release 2015.05.03

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

.travis.yml

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

AUTHORS

@@ -112,3 +112,15 @@ Frans de Jonge
 Robin de Rooij
 Ryan Schmidt
 Leslie P. Polzer
+Duncan Keall
+Alexander Mamay
+Devin J. Pohly
+Eduardo Ferro Aldama
+Jeff Buchbinder
+Amish Bhadeshia
+Joram Schrijver
+Will W.
+Mohammad Teimori Pabandi
+Roman Le Négrate
+Matthias Küch
+Julian Richen

CONTRIBUTING.md

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

Makefile

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

README.md

@@ -5,6 +5,7 @@ youtube-dl - download videos from youtube.com or other video platforms
 - [OPTIONS](#options)
 - [CONFIGURATION](#configuration)
 - [OUTPUT TEMPLATE](#output-template)
+- [FORMAT SELECTION](#format-selection)
 - [VIDEO SELECTION](#video-selection)
 - [FAQ](#faq)
 - [DEVELOPER INSTRUCTIONS](#developer-instructions)
@@ -45,367 +46,191 @@ which means you can modify it, redistribute it or use it however you like.
     youtube-dl [OPTIONS] URL [URL...]
 
 # OPTIONS
-    -h, --help                       print this help text and exit
-    --version                        print program version and exit
-    -U, --update                     update this program to latest version. Make
-                                     sure that you have sufficient permissions
-                                     (run with sudo if needed)
-    -i, --ignore-errors              continue on download errors, for example to
-                                     skip unavailable videos in a playlist
-    --abort-on-error                 Abort downloading of further videos (in the
-                                     playlist or the command line) if an error
-                                     occurs
-    --dump-user-agent                display the current browser identification
-    --list-extractors                List all supported extractors and the URLs
-                                     they would handle
-    --extractor-descriptions         Output descriptions of all supported
-                                     extractors
-    --default-search PREFIX          Use this prefix for unqualified URLs. For
-                                     example "gvsearch2:" downloads two videos
-                                     from google videos for  youtube-dl "large
-                                     apple". Use the value "auto" to let
-                                     youtube-dl guess ("auto_warning" to emit a
-                                     warning when guessing). "error" just throws
-                                     an error. The default value "fixup_error"
-                                     repairs broken URLs, but emits an error if
-                                     this is not possible instead of searching.
-    --ignore-config                  Do not read configuration files. When given
-                                     in the global configuration file /etc
-                                     /youtube-dl.conf: Do not read the user
-                                     configuration in ~/.config/youtube-
-                                     dl/config (%APPDATA%/youtube-dl/config.txt
-                                     on Windows)
-    --flat-playlist                  Do not extract the videos of a playlist,
-                                     only list them.
-    --no-color                       Do not emit color codes in output.
+    -h, --help                       Print this help text and exit
+    --version                        Print program version and exit
+    -U, --update                     Update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed)
+    -i, --ignore-errors              Continue on download errors, for example to skip unavailable videos in a playlist
+    --abort-on-error                 Abort downloading of further videos (in the playlist or the command line) if an error occurs
+    --dump-user-agent                Display the current browser identification
+    --list-extractors                List all supported extractors and the URLs they would handle
+    --extractor-descriptions         Output descriptions of all supported extractors
+    --default-search PREFIX          Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large apple".
+                                     Use the value "auto" to let youtube-dl guess ("auto_warning" to emit a warning when guessing). "error" just throws an error. The
+                                     default value "fixup_error" repairs broken URLs, but emits an error if this is not possible instead of searching.
+    --ignore-config                  Do not read configuration files. When given in the global configuration file /etc/youtube-dl.conf: Do not read the user configuration
+                                     in ~/.config/youtube-dl/config (%APPDATA%/youtube-dl/config.txt on Windows)
+    --flat-playlist                  Do not extract the videos of a playlist, only list them.
+    --no-color                       Do not emit color codes in output
 
 ## Network Options:
-    --proxy URL                      Use the specified HTTP/HTTPS proxy. Pass in
-                                     an empty string (--proxy "") for direct
-                                     connection
+    --proxy URL                      Use the specified HTTP/HTTPS proxy. Pass in an empty string (--proxy "") for direct connection
     --socket-timeout SECONDS         Time to wait before giving up, in seconds
-    --source-address IP              Client-side IP address to bind to
-                                     (experimental)
-    -4, --force-ipv4                 Make all connections via IPv4
-                                     (experimental)
-    -6, --force-ipv6                 Make all connections via IPv6
-                                     (experimental)
+    --source-address IP              Client-side IP address to bind to (experimental)
+    -4, --force-ipv4                 Make all connections via IPv4 (experimental)
+    -6, --force-ipv6                 Make all connections via IPv6 (experimental)
+    --cn-verification-proxy URL      Use this proxy to verify the IP address for some Chinese sites. The default proxy specified by --proxy (or none, if the options is
+                                     not present) is used for the actual downloading. (experimental)
 
 ## Video Selection:
-    --playlist-start NUMBER          playlist video to start at (default is 1)
-    --playlist-end NUMBER            playlist video to end at (default is last)
-    --playlist-items ITEM_SPEC       playlist video items to download. Specify
-                                     indices of the videos in the playlist
-                                     seperated by commas like: "--playlist-items
-                                     1,2,5,8" if you want to download videos
-                                     indexed 1, 2, 5, 8 in the playlist. You can
-                                     specify range: "--playlist-items
-                                     1-3,7,10-13", it will download the videos
-                                     at index 1, 2, 3, 7, 10, 11, 12 and 13.
-    --match-title REGEX              download only matching titles (regex or
-                                     caseless sub-string)
-    --reject-title REGEX             skip download for matching titles (regex or
-                                     caseless sub-string)
+    --playlist-start NUMBER          Playlist video to start at (default is 1)
+    --playlist-end NUMBER            Playlist video to end at (default is last)
+    --playlist-items ITEM_SPEC       Playlist video items to download. Specify indices of the videos in the playlist 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)
     --max-downloads NUMBER           Abort after downloading NUMBER files
-    --min-filesize SIZE              Do not download any videos smaller than
-                                     SIZE (e.g. 50k or 44.6m)
-    --max-filesize SIZE              Do not download any videos larger than SIZE
-                                     (e.g. 50k or 44.6m)
-    --date DATE                      download only videos uploaded in this date
-    --datebefore DATE                download only videos uploaded on or before
-                                     this date (i.e. inclusive)
-    --dateafter DATE                 download only videos uploaded on or after
-                                     this date (i.e. inclusive)
-    --min-views COUNT                Do not download any videos with less than
-                                     COUNT views
-    --max-views COUNT                Do not download any videos with more than
-                                     COUNT views
-    --match-filter FILTER            (Experimental) Generic video filter.
-                                     Specify any key (see help for -o for a list
-                                     of available keys) to match if the key is
-                                     present, !key to check if the key is not
-                                     present,key > NUMBER (like "comment_count >
-                                     12", also works with >=, <, <=, !=, =) to
-                                     compare against a number, and & to require
-                                     multiple matches. Values which are not
-                                     known are excluded unless you put a
-                                     question mark (?) after the operator.For
-                                     example, to only match videos that have
-                                     been liked more than 100 times and disliked
-                                     less than 50 times (or the dislike
-                                     functionality is not available at the given
-                                     service), but who also have a description,
-                                     use  --match-filter "like_count > 100 &
+    --min-filesize SIZE              Do not download any videos smaller than SIZE (e.g. 50k or 44.6m)
+    --max-filesize SIZE              Do not download any videos larger than SIZE (e.g. 50k or 44.6m)
+    --date DATE                      Download only videos uploaded in this date
+    --datebefore DATE                Download only videos uploaded on or before this date (i.e. inclusive)
+    --dateafter DATE                 Download only videos uploaded on or after this date (i.e. inclusive)
+    --min-views COUNT                Do not download any videos with less than COUNT views
+    --max-views COUNT                Do not download any videos with more than COUNT views
+    --match-filter FILTER            Generic video filter (experimental). Specify any key (see help for -o for a list of available keys) to match if the key is present,
+                                     !key to check if the key is not present,key > NUMBER (like "comment_count > 12", also works with >=, <, <=, !=, =) to compare against
+                                     a number, and & to require multiple matches. Values which are not known are excluded unless you put a question mark (?) after the
+                                     operator.For example, to only match videos that have been liked more than 100 times and disliked less than 50 times (or the dislike
+                                     functionality is not available at the given service), but who also have a description, use  --match-filter "like_count > 100 &
                                      dislike_count <? 50 & description" .
-    --no-playlist                    If the URL refers to a video and a
-                                     playlist, download only the video.
-    --age-limit YEARS                download only videos suitable for the given
-                                     age
-    --download-archive FILE          Download only videos not listed in the
-                                     archive file. Record the IDs of all
-                                     downloaded videos in it.
-    --include-ads                    Download advertisements as well
-                                     (experimental)
+    --no-playlist                    Download only the video, if the URL refers to a video and a playlist.
+    --yes-playlist                   Download the playlist, if the URL refers to a video and a playlist.
+    --age-limit YEARS                Download only videos suitable for the given age
+    --download-archive FILE          Download only videos not listed in the archive file. Record the IDs of all downloaded videos in it.
+    --include-ads                    Download advertisements as well (experimental)
 
 ## Download Options:
-    -r, --rate-limit LIMIT           maximum download rate in bytes per second
-                                     (e.g. 50K or 4.2M)
-    -R, --retries RETRIES            number of retries (default is 10), or
-                                     "infinite".
-    --buffer-size SIZE               size of download buffer (e.g. 1024 or 16K)
-                                     (default is 1024)
-    --no-resize-buffer               do not automatically adjust the buffer
-                                     size. By default, the buffer size is
-                                     automatically resized from an initial value
-                                     of SIZE.
+    -r, --rate-limit LIMIT           Maximum download rate in bytes per second (e.g. 50K or 4.2M)
+    -R, --retries RETRIES            Number of retries (default is 10), or "infinite".
+    --buffer-size SIZE               Size of download buffer (e.g. 1024 or 16K) (default is 1024)
+    --no-resize-buffer               Do not automatically adjust the buffer size. By default, the buffer size is automatically resized from an initial value of SIZE.
     --playlist-reverse               Download playlist videos in reverse order
-    --xattr-set-filesize             (experimental) set file xattribute
-                                     ytdl.filesize with expected filesize
-    --hls-prefer-native              (experimental) Use the native HLS
-                                     downloader instead of ffmpeg.
-    --external-downloader COMMAND    (experimental) Use the specified external
-                                     downloader. Currently supports
-                                     aria2c,curl,wget
+    --xattr-set-filesize             Set file xattribute ytdl.filesize with expected filesize (experimental)
+    --hls-prefer-native              Use the native HLS downloader instead of ffmpeg (experimental)
+    --external-downloader COMMAND    Use the specified external downloader. Currently supports aria2c,curl,wget
+    --external-downloader-args ARGS  Give these arguments to the external downloader
 
 ## Filesystem Options:
-    -a, --batch-file FILE            file containing URLs to download ('-' for
-                                     stdin)
-    --id                             use only video ID in file name
-    -o, --output TEMPLATE            output filename template. Use %(title)s to
-                                     get the title, %(uploader)s for the
-                                     uploader name, %(uploader_id)s for the
-                                     uploader nickname if different,
-                                     %(autonumber)s to get an automatically
-                                     incremented number, %(ext)s for the
-                                     filename extension, %(format)s for the
-                                     format description (like "22 - 1280x720" or
-                                     "HD"), %(format_id)s for the unique id of
-                                     the format (like Youtube's itags: "137"),
-                                     %(upload_date)s for the upload date
-                                     (YYYYMMDD), %(extractor)s for the provider
-                                     (youtube, metacafe, etc), %(id)s for the
-                                     video id, %(playlist_title)s,
-                                     %(playlist_id)s, or %(playlist)s (=title if
-                                     present, ID otherwise) for the playlist the
-                                     video is in, %(playlist_index)s for the
-                                     position in the playlist. %(height)s and
-                                     %(width)s for the width and height of the
-                                     video format. %(resolution)s for a textual
-                                     description of the resolution of the video
-                                     format. %% for a literal percent. Use - to
-                                     output to stdout. Can also be used to
-                                     download to a different directory, for
-                                     example with -o '/my/downloads/%(uploader)s
-                                     /%(title)s-%(id)s.%(ext)s' .
-    --autonumber-size NUMBER         Specifies the number of digits in
-                                     %(autonumber)s when it is present in output
-                                     filename template or --auto-number option
-                                     is given
-    --restrict-filenames             Restrict filenames to only ASCII
-                                     characters, and avoid "&" and spaces in
-                                     filenames
-    -A, --auto-number                [deprecated; use  -o
-                                     "%(autonumber)s-%(title)s.%(ext)s" ] number
-                                     downloaded files starting from 00000
-    -t, --title                      [deprecated] use title in file name
-                                     (default)
-    -l, --literal                    [deprecated] alias of --title
-    -w, --no-overwrites              do not overwrite files
-    -c, --continue                   force resume of partially downloaded files.
-                                     By default, youtube-dl will resume
-                                     downloads if possible.
-    --no-continue                    do not resume partially downloaded files
-                                     (restart from beginning)
-    --no-part                        do not use .part files - write directly
-                                     into output file
-    --no-mtime                       do not use the Last-modified header to set
-                                     the file modification time
-    --write-description              write video description to a .description
-                                     file
-    --write-info-json                write video metadata to a .info.json file
-    --write-annotations              write video annotations to a .annotation
-                                     file
-    --load-info FILE                 json file containing the video information
-                                     (created with the "--write-json" option)
-    --cookies FILE                   file to read cookies from and dump cookie
-                                     jar in
-    --cache-dir DIR                  Location in the filesystem where youtube-dl
-                                     can store some downloaded information
-                                     permanently. By default $XDG_CACHE_HOME
-                                     /youtube-dl or ~/.cache/youtube-dl . At the
-                                     moment, only YouTube player files (for
-                                     videos with obfuscated signatures) are
-                                     cached, but that may change.
+    -a, --batch-file FILE            File containing URLs to download ('-' for stdin)
+    --id                             Use only video ID in file name
+    -o, --output TEMPLATE            Output filename template. Use %(title)s to get the title, %(uploader)s for the uploader name, %(uploader_id)s for the uploader
+                                     nickname if different, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(format)s for
+                                     the format description (like "22 - 1280x720" or "HD"), %(format_id)s for the unique id of the format (like YouTube's itags: "137"),
+                                     %(upload_date)s for the upload date (YYYYMMDD), %(extractor)s for the provider (youtube, metacafe, etc), %(id)s for the video id,
+                                     %(playlist_title)s, %(playlist_id)s, or %(playlist)s (=title if present, ID otherwise) for the playlist the video is in,
+                                     %(playlist_index)s for the position in the playlist. %(height)s and %(width)s for the width and height of the video format.
+                                     %(resolution)s for a textual description of the resolution of the video format. %% for a literal percent. Use - to output to stdout.
+                                     Can also be used to download to a different directory, for example with -o '/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s' .
+    --autonumber-size NUMBER         Specify the number of digits in %(autonumber)s when it is present in output filename template or --auto-number option is given
+    --restrict-filenames             Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames
+    -A, --auto-number                [deprecated; use  -o "%(autonumber)s-%(title)s.%(ext)s" ] Number downloaded files starting from 00000
+    -t, --title                      [deprecated] Use title in file name (default)
+    -l, --literal                    [deprecated] Alias of --title
+    -w, --no-overwrites              Do not overwrite files
+    -c, --continue                   Force resume of partially downloaded files. By default, youtube-dl will resume downloads if possible.
+    --no-continue                    Do not resume partially downloaded files (restart from beginning)
+    --no-part                        Do not use .part files - write directly into output file
+    --no-mtime                       Do not use the Last-modified header to set the file modification time
+    --write-description              Write video description to a .description file
+    --write-info-json                Write video metadata to a .info.json file
+    --write-annotations              Write video annotations to a .annotations.xml file
+    --load-info FILE                 JSON file containing the video information (created with the "--write-info-json" option)
+    --cookies FILE                   File to read cookies from and dump cookie jar in
+    --cache-dir DIR                  Location in the filesystem where youtube-dl can store some downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl
+                                     or ~/.cache/youtube-dl . At the moment, only YouTube player files (for videos with obfuscated signatures) are cached, but that may
+                                     change.
     --no-cache-dir                   Disable filesystem caching
     --rm-cache-dir                   Delete all filesystem cache files
 
 ## Thumbnail images:
-    --write-thumbnail                write thumbnail image to disk
-    --write-all-thumbnails           write all thumbnail image formats to disk
-    --list-thumbnails                Simulate and list all available thumbnail
-                                     formats
+    --write-thumbnail                Write thumbnail image to disk
+    --write-all-thumbnails           Write all thumbnail image formats to disk
+    --list-thumbnails                Simulate and list all available thumbnail formats
 
 ## Verbosity / Simulation Options:
-    -q, --quiet                      activates quiet mode
+    -q, --quiet                      Activate quiet mode
     --no-warnings                    Ignore warnings
-    -s, --simulate                   do not download the video and do not write
-                                     anything to disk
-    --skip-download                  do not download the video
-    -g, --get-url                    simulate, quiet but print URL
-    -e, --get-title                  simulate, quiet but print title
-    --get-id                         simulate, quiet but print id
-    --get-thumbnail                  simulate, quiet but print thumbnail URL
-    --get-description                simulate, quiet but print video description
-    --get-duration                   simulate, quiet but print video length
-    --get-filename                   simulate, quiet but print output filename
-    --get-format                     simulate, quiet but print output format
-    -j, --dump-json                  simulate, quiet but print JSON information.
-                                     See --output for a description of available
-                                     keys.
-    -J, --dump-single-json           simulate, quiet but print JSON information
-                                     for each command-line argument. If the URL
-                                     refers to a playlist, dump the whole
-                                     playlist information in a single line.
-    --print-json                     Be quiet and print the video information as
-                                     JSON (video is still being downloaded).
-    --newline                        output progress bar as new lines
-    --no-progress                    do not print progress bar
-    --console-title                  display progress in console titlebar
-    -v, --verbose                    print various debugging information
-    --dump-intermediate-pages        print downloaded pages to debug problems
-                                     (very verbose)
-    --write-pages                    Write downloaded intermediary pages to
-                                     files in the current directory to debug
-                                     problems
+    -s, --simulate                   Do not download the video and do not write anything to disk
+    --skip-download                  Do not download the video
+    -g, --get-url                    Simulate, quiet but print URL
+    -e, --get-title                  Simulate, quiet but print title
+    --get-id                         Simulate, quiet but print id
+    --get-thumbnail                  Simulate, quiet but print thumbnail URL
+    --get-description                Simulate, quiet but print video description
+    --get-duration                   Simulate, quiet but print video length
+    --get-filename                   Simulate, quiet but print output filename
+    --get-format                     Simulate, quiet but print output format
+    -j, --dump-json                  Simulate, quiet but print JSON information. See --output for a description of available keys.
+    -J, --dump-single-json           Simulate, quiet but print JSON information for each command-line argument. If the URL refers to a playlist, dump the whole playlist
+                                     information in a single line.
+    --print-json                     Be quiet and print the video information as JSON (video is still being downloaded).
+    --newline                        Output progress bar as new lines
+    --no-progress                    Do not print progress bar
+    --console-title                  Display progress in console titlebar
+    -v, --verbose                    Print various debugging information
+    --dump-pages                     Print downloaded pages to debug problems (very verbose)
+    --write-pages                    Write downloaded intermediary pages to files in the current directory to debug problems
     --print-traffic                  Display sent and read HTTP traffic
-    -C, --call-home                  Contact the youtube-dl server for
-                                     debugging.
-    --no-call-home                   Do NOT contact the youtube-dl server for
-                                     debugging.
+    -C, --call-home                  Contact the youtube-dl server for debugging
+    --no-call-home                   Do NOT contact the youtube-dl server for debugging
 
 ## Workarounds:
     --encoding ENCODING              Force the specified encoding (experimental)
-    --no-check-certificate           Suppress HTTPS certificate validation.
-    --prefer-insecure                Use an unencrypted connection to retrieve
-                                     information about the video. (Currently
-                                     supported only for YouTube)
-    --user-agent UA                  specify a custom user agent
-    --referer URL                    specify a custom referer, use if the video
-                                     access is restricted to one domain
-    --add-header FIELD:VALUE         specify a custom HTTP header and its value,
-                                     separated by a colon ':'. You can use this
-                                     option multiple times
-    --bidi-workaround                Work around terminals that lack
-                                     bidirectional text support. Requires bidiv
-                                     or fribidi executable in PATH
-    --sleep-interval SECONDS         Number of seconds to sleep before each
-                                     download.
+    --no-check-certificate           Suppress HTTPS certificate validation
+    --prefer-insecure                Use an unencrypted connection to retrieve information about the video. (Currently supported only for YouTube)
+    --user-agent UA                  Specify a custom user agent
+    --referer URL                    Specify a custom referer, use if the video access is restricted to one domain
+    --add-header FIELD:VALUE         Specify a custom HTTP header and its value, separated by a colon ':'. You can use this option multiple times
+    --bidi-workaround                Work around terminals that lack bidirectional text support. Requires bidiv or fribidi executable in PATH
+    --sleep-interval SECONDS         Number of seconds to sleep before each download.
 
 ## Video Format Options:
-    -f, --format FORMAT              video format code, specify the order of
-                                     preference using slashes, as in -f 22/17/18
-                                     .  Instead of format codes, you can select
-                                     by extension for the extensions aac, m4a,
-                                     mp3, mp4, ogg, wav, webm. You can also use
-                                     the special names "best", "bestvideo",
-                                     "bestaudio", "worst".  You can filter the
-                                     video results by putting a condition in
-                                     brackets, as in -f "best[height=720]" (or
-                                     -f "[filesize>10M]").  This works for
-                                     filesize, height, width, tbr, abr, vbr,
-                                     asr, and fps and the comparisons <, <=, >,
-                                     >=, =, != and for ext, acodec, vcodec,
-                                     container, and protocol and the comparisons
-                                     =, != . Formats for which the value is not
-                                     known are excluded unless you put a
-                                     question mark (?) after the operator. You
-                                     can combine format filters, so  -f "[height
-                                     <=? 720][tbr>500]" selects up to 720p
-                                     videos (or videos where the height is not
-                                     known) with a bitrate of at least 500
-                                     KBit/s. By default, youtube-dl will pick
-                                     the best quality. Use commas to download
-                                     multiple audio formats, such as -f
-                                     136/137/mp4/bestvideo,140/m4a/bestaudio.
-                                     You can merge the video and audio of two
-                                     formats into a single file using -f <video-
-                                     format>+<audio-format> (requires ffmpeg or
-                                     avconv), for example -f
-                                     bestvideo+bestaudio.
-    --all-formats                    download all available video formats
-    --prefer-free-formats            prefer free video formats unless a specific
-                                     one is requested
-    --max-quality FORMAT             highest quality format to download
-    -F, --list-formats               list all available formats
-    --youtube-skip-dash-manifest     Do not download the DASH manifest on
-                                     YouTube videos
-    --merge-output-format FORMAT     If a merge is required (e.g.
-                                     bestvideo+bestaudio), output to given
-                                     container format. One of mkv, mp4, ogg,
-                                     webm, flv.Ignored if no merge is required
+    -f, --format FORMAT              Video format code, see the "FORMAT SELECTION" for all the info
+    --all-formats                    Download all available video formats
+    --prefer-free-formats            Prefer free video formats unless a specific one is requested
+    -F, --list-formats               List all available formats
+    --youtube-skip-dash-manifest     Do not download the DASH 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)
-    --recode-video FORMAT            Encode the video to another format if
-                                     necessary (currently supported:
-                                     mp4|flv|ogg|webm|mkv)
-    -k, --keep-video                 keeps the video file on disk after the
-                                     post-processing; the video is erased by
-                                     default
-    --no-post-overwrites             do not overwrite post-processed files; the
-                                     post-processed files are overwritten by
-                                     default
-    --embed-subs                     embed subtitles in the video (only for mp4
-                                     videos)
-    --embed-thumbnail                embed thumbnail in the audio as cover art
-    --add-metadata                   write metadata to the video file
-    --xattrs                         write metadata to the video file's xattrs
-                                     (using dublin core and xdg standards)
-    --fixup POLICY                   Automatically correct known faults of the
-                                     file. One of never (do nothing), warn (only
-                                     emit a warning), detect_or_warn(the
-                                     default; fix file if we can, warn
-                                     otherwise)
-    --prefer-avconv                  Prefer avconv over ffmpeg for running the
-                                     postprocessors (default)
-    --prefer-ffmpeg                  Prefer ffmpeg over avconv for running the
-                                     postprocessors
-    --ffmpeg-location PATH           Location of the ffmpeg/avconv binary;
-                                     either the path to the binary or its
-                                     containing directory.
-    --exec CMD                       Execute a command on the file after
-                                     downloading, similar to find's -exec
-                                     syntax. Example: --exec 'adb push {}
-                                     /sdcard/Music/ && rm {}'
+    -x, --extract-audio              Convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)
+    --audio-format FORMAT            Specify audio format: "best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; "best" by default
+    --audio-quality QUALITY          Specify ffmpeg/avconv audio quality, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default
+                                     5)
+    --recode-video FORMAT            Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm|mkv)
+    -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)
+    --fixup POLICY                   Automatically correct known faults of the file. One of never (do nothing), warn (only emit a warning), detect_or_warn(the default;
+                                     fix file if we can, warn otherwise)
+    --prefer-avconv                  Prefer avconv over ffmpeg for running the postprocessors (default)
+    --prefer-ffmpeg                  Prefer ffmpeg over avconv for running the postprocessors
+    --ffmpeg-location PATH           Location of the ffmpeg/avconv binary; either the path to the binary or its containing directory.
+    --exec CMD                       Execute a command on the file after downloading, similar to find's -exec syntax. Example: --exec 'adb push {} /sdcard/Music/ && rm
+                                     {}'
+    --convert-subtitles FORMAT       Convert the subtitles to other format (currently supported: srt|ass|vtt)
 
 # CONFIGURATION
 
@@ -437,6 +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:
@@ -487,9 +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?
 
@@ -521,10 +357,30 @@ YouTube has switched to a new video info format in July 2011 which is not suppor
 
 YouTube requires an additional signature since September 2012 which is not supported by old versions of youtube-dl. See [above](#how-do-i-update-youtube-dl) for how to update youtube-dl.
 
+### Video URL contains an ampersand and I'm getting some strange output `[1] 2839` or `'v' is not recognized as an internal or external command` ###
+
+That's actually the output from your shell. Since ampersand is one of the special shell characters it's interpreted by shell preventing you from passing the whole URL to youtube-dl. To disable your shell from interpreting the ampersands (or any other special characters) you have to either put the whole URL in quotes or escape them with a backslash (which approach will work depends on your shell).
+
+For example if your URL is https://www.youtube.com/watch?t=4&v=BaW_jenozKc you should end up with following command:
+
+```youtube-dl 'https://www.youtube.com/watch?t=4&v=BaW_jenozKc'```
+
+or
+
+```youtube-dl https://www.youtube.com/watch?t=4\&v=BaW_jenozKc```
+
+For Windows you have to use the double quotes:
+
+```youtube-dl "https://www.youtube.com/watch?t=4&v=BaW_jenozKc"```
+
 ### ExtractorError: Could not find JS function u'OF'
 
 In February 2015, the new YouTube player contained a character sequence in a string that was misinterpreted by old versions of youtube-dl. See [above](#how-do-i-update-youtube-dl) for how to update youtube-dl.
 
+### HTTP Error 429: Too Many Requests or 402: Payment Required
+
+These two error codes indicate that the service is blocking your IP address because of overuse. Contact the service and ask them to unblock your IP address, or - if you have acquired a whitelisted IP address already - use the [`--proxy` or `--network-address` options](#network-options) to select another IP address.
+
 ### SyntaxError: Non-ASCII character ###
 
 The error
@@ -569,6 +425,18 @@ A note on the service that they don't host the infringing content, but just link
 
 Support requests for services that **do** purchase the rights to distribute their content are perfectly fine though. If in doubt, you can simply include a source that mentions the legitimate purchase of content.
 
+### How can I speed up work on my issue?
+
+(Also known as: Help, my important issue not being solved!) The youtube-dl core developer team is quite small. While we do our best to solve as many issues as possible, sometimes that can take quite a while. To speed up your issue, here's what you can do:
+
+First of all, please do report the issue [at our issue tracker](https://yt-dl.org/bugs). That allows us to coordinate all efforts by users and developers, and serves as a unified point. Unfortunately, the youtube-dl project has grown too large to use personal email as an effective communication channel.
+
+Please read the [bug reporting instructions](#bugs) below. A lot of bugs lack all the necessary information. If you can, offer proxy, VPN, or shell access to the youtube-dl developers. If you are able to, test the issue from multiple computers in multiple countries to exclude local censorship or misconfiguration issues.
+
+If nobody is interested in solving your issue, you are welcome to take matters into your own hands and submit a pull request (or coerce/pay somebody else to do so).
+
+Feel free to bump the issue from time to time by writing a small comment ("Issue is still present in youtube-dl version ...from France, but fixed from Belgium"), but please not more than once a month. Please do not declare your issue as `important` or `urgent`.
+
 ### How can I detect whether a given URL is supported by youtube-dl?
 
 For one, have a look at the [list of supported sites](docs/supportedsites.md). Note that it can sometimes happen that the site changes its URL scheme (say, from http://example.com/video/1234567 to http://example.com/v/1234567 ) and youtube-dl reports an URL of a service in that list as unsupported. In that case, simply report a bug.
@@ -668,6 +536,7 @@ youtube-dl makes the best effort to be a good command-line program, and thus sho
 From a Python program, you can embed youtube-dl in a more powerful fashion, like this:
 
 ```python
+from __future__ import unicode_literals
 import youtube_dl
 
 ydl_opts = {}
@@ -680,6 +549,7 @@ Most likely, you'll want to use various options. For a list of what can be done,
 Here's a more complete example of a program that outputs only errors (and a short message after the download is finished), and downloads/converts the video to an mp3 file:
 
 ```python
+from __future__ import unicode_literals
 import youtube_dl
 
 
@@ -737,7 +607,9 @@ If your report is shorter than two lines, it is almost certainly missing some of
 
 For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the -v flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information.
 
-Site support requests **must contain an example URL**. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL.
+If your server has multiple IPs or you suspect censorship, adding --call-home may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/).
+
+**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL.
 
 ###  Are you using the latest version?
 

devscripts/check-porn.py

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

devscripts/generate_aes_testdata.py

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

docs/supportedsites.md

@@ -2,6 +2,8 @@
  - **1tv**: Первый канал
  - **1up.com**
  - **220.ro**
+ - **22tracks:genre**
+ - **22tracks:track**
  - **24video**
  - **3sat**
  - **4tube**
@@ -17,6 +19,7 @@
  - **AdultSwim**
  - **Aftenposten**
  - **Aftonbladet**
+ - **AirMozilla**
  - **AlJazeera**
  - **Allocine**
  - **AlphaPorno**
@@ -41,11 +44,13 @@
  - **audiomack**
  - **audiomack:album**
  - **Azubu**
+ - **BaiduVideo**
  - **bambuser**
  - **bambuser:channel**
  - **Bandcamp**
  - **Bandcamp:album**
  - **bbc.co.uk**: BBC iPlayer
+ - **BeatportPro**
  - **Beeg**
  - **BehindKink**
  - **Bet**
@@ -94,6 +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
@@ -107,15 +113,19 @@
  - **DctpTv**
  - **DeezerPlaylist**
  - **defense.gouv.fr**
+ - **DHM**: Filmarchiv - Deutsches Historisches Museum
  - **Discovery**
  - **divxstage**: DivxStage
  - **Dotsub**
+ - **DouyuTV**
  - **DRBonanza**
  - **Dropbox**
  - **DrTuber**
  - **DRTV**
  - **Dump**
+ - **Dumpert**
  - **dvtv**: http://video.aktualne.cz/
+ - **EaglePlatform**
  - **EbaumsWorld**
  - **EchoMsk**
  - **eHow**
@@ -143,8 +153,10 @@
  - **Firstpost**
  - **Flickr**
  - **Folketinget**: Folketinget (ft.dk; Danish parliament)
+ - **FootyRoom**
  - **Foxgay**
  - **FoxNews**
+ - **FoxSports**
  - **france2.fr:generation-quoi**
  - **FranceCulture**
  - **FranceInter**
@@ -157,11 +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)
@@ -169,9 +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**
@@ -209,6 +223,8 @@
  - **Jove**
  - **jpopsuki.tv**
  - **Jukebox**
+ - **Kaltura**
+ - **KanalPlay**: Kanal 5/9/11 Play
  - **Kankan**
  - **Karaoketv**
  - **keek**
@@ -220,6 +236,10 @@
  - **Ku6**
  - **la7.tv**
  - **Laola1Tv**
+ - **Letv**
+ - **LetvPlaylist**
+ - **LetvTv**
+ - **Libsyn**
  - **lifenews**: LIFE | NEWS
  - **LiveLeak**
  - **livestream**
@@ -234,11 +254,13 @@
  - **Malemotion**
  - **MDR**
  - **media.ccc.de**
+ - **MegaVideoz**
  - **metacafe**
  - **Metacritic**
  - **Mgoon**
  - **Minhateca**
  - **MinistryGrid**
+ - **miomio.tv**
  - **mitele.es**
  - **mixcloud**
  - **MLB**
@@ -272,6 +294,8 @@
  - **NBA**
  - **NBC**
  - **NBCNews**
+ - **NBCSports**
+ - **NBCSportsVPlayer**
  - **ndr**: NDR.de - Mediathek
  - **NDTV**
  - **NerdCubedFeed**
@@ -299,27 +323,33 @@
  - **npo.nl:radio**
  - **npo.nl:radio:fragment**
  - **NRK**
+ - **NRKPlaylist**
  - **NRKTV**
  - **ntv.ru**
  - **Nuvid**
  - **NYTimes**
  - **ocw.mit.edu**
+ - **Odnoklassniki**
  - **OktoberfestTV**
  - **on.aol.com**
  - **Ooyala**
  - **OpenFilm**
  - **orf:fm4**: radio FM4
+ - **orf:iptv**: iptv.ORF.at
  - **orf:oe1**: Radio Österreich 1
  - **orf:tvthek**: ORF TVthek
  - **parliamentlive.tv**: UK parliament videos
  - **Patreon**
  - **PBS**
+ - **PhilharmonieDeParis**: Philharmonie de Paris
  - **Phoenix**
  - **Photobucket**
+ - **Pladform**
  - **PlanetaPlay**
  - **play.fm**
  - **played.to**
  - **Playvid**
+ - **Playwire**
  - **plus.google**: Google Plus
  - **pluzz.francetv.fr**
  - **podomatic**
@@ -327,15 +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**
@@ -352,6 +389,7 @@
  - **RTP**
  - **RTS**: RTS.ch
  - **rtve.es:alacarta**: RTVE a la carta
+ - **rtve.es:infantil**: RTVE infantil
  - **rtve.es:live**: RTVE.es live streams
  - **RUHD**
  - **rutube**: Rutube videos
@@ -360,6 +398,8 @@
  - **rutube:movie**: Rutube movies
  - **rutube:person**: Rutube person videos
  - **RUTV**: RUTV.RU
+ - **safari**: safaribooksonline.com online video
+ - **safari:course**: safaribooksonline.com online courses
  - **Sandia**: Sandia National Laboratories
  - **Sapo**: SAPO Vídeos
  - **savefrom.net**
@@ -369,6 +409,7 @@
  - **Screencast**
  - **ScreencastOMatic**
  - **ScreenwaveMedia**
+ - **SenateISVP**
  - **ServingSys**
  - **Sexu**
  - **SexyKarma**: Sexy Karma and Watch Indian Porn
@@ -391,8 +432,10 @@
  - **soundgasm**
  - **soundgasm:profile**
  - **southpark.cc.com**
+ - **southpark.cc.com:español**
  - **southpark.de**
  - **Space**
+ - **SpankBang**
  - **Spankwire**
  - **Spiegel**
  - **Spiegel:Article**: Articles on spiegel.de
@@ -401,14 +444,16 @@
  - **Sport5**
  - **SportBox**
  - **SportDeutschland**
+ - **Srf**
  - **SRMediathek**: Saarländischer Rundfunk
+ - **SSA**
  - **stanfordoc**: Stanford Open ClassRoom
  - **Steam**
  - **streamcloud.eu**
  - **StreamCZ**
  - **StreetVoice**
  - **SunPorno**
- - **SVTPlay**
+ - **SVTPlay**: SVT Play and Öppet arkiv
  - **SWRMediathek**
  - **Syfy**
  - **SztvHu**
@@ -422,7 +467,7 @@
  - **TeamFour**
  - **TechTalks**
  - **techtv.mit.edu**
- - **TED**
+ - **ted**
  - **tegenlicht.vpro.nl**
  - **TeleBruxelles**
  - **telecinco.es**
@@ -471,13 +516,17 @@
  - **Ubu**
  - **udemy**
  - **udemy:course**
+ - **UDNEmbed**
+ - **Ultimedia**
  - **Unistra**
  - **Urort**: NRK P3 Urørt
  - **ustream**
  - **ustream:channel**
+ - **Varzesh3**
  - **Vbox7**
  - **VeeHD**
  - **Veoh**
+ - **Vessel**
  - **Vesti**: Вести.Ru
  - **Vevo**
  - **VGTV**
@@ -498,6 +547,7 @@
  - **Vidzi**
  - **vier**
  - **vier:videos**
+ - **Viewster**
  - **viki**
  - **vimeo**
  - **vimeo:album**
@@ -507,7 +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**
@@ -544,6 +594,9 @@
  - **XXXYMovies**
  - **Yahoo**: Yahoo screen and movies
  - **Yam**
+ - **yandexmusic:album**: Яндекс.Музыка - Альбом
+ - **yandexmusic:playlist**: Яндекс.Музыка - Плейлист
+ - **yandexmusic:track**: Яндекс.Музыка - Трек
  - **YesJapan**
  - **Ynet**
  - **YouJizz**
@@ -562,7 +615,7 @@
  - **youtube:show**: YouTube.com (multi-season) shows
  - **youtube:subscriptions**: YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)
  - **youtube:user**: YouTube.com user videos (URL or "ytuser" keyword)
- - **youtube:watch_later**: Youtube watch later list, ":ytwatchlater" for short (requires authentication)
+ - **youtube:watchlater**: Youtube watch later list, ":ytwatchlater" for short (requires authentication)
  - **Zapiks**
  - **ZDF**
  - **ZDFChannel**

test/helper.py

@@ -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

@@ -14,6 +14,9 @@ from test.helper import FakeYDL, assertRegexpMatches
 from youtube_dl import YoutubeDL
 from youtube_dl.extractor import YoutubeIE
 from youtube_dl.postprocessor.common import PostProcessor
+from youtube_dl.utils import match_filter_func
+
+TEST_URL = 'http://localhost/sample.mp4'
 
 
 class YDL(FakeYDL):
@@ -46,8 +49,8 @@ class TestFormatSelection(unittest.TestCase):
         ydl = YDL()
         ydl.params['prefer_free_formats'] = True
         formats = [
-            {'ext': 'webm', 'height': 460, 'url': 'x'},
-            {'ext': 'mp4', 'height': 460, 'url': 'y'},
+            {'ext': 'webm', 'height': 460, 'url': TEST_URL},
+            {'ext': 'mp4', 'height': 460, 'url': TEST_URL},
         ]
         info_dict = _make_result(formats)
         yie = YoutubeIE(ydl)
@@ -60,8 +63,8 @@ class TestFormatSelection(unittest.TestCase):
         ydl = YDL()
         ydl.params['prefer_free_formats'] = True
         formats = [
-            {'ext': 'webm', 'height': 720, 'url': 'a'},
-            {'ext': 'mp4', 'height': 1080, 'url': 'b'},
+            {'ext': 'webm', 'height': 720, 'url': TEST_URL},
+            {'ext': 'mp4', 'height': 1080, 'url': TEST_URL},
         ]
         info_dict['formats'] = formats
         yie = YoutubeIE(ydl)
@@ -74,9 +77,9 @@ class TestFormatSelection(unittest.TestCase):
         ydl = YDL()
         ydl.params['prefer_free_formats'] = False
         formats = [
-            {'ext': 'webm', 'height': 720, 'url': '_'},
-            {'ext': 'mp4', 'height': 720, 'url': '_'},
-            {'ext': 'flv', 'height': 720, 'url': '_'},
+            {'ext': 'webm', 'height': 720, 'url': TEST_URL},
+            {'ext': 'mp4', 'height': 720, 'url': TEST_URL},
+            {'ext': 'flv', 'height': 720, 'url': TEST_URL},
         ]
         info_dict['formats'] = formats
         yie = YoutubeIE(ydl)
@@ -88,8 +91,8 @@ class TestFormatSelection(unittest.TestCase):
         ydl = YDL()
         ydl.params['prefer_free_formats'] = False
         formats = [
-            {'ext': 'flv', 'height': 720, 'url': '_'},
-            {'ext': 'webm', 'height': 720, 'url': '_'},
+            {'ext': 'flv', 'height': 720, 'url': TEST_URL},
+            {'ext': 'webm', 'height': 720, 'url': TEST_URL},
         ]
         info_dict['formats'] = formats
         yie = YoutubeIE(ydl)
@@ -98,45 +101,12 @@ class TestFormatSelection(unittest.TestCase):
         downloaded = ydl.downloaded_info_dicts[0]
         self.assertEqual(downloaded['ext'], 'flv')
 
-    def test_format_limit(self):
-        formats = [
-            {'format_id': 'meh', 'url': 'http://example.com/meh', 'preference': 1},
-            {'format_id': 'good', 'url': 'http://example.com/good', 'preference': 2},
-            {'format_id': 'great', 'url': 'http://example.com/great', 'preference': 3},
-            {'format_id': 'excellent', 'url': 'http://example.com/exc', 'preference': 4},
-        ]
-        info_dict = _make_result(formats)
-
-        ydl = YDL()
-        ydl.process_ie_result(info_dict)
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], 'excellent')
-
-        ydl = YDL({'format_limit': 'good'})
-        assert ydl.params['format_limit'] == 'good'
-        ydl.process_ie_result(info_dict.copy())
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], 'good')
-
-        ydl = YDL({'format_limit': 'great', 'format': 'all'})
-        ydl.process_ie_result(info_dict.copy())
-        self.assertEqual(ydl.downloaded_info_dicts[0]['format_id'], 'meh')
-        self.assertEqual(ydl.downloaded_info_dicts[1]['format_id'], 'good')
-        self.assertEqual(ydl.downloaded_info_dicts[2]['format_id'], 'great')
-        self.assertTrue('3' in ydl.msgs[0])
-
-        ydl = YDL()
-        ydl.params['format_limit'] = 'excellent'
-        ydl.process_ie_result(info_dict.copy())
-        downloaded = ydl.downloaded_info_dicts[0]
-        self.assertEqual(downloaded['format_id'], 'excellent')
-
     def test_format_selection(self):
         formats = [
-            {'format_id': '35', 'ext': 'mp4', 'preference': 1, 'url': '_'},
-            {'format_id': '45', 'ext': 'webm', 'preference': 2, 'url': '_'},
-            {'format_id': '47', 'ext': 'webm', 'preference': 3, 'url': '_'},
-            {'format_id': '2', 'ext': 'flv', 'preference': 4, 'url': '_'},
+            {'format_id': '35', 'ext': 'mp4', 'preference': 1, 'url': TEST_URL},
+            {'format_id': '45', 'ext': 'webm', 'preference': 2, 'url': TEST_URL},
+            {'format_id': '47', 'ext': 'webm', 'preference': 3, 'url': TEST_URL},
+            {'format_id': '2', 'ext': 'flv', 'preference': 4, 'url': TEST_URL},
         ]
         info_dict = _make_result(formats)
 
@@ -167,10 +137,10 @@ class TestFormatSelection(unittest.TestCase):
 
     def test_format_selection_audio(self):
         formats = [
-            {'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none', 'url': '_'},
-            {'format_id': 'audio-mid', 'ext': 'webm', 'preference': 2, 'vcodec': 'none', 'url': '_'},
-            {'format_id': 'audio-high', 'ext': 'flv', 'preference': 3, 'vcodec': 'none', 'url': '_'},
-            {'format_id': 'vid', 'ext': 'mp4', 'preference': 4, 'url': '_'},
+            {'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none', 'url': TEST_URL},
+            {'format_id': 'audio-mid', 'ext': 'webm', 'preference': 2, 'vcodec': 'none', 'url': TEST_URL},
+            {'format_id': 'audio-high', 'ext': 'flv', 'preference': 3, 'vcodec': 'none', 'url': TEST_URL},
+            {'format_id': 'vid', 'ext': 'mp4', 'preference': 4, 'url': TEST_URL},
         ]
         info_dict = _make_result(formats)
 
@@ -185,8 +155,8 @@ class TestFormatSelection(unittest.TestCase):
         self.assertEqual(downloaded['format_id'], 'audio-low')
 
         formats = [
-            {'format_id': 'vid-low', 'ext': 'mp4', 'preference': 1, 'url': '_'},
-            {'format_id': 'vid-high', 'ext': 'mp4', 'preference': 2, 'url': '_'},
+            {'format_id': 'vid-low', 'ext': 'mp4', 'preference': 1, 'url': TEST_URL},
+            {'format_id': 'vid-high', 'ext': 'mp4', 'preference': 2, 'url': TEST_URL},
         ]
         info_dict = _make_result(formats)
 
@@ -228,9 +198,9 @@ class TestFormatSelection(unittest.TestCase):
 
     def test_format_selection_video(self):
         formats = [
-            {'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': '_'},
-            {'format_id': 'dash-video-high', 'ext': 'mp4', 'preference': 2, 'acodec': 'none', 'url': '_'},
-            {'format_id': 'vid', 'ext': 'mp4', 'preference': 3, 'url': '_'},
+            {'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': TEST_URL},
+            {'format_id': 'dash-video-high', 'ext': 'mp4', 'preference': 2, 'acodec': 'none', 'url': TEST_URL},
+            {'format_id': 'vid', 'ext': 'mp4', 'preference': 3, 'url': TEST_URL},
         ]
         info_dict = _make_result(formats)
 
@@ -267,7 +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)
@@ -275,7 +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)
@@ -337,6 +307,8 @@ class TestFormatSelection(unittest.TestCase):
         downloaded = ydl.downloaded_info_dicts[0]
         self.assertEqual(downloaded['format_id'], 'G')
 
+
+class TestYoutubeDL(unittest.TestCase):
     def test_subtitles(self):
         def s_formats(lang, autocaption=False):
             return [{
@@ -438,27 +410,103 @@ class TestFormatSelection(unittest.TestCase):
             def run(self, info):
                 with open(audiofile, 'wt') as f:
                     f.write('EXAMPLE')
-                info['filepath']
-                return False, info
+                return [info['filepath']], info
 
-        def run_pp(params):
+        def run_pp(params, PP):
             with open(filename, 'wt') as f:
                 f.write('EXAMPLE')
             ydl = YoutubeDL(params)
-            ydl.add_post_processor(SimplePP())
+            ydl.add_post_processor(PP())
             ydl.post_process(filename, {'filepath': filename})
 
-        run_pp({'keepvideo': True})
+        run_pp({'keepvideo': True}, SimplePP)
         self.assertTrue(os.path.exists(filename), '%s doesn\'t exist' % filename)
         self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
         os.unlink(filename)
         os.unlink(audiofile)
 
-        run_pp({'keepvideo': False})
+        run_pp({'keepvideo': False}, SimplePP)
         self.assertFalse(os.path.exists(filename), '%s exists' % filename)
         self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
         os.unlink(audiofile)
 
+        class ModifierPP(PostProcessor):
+            def run(self, info):
+                with open(info['filepath'], 'wt') as f:
+                    f.write('MODIFIED')
+                return [], info
+
+        run_pp({'keepvideo': False}, ModifierPP)
+        self.assertTrue(os.path.exists(filename), '%s doesn\'t exist' % filename)
+        os.unlink(filename)
+
+    def test_match_filter(self):
+        class FilterYDL(YDL):
+            def __init__(self, *args, **kwargs):
+                super(FilterYDL, self).__init__(*args, **kwargs)
+                self.params['simulate'] = True
+
+            def process_info(self, info_dict):
+                super(YDL, self).process_info(info_dict)
+
+            def _match_entry(self, info_dict, incomplete):
+                res = super(FilterYDL, self)._match_entry(info_dict, incomplete)
+                if res is None:
+                    self.downloaded_info_dicts.append(info_dict)
+                return res
+
+        first = {
+            'id': '1',
+            'url': TEST_URL,
+            'title': 'one',
+            'extractor': 'TEST',
+            'duration': 30,
+            'filesize': 10 * 1024,
+        }
+        second = {
+            'id': '2',
+            'url': TEST_URL,
+            'title': 'two',
+            'extractor': 'TEST',
+            'duration': 10,
+            'description': 'foo',
+            'filesize': 5 * 1024,
+        }
+        videos = [first, second]
+
+        def get_videos(filter_=None):
+            ydl = FilterYDL({'match_filter': filter_})
+            for v in videos:
+                ydl.process_ie_result(v, download=True)
+            return [v['id'] for v in ydl.downloaded_info_dicts]
+
+        res = get_videos()
+        self.assertEqual(res, ['1', '2'])
+
+        def f(v):
+            if v['id'] == '1':
+                return None
+            else:
+                return 'Video id is not 1'
+        res = get_videos(f)
+        self.assertEqual(res, ['1'])
+
+        f = match_filter_func('duration < 30')
+        res = get_videos(f)
+        self.assertEqual(res, ['2'])
+
+        f = match_filter_func('description = foo')
+        res = get_videos(f)
+        self.assertEqual(res, ['2'])
+
+        f = match_filter_func('description =? foo')
+        res = get_videos(f)
+        self.assertEqual(res, ['1', '2'])
+
+        f = match_filter_func('filesize > 5KiB')
+        res = get_videos(f)
+        self.assertEqual(res, ['1'])
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_aes.py

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

test/test_all_urls.py

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

test/test_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

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

test/test_http.py

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

test/test_netrc.py

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

test/test_postprocessors.py

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

test/test_subtitles.py

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

test/test_unicode_literals.py

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

test/test_utils.py

@@ -24,6 +24,7 @@ from youtube_dl.utils import (
     encodeFilename,
     escape_rfc3986,
     escape_url,
+    ExtractorError,
     find_xpath_attr,
     fix_xml_ampersands,
     InAdvancePagedList,
@@ -38,6 +39,10 @@ from youtube_dl.utils import (
     parse_iso8601,
     read_batch_urls,
     sanitize_filename,
+    sanitize_path,
+    sanitize_url_path_consecutive_slashes,
+    prepend_extension,
+    replace_extension,
     shell_quote,
     smuggle_url,
     str_to_int,
@@ -52,8 +57,11 @@ from youtube_dl.utils import (
     urlencode_postdata,
     version_tuple,
     xpath_with_ns,
+    xpath_text,
     render_table,
     match_str,
+    parse_dfxp_time_expr,
+    dfxp2srt,
 )
 
 
@@ -86,6 +94,11 @@ class TestUtil(unittest.TestCase):
             sanitize_filename('New World record at 0:12:34'),
             'New World record at 0_12_34')
 
+        self.assertEqual(sanitize_filename('--gasdgf'), '_-gasdgf')
+        self.assertEqual(sanitize_filename('--gasdgf', is_id=True), '--gasdgf')
+        self.assertEqual(sanitize_filename('.gasdgf'), 'gasdgf')
+        self.assertEqual(sanitize_filename('.gasdgf', is_id=True), '.gasdgf')
+
         forbidden = '"\0\\/'
         for fc in forbidden:
             for fbc in forbidden:
@@ -126,6 +139,78 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
         self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
 
+    def test_sanitize_path(self):
+        if sys.platform != 'win32':
+            return
+
+        self.assertEqual(sanitize_path('abc'), 'abc')
+        self.assertEqual(sanitize_path('abc/def'), 'abc\\def')
+        self.assertEqual(sanitize_path('abc\\def'), 'abc\\def')
+        self.assertEqual(sanitize_path('abc|def'), 'abc#def')
+        self.assertEqual(sanitize_path('<>:"|?*'), '#######')
+        self.assertEqual(sanitize_path('C:/abc/def'), 'C:\\abc\\def')
+        self.assertEqual(sanitize_path('C?:/abc/def'), 'C##\\abc\\def')
+
+        self.assertEqual(sanitize_path('\\\\?\\UNC\\ComputerName\\abc'), '\\\\?\\UNC\\ComputerName\\abc')
+        self.assertEqual(sanitize_path('\\\\?\\UNC/ComputerName/abc'), '\\\\?\\UNC\\ComputerName\\abc')
+
+        self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
+        self.assertEqual(sanitize_path('\\\\?\\C:/abc'), '\\\\?\\C:\\abc')
+        self.assertEqual(sanitize_path('\\\\?\\C:\\ab?c\\de:f'), '\\\\?\\C:\\ab#c\\de#f')
+        self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
+
+        self.assertEqual(
+            sanitize_path('youtube/%(uploader)s/%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s'),
+            'youtube\\%(uploader)s\\%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s')
+
+        self.assertEqual(
+            sanitize_path('youtube/TheWreckingYard ./00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part'),
+            'youtube\\TheWreckingYard #\\00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part')
+        self.assertEqual(sanitize_path('abc/def...'), 'abc\\def..#')
+        self.assertEqual(sanitize_path('abc.../def'), 'abc..#\\def')
+        self.assertEqual(sanitize_path('abc.../def...'), 'abc..#\\def..#')
+
+        self.assertEqual(sanitize_path('../abc'), '..\\abc')
+        self.assertEqual(sanitize_path('../../abc'), '..\\..\\abc')
+        self.assertEqual(sanitize_path('./abc'), 'abc')
+        self.assertEqual(sanitize_path('./../abc'), '..\\abc')
+
+    def test_sanitize_url_path_consecutive_slashes(self):
+        self.assertEqual(
+            sanitize_url_path_consecutive_slashes('http://hostname/foo//bar/filename.html'),
+            'http://hostname/foo/bar/filename.html')
+        self.assertEqual(
+            sanitize_url_path_consecutive_slashes('http://hostname//foo/bar/filename.html'),
+            'http://hostname/foo/bar/filename.html')
+        self.assertEqual(
+            sanitize_url_path_consecutive_slashes('http://hostname//'),
+            'http://hostname/')
+        self.assertEqual(
+            sanitize_url_path_consecutive_slashes('http://hostname/foo/bar/filename.html'),
+            'http://hostname/foo/bar/filename.html')
+        self.assertEqual(
+            sanitize_url_path_consecutive_slashes('http://hostname/'),
+            'http://hostname/')
+        self.assertEqual(
+            sanitize_url_path_consecutive_slashes('http://hostname/abc//'),
+            'http://hostname/abc/')
+
+    def test_prepend_extension(self):
+        self.assertEqual(prepend_extension('abc.ext', 'temp'), 'abc.temp.ext')
+        self.assertEqual(prepend_extension('abc.ext', 'temp', 'ext'), 'abc.temp.ext')
+        self.assertEqual(prepend_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
+        self.assertEqual(prepend_extension('abc', 'temp'), 'abc.temp')
+        self.assertEqual(prepend_extension('.abc', 'temp'), '.abc.temp')
+        self.assertEqual(prepend_extension('.abc.ext', 'temp'), '.abc.temp.ext')
+
+    def test_replace_extension(self):
+        self.assertEqual(replace_extension('abc.ext', 'temp'), 'abc.temp')
+        self.assertEqual(replace_extension('abc.ext', 'temp', 'ext'), 'abc.temp')
+        self.assertEqual(replace_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
+        self.assertEqual(replace_extension('abc', 'temp'), 'abc.temp')
+        self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
+        self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
+
     def test_ordered_set(self):
         self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
         self.assertEqual(orderedSet([]), [])
@@ -135,6 +220,8 @@ class TestUtil(unittest.TestCase):
 
     def test_unescape_html(self):
         self.assertEqual(unescapeHTML('%20;'), '%20;')
+        self.assertEqual(unescapeHTML('&#x2F;'), '/')
+        self.assertEqual(unescapeHTML('&#47;'), '/')
         self.assertEqual(
             unescapeHTML('&eacute;'), 'é')
 
@@ -160,6 +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>
@@ -187,6 +275,17 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(find('media:song/media:author').text, 'The Author')
         self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
 
+    def test_xpath_text(self):
+        testxml = '''<root>
+            <div>
+                <p>Foo</p>
+            </div>
+        </root>'''
+        doc = xml.etree.ElementTree.fromstring(testxml)
+        self.assertEqual(xpath_text(doc, 'div/p'), 'Foo')
+        self.assertTrue(xpath_text(doc, 'div/bar') is None)
+        self.assertRaises(ExtractorError, xpath_text, doc, 'div/bar', fatal=True)
+
     def test_smuggle_url(self):
         data = {"ö": "ö", "abc": [3]}
         url = 'https://foo.bar/baz?x=y#a'
@@ -244,6 +343,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(parse_duration('2.5 hours'), 9000)
         self.assertEqual(parse_duration('02:03:04'), 7384)
         self.assertEqual(parse_duration('01:02:03:04'), 93784)
+        self.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
 
     def test_fix_xml_ampersands(self):
         self.assertEqual(
@@ -391,6 +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"')
@@ -495,6 +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()

tox.ini

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

youtube_dl/YoutubeDL.py

@@ -4,8 +4,10 @@
 from __future__ import absolute_import, unicode_literals
 
 import collections
+import contextlib
 import datetime
 import errno
+import fileinput
 import io
 import itertools
 import json
@@ -28,6 +30,7 @@ from .compat import (
     compat_basestring,
     compat_cookiejar,
     compat_expanduser,
+    compat_get_terminal_size,
     compat_http_client,
     compat_kwargs,
     compat_str,
@@ -46,21 +49,21 @@ from .utils import (
     ExtractorError,
     format_bytes,
     formatSeconds,
-    get_term_width,
     locked_file,
     make_HTTPS_handler,
     MaxDownloadsReached,
     PagedList,
     parse_filesize,
+    PerRequestProxyHandler,
     PostProcessingError,
     platform_name,
     preferredencoding,
     render_table,
     SameFileError,
     sanitize_filename,
+    sanitize_path,
     std_headers,
     subtitles_filename,
-    takewhile_inclusive,
     UnavailableVideoError,
     url_basename,
     version_tuple,
@@ -68,6 +71,7 @@ from .utils import (
     write_string,
     YoutubeDLHandler,
     prepend_extension,
+    replace_extension,
     args_to_str,
     age_restricted,
 )
@@ -131,7 +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.
@@ -181,6 +184,8 @@ class YoutubeDL(object):
     prefer_insecure:   Use HTTP instead of HTTPS to retrieve information.
                        At the moment, this is only supported by YouTube.
     proxy:             URL of the proxy server to use
+    cn_verification_proxy:  URL of the proxy to use for IP address verification
+                       on Chinese sites. (Experimental)
     socket_timeout:    Time to wait for unresponsive hosts, in seconds
     bidi_workaround:   Work around buggy terminals without bidirectional text
                        support, using fridibi
@@ -247,10 +252,10 @@ class YoutubeDL(object):
     hls_prefer_native: Use the native HLS downloader instead of ffmpeg/avconv.
 
     The following parameters are not used by YoutubeDL itself, they are used by
-    the FileDownloader:
+    the downloader (see youtube_dl/downloader/common.py):
     nopart, updatetime, buffersize, ratelimit, min_filesize, max_filesize, test,
     noresizebuffer, retries, continuedl, noprogress, consoletitle,
-    xattr_set_filesize.
+    xattr_set_filesize, external_downloader_args.
 
     The following options are used by the post processors:
     prefer_ffmpeg:     If True, use ffmpeg instead of avconv if both are available,
@@ -284,7 +289,7 @@ class YoutubeDL(object):
             try:
                 import pty
                 master, slave = pty.openpty()
-                width = get_term_width()
+                width = compat_get_terminal_size().columns
                 if width is None:
                     width_args = []
                 else:
@@ -317,8 +322,10 @@ class YoutubeDL(object):
                 'Set the LC_ALL environment variable to fix this.')
             self.params['restrictfilenames'] = True
 
-        if '%(stitle)s' in self.params.get('outtmpl', ''):
-            self.report_warning('%(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.')
+        if isinstance(params.get('outtmpl'), bytes):
+            self.report_warning(
+                'Parameter outtmpl is bytes, but should be a unicode string. '
+                'Put  from __future__ import unicode_literals  at the top of your code file or consider switching to Python 3.x.')
 
         self._setup_opener()
 
@@ -557,7 +564,7 @@ class YoutubeDL(object):
                                  if v is not None)
             template_dict = collections.defaultdict(lambda: 'NA', template_dict)
 
-            outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
+            outtmpl = sanitize_path(self.params.get('outtmpl', DEFAULT_OUTTMPL))
             tmpl = compat_expanduser(outtmpl)
             filename = tmpl % template_dict
             # Temporary fix for #4787
@@ -624,7 +631,7 @@ class YoutubeDL(object):
         Returns a list with a dictionary for each video we find.
         If 'download', also downloads the videos.
         extra_info is a dict containing the extra values to add to each result
-         '''
+        '''
 
         if ie_key:
             ies = [self.get_info_extractor(ie_key)]
@@ -908,10 +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
@@ -1055,12 +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:
@@ -1078,10 +1085,13 @@ 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 = []
-        # The -1 is for supporting YoutubeIE
-        if req_format in ('-1', 'all'):
+        if req_format == 'all':
             formats_to_download = formats
         else:
             for rfstr in req_format.split(','):
@@ -1208,9 +1218,6 @@ class YoutubeDL(object):
         if len(info_dict['title']) > 200:
             info_dict['title'] = info_dict['title'][:197] + '...'
 
-        # Keep for backwards compatibility
-        info_dict['stitle'] = info_dict['title']
-
         if 'format' not in info_dict:
             info_dict['format'] = info_dict['ext']
 
@@ -1256,7 +1263,7 @@ class YoutubeDL(object):
             return
 
         try:
-            dn = os.path.dirname(encodeFilename(filename))
+            dn = os.path.dirname(sanitize_path(encodeFilename(filename)))
             if dn and not os.path.exists(dn):
                 os.makedirs(dn)
         except (OSError, IOError) as err:
@@ -1264,7 +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:
@@ -1279,7 +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:
@@ -1300,17 +1307,18 @@ class YoutubeDL(object):
             # subtitles download errors are already managed as troubles in relevant IE
             # that way it will silently go on when used with unsupporting IE
             subtitles = info_dict['requested_subtitles']
+            ie = self.get_info_extractor(info_dict['extractor_key'])
             for sub_lang, sub_info in subtitles.items():
                 sub_format = sub_info['ext']
                 if sub_info.get('data') is not None:
                     sub_data = sub_info['data']
                 else:
                     try:
-                        uf = self.urlopen(sub_info['url'])
-                        sub_data = uf.read().decode('utf-8')
-                    except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+                        sub_data = ie._download_webpage(
+                            sub_info['url'], info_dict['id'], note=False)
+                    except ExtractorError as err:
                         self.report_warning('Unable to download subtitle for "%s": %s' %
-                                            (sub_lang, compat_str(err)))
+                                            (sub_lang, compat_str(err.cause)))
                         continue
                 try:
                     sub_filename = subtitles_filename(filename, sub_lang, sub_format)
@@ -1325,13 +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
@@ -1351,7 +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 '
@@ -1359,16 +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)
@@ -1451,8 +1492,11 @@ class YoutubeDL(object):
         return self._download_retcode
 
     def download_with_info_file(self, info_filename):
-        with io.open(info_filename, 'r', encoding='utf-8') as f:
-            info = json.load(f)
+        with contextlib.closing(fileinput.FileInput(
+                [info_filename], mode='r',
+                openhook=fileinput.hook_encoded('utf-8'))) as f:
+            # FileInput doesn't have a read method, we can't call json.load
+            info = self.filter_requested_info(json.loads('\n'.join(f)))
         try:
             self.process_ie_result(info, download=True)
         except DownloadError:
@@ -1464,6 +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)
@@ -1473,24 +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
@@ -1693,10 +1736,10 @@ class YoutubeDL(object):
             out = out.decode().strip()
             if re.match('[0-9a-f]+', out):
                 self._write_string('[debug] Git HEAD: ' + out + '\n')
-        except:
+        except Exception:
             try:
                 sys.exc_clear()
-            except:
+            except Exception:
                 pass
         self._write_string('[debug] Python version %s - %s\n' % (
             platform.python_version(), platform_name()))
@@ -1756,13 +1799,14 @@ class YoutubeDL(object):
             # Set HTTPS proxy to HTTP one if given (https://github.com/rg3/youtube-dl/issues/805)
             if 'http' in proxies and 'https' not in proxies:
                 proxies['https'] = proxies['http']
-        proxy_handler = compat_urllib_request.ProxyHandler(proxies)
+        proxy_handler = PerRequestProxyHandler(proxies)
 
         debuglevel = 1 if self.params.get('debug_printtraffic') else 0
         https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel)
         ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel)
         opener = compat_urllib_request.build_opener(
-            https_handler, proxy_handler, cookie_processor, ydlh)
+            proxy_handler, https_handler, cookie_processor, ydlh)
+
         # Delete the default user-agent header, which would otherwise apply in
         # cases where our custom HTTP handler doesn't come into play
         # (See https://github.com/rg3/youtube-dl/issues/1309 for details)

youtube_dl/__init__.py

@@ -9,6 +9,7 @@ import codecs
 import io
 import os
 import random
+import shlex
 import sys
 
 
@@ -170,6 +171,9 @@ def _real_main(argv=None):
     if opts.recodevideo is not None:
         if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']:
             parser.error('invalid video recode format specified')
+    if opts.convertsubtitles is not None:
+        if opts.convertsubtitles not in ['srt', 'vtt', 'ass']:
+            parser.error('invalid subtitle format specified')
 
     if opts.date is not None:
         date = DateRange.day(opts.date)
@@ -185,10 +189,6 @@ def _real_main(argv=None):
     if opts.allsubtitles and not opts.writeautomaticsub:
         opts.writesubtitles = True
 
-    if sys.version_info < (3,):
-        # In Python 2, sys.argv is a bytestring (also note http://bugs.python.org/issue2128 for Windows systems)
-        if opts.outtmpl is not None:
-            opts.outtmpl = opts.outtmpl.decode(preferredencoding())
     outtmpl = ((opts.outtmpl is not None and opts.outtmpl) or
                (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s') or
                (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s') or
@@ -209,6 +209,11 @@ def _real_main(argv=None):
     # PostProcessors
     postprocessors = []
     # Add the metadata pp first, the other pps will copy it
+    if opts.metafromtitle:
+        postprocessors.append({
+            'key': 'MetadataFromTitle',
+            'titleformat': opts.metafromtitle
+        })
     if opts.addmetadata:
         postprocessors.append({'key': 'FFmpegMetadata'})
     if opts.extractaudio:
@@ -223,6 +228,11 @@ def _real_main(argv=None):
             'key': 'FFmpegVideoConvertor',
             'preferedformat': opts.recodevideo,
         })
+    if opts.convertsubtitles:
+        postprocessors.append({
+            'key': 'FFmpegSubtitlesConvertor',
+            'format': opts.convertsubtitles,
+        })
     if opts.embedsubtitles:
         postprocessors.append({
             'key': 'FFmpegEmbedSubtitle',
@@ -230,9 +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:
@@ -247,6 +255,9 @@ def _real_main(argv=None):
             xattr  # Confuse flake8
         except ImportError:
             parser.error('setting filesize xattr requested but python-xattr is not available')
+    external_downloader_args = None
+    if opts.external_downloader_args:
+        external_downloader_args = shlex.split(opts.external_downloader_args)
     match_filter = (
         None if opts.match_filter is None
         else match_filter_func(opts.match_filter))
@@ -272,7 +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,
@@ -351,6 +361,8 @@ def _real_main(argv=None):
         'no_color': opts.no_color,
         'ffmpeg_location': opts.ffmpeg_location,
         'hls_prefer_native': opts.hls_prefer_native,
+        'external_downloader_args': external_downloader_args,
+        'cn_verification_proxy': opts.cn_verification_proxy,
     }
 
     with YoutubeDL(ydl_opts) as ydl:

youtube_dl/compat.py

@@ -1,9 +1,11 @@
 from __future__ import unicode_literals
 
+import collections
 import getpass
 import optparse
 import os
 import re
+import shutil
 import socket
 import subprocess
 import sys
@@ -44,11 +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
@@ -364,6 +361,33 @@ def workaround_optparse_bug9161():
             return real_add_option(self, *bargs, **bkwargs)
         optparse.OptionGroup.add_option = _compat_add_option
 
+if hasattr(shutil, 'get_terminal_size'):  # Python >= 3.3
+    compat_get_terminal_size = shutil.get_terminal_size
+else:
+    _terminal_size = collections.namedtuple('terminal_size', ['columns', 'lines'])
+
+    def compat_get_terminal_size():
+        columns = compat_getenv('COLUMNS', None)
+        if columns:
+            columns = int(columns)
+        else:
+            columns = None
+        lines = compat_getenv('LINES', None)
+        if lines:
+            lines = int(lines)
+        else:
+            lines = None
+
+        try:
+            sp = subprocess.Popen(
+                ['stty', 'size'],
+                stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+            out, err = sp.communicate()
+            lines, columns = map(int, out.split())
+        except Exception:
+            pass
+        return _terminal_size(columns, lines)
+
 
 __all__ = [
     'compat_HTTPError',
@@ -371,10 +395,10 @@ __all__ = [
     'compat_chr',
     'compat_cookiejar',
     'compat_expanduser',
+    'compat_get_terminal_size',
     '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,
 )
@@ -42,6 +43,8 @@ class FileDownloader(object):
     max_filesize:       Skip files larger than this size
     xattr_set_filesize: Set ytdl.filesize user xattribute with expected size.
                         (experimenatal)
+    external_downloader_args:  A list of additional command-line arguments for the
+                        external downloader.
 
     Subclasses of this one must re-define the real_download method.
     """
@@ -202,7 +205,7 @@ class FileDownloader(object):
             return
         try:
             os.utime(filename, (time.time(), filetime))
-        except:
+        except Exception:
             pass
         return filetime
 
@@ -316,7 +319,7 @@ class FileDownloader(object):
         )
 
         continuedl_and_exists = (
-            self.params.get('continuedl', False) and
+            self.params.get('continuedl', True) and
             os.path.isfile(encodeFilename(filename)) and
             not self.params.get('nopart', False)
         )
@@ -351,19 +354,15 @@ class FileDownloader(object):
         # this interface
         self._progress_hooks.append(ph)
 
-    def _debug_cmd(self, args, subprocess_encoding, exe=None):
+    def _debug_cmd(self, args, exe=None):
         if not self.params.get('verbose', False):
             return
 
-        if exe is None:
-            exe = os.path.basename(args[0])
+        str_args = [decodeArgument(a) for a in args]
+
+        if exe is None:
+            exe = os.path.basename(str_args[0])
 
-        if subprocess_encoding:
-            str_args = [
-                a.decode(subprocess_encoding) if isinstance(a, bytes) else a
-                for a in args]
-        else:
-            str_args = args
         try:
             import pipes
             shell_quote = lambda args: ' '.join(map(pipes.quote, str_args))

youtube_dl/downloader/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,
 )
 
 
@@ -51,19 +51,18 @@ class ExternalFD(FileDownloader):
             return []
         return [command_option, source_address]
 
+    def _configuration_args(self, default=[]):
+        ex_args = self.params.get('external_downloader_args')
+        if ex_args is None:
+            return default
+        assert isinstance(ex_args, list)
+        return ex_args
+
     def _call_downloader(self, tmpfilename, info_dict):
         """ Either overwrite this or implement _make_cmd """
-        cmd = self._make_cmd(tmpfilename, info_dict)
+        cmd = [encodeArgument(a) for a in self._make_cmd(tmpfilename, info_dict)]
 
-        if sys.platform == 'win32' and sys.version_info < (3, 0):
-            # Windows subprocess module does not actually support Unicode
-            # on Python 2.x
-            # See http://stackoverflow.com/a/9951851/35070
-            subprocess_encoding = sys.getfilesystemencoding()
-            cmd = [a.encode(subprocess_encoding, 'ignore') for a in cmd]
-        else:
-            subprocess_encoding = None
-        self._debug_cmd(cmd, subprocess_encoding)
+        self._debug_cmd(cmd)
 
         p = subprocess.Popen(
             cmd, stderr=subprocess.PIPE)
@@ -79,6 +78,7 @@ class CurlFD(ExternalFD):
         for key, val in info_dict['http_headers'].items():
             cmd += ['--header', '%s: %s' % (key, val)]
         cmd += self._source_address('--interface')
+        cmd += self._configuration_args()
         cmd += ['--', info_dict['url']]
         return cmd
 
@@ -89,15 +89,16 @@ class WgetFD(ExternalFD):
         for key, val in info_dict['http_headers'].items():
             cmd += ['--header', '%s: %s' % (key, val)]
         cmd += self._source_address('--bind-address')
+        cmd += self._configuration_args()
         cmd += ['--', info_dict['url']]
         return cmd
 
 
 class Aria2cFD(ExternalFD):
     def _make_cmd(self, tmpfilename, info_dict):
-        cmd = [
-            self.exe, '-c',
-            '--min-split-size', '1M', '--max-connection-per-server', '4']
+        cmd = [self.exe, '-c']
+        cmd += self._configuration_args([
+            '--min-split-size', '1M', '--max-connection-per-server', '4'])
         dn = os.path.dirname(tmpfilename)
         if dn:
             cmd += ['--dir', dn]

youtube_dl/downloader/f4m.py

@@ -11,6 +11,7 @@ from .common import FileDownloader
 from .http import HttpFD
 from ..compat import (
     compat_urlparse,
+    compat_urllib_error,
 )
 from ..utils import (
     struct_pack,
@@ -121,7 +122,8 @@ class FlvReader(io.BytesIO):
 
         self.read_unsigned_int()  # BootstrapinfoVersion
         # Profile,Live,Update,Reserved
-        self.read(1)
+        flags = self.read_unsigned_char()
+        live = flags & 0x20 != 0
         # time scale
         self.read_unsigned_int()
         # CurrentMediaTime
@@ -160,6 +162,7 @@ class FlvReader(io.BytesIO):
         return {
             'segments': segments,
             'fragments': fragments,
+            'live': live,
         }
 
     def read_bootstrap_info(self):
@@ -182,6 +185,10 @@ def build_fragments_list(boot_info):
     for segment, fragments_count in segment_run_table['segment_run']:
         for _ in range(fragments_count):
             res.append((segment, next(fragments_counter)))
+
+    if boot_info['live']:
+        res = res[-2:]
+
     return res
 
 
@@ -246,6 +253,38 @@ class F4mFD(FileDownloader):
             self.report_error('Unsupported DRM')
         return media
 
+    def _get_bootstrap_from_url(self, bootstrap_url):
+        bootstrap = self.ydl.urlopen(bootstrap_url).read()
+        return read_bootstrap_info(bootstrap)
+
+    def _update_live_fragments(self, bootstrap_url, latest_fragment):
+        fragments_list = []
+        retries = 30
+        while (not fragments_list) and (retries > 0):
+            boot_info = self._get_bootstrap_from_url(bootstrap_url)
+            fragments_list = build_fragments_list(boot_info)
+            fragments_list = [f for f in fragments_list if f[1] > latest_fragment]
+            if not fragments_list:
+                # Retry after a while
+                time.sleep(5.0)
+                retries -= 1
+
+        if not fragments_list:
+            self.report_error('Failed to update fragments')
+
+        return fragments_list
+
+    def _parse_bootstrap_node(self, node, base_url):
+        if node.text is None:
+            bootstrap_url = compat_urlparse.urljoin(
+                base_url, node.attrib['url'])
+            boot_info = self._get_bootstrap_from_url(bootstrap_url)
+        else:
+            bootstrap_url = None
+            bootstrap = base64.b64decode(node.text.encode('ascii'))
+            boot_info = read_bootstrap_info(bootstrap)
+        return (boot_info, bootstrap_url)
+
     def real_download(self, filename, info_dict):
         man_url = info_dict['url']
         requested_bitrate = info_dict.get('tbr')
@@ -265,18 +304,13 @@ class F4mFD(FileDownloader):
 
         base_url = compat_urlparse.urljoin(man_url, media.attrib['url'])
         bootstrap_node = doc.find(_add_ns('bootstrapInfo'))
-        if bootstrap_node.text is None:
-            bootstrap_url = compat_urlparse.urljoin(
-                base_url, bootstrap_node.attrib['url'])
-            bootstrap = self.ydl.urlopen(bootstrap_url).read()
-        else:
-            bootstrap = base64.b64decode(bootstrap_node.text)
+        boot_info, bootstrap_url = self._parse_bootstrap_node(bootstrap_node, base_url)
+        live = boot_info['live']
         metadata_node = media.find(_add_ns('metadata'))
         if metadata_node is not None:
-            metadata = base64.b64decode(metadata_node.text)
+            metadata = base64.b64decode(metadata_node.text.encode('ascii'))
         else:
             metadata = None
-        boot_info = read_bootstrap_info(bootstrap)
 
         fragments_list = build_fragments_list(boot_info)
         if self.params.get('test', False):
@@ -301,7 +335,8 @@ class F4mFD(FileDownloader):
         (dest_stream, tmpfilename) = sanitize_open(tmpfilename, 'wb')
 
         write_flv_header(dest_stream)
-        write_metadata_tag(dest_stream, metadata)
+        if not live:
+            write_metadata_tag(dest_stream, metadata)
 
         # This dict stores the download progress, it's updated by the progress
         # hook
@@ -348,24 +383,47 @@ class F4mFD(FileDownloader):
         http_dl.add_progress_hook(frag_progress_hook)
 
         frags_filenames = []
-        for (seg_i, frag_i) in fragments_list:
+        while fragments_list:
+            seg_i, frag_i = fragments_list.pop(0)
             name = 'Seg%d-Frag%d' % (seg_i, frag_i)
             url = base_url + name
             if akamai_pv:
                 url += '?' + akamai_pv.strip(';')
+            if info_dict.get('extra_param_to_segment_url'):
+                url += info_dict.get('extra_param_to_segment_url')
             frag_filename = '%s-%s' % (tmpfilename, name)
-            success = http_dl.download(frag_filename, {'url': url})
-            if not success:
-                return False
-            with open(frag_filename, 'rb') as down:
-                down_data = down.read()
-                reader = FlvReader(down_data)
-                while True:
-                    _, box_type, box_data = reader.read_box_info()
-                    if box_type == b'mdat':
-                        dest_stream.write(box_data)
-                        break
-            frags_filenames.append(frag_filename)
+            try:
+                success = http_dl.download(frag_filename, {'url': url})
+                if not success:
+                    return False
+                with open(frag_filename, 'rb') as down:
+                    down_data = down.read()
+                    reader = FlvReader(down_data)
+                    while True:
+                        _, box_type, box_data = reader.read_box_info()
+                        if box_type == b'mdat':
+                            dest_stream.write(box_data)
+                            break
+                if live:
+                    os.remove(frag_filename)
+                else:
+                    frags_filenames.append(frag_filename)
+            except (compat_urllib_error.HTTPError, ) as err:
+                if live and (err.code == 404 or err.code == 410):
+                    # We didn't keep up with the live window. Continue
+                    # with the next available fragment.
+                    msg = 'Fragment %d unavailable' % frag_i
+                    self.report_warning(msg)
+                    fragments_list = []
+                else:
+                    raise
+
+            if not fragments_list and live and bootstrap_url:
+                fragments_list = self._update_live_fragments(bootstrap_url, frag_i)
+                total_frags += len(fragments_list)
+                if fragments_list and (fragments_list[0][1] > frag_i + 1):
+                    msg = 'Missed %d fragments' % (fragments_list[0][1] - (frag_i + 1))
+                    self.report_warning(msg)
 
         dest_stream.close()
 

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)
 
@@ -49,7 +44,7 @@ class HttpFD(FileDownloader):
 
         open_mode = 'wb'
         if resume_len != 0:
-            if self.params.get('continuedl', False):
+            if self.params.get('continuedl', True):
                 self.report_resuming_byte(resume_len)
                 request.add_header('Range', 'bytes=%d-' % resume_len)
                 open_mode = 'ab'
@@ -92,6 +87,8 @@ class HttpFD(FileDownloader):
                             self._hook_progress({
                                 'filename': filename,
                                 'status': 'finished',
+                                'downloaded_bytes': resume_len,
+                                'total_bytes': resume_len,
                             })
                             return True
                         else:
@@ -218,12 +215,6 @@ class HttpFD(FileDownloader):
         if tmpfilename != '-':
             stream.close()
 
-        self._hook_progress({
-            'downloaded_bytes': byte_counter,
-            'total_bytes': data_len,
-            'tmpfilename': tmpfilename,
-            'status': 'error',
-        })
         if data_len is not None and byte_counter != data_len:
             raise ContentTooShortError(byte_counter, int(data_len))
         self.try_rename(tmpfilename, filename)

youtube_dl/downloader/rtmp.py

@@ -3,7 +3,6 @@ from __future__ import unicode_literals
 import os
 import re
 import subprocess
-import sys
 import time
 
 from .common import FileDownloader
@@ -11,6 +10,7 @@ from ..compat import compat_str
 from ..utils import (
     check_executable,
     encodeFilename,
+    encodeArgument,
     get_exe_version,
 )
 
@@ -105,7 +105,7 @@ class RtmpFD(FileDownloader):
         protocol = info_dict.get('rtmp_protocol', None)
         real_time = info_dict.get('rtmp_real_time', False)
         no_resume = info_dict.get('no_resume', False)
-        continue_dl = info_dict.get('continuedl', False)
+        continue_dl = info_dict.get('continuedl', True)
 
         self.report_destination(filename)
         tmpfilename = self.temp_name(filename)
@@ -119,7 +119,9 @@ class RtmpFD(FileDownloader):
         # Download using rtmpdump. rtmpdump returns exit code 2 when
         # the connection was interrumpted and resuming appears to be
         # possible. This is part of rtmpdump's normal usage, AFAIK.
-        basic_args = ['rtmpdump', '--verbose', '-r', url, '-o', tmpfilename]
+        basic_args = [
+            'rtmpdump', '--verbose', '-r', url,
+            '-o', tmpfilename]
         if player_url is not None:
             basic_args += ['--swfVfy', player_url]
         if page_url is not None:
@@ -152,16 +154,9 @@ class RtmpFD(FileDownloader):
         if not live and continue_dl:
             args += ['--skip', '1']
 
-        if sys.platform == 'win32' and sys.version_info < (3, 0):
-            # Windows subprocess module does not actually support Unicode
-            # on Python 2.x
-            # See http://stackoverflow.com/a/9951851/35070
-            subprocess_encoding = sys.getfilesystemencoding()
-            args = [a.encode(subprocess_encoding, 'ignore') for a in args]
-        else:
-            subprocess_encoding = None
+        args = [encodeArgument(a) for a in args]
 
-        self._debug_cmd(args, subprocess_encoding, exe='rtmpdump')
+        self._debug_cmd(args, exe='rtmpdump')
 
         RD_SUCCESS = 0
         RD_FAILED = 1
@@ -178,7 +173,11 @@ class RtmpFD(FileDownloader):
             prevsize = os.path.getsize(encodeFilename(tmpfilename))
             self.to_screen('[rtmpdump] %s bytes' % prevsize)
             time.sleep(5.0)  # This seems to be needed
-            retval = run_rtmpdump(basic_args + ['-e'] + [[], ['-k', '1']][retval == RD_FAILED])
+            args = basic_args + ['--resume']
+            if retval == RD_FAILED:
+                args += ['--skip', '1']
+            args = [encodeArgument(a) for a in args]
+            retval = run_rtmpdump(args)
             cursize = os.path.getsize(encodeFilename(tmpfilename))
             if prevsize == cursize and retval == RD_FAILED:
                 break

youtube_dl/downloader/rtsp.py

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

youtube_dl/extractor/__init__.py

@@ -8,6 +8,7 @@ from .adobetv import AdobeTVIE
 from .adultswim import AdultSwimIE
 from .aftenposten import AftenpostenIE
 from .aftonbladet import AftonbladetIE
+from .airmozilla import AirMozillaIE
 from .aljazeera import AlJazeeraIE
 from .alphaporno import AlphaPornoIE
 from .anitube import AnitubeIE
@@ -31,11 +32,13 @@ from .atresplayer import AtresPlayerIE
 from .atttechchannel import ATTTechChannelIE
 from .audiomack import AudiomackIE, AudiomackAlbumIE
 from .azubu import AzubuIE
+from .baidu import BaiduVideoIE
 from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE
 from .bbccouk import BBCCoUkIE
 from .beeg import BeegIE
 from .behindkink import BehindKinkIE
+from .beatportpro import BeatportProIE
 from .bet import BetIE
 from .bild import BildIE
 from .bilibili import BiliBiliIE
@@ -68,6 +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
@@ -88,6 +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
@@ -104,17 +109,21 @@ from .dbtv import DBTVIE
 from .dctp import DctpTvIE
 from .deezer import DeezerPlaylistIE
 from .dfb import DFBIE
+from .dhm import DHMIE
 from .dotsub import DotsubIE
+from .douyutv import DouyuTVIE
 from .dreisat import DreiSatIE
 from .drbonanza import DRBonanzaIE
 from .drtuber import DrTuberIE
 from .drtv import DRTVIE
 from .dvtv import DVTVIE
 from .dump import DumpIE
+from .dumpert import DumpertIE
 from .defense import DefenseGouvFrIE
 from .discovery import DiscoveryIE
 from .divxstage import DivxStageIE
 from .dropbox import DropboxIE
+from .eagleplatform import EaglePlatformIE
 from .ebaumsworld import EbaumsWorldIE
 from .echomsk import EchoMskIE
 from .ehow import EHowIE
@@ -149,9 +158,11 @@ from .fktv import (
 )
 from .flickr import FlickrIE
 from .folketinget import FolketingetIE
+from .footyroom import FootyRoomIE
 from .fourtube import FourTubeIE
 from .foxgay import FoxgayIE
 from .foxnews import FoxNewsIE
+from .foxsports import FoxSportsIE
 from .franceculture import FranceCultureIE
 from .franceinter import FranceInterIE
 from .francetv import (
@@ -170,11 +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
@@ -186,7 +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
@@ -226,6 +239,8 @@ from .jeuxvideo import JeuxVideoIE
 from .jove import JoveIE
 from .jukebox import JukeboxIE
 from .jpopsukitv import JpopsukiIE
+from .kaltura import KalturaIE
+from .kanalplay import KanalPlayIE
 from .kankan import KankanIE
 from .karaoketv import KaraoketvIE
 from .keezmovies import KeezMoviesIE
@@ -237,6 +252,12 @@ from .krasview import KrasViewIE
 from .ku6 import Ku6IE
 from .la7 import LA7IE
 from .laola1tv import Laola1TvIE
+from .letv import (
+    LetvIE,
+    LetvTvIE,
+    LetvPlaylistIE
+)
+from .libsyn import LibsynIE
 from .lifenews import LifeNewsIE
 from .liveleak import LiveLeakIE
 from .livestream import (
@@ -255,11 +276,13 @@ from .macgamestore import MacGameStoreIE
 from .mailru import MailRuIE
 from .malemotion import MalemotionIE
 from .mdr import MDRIE
+from .megavideoz import MegaVideozIE
 from .metacafe import MetacafeIE
 from .metacritic import MetacriticIE
 from .mgoon import MgoonIE
 from .minhateca import MinhatecaIE
 from .ministrygrid import MinistryGridIE
+from .miomio import MioMioIE
 from .mit import TechTVMITIE, MITIE, OCWMITIE
 from .mitele import MiTeleIE
 from .mixcloud import MixcloudIE
@@ -295,6 +318,8 @@ from .nba import NBAIE
 from .nbc import (
     NBCIE,
     NBCNewsIE,
+    NBCSportsIE,
+    NBCSportsVPlayerIE,
 )
 from .ndr import NDRIE
 from .ndtv import NDTVIE
@@ -333,12 +358,14 @@ from .npo import (
 )
 from .nrk import (
     NRKIE,
+    NRKPlaylistIE,
     NRKTVIE,
 )
 from .ntvde import NTVDeIE
 from .ntvru import NTVRuIE
 from .nytimes import NYTimesIE
 from .nuvid import NuvidIE
+from .odnoklassniki import OdnoklassnikiIE
 from .oktoberfesttv import OktoberfestTVIE
 from .ooyala import OoyalaIE
 from .openfilm import OpenFilmIE
@@ -346,16 +373,20 @@ from .orf import (
     ORFTVthekIE,
     ORFOE1IE,
     ORFFM4IE,
+    ORFIPTVIE,
 )
 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
+from .pladform import PladformIE
 from .played import PlayedIE
 from .playfm import PlayFMIE
 from .playvid import PlayvidIE
+from .playwire import PlaywireIE
 from .podomatic import PodomaticIE
 from .pornhd import PornHdIE
 from .pornhub import (
@@ -363,13 +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
@@ -388,7 +428,7 @@ from .rtlnow import RTLnowIE
 from .rtl2 import RTL2IE
 from .rtp import RTPIE
 from .rts import RTSIE
-from .rtve import RTVEALaCartaIE, RTVELiveIE
+from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE
 from .ruhd import RUHDIE
 from .rutube import (
     RutubeIE,
@@ -399,13 +439,18 @@ from .rutube import (
 )
 from .rutv import RUTVIE
 from .sandia import SandiaIE
+from .safari import (
+    SafariIE,
+    SafariCourseIE,
+)
 from .sapo import SapoIE
 from .savefrom import SaveFromIE
 from .sbs import SBSIE
 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
@@ -435,9 +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
@@ -445,7 +492,9 @@ from .spike import SpikeIE
 from .sport5 import Sport5IE
 from .sportbox import SportBoxIE
 from .sportdeutschland import SportDeutschlandIE
+from .srf import SrfIE
 from .srmediathek import SRMediathekIE
+from .ssa import SSAIE
 from .stanfordoc import StanfordOpenClassroomIE
 from .steam import SteamIE
 from .streamcloud import StreamcloudIE
@@ -504,6 +553,10 @@ from .tvp import TvpIE, TvpSeriesIE
 from .tvplay import TVPlayIE
 from .tweakers import TweakersIE
 from .twentyfourvideo import TwentyFourVideoIE
+from .twentytwotracks import (
+    TwentyTwoTracksIE,
+    TwentyTwoTracksGenreIE
+)
 from .twitch import (
     TwitchVideoIE,
     TwitchChapterIE,
@@ -518,12 +571,16 @@ from .udemy import (
     UdemyIE,
     UdemyCourseIE
 )
+from .udn import UDNEmbedIE
+from .ultimedia import UltimediaIE
 from .unistra import UnistraIE
 from .urort import UrortIE
 from .ustream import UstreamIE, UstreamChannelIE
+from .varzesh3 import Varzesh3IE
 from .vbox7 import Vbox7IE
 from .veehd import VeeHDIE
 from .veoh import VeohIE
+from .vessel import VesselIE
 from .vesti import VestiIE
 from .vevo import VevoIE
 from .vgtv import VGTVIE
@@ -541,6 +598,7 @@ from .videoweed import VideoWeedIE
 from .vidme import VidmeIE
 from .vidzi import VidziIE
 from .vier import VierIE, VierVideosIE
+from .viewster import ViewsterIE
 from .vimeo import (
     VimeoIE,
     VimeoAlbumIE,
@@ -597,6 +655,11 @@ from .yahoo import (
     YahooSearchIE,
 )
 from .yam import YamIE
+from .yandexmusic import (
+    YandexMusicTrackIE,
+    YandexMusicAlbumIE,
+    YandexMusicPlaylistIE,
+)
 from .yesjapan import YesJapanIE
 from .ynet import YnetIE
 from .youjizz import YouJizzIE

youtube_dl/extractor/addanime.py

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

youtube_dl/extractor/adultswim.py

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

youtube_dl/extractor/aftenposten.py

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

youtube_dl/extractor/aftonbladet.py

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

youtube_dl/extractor/airmozilla.py

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

youtube_dl/extractor/ard.py

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

youtube_dl/extractor/arte.py

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

youtube_dl/extractor/atresplayer.py

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

youtube_dl/extractor/baidu.py

@@ -0,0 +1,68 @@
+# 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/beatportpro.py

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

youtube_dl/extractor/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/breakcom.py

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

youtube_dl/extractor/brightcove.py

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

youtube_dl/extractor/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/cloudy.py

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

youtube_dl/extractor/cnn.py

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

youtube_dl/extractor/comedycentral.py

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

youtube_dl/extractor/common.py

@@ -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')
@@ -767,6 +777,10 @@ class InfoExtractor(object):
                 formats)
 
     def _is_valid_url(self, url, video_id, item='video'):
+        url = self._proto_relative_url(url, scheme='http:')
+        # For now assume non HTTP(S) URLs always valid
+        if not (url.startswith('http://') or url.startswith('https://')):
+            return True
         try:
             self._request_webpage(url, video_id, 'Checking %s URL' % item)
             return True
@@ -818,7 +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,
@@ -835,7 +849,7 @@ class InfoExtractor(object):
                               m3u8_id=None):
 
         formats = [{
-            'format_id': '-'.join(filter(None, [m3u8_id, 'm3u8-meta'])),
+            'format_id': '-'.join(filter(None, [m3u8_id, 'meta'])),
             'url': m3u8_url,
             'ext': ext,
             'protocol': 'm3u8',
@@ -879,8 +893,13 @@ class InfoExtractor(object):
                     formats.append({'url': format_url(line)})
                     continue
                 tbr = int_or_none(last_info.get('BANDWIDTH'), scale=1000)
+                format_id = []
+                if m3u8_id:
+                    format_id.append(m3u8_id)
+                last_media_name = last_media.get('NAME') if last_media else None
+                format_id.append(last_media_name if last_media_name else '%d' % (tbr if tbr else len(formats)))
                 f = {
-                    'format_id': '-'.join(filter(None, [m3u8_id, 'm3u8-%d' % (tbr if tbr else len(formats))])),
+                    'format_id': '-'.join(format_id),
                     'url': format_url(line.strip()),
                     'tbr': tbr,
                     'ext': ext,
@@ -921,39 +940,57 @@ class InfoExtractor(object):
 
         formats = []
         rtmp_count = 0
-        for video in smil.findall('./body/switch/video'):
-            src = video.get('src')
-            if not src:
-                continue
-            bitrate = int_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000)
-            width = int_or_none(video.get('width'))
-            height = int_or_none(video.get('height'))
-            proto = video.get('proto')
-            if not proto:
-                if base:
-                    if base.startswith('rtmp'):
-                        proto = 'rtmp'
-                    elif base.startswith('http'):
-                        proto = 'http'
-            ext = video.get('ext')
-            if proto == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(src, video_id, ext))
-            elif proto == 'rtmp':
-                rtmp_count += 1
-                streamer = video.get('streamer') or base
-                formats.append({
-                    'url': streamer,
-                    'play_path': src,
-                    'ext': 'flv',
-                    'format_id': 'rtmp-%d' % (rtmp_count if bitrate is None else bitrate),
-                    'tbr': bitrate,
-                    'width': width,
-                    'height': height,
-                })
+        if smil.findall('./body/seq/video'):
+            video = smil.findall('./body/seq/video')[0]
+            fmts, rtmp_count = self._parse_smil_video(video, video_id, base, rtmp_count)
+            formats.extend(fmts)
+        else:
+            for video in smil.findall('./body/switch/video'):
+                fmts, rtmp_count = self._parse_smil_video(video, video_id, base, rtmp_count)
+                formats.extend(fmts)
+
         self._sort_formats(formats)
 
         return formats
 
+    def _parse_smil_video(self, video, video_id, base, rtmp_count):
+        src = video.get('src')
+        if not src:
+            return ([], rtmp_count)
+        bitrate = int_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000)
+        width = int_or_none(video.get('width'))
+        height = int_or_none(video.get('height'))
+        proto = video.get('proto')
+        if not proto:
+            if base:
+                if base.startswith('rtmp'):
+                    proto = 'rtmp'
+                elif base.startswith('http'):
+                    proto = 'http'
+        ext = video.get('ext')
+        if proto == 'm3u8':
+            return (self._extract_m3u8_formats(src, video_id, ext), rtmp_count)
+        elif proto == 'rtmp':
+            rtmp_count += 1
+            streamer = video.get('streamer') or base
+            return ([{
+                'url': streamer,
+                'play_path': src,
+                'ext': 'flv',
+                'format_id': 'rtmp-%d' % (rtmp_count if bitrate is None else bitrate),
+                'tbr': bitrate,
+                'width': width,
+                'height': height,
+            }], rtmp_count)
+        elif proto.startswith('http'):
+            return ([{
+                'url': base + src,
+                'ext': ext or 'flv',
+                'tbr': bitrate,
+                'width': width,
+                'height': height,
+            }], rtmp_count)
+
     def _live_title(self, name):
         """ Generate the title for a live video """
         now = datetime.datetime.now()
@@ -1035,6 +1072,9 @@ class InfoExtractor(object):
     def _get_automatic_captions(self, *args, **kwargs):
         raise NotImplementedError("This method must be implemented by subclasses")
 
+    def _subtitles_timecode(self, seconds):
+        return '%02d:%02d:%02d.%03d' % (seconds / 3600, (seconds % 3600) / 60, seconds % 60, (seconds % 1) * 1000)
+
 
 class SearchInfoExtractor(InfoExtractor):
     """

youtube_dl/extractor/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

@@ -23,12 +23,12 @@ from ..utils import (
 )
 from ..aes import (
     aes_cbc_decrypt,
-    inc,
 )
 
 
 class CrunchyrollIE(InfoExtractor):
     _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
+    _NETRC_MACHINE = 'crunchyroll'
     _TESTS = [{
         'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
         'info_dict': {
@@ -101,13 +101,6 @@ class CrunchyrollIE(InfoExtractor):
 
         key = obfuscate_key(id)
 
-        class Counter:
-            __value = iv
-
-            def next_value(self):
-                temp = self.__value
-                self.__value = inc(self.__value)
-                return temp
         decrypted_data = intlist_to_bytes(aes_cbc_decrypt(data, key, iv))
         return zlib.decompress(decrypted_data)
 
@@ -270,8 +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

@@ -25,8 +25,7 @@ class DailymotionBaseInfoExtractor(InfoExtractor):
     def _build_request(url):
         """Build a request with the family filter disabled"""
         request = compat_urllib_request.Request(url)
-        request.add_header('Cookie', 'family_filter=off')
-        request.add_header('Cookie', 'ff=off')
+        request.add_header('Cookie', 'family_filter=off; ff=off')
         return request
 
 
@@ -46,13 +45,13 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
 
     _TESTS = [
         {
-            'url': 'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech',
-            'md5': '392c4b85a60a90dc4792da41ce3144eb',
+            'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames',
+            'md5': '2137c41a8e78554bb09225b8eb322406',
             'info_dict': {
-                'id': 'x33vw9',
+                'id': 'x2iuewm',
                 'ext': 'mp4',
-                'uploader': 'Amphora Alex and Van .',
-                'title': 'Tutoriel de Youtubeur"DL DES VIDEO DE YOUTUBE"',
+                'uploader': 'IGN',
+                'title': 'Steam Machine Models, Pricing Listed on Steam Store - IGN News',
             }
         },
         # Vevo video
@@ -86,7 +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)
@@ -111,9 +110,10 @@ 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_page = self._download_webpage(embed_url, video_id,
-                                            'Downloading embed page')
+        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')
         info = self._search_regex(r'var info = ({.*?}),$', embed_page,
                                   'video info', flags=re.MULTILINE)
         info = json.loads(info)
@@ -224,7 +224,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
 
 class DailymotionUserIE(DailymotionPlaylistIE):
     IE_NAME = 'dailymotion:user'
-    _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?:old/)?user/(?P<user>[^/]+)'
     _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
     _TESTS = [{
         'url': 'https://www.dailymotion.com/user/nqtv',

youtube_dl/extractor/dhm.py

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

youtube_dl/extractor/dotsub.py

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

youtube_dl/extractor/douyutv.py

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

youtube_dl/extractor/dreisat.py

@@ -3,24 +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

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

youtube_dl/extractor/eagleplatform.py

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

youtube_dl/extractor/eighttracks.py

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

youtube_dl/extractor/ellentv.py

@@ -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/eporner.py

@@ -35,10 +35,7 @@ class EpornerIE(InfoExtractor):
         title = self._html_search_regex(
             r'<title>(.*?) - EPORNER', webpage, 'title')
 
-        redirect_code = self._html_search_regex(
-            r'<script type="text/javascript" src="/config5/%s/([a-f\d]+)/">' % video_id,
-            webpage, 'redirect_code')
-        redirect_url = 'http://www.eporner.com/config5/%s/%s' % (video_id, redirect_code)
+        redirect_url = 'http://www.eporner.com/config5/%s' % video_id
         player_code = self._download_webpage(
             redirect_url, display_id, note='Downloading player config')
 
@@ -69,5 +66,5 @@ class EpornerIE(InfoExtractor):
             'duration': duration,
             'view_count': view_count,
             'formats': formats,
-            'age_limit': self._rta_search(webpage),
+            'age_limit': 18,
         }

youtube_dl/extractor/eroprofile.py

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

youtube_dl/extractor/escapist.py

@@ -1,84 +1,105 @@
 from __future__ import unicode_literals
 
+import json
+
 from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse,
-)
+from ..compat import compat_urllib_request
+
 from ..utils import (
-    ExtractorError,
-    js_to_json,
+    determine_ext,
+    clean_html,
+    qualities,
 )
 
 
+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]+)-[^/?#]*(?:$|[?#])'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
-        'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
+        'md5': 'c6793dbda81388f4264c1ba18684a74d',
         'info_dict': {
             'id': '6618',
             'ext': 'mp4',
             'description': "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
-            'uploader_id': 'the-escapist-presents',
-            'uploader': 'The Escapist Presents',
             'title': "Breaking Down Baldur's Gate",
             'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 264,
         }
-    }
+    }, {
+        'url': 'http://www.escapistmagazine.com/videos/view/zero-punctuation/10044-Evolve-One-vs-Multiplayer',
+        'md5': 'cf8842a8a46444d241f9a9980d7874f2',
+        'info_dict': {
+            'id': '10044',
+            'ext': 'mp4',
+            'description': 'This week, Zero Punctuation reviews Evolve.',
+            'title': 'Evolve - One vs Multiplayer',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 304,
+        }
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         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)
+        imsVideo = self._parse_json(
+            self._search_regex(
+                r'imsVideo\.play\(({.+?})\);', webpage, 'imsVideo'),
+            video_id)
+        video_id = imsVideo['videoID']
+        key = imsVideo['hash']
 
-        raw_title = self._html_search_meta('title', webpage, fatal=True)
-        title = raw_title.partition(' : ')[2]
-
-        config_url = compat_urllib_parse.unquote(self._html_search_regex(
-            r'<param\s+name="flashvars"\s+value="config=([^"&]+)', webpage, 'config URL'))
+        quality = qualities(['lq', 'hq', 'hd'])
 
         formats = []
+        for q in ['lq', 'hq', 'hd']:
+            config_req = compat_urllib_request.Request(
+                'http://www.escapistmagazine.com/videos/'
+                'vidconfig.php?videoID=%s&hash=%s&quality=%s' % (video_id, key, 'mp4_' + q))
+            config_req.add_header('Referer', url)
+            config = self._download_webpage(config_req, video_id, 'Downloading video config ' + q.upper())
 
-        def _add_format(name, cfgurl, quality):
-            config = self._download_json(
-                cfgurl, video_id,
-                'Downloading ' + name + ' configuration',
-                'Unable to download ' + name + ' configuration',
-                transform_source=js_to_json)
+            data = json.loads(_decrypt_config(key, config))
 
-            playlist = config['playlist']
-            video_url = next(
-                p['url'] for p in playlist
-                if p.get('eventCategory') == 'Video')
-            formats.append({
-                'url': video_url,
-                'format_id': name,
-                'quality': quality,
-            })
+            title = clean_html(data['videoData']['title'])
+            duration = data['videoData']['duration'] / 1000
 
-        _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
+            for i, v in enumerate(data['files']['videos']):
 
-        self._sort_formats(formats)
+                formats.append({
+                    'url': v,
+                    'format_id': determine_ext(v) + '_' + q + str(i),
+                    'quality': quality(q),
+                })
 
         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,
         }

youtube_dl/extractor/extremetube.py

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

youtube_dl/extractor/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

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

youtube_dl/extractor/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/funnyordie.py

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

youtube_dl/extractor/gamersyde.py

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

youtube_dl/extractor/gamestar.py

@@ -1,6 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
@@ -31,7 +33,7 @@ class GameStarIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         og_title = self._og_search_title(webpage)
-        title = og_title.replace(' - Video bei GameStar.de', '').strip()
+        title = re.sub(r'\s*- Video (bei|-) GameStar\.de$', '', og_title)
 
         url = 'http://gamestar.de/_misc/videos/portal/getVideoUrl.cfm?premium=0&videoId=' + video_id
 

youtube_dl/extractor/gazeta.py

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

youtube_dl/extractor/gdcvault.py

@@ -11,13 +11,15 @@ 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 = [
         {
             'url': 'http://www.gdcvault.com/play/1019721/Doki-Doki-Universe-Sweet-Simple',
             '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)'
             }
@@ -26,6 +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'
             },
@@ -38,10 +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,
         }
     ]
 
@@ -89,7 +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.')
@@ -106,9 +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
 
@@ -116,8 +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\("(/[^"]+)"\)\);',
@@ -130,6 +140,7 @@ class GDCVaultIE(InfoExtractor):
 
             return {
                 'id': video_id,
+                'display_id': display_id,
                 'url': video_url,
                 'ext': 'flv',
                 'title': title,
@@ -140,7 +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:
@@ -158,7 +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)
@@ -167,6 +178,7 @@ class GDCVaultIE(InfoExtractor):
 
         return {
             'id': video_id,
+            'display_id': display_id,
             'title': video_title,
             'formats': video_formats,
         }

youtube_dl/extractor/generic.py

@@ -26,12 +26,17 @@ from ..utils import (
     unsmuggle_url,
     UnsupportedError,
     url_basename,
+    xpath_text,
 )
 from .brightcove import BrightcoveIE
+from .nbc import NBCSportsVPlayerIE
 from .ooyala import OoyalaIE
 from .rutv import RUTVIE
 from .smotri import SmotriIE
 from .condenast import CondeNastIE
+from .udn import UDNEmbedIE
+from .senateisvp import SenateISVPIE
+from .bliptv import BlipTVIE
 
 
 class GenericIE(InfoExtractor):
@@ -408,6 +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',
@@ -526,6 +544,17 @@ class GenericIE(InfoExtractor):
             },
             'add_ie': ['Viddler'],
         },
+        # Libsyn embed
+        {
+            'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
+            'info_dict': {
+                'id': '3377616',
+                'ext': 'mp3',
+                'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
+                'description': 'md5:601cb790edd05908957dae8aaa866465',
+                'upload_date': '20150220',
+            },
+        },
         # jwplayer YouTube
         {
             'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
@@ -557,6 +586,163 @@ class GenericIE(InfoExtractor):
                 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
             }
         },
+        # Kaltura embed
+        {
+            'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
+            'info_dict': {
+                'id': '1_eergr3h1',
+                'ext': 'mp4',
+                'upload_date': '20150226',
+                'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
+                'timestamp': int,
+                'title': 'John Carlson Postgame 2/25/15',
+            },
+        },
+        # Eagle.Platform embed (generic URL)
+        {
+            'url': 'http://lenta.ru/news/2015/03/06/navalny/',
+            'info_dict': {
+                'id': '227304',
+                'ext': 'mp4',
+                'title': 'Навальный вышел на свободу',
+                'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'duration': 87,
+                'view_count': int,
+                'age_limit': 0,
+            },
+        },
+        # ClipYou (Eagle.Platform) embed (custom URL)
+        {
+            'url': 'http://muz-tv.ru/play/7129/',
+            'info_dict': {
+                'id': '12820',
+                'ext': 'mp4',
+                'title': "'O Sole Mio",
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'duration': 216,
+                'view_count': int,
+            },
+        },
+        # Pladform embed
+        {
+            'url': 'http://muz-tv.ru/kinozal/view/7400/',
+            'info_dict': {
+                'id': '100183293',
+                'ext': 'mp4',
+                'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
+                'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'duration': 694,
+                'age_limit': 0,
+            },
+        },
+        # Playwire embed
+        {
+            'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
+            'info_dict': {
+                'id': '3519514',
+                'ext': 'mp4',
+                'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
+                'thumbnail': 're:^https?://.*\.png$',
+                'duration': 45.115,
+            },
+        },
+        # 5min embed
+        {
+            'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
+            'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
+            'info_dict': {
+                'id': '518726732',
+                'ext': 'mp4',
+                'title': 'Facebook Creates "On This Day" | Crunch Report',
+            },
+        },
+        # RSS feed with enclosure
+        {
+            'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
+            'info_dict': {
+                'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
+                'ext': 'm4v',
+                'upload_date': '20150228',
+                'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
+            }
+        },
+        # Crooks and Liars embed
+        {
+            'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
+            'info_dict': {
+                'id': '8RUoRhRi',
+                'ext': 'mp4',
+                'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
+                'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
+                'timestamp': 1428207000,
+                'upload_date': '20150405',
+                'uploader': 'Heather',
+            },
+        },
+        # Crooks and Liars external embed
+        {
+            'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
+            'info_dict': {
+                'id': 'MTE3MjUtMzQ2MzA',
+                'ext': 'mp4',
+                'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
+                'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
+                'timestamp': 1265032391,
+                'upload_date': '20100201',
+                'uploader': 'Heather',
+            },
+        },
+        # NBC Sports vplayer embed
+        {
+            'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
+            'info_dict': {
+                'id': 'ln7x1qSThw4k',
+                'ext': 'flv',
+                'title': "PFT Live: New leader in the 'new-look' defense",
+                'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
+            },
+        },
+        # UDN embed
+        {
+            'url': 'http://www.udn.com/news/story/7314/822787',
+            'md5': 'fd2060e988c326991037b9aff9df21a6',
+            'info_dict': {
+                'id': '300346',
+                'ext': 'mp4',
+                'title': '中一中男師變性 全校師生力挺',
+                'thumbnail': 're:^https?://.*\.jpg$',
+            }
+        },
+        # Ooyala embed
+        {
+            'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
+            'info_dict': {
+                'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
+                'ext': 'mp4',
+                'description': 'VIDEO: Index/Match versus VLOOKUP.',
+                'title': 'This is what separates the Excel masters from the wannabes',
+            },
+            'params': {
+                # m3u8 downloads
+                'skip_download': True,
+            }
+        },
+        # Contains a SMIL manifest
+        {
+            'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
+            'info_dict': {
+                'id': 'file',
+                'ext': 'flv',
+                'title': '+ Football: Lottery Champions League Europe',
+                'uploader': 'www.telewebion.com',
+            },
+            'params': {
+                # rtmpe downloads
+                'skip_download': True,
+            }
+        }
     ]
 
     def report_following_redirect(self, new_url):
@@ -568,11 +754,24 @@ class GenericIE(InfoExtractor):
         playlist_desc_el = doc.find('./channel/description')
         playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
 
-        entries = [{
-            '_type': 'url',
-            'url': e.find('link').text,
-            'title': e.find('title').text,
-        } for e in doc.findall('./channel/item')]
+        entries = []
+        for it in doc.findall('./channel/item'):
+            next_url = xpath_text(it, 'link', fatal=False)
+            if not next_url:
+                enclosure_nodes = it.findall('./enclosure')
+                for e in enclosure_nodes:
+                    next_url = e.attrib.get('url')
+                    if next_url:
+                        break
+
+            if not next_url:
+                continue
+
+            entries.append({
+                '_type': 'url',
+                'url': next_url,
+                'title': it.find('title').text,
+            })
 
         return {
             '_type': 'playlist',
@@ -888,12 +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(
@@ -931,10 +1127,24 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(mobj.group('url'))
 
+        # Look for NYTimes player
+        mobj = re.search(
+            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
+            webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'))
+
+        # Look for Libsyn player
+        mobj = re.search(
+            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'))
+
         # Look for Ooyala videos
         mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
                 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
-                re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage))
+                re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
+                re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
         if mobj is not None:
             return OoyalaIE._build_url_result(mobj.group('ec'))
 
@@ -1092,6 +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')
 
@@ -1113,6 +1327,65 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'Zapiks')
 
+        # Look for Kaltura embeds
+        mobj = re.search(
+            r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage)
+        if mobj is not None:
+            return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
+
+        # Look for Eagle.Platform embeds
+        mobj = re.search(
+            r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'EaglePlatform')
+
+        # Look for ClipYou (uses Eagle.Platform) embeds
+        mobj = re.search(
+            r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
+        if mobj is not None:
+            return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
+
+        # Look for Pladform embeds
+        mobj = re.search(
+            r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'Pladform')
+
+        # Look for Playwire embeds
+        mobj = re.search(
+            r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'))
+
+        # Look for 5min embeds
+        mobj = re.search(
+            r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
+        if mobj is not None:
+            return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
+
+        # Look for Crooks and Liars embeds
+        mobj = re.search(
+            r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'))
+
+        # Look for NBC Sports VPlayer embeds
+        nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
+        if nbc_sports_url:
+            return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
+
+        # Look for UDN embeds
+        mobj = re.search(
+            r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
+        if mobj is not None:
+            return self.url_result(
+                compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
+
+        # 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
@@ -1169,10 +1442,16 @@ class GenericIE(InfoExtractor):
             # HTML5 video
             found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
         if not found:
+            REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
             found = re.search(
                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
-                r'(?:[a-z-]+="[^"]+"\s+)*?content="[0-9]{,2};url=\'?([^\'"]+)',
+                r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
                 webpage)
+            if not found:
+                # Look also in Refresh HTTP header
+                refresh_header = head_response.headers.get('Refresh')
+                if refresh_header:
+                    found = re.search(REDIRECT_REGEX, refresh_header)
             if found:
                 new_url = found.group(1)
                 self.report_following_redirect(new_url)
@@ -1196,19 +1475,30 @@ 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]
         else:
             for num, e in enumerate(entries, start=1):
-                e['title'] = '%s (%d)' % (e['title'], num)
+                # 'url' results don't have a title
+                if e.get('title') is not None:
+                    e['title'] = '%s (%d)' % (e['title'], num)
             return {
                 '_type': 'playlist',
                 'entries': entries,

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/globo.py

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

youtube_dl/extractor/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 is not None:
-                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/jeuxvideo.py

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

youtube_dl/extractor/kaltura.py

@@ -0,0 +1,138 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_parse
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+)
+
+
+class KalturaIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+    (?:kaltura:|
+       https?://(:?(?:www|cdnapisec)\.)?kaltura\.com/index\.php/kwidget/(?:[^/]+/)*?wid/_
+    )(?P<partner_id>\d+)
+    (?::|
+       /(?:[^/]+/)*?entry_id/
+    )(?P<id>[0-9a-z_]+)'''
+    _API_BASE = 'http://cdnapi.kaltura.com/api_v3/index.php?'
+    _TESTS = [
+        {
+            'url': 'kaltura:269692:1_1jc2y3e4',
+            'md5': '3adcbdb3dcc02d647539e53f284ba171',
+            'info_dict': {
+                'id': '1_1jc2y3e4',
+                'ext': 'mp4',
+                'title': 'Track 4',
+                'upload_date': '20131219',
+                'uploader_id': 'mlundberg@wolfgangsvault.com',
+                'description': 'The Allman Brothers Band, 12/16/1981',
+                'thumbnail': 're:^https?://.*/thumbnail/.*',
+                'timestamp': int,
+            },
+        },
+        {
+            'url': 'http://www.kaltura.com/index.php/kwidget/cache_st/1300318621/wid/_269692/uiconf_id/3873291/entry_id/1_1jc2y3e4',
+            'only_matching': True,
+        },
+        {
+            'url': 'https://cdnapisec.kaltura.com/index.php/kwidget/wid/_557781/uiconf_id/22845202/entry_id/1_plr1syf3',
+            'only_matching': True,
+        },
+    ]
+
+    def _kaltura_api_call(self, video_id, actions, *args, **kwargs):
+        params = actions[0]
+        if len(actions) > 1:
+            for i, a in enumerate(actions[1:], start=1):
+                for k, v in a.items():
+                    params['%d:%s' % (i, k)] = v
+
+        query = compat_urllib_parse.urlencode(params)
+        url = self._API_BASE + query
+        data = self._download_json(url, video_id, *args, **kwargs)
+
+        status = data if len(actions) == 1 else data[0]
+        if status.get('objectType') == 'KalturaAPIException':
+            raise ExtractorError(
+                '%s said: %s' % (self.IE_NAME, status['message']))
+
+        return data
+
+    def _get_kaltura_signature(self, video_id, partner_id):
+        actions = [{
+            'apiVersion': '3.1',
+            'expiry': 86400,
+            'format': 1,
+            'service': 'session',
+            'action': 'startWidgetSession',
+            'widgetId': '_%s' % partner_id,
+        }]
+        return self._kaltura_api_call(
+            video_id, actions, note='Downloading Kaltura signature')['ks']
+
+    def _get_video_info(self, video_id, partner_id):
+        signature = self._get_kaltura_signature(video_id, partner_id)
+        actions = [
+            {
+                'action': 'null',
+                'apiVersion': '3.1.5',
+                'clientTag': 'kdp:v3.8.5',
+                'format': 1,  # JSON, 2 = XML, 3 = PHP
+                'service': 'multirequest',
+                'ks': signature,
+            },
+            {
+                'action': 'get',
+                'entryId': video_id,
+                'service': 'baseentry',
+                'version': '-1',
+            },
+            {
+                'action': 'getContextData',
+                'contextDataParams:objectType': 'KalturaEntryContextDataParams',
+                'contextDataParams:referrer': 'http://www.kaltura.com/',
+                'contextDataParams:streamerType': 'http',
+                'entryId': video_id,
+                'service': 'baseentry',
+            },
+        ]
+        return self._kaltura_api_call(
+            video_id, actions, note='Downloading video info JSON')
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        partner_id, entry_id = mobj.group('partner_id'), mobj.group('id')
+
+        info, source_data = self._get_video_info(entry_id, partner_id)
+
+        formats = [{
+            'format_id': '%(fileExt)s-%(bitrate)s' % f,
+            'ext': f['fileExt'],
+            'tbr': f['bitrate'],
+            'fps': f.get('frameRate'),
+            'filesize_approx': int_or_none(f.get('size'), invscale=1024),
+            'container': f.get('containerFormat'),
+            'vcodec': f.get('videoCodecId'),
+            'height': f.get('height'),
+            'width': f.get('width'),
+            'url': '%s/flavorId/%s' % (info['dataUrl'], f['id']),
+        } for f in source_data['flavorAssets']]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': info['name'],
+            'formats': formats,
+            'description': info.get('description'),
+            'thumbnail': info.get('thumbnailUrl'),
+            'duration': info.get('duration'),
+            'timestamp': info.get('createdAt'),
+            'uploader_id': info.get('userId'),
+            'view_count': info.get('plays'),
+        }

youtube_dl/extractor/kanalplay.py

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

youtube_dl/extractor/krasview.py

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

youtube_dl/extractor/laola1tv.py

@@ -27,8 +27,6 @@ class Laola1TvIE(InfoExtractor):
         }
     }
 
-    _BROKEN = True  # Not really - extractor works fine, but f4m downloader does not support live streams yet.
-
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
@@ -57,11 +55,7 @@ class Laola1TvIE(InfoExtractor):
         title = xpath_text(hd_doc, './/video/title', fatal=True)
         flash_url = xpath_text(hd_doc, './/video/url', fatal=True)
         uploader = xpath_text(hd_doc, './/video/meta_organistation')
-
         is_live = xpath_text(hd_doc, './/video/islive') == 'true'
-        if is_live:
-            raise ExtractorError(
-                'Live streams are not supported by the f4m downloader.')
 
         categories = xpath_text(hd_doc, './/video/meta_sports')
         if categories:

youtube_dl/extractor/letv.py

@@ -0,0 +1,207 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import datetime
+import re
+import time
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_parse,
+    compat_urllib_request,
+    compat_urlparse,
+)
+from ..utils import (
+    determine_ext,
+    ExtractorError,
+    parse_iso8601,
+)
+
+
+class LetvIE(InfoExtractor):
+    _VALID_URL = r'http://www\.letv\.com/ptv/vplay/(?P<id>\d+).html'
+
+    _TESTS = [{
+        'url': 'http://www.letv.com/ptv/vplay/22005890.html',
+        'md5': 'cab23bd68d5a8db9be31c9a222c1e8df',
+        'info_dict': {
+            'id': '22005890',
+            'ext': 'mp4',
+            'title': '第87届奥斯卡颁奖礼完美落幕 《鸟人》成最大赢家',
+            'timestamp': 1424747397,
+            'upload_date': '20150224',
+            'description': 'md5:a9cb175fd753e2962176b7beca21a47c',
+        }
+    }, {
+        'url': 'http://www.letv.com/ptv/vplay/1415246.html',
+        'info_dict': {
+            'id': '1415246',
+            'ext': 'mp4',
+            'title': '美人天下01',
+            'description': 'md5:f88573d9d7225ada1359eaf0dbf8bcda',
+        },
+    }, {
+        'note': 'This video is available only in Mainland China, thus a proxy is needed',
+        'url': 'http://www.letv.com/ptv/vplay/1118082.html',
+        'md5': 'f80936fbe20fb2f58648e81386ff7927',
+        'info_dict': {
+            'id': '1118082',
+            'ext': 'mp4',
+            'title': '与龙共舞 完整版',
+            'description': 'md5:7506a5eeb1722bb9d4068f85024e3986',
+        },
+        'params': {
+            'cn_verification_proxy': 'http://proxy.uku.im:8888'
+        },
+    }]
+
+    @staticmethod
+    def urshift(val, n):
+        return val >> n if val >= 0 else (val + 0x100000000) >> n
+
+    # ror() and calc_time_key() are reversed from a embedded swf file in KLetvPlayer.swf
+    def ror(self, param1, param2):
+        _loc3_ = 0
+        while _loc3_ < param2:
+            param1 = self.urshift(param1, 1) + ((param1 & 1) << 31)
+            _loc3_ += 1
+        return param1
+
+    def calc_time_key(self, param1):
+        _loc2_ = 773625421
+        _loc3_ = self.ror(param1, _loc2_ % 13)
+        _loc3_ = _loc3_ ^ _loc2_
+        _loc3_ = self.ror(_loc3_, _loc2_ % 17)
+        return _loc3_
+
+    def _real_extract(self, url):
+        media_id = self._match_id(url)
+        page = self._download_webpage(url, media_id)
+        params = {
+            'id': media_id,
+            'platid': 1,
+            'splatid': 101,
+            'format': 1,
+            'tkey': self.calc_time_key(int(time.time())),
+            'domain': 'www.letv.com'
+        }
+        play_json_req = compat_urllib_request.Request(
+            'http://api.letv.com/mms/out/video/playJson?' + compat_urllib_parse.urlencode(params)
+        )
+        cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
+        if cn_verification_proxy:
+            play_json_req.add_header('Ytdl-request-proxy', cn_verification_proxy)
+
+        play_json = self._download_json(
+            play_json_req,
+            media_id, 'Downloading playJson data')
+
+        # Check for errors
+        playstatus = play_json['playstatus']
+        if playstatus['status'] == 0:
+            flag = playstatus['flag']
+            if flag == 1:
+                msg = 'Country %s auth error' % playstatus['country']
+            else:
+                msg = 'Generic error. flag = %d' % flag
+            raise ExtractorError(msg, expected=True)
+
+        playurl = play_json['playurl']
+
+        formats = ['350', '1000', '1300', '720p', '1080p']
+        dispatch = playurl['dispatch']
+
+        urls = []
+        for format_id in formats:
+            if format_id in dispatch:
+                media_url = playurl['domain'][0] + dispatch[format_id][0]
+
+                # Mimic what flvxz.com do
+                url_parts = list(compat_urlparse.urlparse(media_url))
+                qs = dict(compat_urlparse.parse_qs(url_parts[4]))
+                qs.update({
+                    'platid': '14',
+                    'splatid': '1401',
+                    'tss': 'no',
+                    'retry': 1
+                })
+                url_parts[4] = compat_urllib_parse.urlencode(qs)
+                media_url = compat_urlparse.urlunparse(url_parts)
+
+                url_info_dict = {
+                    'url': media_url,
+                    'ext': determine_ext(dispatch[format_id][1]),
+                    'format_id': format_id,
+                }
+
+                if format_id[-1:] == 'p':
+                    url_info_dict['height'] = format_id[:-1]
+
+                urls.append(url_info_dict)
+
+        publish_time = parse_iso8601(self._html_search_regex(
+            r'发布时间&nbsp;([^<>]+) ', page, 'publish time', default=None),
+            delimiter=' ', timezone=datetime.timedelta(hours=8))
+        description = self._html_search_meta('description', page, fatal=False)
+
+        return {
+            'id': media_id,
+            'formats': urls,
+            'title': playurl['title'],
+            'thumbnail': playurl['pic'],
+            'description': description,
+            'timestamp': publish_time,
+        }
+
+
+class LetvTvIE(InfoExtractor):
+    _VALID_URL = r'http://www.letv.com/tv/(?P<id>\d+).html'
+    _TESTS = [{
+        'url': 'http://www.letv.com/tv/46177.html',
+        'info_dict': {
+            'id': '46177',
+            'title': '美人天下',
+            'description': 'md5:395666ff41b44080396e59570dbac01c'
+        },
+        'playlist_count': 35
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        page = self._download_webpage(url, playlist_id)
+
+        media_urls = list(set(re.findall(
+            r'http://www.letv.com/ptv/vplay/\d+.html', page)))
+        entries = [self.url_result(media_url, ie='Letv')
+                   for media_url in media_urls]
+
+        title = self._html_search_meta('keywords', page,
+                                       fatal=False).split('，')[0]
+        description = self._html_search_meta('description', page, fatal=False)
+
+        return self.playlist_result(entries, playlist_id, playlist_title=title,
+                                    playlist_description=description)
+
+
+class LetvPlaylistIE(LetvTvIE):
+    _VALID_URL = r'http://tv.letv.com/[a-z]+/(?P<id>[a-z]+)/index.s?html'
+    _TESTS = [{
+        'url': 'http://tv.letv.com/izt/wuzetian/index.html',
+        'info_dict': {
+            'id': 'wuzetian',
+            'title': '武媚娘传奇',
+            'description': 'md5:e12499475ab3d50219e5bba00b3cb248'
+        },
+        # This playlist contains some extra videos other than the drama itself
+        'playlist_mincount': 96
+    }, {
+        'url': 'http://tv.letv.com/pzt/lswjzzjc/index.shtml',
+        'info_dict': {
+            'id': 'lswjzzjc',
+            # The title should be "劲舞青春", but I can't find a simple way to
+            # determine the playlist title
+            'title': '乐视午间自制剧场',
+            'description': 'md5:b1eef244f45589a7b5b1af9ff25a4489'
+        },
+        'playlist_mincount': 7
+    }]