'title': xpath_text(concert, './titre', 'title', fatal=True),
+            'formats': formats,
+        }
+
+        fichiers = concert.find('./fichiers')
+        stream = fichiers.attrib['serveurstream']
+        for fichier in fichiers.findall('./fichier'):
+            info_dict['duration'] = float_or_none(fichier.get('timecodefin'))
+            for quality, (format_id, suffix) in enumerate([('lq', ''), ('hq', '_hd')]):
+                format_url = fichier.get('url%s' % suffix)
+                if not format_url:
+                    continue
+                formats.append({
+                    'url': stream,
+                    'play_path': format_url,
+                    'ext': 'flv',
+                    'format_id': format_id,
+                    'width': int_or_none(concert.get('largeur%s' % suffix)),
+                    'height': int_or_none(concert.get('hauteur%s' % suffix)),
+                    'quality': quality,
+                })
+        self._sort_formats(formats)
+
+        date, hour = concert.get('date'), concert.get('heure')
+        if date and hour:
+            info_dict['timestamp'] = parse_iso8601(
+                '%s-%s-%sT%s:00' % (date[0:4], date[4:6], date[6:8], hour))
+        elif date:
+            info_dict['upload_date'] = date
+
+        return info_dict

youtube_dl/extractor/pladform.py

@@ -30,7 +30,7 @@ class PladformIE(InfoExtractor):
         'info_dict': {
             'id': '100183293',
             'ext': 'mp4',
-            'title': 'Тайны перевала Дятлова • Тайна перевала Дятлова 1 серия 2 часть',
+            '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,

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/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/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'):

youtube_dl/extractor/rutv.py

@@ -84,11 +84,20 @@ class RUTVIE(InfoExtractor):
                 'title': 'Сочи-2014. Биатлон. Индивидуальная гонка. Мужчины ',
                 'description': 'md5:9e0ed5c9d2fa1efbfdfed90c9a6d179c',
             },
+            'skip': 'Translation has finished',
+        },
+        {
+            'url': 'http://live.russia.tv/index/index/channel_id/3',
+            'info_dict': {
+                'id': '21',
+                'ext': 'mp4',
+                'title': 're:^Россия 24. Прямой эфир [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+                'is_live': True,
+            },
             'params': {
-                # rtmp download
+                # m3u8 download
                 'skip_download': True,
             },
-            'skip': 'Translation has finished',
         },
     ]
 
@@ -181,12 +190,15 @@ class RUTVIE(InfoExtractor):
 
         self._sort_formats(formats)
 
+        is_live = video_type == 'live'
+
         return {
             'id': video_id,
-            'title': title,
+            'title': self._live_title(title) if is_live else title,
             'description': description,
             'thumbnail': thumbnail,
             'view_count': view_count,
             'duration': duration,
             'formats': formats,
+            'is_live': is_live,
         }

youtube_dl/extractor/screenwavemedia.py

@@ -81,60 +81,6 @@ class ScreenwaveMediaIE(InfoExtractor):
         }
 
 
-class CinemassacreIE(InfoExtractor):
-    _VALID_URL = 'https?://(?:www\.)?cinemassacre\.com/(?P<date_y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/(?P<display_id>[^?#/]+)'
-    _TESTS = [
-        {
-            'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
-            'md5': 'fde81fbafaee331785f58cd6c0d46190',
-            'info_dict': {
-                'id': 'Cinemassacre-19911',
-                'ext': 'mp4',
-                'upload_date': '20121110',
-                'title': '“Angry Video Game Nerd: The Movie” – Trailer',
-                'description': 'md5:fb87405fcb42a331742a0dce2708560b',
-            },
-        },
-        {
-            'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
-            'md5': 'd72f10cd39eac4215048f62ab477a511',
-            'info_dict': {
-                'id': 'Cinemassacre-521be8ef82b16',
-                'ext': 'mp4',
-                'upload_date': '20131002',
-                'title': 'The Mummy’s Hand (1940)',
-            },
-        }
-    ]
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        display_id = mobj.group('display_id')
-        video_date = mobj.group('date_y') + mobj.group('date_m') + mobj.group('date_d')
-
-        webpage = self._download_webpage(url, display_id)
-
-        playerdata_url = self._search_regex(
-            r'src="(http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
-            webpage, 'player data URL')
-        video_title = self._html_search_regex(
-            r'<title>(?P<title>.+?)\|', webpage, 'title')
-        video_description = self._html_search_regex(
-            r'<div class="entry-content">(?P<description>.+?)</div>',
-            webpage, 'description', flags=re.DOTALL, fatal=False)
-        video_thumbnail = self._og_search_thumbnail(webpage)
-
-        return {
-            '_type': 'url_transparent',
-            'display_id': display_id,
-            'title': video_title,
-            'description': video_description,
-            'upload_date': video_date,
-            'thumbnail': video_thumbnail,
-            'url': playerdata_url,
-        }
-
-
 class TeamFourIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?teamfourstar\.com/video/(?P<id>[a-z0-9\-]+)/?'
     _TEST = {

youtube_dl/extractor/senateisvp.py

@@ -0,0 +1,141 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    unsmuggle_url,
+)
+from ..compat import (
+    compat_parse_qs,
+    compat_urlparse,
+)
+
+
+class SenateISVPIE(InfoExtractor):
+    _COMM_MAP = [
+        ["ag", "76440", "http://ag-f.akamaihd.net"],
+        ["aging", "76442", "http://aging-f.akamaihd.net"],
+        ["approps", "76441", "http://approps-f.akamaihd.net"],
+        ["armed", "76445", "http://armed-f.akamaihd.net"],
+        ["banking", "76446", "http://banking-f.akamaihd.net"],
+        ["budget", "76447", "http://budget-f.akamaihd.net"],
+        ["cecc", "76486", "http://srs-f.akamaihd.net"],
+        ["commerce", "80177", "http://commerce1-f.akamaihd.net"],
+        ["csce", "75229", "http://srs-f.akamaihd.net"],
+        ["dpc", "76590", "http://dpc-f.akamaihd.net"],
+        ["energy", "76448", "http://energy-f.akamaihd.net"],
+        ["epw", "76478", "http://epw-f.akamaihd.net"],
+        ["ethics", "76449", "http://ethics-f.akamaihd.net"],
+        ["finance", "76450", "http://finance-f.akamaihd.net"],
+        ["foreign", "76451", "http://foreign-f.akamaihd.net"],
+        ["govtaff", "76453", "http://govtaff-f.akamaihd.net"],
+        ["help", "76452", "http://help-f.akamaihd.net"],
+        ["indian", "76455", "http://indian-f.akamaihd.net"],
+        ["intel", "76456", "http://intel-f.akamaihd.net"],
+        ["intlnarc", "76457", "http://intlnarc-f.akamaihd.net"],
+        ["jccic", "85180", "http://jccic-f.akamaihd.net"],
+        ["jec", "76458", "http://jec-f.akamaihd.net"],
+        ["judiciary", "76459", "http://judiciary-f.akamaihd.net"],
+        ["rpc", "76591", "http://rpc-f.akamaihd.net"],
+        ["rules", "76460", "http://rules-f.akamaihd.net"],
+        ["saa", "76489", "http://srs-f.akamaihd.net"],
+        ["smbiz", "76461", "http://smbiz-f.akamaihd.net"],
+        ["srs", "75229", "http://srs-f.akamaihd.net"],
+        ["uscc", "76487", "http://srs-f.akamaihd.net"],
+        ["vetaff", "76462", "http://vetaff-f.akamaihd.net"],
+        ["arch", "", "http://ussenate-f.akamaihd.net/"]
+    ]
+    _IE_NAME = 'senate.gov'
+    _VALID_URL = r'http://www\.senate\.gov/isvp/\?(?P<qs>.+)'
+    _TESTS = [{
+        'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png',
+        'info_dict': {
+            'id': 'judiciary031715',
+            'ext': 'flv',
+            'title': 'Integrated Senate Video Player',
+            'thumbnail': 're:^https?://.*\.(?:jpg|png)$',
+        }
+    }, {
+        'url': 'http://www.senate.gov/isvp/?type=live&comm=commerce&filename=commerce011514.mp4&auto_play=false',
+        'info_dict': {
+            'id': 'commerce011514',
+            'ext': 'flv',
+            'title': 'Integrated Senate Video Player'
+        }
+    }, {
+        'url': 'http://www.senate.gov/isvp/?type=arch&comm=intel&filename=intel090613&hc_location=ufi',
+        # checksum differs each time
+        'info_dict': {
+            'id': 'intel090613',
+            'ext': 'mp4',
+            'title': 'Integrated Senate Video Player'
+        }
+    }]
+
+    @staticmethod
+    def _search_iframe_url(webpage):
+        mobj = re.search(
+            r"<iframe[^>]+src=['\"](?P<url>http://www\.senate\.gov/isvp/\?[^'\"]+)['\"]",
+            webpage)
+        if mobj:
+            return mobj.group('url')
+
+    def _get_info_for_comm(self, committee):
+        for entry in self._COMM_MAP:
+            if entry[0] == committee:
+                return entry[1:]
+
+    def _real_extract(self, url):
+        url, smuggled_data = unsmuggle_url(url, {})
+
+        qs = compat_parse_qs(re.match(self._VALID_URL, url).group('qs'))
+        if not qs.get('filename') or not qs.get('type') or not qs.get('comm'):
+            raise ExtractorError('Invalid URL', expected=True)
+
+        video_id = re.sub(r'.mp4$', '', qs['filename'][0])
+
+        webpage = self._download_webpage(url, video_id)
+
+        if smuggled_data.get('force_title'):
+            title = smuggled_data['force_title']
+        else:
+            title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, video_id)
+        poster = qs.get('poster')
+        thumbnail = poster[0] if poster else None
+
+        video_type = qs['type'][0]
+        committee = video_type if video_type == 'arch' else qs['comm'][0]
+        stream_num, domain = self._get_info_for_comm(committee)
+
+        formats = []
+        if video_type == 'arch':
+            filename = video_id if '.' in video_id else video_id + '.mp4'
+            formats = [{
+                # All parameters in the query string are necessary to prevent a 403 error
+                'url': compat_urlparse.urljoin(domain, filename) + '?v=3.1.0&fp=&r=&g=',
+            }]
+        else:
+            hdcore_sign = '?hdcore=3.1.0'
+            url_params = (domain, video_id, stream_num)
+            f4m_url = '%s/z/%s_1@%s/manifest.f4m' % url_params + hdcore_sign
+            m3u8_url = '%s/i/%s_1@%s/master.m3u8' % url_params
+            for entry in self._extract_f4m_formats(f4m_url, video_id, f4m_id='f4m'):
+                # URLs without the extra param induce an 404 error
+                entry.update({'extra_param_to_segment_url': hdcore_sign})
+                formats.append(entry)
+            for entry in self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', m3u8_id='m3u8'):
+                mobj = re.search(r'(?P<tag>(?:-p|-b)).m3u8', entry['url'])
+                if mobj:
+                    entry['format_id'] += mobj.group('tag')
+                formats.append(entry)
+
+            self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/sohu.py

@@ -47,6 +47,7 @@ class SohuIE(InfoExtractor):
         'url': 'http://my.tv.sohu.com/pl/8384802/78910339.shtml',
         'info_dict': {
             'id': '78910339',
+            'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
         },
         'playlist': [{
             'md5': 'bdbfb8f39924725e6589c146bc1883ad',
@@ -110,7 +111,7 @@ class SohuIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
-        title = self._og_search_title(webpage)
+        title = re.sub(r' - 搜狐视频$', '', self._og_search_title(webpage))
 
         vid = self._html_search_regex(
             r'var vid ?= ?["\'](\d+)["\']',
@@ -172,9 +173,10 @@ class SohuIE(InfoExtractor):
             info['id'] = video_id
         else:
             info = {
-                '_type': 'playlist',
+                '_type': 'multi_video',
                 'entries': playlist,
                 'id': video_id,
+                'title': title,
             }
 
         return info

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')
@@ -274,9 +279,8 @@ class SoundcloudSetIE(SoundcloudIE):
         info = self._download_json(resolv_url, full_title)
 
         if 'errors' in info:
-            for err in info['errors']:
-                self._downloader.report_error('unable to download video webpage: %s' % compat_str(err['error_message']))
-            return
+            msgs = (compat_str(err['error_message']) for err in info['errors'])
+            raise ExtractorError('unable to download video webpage: %s' % ','.join(msgs))
 
         return {
             '_type': 'playlist',

youtube_dl/extractor/southpark.py

@@ -1,3 +1,4 @@
+# encoding: utf-8
 from __future__ import unicode_literals
 
 from .mtv import MTVServicesInfoExtractor
@@ -5,7 +6,7 @@ from .mtv import MTVServicesInfoExtractor
 
 class SouthParkIE(MTVServicesInfoExtractor):
     IE_NAME = 'southpark.cc.com'
-    _VALID_URL = r'https?://(www\.)?(?P<url>southpark\.cc\.com/(clips|full-episodes)/(?P<id>.+?)(\?|#|$))'
+    _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.cc\.com/(?:clips|full-episodes)/(?P<id>.+?)(\?|#|$))'
 
     _FEED_URL = 'http://www.southparkstudios.com/feeds/video-player/mrss'
 
@@ -20,9 +21,20 @@ class SouthParkIE(MTVServicesInfoExtractor):
     }]
 
 
+class SouthParkEsIE(SouthParkIE):
+    IE_NAME = 'southpark.cc.com:español'
+    _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.cc\.com/episodios-en-espanol/(?P<id>.+?)(\?|#|$))'
+    _LANG = 'es'
+
+    _TESTS = [{
+        'url': 'http://southpark.cc.com/episodios-en-espanol/s01e01-cartman-consigue-una-sonda-anal#source=351c1323-0b96-402d-a8b9-40d01b2e9bde&position=1&sort=!airdate',
+        'playlist_count': 4,
+    }]
+
+
 class SouthparkDeIE(SouthParkIE):
     IE_NAME = 'southpark.de'
-    _VALID_URL = r'https?://(www\.)?(?P<url>southpark\.de/(clips|alle-episoden)/(?P<id>.+?)(\?|#|$))'
+    _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.de/(?:clips|alle-episoden)/(?P<id>.+?)(\?|#|$))'
     _FEED_URL = 'http://www.southpark.de/feeds/video-player/mrss/'
 
     _TESTS = [{

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,
+        }

youtube_dl/extractor/teamcoco.py

@@ -1,10 +1,14 @@
+# -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 
 import base64
 import re
 
 from .common import InfoExtractor
-from ..utils import qualities
+from ..utils import (
+    ExtractorError,
+    qualities,
+)
 
 
 class TeamcocoIE(InfoExtractor):
@@ -18,6 +22,7 @@ class TeamcocoIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'Conan Becomes A Mary Kay Beauty Consultant',
                 'description': 'Mary Kay is perhaps the most trusted name in female beauty, so of course Conan is a natural choice to sell their products.',
+                'duration': 504,
                 'age_limit': 0,
             }
         }, {
@@ -28,8 +33,20 @@ class TeamcocoIE(InfoExtractor):
                 'ext': 'mp4',
                 'description': 'Louis C.K. got starstruck by George W. Bush, so what? Part one.',
                 'title': 'Louis C.K. Interview Pt. 1 11/3/11',
+                'duration': 288,
                 'age_limit': 0,
             }
+        }, {
+            'url': 'http://teamcoco.com/video/timothy-olyphant-drinking-whiskey',
+            'info_dict': {
+                'id': '88748',
+                'ext': 'mp4',
+                'title': 'Timothy Olyphant Raises A Toast To “Justified”',
+                'description': 'md5:15501f23f020e793aeca761205e42c24',
+            },
+            'params': {
+                'skip_download': True,  # m3u8 downloads
+            }
         }
     ]
     _VIDEO_ID_REGEXES = (
@@ -49,35 +66,50 @@ class TeamcocoIE(InfoExtractor):
             video_id = self._html_search_regex(
                 self._VIDEO_ID_REGEXES, webpage, 'video id')
 
-        embed_url = 'http://teamcoco.com/embed/v/%s' % video_id
-        embed = self._download_webpage(
-            embed_url, video_id, 'Downloading embed page')
+        preload = None
+        preloads = re.findall(r'"preload":\s*"([^"]+)"', webpage)
+        if preloads:
+            preload = max([(len(p), p) for p in preloads])[1]
+
+        if not preload:
+            preload = ''.join(re.findall(r'this\.push\("([^"]+)"\);', webpage))
+
+        if not preload:
+            preload = self._html_search_regex([
+                r'player,\[?"([^"]+)"\]?', r'player.init\(\[?"([^"]+)"\]?\)'
+            ], webpage.replace('","', ''), 'preload data', default=None)
+
+        if not preload:
+            raise ExtractorError(
+                'Preload information could not be extracted', expected=True)
 
-        player_data = self._parse_json(self._search_regex(
-            r'Y\.Ginger\.Module\.Player(?:;var\s*player\s*=\s*new\s*m)?\((\{.*?\})\);', embed, 'player data'), video_id)
         data = self._parse_json(
-            base64.b64decode(player_data['preload'].encode('ascii')).decode('utf-8'), video_id)
+            base64.b64decode(preload.encode('ascii')).decode('utf-8'), video_id)
 
         formats = []
         get_quality = qualities(['500k', '480p', '1000k', '720p', '1080p'])
         for filed in data['files']:
-            m_format = re.search(r'(\d+(k|p))\.mp4', filed['url'])
-            if m_format is not None:
-                format_id = m_format.group(1)
+            if filed['type'] == 'hls':
+                formats.extend(self._extract_m3u8_formats(
+                    filed['url'], video_id, ext='mp4'))
             else:
-                format_id = filed['bitrate']
-            tbr = (
-                int(filed['bitrate'])
-                if filed['bitrate'].isdigit()
-                else None)
+                m_format = re.search(r'(\d+(k|p))\.mp4', filed['url'])
+                if m_format is not None:
+                    format_id = m_format.group(1)
+                else:
+                    format_id = filed['bitrate']
+                tbr = (
+                    int(filed['bitrate'])
+                    if filed['bitrate'].isdigit()
+                    else None)
 
-            formats.append({
-                'url': filed['url'],
-                'ext': 'mp4',
-                'tbr': tbr,
-                'format_id': format_id,
-                'quality': get_quality(format_id),
-            })
+                formats.append({
+                    'url': filed['url'],
+                    'ext': 'mp4',
+                    'tbr': tbr,
+                    'format_id': format_id,
+                    'quality': get_quality(format_id),
+                })
 
         self._sort_formats(formats)
 
@@ -88,5 +120,6 @@ class TeamcocoIE(InfoExtractor):
             'title': data['title'],
             'thumbnail': data.get('thumb', {}).get('href'),
             'description': data.get('teaser'),
+            'duration': data.get('duration'),
             'age_limit': self._family_friendly_search(webpage),
         }

youtube_dl/extractor/ted.py

@@ -5,12 +5,12 @@ import re
 
 from .common import InfoExtractor
 
-from ..compat import (
-    compat_str,
-)
+from ..compat import compat_str
+from ..utils import int_or_none
 
 
 class TEDIE(InfoExtractor):
+    IE_NAME = 'ted'
     _VALID_URL = r'''(?x)
         (?P<proto>https?://)
         (?P<type>www|embed(?:-ssl)?)(?P<urlmain>\.ted\.com/
@@ -170,17 +170,51 @@ class TEDIE(InfoExtractor):
                 finfo = self._NATIVE_FORMATS.get(f['format_id'])
                 if finfo:
                     f.update(finfo)
-        else:
-            # Use rtmp downloads
-            formats = [{
-                'format_id': f['name'],
-                'url': talk_info['streamer'],
-                'play_path': f['file'],
-                'ext': 'flv',
-                'width': f['width'],
-                'height': f['height'],
-                'tbr': f['bitrate'],
-            } for f in talk_info['resources']['rtmp']]
+
+        for format_id, resources in talk_info['resources'].items():
+            if format_id == 'h264':
+                for resource in resources:
+                    bitrate = int_or_none(resource.get('bitrate'))
+                    formats.append({
+                        'url': resource['file'],
+                        'format_id': '%s-%sk' % (format_id, bitrate),
+                        'tbr': bitrate,
+                    })
+            elif format_id == 'rtmp':
+                streamer = talk_info.get('streamer')
+                if not streamer:
+                    continue
+                for resource in resources:
+                    formats.append({
+                        'format_id': '%s-%s' % (format_id, resource.get('name')),
+                        'url': streamer,
+                        'play_path': resource['file'],
+                        'ext': 'flv',
+                        'width': int_or_none(resource.get('width')),
+                        'height': int_or_none(resource.get('height')),
+                        'tbr': int_or_none(resource.get('bitrate')),
+                    })
+            elif format_id == 'hls':
+                hls_formats = self._extract_m3u8_formats(
+                    resources.get('stream'), video_name, 'mp4', m3u8_id=format_id)
+                for f in hls_formats:
+                    if f.get('format_id') == 'hls-meta':
+                        continue
+                    if not f.get('height'):
+                        f['vcodec'] = 'none'
+                    else:
+                        f['acodec'] = 'none'
+                formats.extend(hls_formats)
+
+        audio_download = talk_info.get('audioDownload')
+        if audio_download:
+            formats.append({
+                'url': audio_download,
+                'format_id': 'audio',
+                'vcodec': 'none',
+                'preference': -0.5,
+            })
+
         self._sort_formats(formats)
 
         video_id = compat_str(talk_info['id'])

youtube_dl/extractor/testtube.py

@@ -15,19 +15,37 @@ class TestTubeIE(InfoExtractor):
             'id': '60163',
             'display_id': '5-weird-ways-plants-can-eat-animals',
             'duration': 275,
-            'ext': 'mp4',
+            'ext': 'webm',
             'title': '5 Weird Ways Plants Can Eat Animals',
             'description': 'Why have some plants evolved to eat meat?',
             'thumbnail': 're:^https?://.*\.jpg$',
             'uploader': 'DNews',
             'uploader_id': 'dnews',
         },
+    }, {
+        'url': 'https://testtube.com/iflscience/insane-jet-ski-flipping',
+        'info_dict': {
+            'id': 'fAGfJ4YjVus',
+            'ext': 'mp4',
+            'title': 'Flipping Jet-Ski Skills | Outrageous Acts of Science',
+            'uploader': 'Science Channel',
+            'uploader_id': 'ScienceChannel',
+            'upload_date': '20150203',
+            'description': 'md5:e61374030015bae1d2e22f096d4769d6',
+        }
     }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
 
         webpage = self._download_webpage(url, display_id)
+
+        youtube_url = self._html_search_regex(
+            r'<iframe[^>]+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"',
+            webpage, 'youtube iframe', default=None)
+        if youtube_url:
+            return self.url_result(youtube_url, 'Youtube', video_id=display_id)
+
         video_id = self._search_regex(
             r"player\.loadRevision3Item\('video_id',\s*([0-9]+)\);",
             webpage, 'video ID')

youtube_dl/extractor/theplatform.py

@@ -17,6 +17,7 @@ from ..utils import (
     ExtractorError,
     xpath_with_ns,
     unsmuggle_url,
+    int_or_none,
 )
 
 _x = lambda p: xpath_with_ns(p, {'smil': 'http://www.w3.org/2005/SMIL21/Language'})
@@ -28,7 +29,7 @@ class ThePlatformIE(InfoExtractor):
            (?P<config>(?:[^/\?]+/(?:swf|config)|onsite)/select/)?
          |theplatform:)(?P<id>[^/\?&]+)'''
 
-    _TEST = {
+    _TESTS = [{
         # from http://www.metacafe.com/watch/cb-e9I_cZgTgIPd/blackberrys_big_bold_z30/
         'url': 'http://link.theplatform.com/s/dJ5BDC/e9I_cZgTgIPd/meta.smil?format=smil&Tracking=true&mbr=true',
         'info_dict': {
@@ -42,7 +43,20 @@ class ThePlatformIE(InfoExtractor):
             # rtmp download
             'skip_download': True,
         },
-    }
+    }, {
+        # from http://www.cnet.com/videos/tesla-model-s-a-second-step-towards-a-cleaner-motoring-future/
+        'url': 'http://link.theplatform.com/s/kYEXFC/22d_qsQ6MIRT',
+        'info_dict': {
+            'id': '22d_qsQ6MIRT',
+            'ext': 'flv',
+            'description': 'md5:ac330c9258c04f9d7512cf26b9595409',
+            'title': 'Tesla Model S: A second step towards a cleaner motoring future',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }]
 
     @staticmethod
     def _sign_url(url, sig_key, sig_secret, life=600, include_qs=False):
@@ -116,6 +130,8 @@ class ThePlatformIE(InfoExtractor):
         body = meta.find(_x('smil:body'))
 
         f4m_node = body.find(_x('smil:seq//smil:video'))
+        if f4m_node is None:
+            f4m_node = body.find(_x('smil:seq/smil:video'))
         if f4m_node is not None and '.f4m' in f4m_node.attrib['src']:
             f4m_url = f4m_node.attrib['src']
             if 'manifest.f4m?' not in f4m_url:
@@ -127,13 +143,19 @@ class ThePlatformIE(InfoExtractor):
         else:
             formats = []
             switch = body.find(_x('smil:switch'))
+            if switch is None:
+                switch = body.find(_x('smil:par//smil:switch'))
+            if switch is None:
+                switch = body.find(_x('smil:par/smil:switch'))
+            if switch is None:
+                switch = body.find(_x('smil:par'))
             if switch is not None:
                 base_url = head.find(_x('smil:meta')).attrib['base']
                 for f in switch.findall(_x('smil:video')):
                     attr = f.attrib
-                    width = int(attr['width'])
-                    height = int(attr['height'])
-                    vbr = int(attr['system-bitrate']) // 1000
+                    width = int_or_none(attr.get('width'))
+                    height = int_or_none(attr.get('height'))
+                    vbr = int_or_none(attr.get('system-bitrate'), 1000)
                     format_id = '%dx%d_%dk' % (width, height, vbr)
                     formats.append({
                         'format_id': format_id,
@@ -146,9 +168,11 @@ class ThePlatformIE(InfoExtractor):
                     })
             else:
                 switch = body.find(_x('smil:seq//smil:switch'))
+                if switch is None:
+                    switch = body.find(_x('smil:seq/smil:switch'))
                 for f in switch.findall(_x('smil:video')):
                     attr = f.attrib
-                    vbr = int(attr['system-bitrate']) // 1000
+                    vbr = int_or_none(attr.get('system-bitrate'), 1000)
                     ext = determine_ext(attr['src'])
                     if ext == 'once':
                         ext = 'mp4'
@@ -167,5 +191,5 @@ class ThePlatformIE(InfoExtractor):
             'formats': formats,
             'description': info['description'],
             'thumbnail': info['defaultThumbnailUrl'],
-            'duration': info['duration'] // 1000,
+            'duration': int_or_none(info.get('duration'), 1000),
         }

youtube_dl/extractor/tumblr.py

@@ -56,6 +56,6 @@ class TumblrIE(InfoExtractor):
             'url': video_url,
             'ext': 'mp4',
             'title': video_title,
-            'description': self._og_search_description(webpage),
-            'thumbnail': self._og_search_thumbnail(webpage),
+            'description': self._og_search_description(webpage, default=None),
+            'thumbnail': self._og_search_thumbnail(webpage, default=None),
         }

youtube_dl/extractor/udn.py

@@ -0,0 +1,74 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+from .common import InfoExtractor
+from ..utils import (
+    js_to_json,
+    ExtractorError,
+)
+from ..compat import compat_urlparse
+
+
+class UDNEmbedIE(InfoExtractor):
+    _VALID_URL = r'https?://video\.udn\.com/(?:embed|play)/news/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://video.udn.com/embed/news/300040',
+        'md5': 'de06b4c90b042c128395a88f0384817e',
+        'info_dict': {
+            'id': '300040',
+            'ext': 'mp4',
+            'title': '生物老師男變女 全校挺"做自己"',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        }
+    }, {
+        'url': 'https://video.udn.com/embed/news/300040',
+        'only_matching': True,
+    }, {
+        # From https://video.udn.com/news/303776
+        'url': 'https://video.udn.com/play/news/303776',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        page = self._download_webpage(url, video_id)
+
+        options = json.loads(js_to_json(self._html_search_regex(
+            r'var options\s*=\s*([^;]+);', page, 'video urls dictionary')))
+
+        video_urls = options['video']
+
+        if video_urls.get('youtube'):
+            return self.url_result(video_urls.get('youtube'), 'Youtube')
+
+        try:
+            del video_urls['youtube']
+        except KeyError:
+            pass
+
+        formats = [{
+            'url': self._download_webpage(
+                compat_urlparse.urljoin(url, api_url), video_id,
+                'retrieve url for %s video' % video_type),
+            'format_id': video_type,
+            'preference': 0 if video_type == 'mp4' else -1,
+        } for video_type, api_url in video_urls.items() if api_url]
+
+        if not formats:
+            raise ExtractorError('No videos found', expected=True)
+
+        self._sort_formats(formats)
+
+        thumbnail = None
+
+        if options.get('gallery') and len(options['gallery']):
+            thumbnail = options['gallery'][0].get('original')
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': options['title'],
+            'thumbnail': thumbnail
+        }

youtube_dl/extractor/ustream.py

@@ -1,17 +1,19 @@
 from __future__ import unicode_literals
 
+import json
 import re
 
 from .common import InfoExtractor
 from ..compat import (
     compat_urlparse,
 )
+from ..utils import ExtractorError
 
 
 class UstreamIE(InfoExtractor):
     _VALID_URL = r'https?://www\.ustream\.tv/(?P<type>recorded|embed|embed/recorded)/(?P<videoID>\d+)'
     IE_NAME = 'ustream'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.ustream.tv/recorded/20274954',
         'md5': '088f151799e8f572f84eb62f17d73e5c',
         'info_dict': {
@@ -20,7 +22,18 @@ class UstreamIE(InfoExtractor):
             'uploader': 'Young Americans for Liberty',
             'title': 'Young Americans for Liberty February 7, 2012 2:28 AM',
         },
-    }
+    }, {
+        # From http://sportscanada.tv/canadagames/index.php/week2/figure-skating/444
+        # Title and uploader available only from params JSON
+        'url': 'http://www.ustream.tv/embed/recorded/59307601?ub=ff0000&lc=ff0000&oc=ffffff&uc=ffffff&v=3&wmode=direct',
+        'md5': '5a2abf40babeac9812ed20ae12d34e10',
+        'info_dict': {
+            'id': '59307601',
+            'ext': 'flv',
+            'title': '-CG11- Canada Games Figure Skating',
+            'uploader': 'sportscanadatv',
+        }
+    }]
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)
@@ -39,16 +52,42 @@ class UstreamIE(InfoExtractor):
             desktop_url = 'http://www.ustream.tv/recorded/' + desktop_video_id
             return self.url_result(desktop_url, 'Ustream')
 
-        video_url = 'http://tcdn.ustream.tv/video/%s' % video_id
+        params = self._download_json(
+            'http://cdngw.ustream.tv/rgwjson/Viewer.getVideo/' + json.dumps({
+                'brandId': 1,
+                'videoId': int(video_id),
+                'autoplay': False,
+            }), video_id)
+
+        if 'error' in params:
+            raise ExtractorError(params['error']['message'], expected=True)
+
+        video_url = params['flv']
+
         webpage = self._download_webpage(url, video_id)
 
         self.report_extraction(video_id)
 
         video_title = self._html_search_regex(r'data-title="(?P<title>.+)"',
-                                              webpage, 'title')
+                                              webpage, 'title', default=None)
+
+        if not video_title:
+            try:
+                video_title = params['moduleConfig']['meta']['title']
+            except KeyError:
+                pass
+
+        if not video_title:
+            video_title = 'Ustream video ' + video_id
 
         uploader = self._html_search_regex(r'data-content-type="channel".*?>(?P<uploader>.*?)</a>',
-                                           webpage, 'uploader', fatal=False, flags=re.DOTALL)
+                                           webpage, 'uploader', fatal=False, flags=re.DOTALL, default=None)
+
+        if not uploader:
+            try:
+                uploader = params['moduleConfig']['meta']['userName']
+            except KeyError:
+                uploader = None
 
         thumbnail = self._html_search_regex(r'<link rel="image_src" href="(?P<thumb>.*?)"',
                                             webpage, 'thumbnail', fatal=False)

youtube_dl/extractor/veehd.py

@@ -17,7 +17,9 @@ from ..utils import (
 class VeeHDIE(InfoExtractor):
     _VALID_URL = r'https?://veehd\.com/video/(?P<id>\d+)'
 
-    _TEST = {
+    # Seems VeeHD videos have multiple copies on several servers, all of
+    # whom have different MD5 checksums, so omit md5 field in all tests
+    _TESTS = [{
         'url': 'http://veehd.com/video/4639434_Solar-Sinter',
         'info_dict': {
             'id': '4639434',
@@ -26,7 +28,26 @@ class VeeHDIE(InfoExtractor):
             'uploader_id': 'VideoEyes',
             'description': 'md5:46a840e8692ddbaffb5f81d9885cb457',
         },
-    }
+        'skip': 'Video deleted',
+    }, {
+        'url': 'http://veehd.com/video/4905758_Elysian-Fields-Channeling',
+        'info_dict': {
+            'id': '4905758',
+            'ext': 'mp4',
+            'title': 'Elysian Fields - Channeling',
+            'description': 'md5:360e4e95fdab58aefbea0f2a19e5604b',
+            'uploader_id': 'spotted',
+        }
+    }, {
+        'url': 'http://veehd.com/video/2046729_2012-2009-DivX-Trailer',
+        'info_dict': {
+            'id': '2046729',
+            'ext': 'avi',
+            'title': '2012 (2009) DivX Trailer',
+            'description': 'md5:75435ee95255e6a9838ac6f6f3a2396b',
+            'uploader_id': 'Movie_Trailers',
+        }
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -48,13 +69,21 @@ class VeeHDIE(InfoExtractor):
         player_page = self._download_webpage(
             player_url, video_id, 'Downloading player page')
 
+        video_url = None
+
         config_json = self._search_regex(
             r'value=\'config=({.+?})\'', player_page, 'config json', default=None)
 
         if config_json:
             config = json.loads(config_json)
             video_url = compat_urlparse.unquote(config['clip']['url'])
-        else:
+
+        if not video_url:
+            video_url = self._html_search_regex(
+                r'<embed[^>]+type="video/divx"[^>]+src="([^"]+)"',
+                player_page, 'video url', default=None)
+
+        if not video_url:
             iframe_src = self._search_regex(
                 r'<iframe[^>]+src="/?([^"]+)"', player_page, 'iframe url')
             iframe_url = 'http://veehd.com/%s' % iframe_src
@@ -82,7 +111,6 @@ class VeeHDIE(InfoExtractor):
             'id': video_id,
             'title': title,
             'url': video_url,
-            'ext': 'mp4',
             'uploader_id': uploader_id,
             'thumbnail': thumbnail,
             'description': description,

youtube_dl/extractor/vgtv.py

@@ -8,7 +8,7 @@ from ..utils import float_or_none
 
 
 class VGTVIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?vgtv\.no/#!/(?:.*)/(?P<id>[0-9]+)'
+    _VALID_URL = r'http://(?:www\.)?vgtv\.no/#!/[^/]+/(?P<id>[0-9]+)'
     _TESTS = [
         {
             # streamType: vod