release 2017.02.10

They should not match e.g. cdnapi.kaltura.computernetworks.com/...

.github/ISSUE_TEMPLATE.md

@@ -6,8 +6,8 @@
 
 ---
 
-### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.01.02*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.02.10*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
-- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.01.02**
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.02.10**
 
 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
 [debug] User config: []
 [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
 [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
-[debug] youtube-dl version 2017.01.02
+[debug] youtube-dl version 2017.02.10
 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
 [debug] Proxy map: {}

.travis.yml

@@ -6,6 +6,7 @@ python:
   - "3.3"
   - "3.4"
   - "3.5"
+  - "3.6"
 sudo: false
 script: nosetests test --verbose
 notifications:

AUTHORS

@@ -191,3 +191,14 @@ Rich Leeper
 Zhong Jianxin
 Thor77
 Mattias Wadman
+Arjan Verwer
+Costy Petrisor
+Logan B
+Alex Seiler
+Vijay Singh
+Paul Hartmann
+Stephen Chen
+Fabian Stahl
+Bagira
+Odd Stråbø
+Philip Herzog

CONTRIBUTING.md

@@ -124,7 +124,7 @@ After you have ensured this site is distributing its content legally, you can fo
                 'id': '42',
                 'ext': 'mp4',
                 'title': 'Video title goes here',
-                'thumbnail': 're:^https?://.*\.jpg$',
+                'thumbnail': r're:^https?://.*\.jpg$',
                 # TODO more properties, either as:
                 # * A value
                 # * MD5 checksum; start the string with md5:

ChangeLog

@@ -1,3 +1,267 @@
+version 2017.02.10
+
+Extractors
+* [xtube] Fix extraction (#12023)
+* [pornhub] Fix extraction (#12007, #12018)
+* [facebook] Improve JS data regular expression (#12042)
+* [kaltura] Improve embed partner id extraction (#12041)
++ [sprout] Add support for sproutonline.com
+* [6play] Improve extraction
++ [scrippsnetworks:watch] Add support for Scripps Networks sites (#10765)
++ [go] Add support for Adobe Pass authentication (#11468, #10831)
+* [6play] Fix extraction (#12011)
++ [nbc] Add support for Adobe Pass authentication (#12006)
+
+
+version 2017.02.07
+
+Core
+* [extractor/common] Fix audio only with audio group in m3u8 (#11995)
++ [downloader/fragment] Respect --no-part
+* [extractor/common] Speed-up HTML5 media entries extraction (#11979)
+
+Extractors
+* [pornhub] Fix extraction (#11997)
++ [canalplus] Add support for cstar.fr (#11990)
++ [extractor/generic] Improve RTMP support (#11993)
++ [gaskrank] Add support for gaskrank.tv (#11685)
+* [bandcamp] Fix extraction for incomplete albums (#11727)
+* [iwara] Fix extraction (#11781)
+* [googledrive] Fix extraction on Python 3.6
++ [videopress] Add support for videopress.com
++ [afreecatv] Extract RTMP formats
+
+
+version 2017.02.04.1
+
+Extractors
++ [twitch:stream] Add support for player.twitch.tv (#11971)
+* [radiocanada] Fix extraction for toutv rtmp formats
+
+
+version 2017.02.04
+
+Core
++ Add --playlist-random to shuffle playlists (#11889, #11901)
+* [utils] Improve comments processing in js_to_json (#11947)
+* [utils] Handle single-line comments in js_to_json
+* [downloader/external:ffmpeg] Minimize the use of aac_adtstoasc filter
+
+Extractors
++ [piksel] Add another app token pattern (#11969)
++ [vk] Capture and output author blocked error message (#11965)
++ [turner] Fix secure HLS formats downloading with ffmpeg (#11358, #11373,
+  #11800)
++ [drtv] Add support for live and radio sections (#1827, #3427)
+* [myspace] Fix extraction and extract HLS and HTTP formats
++ [youtube] Add format info for itag 325 and 328
+* [vine] Fix extraction (#11955)
+- [sportbox] Remove extractor (#11954)
++ [filmon] Add support for filmon.com (#11187)
++ [infoq] Add audio only formats (#11565)
+* [douyutv] Improve room id regular expression (#11931)
+* [iprima] Fix extraction (#11920, #11896)
+* [youtube] Fix ytsearch when cookies are provided (#11924)
+* [go] Relax video id regular expression (#11937)
+* [facebook] Fix title extraction (#11941)
++ [youtube:playlist] Recognize TL playlists (#11945)
++ [bilibili] Support new Bangumi URLs (#11845)
++ [cbc:watch] Extract audio codec for audio only formats (#11893)
++ [elpais] Fix extraction for some URLs (#11765)
+
+
+version 2017.02.01
+
+Extractors
++ [facebook] Add another fallback extraction scenario (#11926)
+* [prosiebensat1] Fix extraction of descriptions (#11810, #11929)
+- [crunchyroll] Remove ScaledBorderAndShadow settings (#9028)
++ [vimeo] Extract upload timestamp
++ [vimeo] Extract license (#8726, #11880)
++ [nrk:series] Add support for series (#11571, #11711)
+
+
+version 2017.01.31
+
+Core
++ [compat] Add compat_etree_register_namespace
+
+Extractors
+* [youtube] Fix extraction for domainless player URLs (#11890, #11891, #11892,
+  #11894, #11895, #11897, #11900, #11903, #11904, #11906, #11907, #11909,
+  #11913, #11914, #11915, #11916, #11917, #11918, #11919)
++ [vimeo] Extract both mixed and separated DASH formats
++ [ruutu] Extract DASH formats
+* [itv] Fix extraction for python 2.6
+
+
+version 2017.01.29
+
+Core
+* [extractor/common] Fix initialization template (#11605, #11825)
++ [extractor/common] Document fragment_base_url and fragment's path fields
+* [extractor/common] Fix duration per DASH segment (#11868)
++ Introduce --autonumber-start option for initial value of %(autonumber)s
+  template (#727, #2702, #9362, #10457, #10529, #11862)
+
+Extractors
++ [azmedien:playlist] Add support for topic and themen playlists (#11817)
+* [npo] Fix subtitles extraction
++ [itv] Extract subtitles
++ [itv] Add support for itv.com (#9240)
++ [mtv81] Add support for mtv81.com (#7619)
++ [vlive] Add support for channels (#11826)
++ [kaltura] Add fallback for fileExt
++ [kaltura] Improve uploader_id extraction
++ [konserthusetplay] Add support for rspoplay.se (#11828)
+
+
+version 2017.01.28
+
+Core
+* [utils] Improve parse_duration
+
+Extractors
+* [crunchyroll] Improve series and season metadata extraction (#11832)
+* [soundcloud] Improve formats extraction and extract audio bitrate
++ [soundcloud] Extract HLS formats
+* [soundcloud] Fix track URL extraction (#11852)
++ [twitch:vod] Expand URL regular expressions (#11846)
+* [aenetworks] Fix season episodes extraction (#11669)
++ [tva] Add support for videos.tva.ca (#11842)
+* [jamendo] Improve and extract more metadata (#11836)
++ [disney] Add support for Disney sites (#7409, #11801, #4975, #11000)
+* [vevo] Remove request to old API and catch API v2 errors
++ [cmt,mtv,southpark] Add support for episode URLs (#11837)
++ [youtube] Add fallback for duration extraction (#11841)
+
+
+version 2017.01.25
+
+Extractors
++ [openload] Fallback video extension to mp4
++ [extractor/generic] Add support for Openload embeds (#11536, #11812)
+* [srgssr] Fix rts video extraction (#11831)
++ [afreecatv:global] Add support for afreeca.tv (#11807)
++ [crackle] Extract vtt subtitles
++ [crackle] Extract multiple resolutions for thumbnails
++ [crackle] Add support for mobile URLs
++ [konserthusetplay] Extract subtitles (#11823)
++ [konserthusetplay] Add support for HLS videos (#11823)
+* [vimeo:review] Fix config URL extraction (#11821)
+
+
+version 2017.01.24
+
+Extractors
+* [pluralsight] Fix extraction (#11820)
++ [nextmedia] Add support for NextTV (壹電視)
+* [24video] Fix extraction (#11811)
+* [youtube:playlist] Fix nonexistent and private playlist detection (#11604)
++ [chirbit] Extract uploader (#11809)
+
+
+version 2017.01.22
+
+Extractors
++ [pornflip] Add support for pornflip.com (#11556, #11795)
+* [chaturbate] Fix extraction (#11797, #11802)
++ [azmedien] Add support for AZ Medien sites (#11784, #11785)
++ [nextmedia] Support redirected URLs
++ [vimeo:channel] Extract videos' titles for playlist entries (#11796)
++ [youtube] Extract episode metadata (#9695, #11774)
++ [cspan] Support Ustream embedded videos (#11547)
++ [1tv] Add support for HLS videos (#11786)
+* [uol] Fix extraction (#11770)
+* [mtv] Relax triforce feed regular expression (#11766)
+
+
+version 2017.01.18
+
+Extractors
+* [bilibili] Fix extraction (#11077)
++ [canalplus] Add fallback for video id (#11764)
+* [20min] Fix extraction (#11683, #11751)
+* [imdb] Extend URL regular expression (#11744)
++ [naver] Add support for tv.naver.com links (#11743)
+
+
+version 2017.01.16
+
+Core
+* [options] Apply custom config to final composite configuration (#11741)
+* [YoutubeDL] Improve protocol auto determining (#11720)
+
+Extractors
+* [xiami] Relax URL regular expressions
+* [xiami] Improve track metadata extraction (#11699)
++ [limelight] Check hand-make direct HTTP links
++ [limelight] Add support for direct HTTP links at video.llnw.net (#11737)
++ [brightcove] Recognize another player ID pattern (#11688)
++ [niconico] Support login via cookies (#7968)
+* [yourupload] Fix extraction (#11601)
++ [beam:live] Add support for beam.pro live streams (#10702, #11596)
+* [vevo] Improve geo restriction detection
++ [dramafever] Add support for URLs with language code (#11714)
+* [cbc] Improve playlist support (#11704)
+
+
+version 2017.01.14
+
+Core
++ [common] Add ability to customize akamai manifest host
++ [utils] Add more date formats
+
+Extractors
+- [mtv] Eliminate _transform_rtmp_url
+* [mtv] Generalize triforce mgid extraction
++ [cmt] Add support for full episodes and video clips (#11623)
++ [mitele] Extract DASH formats
++ [ooyala] Add support for videos with embedToken (#11684)
+* [mixcloud] Fix extraction (#11674)
+* [openload] Fix extraction (#10408)
+* [tv4] Improve extraction (#11698)
+* [freesound] Fix and improve extraction (#11602)
++ [nick] Add support for beta.nick.com (#11655)
+* [mtv,cc] Use HLS by default with native HLS downloader (#11641)
+* [mtv] Fix non-HLS extraction
+
+
+version 2017.01.10
+
+Extractors
+* [youtube] Fix extraction (#11663, #11664)
++ [inc] Add support for inc.com (#11277, #11647)
++ [youtube] Add itag 212 (#11575)
++ [egghead:course] Add support for egghead.io courses
+
+
+version 2017.01.08
+
+Core
+* Fix "invalid escape sequence" errors under Python 3.6 (#11581)
+
+Extractors
++ [hitrecord] Add support for hitrecord.org (#10867, #11626)
+- [videott] Remove extractor
+* [swrmediathek] Improve extraction
+- [sharesix] Remove extractor
+- [aol:features] Remove extractor
+* [sendtonews] Improve info extraction
+* [3sat,phoenix] Fix extraction (#11619)
+* [comedycentral/mtv] Add support for HLS videos (#11600)
+* [discoverygo] Fix JSON data parsing (#11219, #11522)
+
+
+version 2017.01.05
+
+Extractors
++ [zdf] Fix extraction (#11055, #11063)
+* [pornhub:playlist] Improve extraction (#11594)
++ [cctv] Add support for ncpa-classic.com (#11591)
++ [tunein] Add support for embeds (#11579)
+
+
 version 2017.01.02
 
 Extractors

README.md

@@ -88,8 +88,6 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
     --mark-watched                   Mark videos watched (YouTube only)
     --no-mark-watched                Do not mark videos watched (YouTube only)
     --no-color                       Do not emit color codes in output
-    --abort-on-unavailable-fragment  Abort downloading when some fragment is not
-                                     available
 
 ## Network Options:
     --proxy URL                      Use the specified HTTP/HTTPS/SOCKS proxy.
@@ -99,16 +97,13 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
                                      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)
     --geo-verification-proxy URL     Use this proxy to verify the IP address for
                                      some geo-restricted sites. The default
                                      proxy specified by --proxy (or none, if the
                                      options is not present) is used for the
-                                     actual downloading. (experimental)
+                                     actual downloading.
 
 ## Video Selection:
     --playlist-start NUMBER          Playlist video to start at (default is 1)
@@ -139,23 +134,23 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
                                      COUNT views
     --max-views COUNT                Do not download any videos with more than
                                      COUNT views
-    --match-filter FILTER            Generic video filter (experimental).
+    --match-filter FILTER            Generic video filter. Specify any key (see
-                                     Specify any key (see help for -o for a list
+                                     help for -o for a list of available keys)
-                                     of available keys) to match if the key is
+                                     to match if the key is present, !key to
-                                     present, !key to check if the key is not
+                                     check if the key is not present,key >
-                                     present,key > NUMBER (like "comment_count >
+                                     NUMBER (like "comment_count > 12", also
-                                     12", also works with >=, <, <=, !=, =) to
+                                     works with >=, <, <=, !=, =) to compare
-                                     compare against a number, and & to require
+                                     against a number, and & to require multiple
-                                     multiple matches. Values which are not
+                                     matches. Values which are not known are
-                                     known are excluded unless you put a
+                                     excluded unless you put a question mark (?)
-                                     question mark (?) after the operator.For
+                                     after the operator.For example, to only
-                                     example, to only match videos that have
+                                     match videos that have been liked more than
-                                     been liked more than 100 times and disliked
+                                     100 times and disliked less than 50 times
-                                     less than 50 times (or the dislike
+                                     (or the dislike functionality is not
-                                     functionality is not available at the given
+                                     available at the given service), but who
-                                     service), but who also have a description,
+                                     also have a description, use --match-filter
-                                     use --match-filter "like_count > 100 &
+                                     "like_count > 100 & dislike_count <? 50 &
-                                     dislike_count <? 50 & description" .
+                                     description" .
     --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
@@ -178,6 +173,8 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
                                      only)
     --skip-unavailable-fragments     Skip unavailable fragments (DASH and
                                      hlsnative only)
+    --abort-on-unavailable-fragment  Abort downloading when some fragment is not
+                                     available
     --buffer-size SIZE               Size of download buffer (e.g. 1024 or 16K)
                                      (default is 1024)
     --no-resize-buffer               Do not automatically adjust the buffer
@@ -185,6 +182,7 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
                                      automatically resized from an initial value
                                      of SIZE.
     --playlist-reverse               Download playlist videos in reverse order
+    --playlist-random                Download playlist videos in random order
     --xattr-set-filesize             Set file xattribute ytdl.filesize with
                                      expected file size (experimental)
     --hls-prefer-native              Use the native HLS downloader instead of
@@ -210,7 +208,9 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
     --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
+                                     is given (default is 5)
+    --autonumber-start NUMBER        Specify the start value for %(autonumber)s
+                                     (default is 1)
     --restrict-filenames             Restrict filenames to only ASCII
                                      characters, and avoid "&" and spaces in
                                      filenames
@@ -374,7 +374,7 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
                                      avprobe)
     --audio-format FORMAT            Specify audio format: "best", "aac",
                                      "vorbis", "mp3", "m4a", "opus", or "wav";
-                                     "best" by default
+                                     "best" by default; No effect without -x
     --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
@@ -446,6 +446,8 @@ Note that options in configuration file are just the same options aka switches u
 
 You can use `--ignore-config` if you want to disable the configuration file for a particular youtube-dl run.
 
+You can also use `--config-location` if you want to use custom configuration file for a particular youtube-dl run.
+
 ### Authentication with `.netrc` file
 
 You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every youtube-dl execution and prevent tracking plain text passwords in the shell command history. You can achieve this using a [`.netrc` file](http://stackoverflow.com/tags/.netrc/info) on a per extractor basis. For that you will need to create a `.netrc` file in your `$HOME` and restrict permissions to read/write by only you:
@@ -839,7 +841,7 @@ Use the `--cookies` option, for example `--cookies /path/to/cookies/file.txt`.
 
 In order to extract cookies from browser use any conforming browser extension for exporting cookies. For example, [cookies.txt](https://chrome.google.com/webstore/detail/cookiestxt/njabckikapfpffapmjgojcnbfjonfjfg) (for Chrome) or [Export Cookies](https://addons.mozilla.org/en-US/firefox/addon/export-cookies/) (for Firefox).
 
-Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows, `LF` (`\n`) for Linux and `CR` (`\r`) for Mac OS. `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format.
+Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows and `LF` (`\n`) for Unix and Unix-like systems (Linux, Mac OS, etc.). `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format.
 
 Passing cookies to youtube-dl is a good way to workaround login when a particular extractor does not implement it explicitly. Another use case is working around [CAPTCHA](https://en.wikipedia.org/wiki/CAPTCHA) some websites require you to solve in particular cases in order to get access (e.g. YouTube, CloudFlare).
 
@@ -961,7 +963,7 @@ After you have ensured this site is distributing its content legally, you can fo
                 'id': '42',
                 'ext': 'mp4',
                 'title': 'Video title goes here',
-                'thumbnail': 're:^https?://.*\.jpg$',
+                'thumbnail': r're:^https?://.*\.jpg$',
                 # TODO more properties, either as:
                 # * A value
                 # * MD5 checksum; start the string with md5:

docs/supportedsites.md

@@ -11,6 +11,7 @@
  - **4tube**
  - **56.com**
  - **5min**
+ - **6play**
  - **8tracks**
  - **91porn**
  - **9c9media**
@@ -33,7 +34,8 @@
  - **AdobeTVVideo**
  - **AdultSwim**
  - **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network
- - **AfreecaTV**: afreecatv.com
+ - **afreecatv**: afreecatv.com
+ - **afreecatv:global**: afreecatv.com
  - **AirMozilla**
  - **AlJazeera**
  - **Allocine**
@@ -74,6 +76,8 @@
  - **awaan:live**
  - **awaan:season**
  - **awaan:video**
+ - **AZMedien**: AZ Medien videos
+ - **AZMedienPlaylist**: AZ Medien playlists
  - **Azubu**
  - **AzubuLive**
  - **BaiduVideo**: 百度视频
@@ -81,11 +85,13 @@
  - **bambuser:channel**
  - **Bandcamp**
  - **Bandcamp:album**
+ - **bangumi.bilibili.com**: BiliBili番剧
  - **bbc**: BBC
  - **bbc.co.uk**: BBC iPlayer
  - **bbc.co.uk:article**: BBC articles
  - **bbc.co.uk:iplayer:playlist**
  - **bbc.co.uk:playlist**
+ - **Beam:live**
  - **Beatport**
  - **Beeg**
  - **BehindKink**
@@ -198,6 +204,7 @@
  - **Digiteka**
  - **Discovery**
  - **DiscoveryGo**
+ - **Disney**
  - **Dotsub**
  - **DouyuTV**: 斗鱼
  - **DPlay**
@@ -206,7 +213,8 @@
  - **DRBonanza**
  - **Dropbox**
  - **DrTuber**
- - **DRTV**
+ - **drtv**
+ - **drtv:live**
  - **Dumpert**
  - **dvtv**: http://video.aktualne.cz/
  - **dw**
@@ -214,6 +222,7 @@
  - **EaglePlatform**
  - **EbaumsWorld**
  - **EchoMsk**
+ - **egghead:course**: egghead.io course
  - **eHow**
  - **Einthusan**
  - **eitb.tv**
@@ -240,8 +249,9 @@
  - **fc2**
  - **fc2:embed**
  - **Fczenit**
- - **features.aol.com**
  - **fernsehkritik.tv**
+ - **filmon**
+ - **filmon:channel**
  - **Firstpost**
  - **FiveTV**
  - **Flickr**
@@ -273,6 +283,7 @@
  - **Gamersyde**
  - **GameSpot**
  - **GameStar**
+ - **Gaskrank**
  - **Gazeta**
  - **GDCVault**
  - **generic**: Generic downloader that works on some sites
@@ -304,6 +315,7 @@
  - **history:topic**: History.com Topic
  - **hitbox**
  - **hitbox:live**
+ - **HitRecord**
  - **HornBunny**
  - **HotNewHipHop**
  - **HotStar**
@@ -321,6 +333,7 @@
  - **Imgur**
  - **ImgurAlbum**
  - **Ina**
+ - **Inc**
  - **Indavideo**
  - **IndavideoEmbed**
  - **InfoQ**
@@ -330,6 +343,7 @@
  - **IPrima**
  - **iqiyi**: 爱奇艺
  - **Ir90Tv**
+ - **ITV**
  - **ivi**: ivi.ru
  - **ivi:compilation**: ivi.ru compilations
  - **ivideon**: Ivideon TV
@@ -438,6 +452,7 @@
  - **mtg**: MTG services
  - **mtv**
  - **mtv.de**
+ - **mtv81**
  - **mtv:video**
  - **mtvservices:embedded**
  - **MuenchenTV**: münchen.tv
@@ -480,6 +495,7 @@
  - **Newstube**
  - **NextMedia**: 蘋果日報
  - **NextMediaActionNews**: 蘋果日報 - 動新聞
+ - **NextTV**: 壹電視
  - **nfb**: National Film Board of Canada
  - **nfl.com**
  - **NhkVod**
@@ -518,6 +534,7 @@
  - **NRKTV**: NRK TV and NRK Radio
  - **NRKTVDirekte**: NRK TV Direkte and NRK Radio Direkte
  - **NRKTVEpisodes**
+ - **NRKTVSeries**
  - **ntv.ru**
  - **Nuvid**
  - **NYTimes**
@@ -569,6 +586,7 @@
  - **PolskieRadio**
  - **PolskieRadioCategory**
  - **PornCom**
+ - **PornFlip**
  - **PornHd**
  - **PornHub**: PornHub and Thumbzilla
  - **PornHubPlaylist**
@@ -650,7 +668,7 @@
  - **screen.yahoo:search**: Yahoo screen search
  - **Screencast**
  - **ScreencastOMatic**
- - **ScreenJunkies**
+ - **scrippsnetworks:watch**
  - **Seeker**
  - **SenateISVP**
  - **SendtoNews**
@@ -658,10 +676,8 @@
  - **Sexu**
  - **Shahid**
  - **Shared**: shared.sx
- - **ShareSix**
  - **ShowRoomLive**
  - **Sina**
- - **SixPlay**
  - **skynewsarabia:article**
  - **skynewsarabia:video**
  - **SkySports**
@@ -693,10 +709,10 @@
  - **Spiegeltv**
  - **Spike**
  - **Sport5**
- - **SportBox**
  - **SportBoxEmbed**
  - **SportDeutschland**
  - **Sportschau**
+ - **Sprout**
  - **sr:mediathek**: Saarländischer Rundfunk
  - **SRGSSR**
  - **SRGSSRPlay**: srf.ch, rts.ch, rsi.ch, rtr.ch and swissinfo.ch play sites
@@ -779,6 +795,7 @@
  - **TV2Article**
  - **TV3**
  - **TV4**: tv4.se and tv4play.se
+ - **TVA**
  - **TVANouvelles**
  - **TVANouvellesArticle**
  - **TVC**
@@ -845,7 +862,7 @@
  - **videomore:season**
  - **videomore:video**
  - **VideoPremium**
- - **VideoTt**: video.tt - Your True Tube (Currently broken)
+ - **VideoPress**
  - **videoweed**: VideoWeed
  - **Vidio**
  - **vidme**
@@ -880,6 +897,7 @@
  - **vk:uservideos**: VK - User's Videos
  - **vk:wallpost**
  - **vlive**
+ - **vlive:channel**
  - **Vodlocker**
  - **VODPlatform**
  - **VoiceRepublic**

test/test_utils.py

@@ -295,6 +295,9 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unified_strdate('27.02.2016 17:30'), '20160227')
         self.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None)
         self.assertEqual(unified_strdate('Feb 7, 2016 at 6:35 pm'), '20160207')
+        self.assertEqual(unified_strdate('July 15th, 2013'), '20130715')
+        self.assertEqual(unified_strdate('September 1st, 2013'), '20130901')
+        self.assertEqual(unified_strdate('Sep 2nd, 2013'), '20130902')
 
     def test_unified_timestamps(self):
         self.assertEqual(unified_timestamp('December 21, 2010'), 1292889600)
@@ -507,6 +510,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
         self.assertEqual(parse_duration('87 Min.'), 5220)
         self.assertEqual(parse_duration('PT1H0.040S'), 3600.04)
+        self.assertEqual(parse_duration('PT00H03M30SZ'), 210)
 
     def test_fix_xml_ampersands(self):
         self.assertEqual(
@@ -781,12 +785,27 @@ class TestUtil(unittest.TestCase):
         on = js_to_json('["abc", "def",]')
         self.assertEqual(json.loads(on), ['abc', 'def'])
 
+        on = js_to_json('[/*comment\n*/"abc"/*comment\n*/,/*comment\n*/"def",/*comment\n*/]')
+        self.assertEqual(json.loads(on), ['abc', 'def'])
+
+        on = js_to_json('[//comment\n"abc" //comment\n,//comment\n"def",//comment\n]')
+        self.assertEqual(json.loads(on), ['abc', 'def'])
+
         on = js_to_json('{"abc": "def",}')
         self.assertEqual(json.loads(on), {'abc': 'def'})
 
+        on = js_to_json('{/*comment\n*/"abc"/*comment\n*/:/*comment\n*/"def"/*comment\n*/,/*comment\n*/}')
+        self.assertEqual(json.loads(on), {'abc': 'def'})
+
         on = js_to_json('{ 0: /* " \n */ ",]" , }')
         self.assertEqual(json.loads(on), {'0': ',]'})
 
+        on = js_to_json('{ /*comment\n*/0/*comment\n*/: /* " \n */ ",]" , }')
+        self.assertEqual(json.loads(on), {'0': ',]'})
+
+        on = js_to_json('{ 0: // comment\n1 }')
+        self.assertEqual(json.loads(on), {'0': 1})
+
         on = js_to_json(r'["<p>x<\/p>"]')
         self.assertEqual(json.loads(on), ['<p>x</p>'])
 
@@ -796,15 +815,27 @@ class TestUtil(unittest.TestCase):
         on = js_to_json("['a\\\nb']")
         self.assertEqual(json.loads(on), ['ab'])
 
+        on = js_to_json("/*comment\n*/[/*comment\n*/'a\\\nb'/*comment\n*/]/*comment\n*/")
+        self.assertEqual(json.loads(on), ['ab'])
+
         on = js_to_json('{0xff:0xff}')
         self.assertEqual(json.loads(on), {'255': 255})
 
+        on = js_to_json('{/*comment\n*/0xff/*comment\n*/:/*comment\n*/0xff/*comment\n*/}')
+        self.assertEqual(json.loads(on), {'255': 255})
+
         on = js_to_json('{077:077}')
         self.assertEqual(json.loads(on), {'63': 63})
 
+        on = js_to_json('{/*comment\n*/077/*comment\n*/:/*comment\n*/077/*comment\n*/}')
+        self.assertEqual(json.loads(on), {'63': 63})
+
         on = js_to_json('{42:42}')
         self.assertEqual(json.loads(on), {'42': 42})
 
+        on = js_to_json('{/*comment\n*/42/*comment\n*/:/*comment\n*/42/*comment\n*/}')
+        self.assertEqual(json.loads(on), {'42': 42})
+
     def test_extract_attributes(self):
         self.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'})
         self.assertEqual(extract_attributes("<e x='y'>"), {'x': 'y'})

youtube_dl/YoutubeDL.py

@@ -24,6 +24,7 @@ import sys
 import time
 import tokenize
 import traceback
+import random
 
 from .compat import (
     compat_basestring,
@@ -159,6 +160,7 @@ class YoutubeDL(object):
     playlistend:       Playlist item to end at.
     playlist_items:    Specific indices of playlist to download.
     playlistreverse:   Download playlist items in reverse order.
+    playlistrandom:    Download playlist items in random order.
     matchtitle:        Download only matching titles.
     rejecttitle:       Reject downloads for matching titles.
     logger:            Log messages to a logging.Logger instance.
@@ -584,7 +586,7 @@ class YoutubeDL(object):
             if autonumber_size is None:
                 autonumber_size = 5
             autonumber_templ = '%0' + str(autonumber_size) + 'd'
-            template_dict['autonumber'] = autonumber_templ % self._num_downloads
+            template_dict['autonumber'] = autonumber_templ % (self.params.get('autonumber_start', 1) - 1 + self._num_downloads)
             if template_dict.get('playlist_index') is not None:
                 template_dict['playlist_index'] = '%0*d' % (len(str(template_dict['n_entries'])), template_dict['playlist_index'])
             if template_dict.get('resolution') is None:
@@ -842,6 +844,9 @@ class YoutubeDL(object):
             if self.params.get('playlistreverse', False):
                 entries = entries[::-1]
 
+            if self.params.get('playlistrandom', False):
+                random.shuffle(entries)
+
             for i, entry in enumerate(entries, 1):
                 self.to_screen('[download] Downloading video %s of %s' % (i, n_entries))
                 extra = {
@@ -1339,7 +1344,7 @@ class YoutubeDL(object):
                 format['format_id'] = compat_str(i)
             else:
                 # Sanitize format_id from characters used in format selector expression
-                format['format_id'] = re.sub('[\s,/+\[\]()]', '_', format['format_id'])
+                format['format_id'] = re.sub(r'[\s,/+\[\]()]', '_', format['format_id'])
             format_id = format['format_id']
             if format_id not in formats_dict:
                 formats_dict[format_id] = []
@@ -1363,7 +1368,7 @@ class YoutubeDL(object):
                 format['ext'] = determine_ext(format['url']).lower()
             # Automatically determine protocol if missing (useful for format
             # selection purposes)
-            if 'protocol' not in format:
+            if format.get('protocol') is None:
                 format['protocol'] = determine_protocol(format)
             # Add HTTP headers, so that external programs can use them from the
             # json output

youtube_dl/__init__.py

@@ -133,6 +133,12 @@ def _real_main(argv=None):
         parser.error('TV Provider account username missing\n')
     if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
         parser.error('using output template conflicts with using title, video ID or auto number')
+    if opts.autonumber_size is not None:
+        if opts.autonumber_size <= 0:
+            parser.error('auto number size must be positive')
+    if opts.autonumber_start is not None:
+        if opts.autonumber_start < 0:
+            parser.error('auto number start must be positive or 0')
     if opts.usetitle and opts.useid:
         parser.error('using title conflicts with using video ID')
     if opts.username is not None and opts.password is None:
@@ -321,6 +327,7 @@ def _real_main(argv=None):
         'listformats': opts.listformats,
         'outtmpl': outtmpl,
         'autonumber_size': opts.autonumber_size,
+        'autonumber_start': opts.autonumber_start,
         'restrictfilenames': opts.restrictfilenames,
         'ignoreerrors': opts.ignoreerrors,
         'force_generic_extractor': opts.force_generic_extractor,
@@ -337,6 +344,7 @@ def _real_main(argv=None):
         'playliststart': opts.playliststart,
         'playlistend': opts.playlistend,
         'playlistreverse': opts.playlist_reverse,
+        'playlistrandom': opts.playlist_random,
         'noplaylist': opts.noplaylist,
         'logtostderr': opts.outtmpl == '-',
         'consoletitle': opts.consoletitle,

youtube_dl/compat.py

@@ -2344,7 +2344,7 @@ try:
     from urllib.parse import unquote_plus as compat_urllib_parse_unquote_plus
 except ImportError:  # Python 2
     _asciire = (compat_urllib_parse._asciire if hasattr(compat_urllib_parse, '_asciire')
-                else re.compile('([\x00-\x7f]+)'))
+                else re.compile(r'([\x00-\x7f]+)'))
 
     # HACK: The following are the correct unquote_to_bytes, unquote and unquote_plus
     # implementations from cpython 3.4.3's stdlib. Python 2's version
@@ -2529,6 +2529,24 @@ else:
                 el.text = el.text.decode('utf-8')
         return doc
 
+if hasattr(etree, 'register_namespace'):
+    compat_etree_register_namespace = etree.register_namespace
+else:
+    def compat_etree_register_namespace(prefix, uri):
+        """Register a namespace prefix.
+        The registry is global, and any existing mapping for either the
+        given prefix or the namespace URI will be removed.
+        *prefix* is the namespace prefix, *uri* is a namespace uri. Tags and
+        attributes in this namespace will be serialized with prefix if possible.
+        ValueError is raised if prefix is reserved or is invalid.
+        """
+        if re.match(r"ns\d+$", prefix):
+            raise ValueError("Prefix format reserved for internal use")
+        for k, v in list(etree._namespace_map.items()):
+            if k == uri or v == prefix:
+                del etree._namespace_map[k]
+        etree._namespace_map[uri] = prefix
+
 if sys.version_info < (2, 7):
     # Here comes the crazy part: In 2.6, if the xpath is a unicode,
     # .//node does not match if a node is a direct child of . !
@@ -2865,6 +2883,7 @@ __all__ = [
     'compat_cookiejar',
     'compat_cookies',
     'compat_etree_fromstring',
+    'compat_etree_register_namespace',
     'compat_expanduser',
     'compat_get_terminal_size',
     'compat_getenv',

youtube_dl/downloader/external.py

@@ -17,6 +17,7 @@ from ..utils import (
     encodeArgument,
     handle_youtubedl_headers,
     check_executable,
+    is_outdated_version,
 )
 
 
@@ -198,6 +199,15 @@ class FFmpegFD(ExternalFD):
 
         args = [ffpp.executable, '-y']
 
+        seekable = info_dict.get('_seekable')
+        if seekable is not None:
+            # setting -seekable prevents ffmpeg from guessing if the server
+            # supports seeking(by adding the header `Range: bytes=0-`), which
+            # can cause problems in some cases
+            # https://github.com/rg3/youtube-dl/issues/11800#issuecomment-275037127
+            # http://trac.ffmpeg.org/ticket/6125#comment:10
+            args += ['-seekable', '1' if seekable else '0']
+
         args += self._configuration_args()
 
         # start_time = info_dict.get('start_time') or 0
@@ -264,7 +274,9 @@ class FFmpegFD(ExternalFD):
             if self.params.get('hls_use_mpegts', False) or tmpfilename == '-':
                 args += ['-f', 'mpegts']
             else:
-                args += ['-f', 'mp4', '-bsf:a', 'aac_adtstoasc']
+                args += ['-f', 'mp4']
+                if (ffpp.basename == 'ffmpeg' and is_outdated_version(ffpp._versions['ffmpeg'], '3.2', False)) and (not info_dict.get('acodec') or info_dict['acodec'].split('.')[0] in ('aac', 'mp4a')):
+                    args += ['-bsf:a', 'aac_adtstoasc']
         elif protocol == 'rtmp':
             args += ['-f', 'flv']
         else:

youtube_dl/downloader/fragment.py

@@ -61,6 +61,7 @@ class FragmentFD(FileDownloader):
                 'noprogress': True,
                 'ratelimit': self.params.get('ratelimit'),
                 'retries': self.params.get('retries', 0),
+                'nopart': self.params.get('nopart', False),
                 'test': self.params.get('test', False),
             }
         )

youtube_dl/extractor/abcnews.py

@@ -23,7 +23,7 @@ class AbcNewsVideoIE(AMPIE):
             'title': '\'This Week\' Exclusive: Iran\'s Foreign Minister Zarif',
             'description': 'George Stephanopoulos goes one-on-one with Iranian Foreign Minister Dr. Javad Zarif.',
             'duration': 180,
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
         },
         'params': {
             # m3u8 download
@@ -59,7 +59,7 @@ class AbcNewsIE(InfoExtractor):
             'display_id': 'dramatic-video-rare-death-job-america',
             'title': 'Occupational Hazards',
             'description': 'Nightline investigates the dangers that lurk at various jobs.',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'upload_date': '20100428',
             'timestamp': 1272412800,
         },

youtube_dl/extractor/abcotvs.py

@@ -23,7 +23,7 @@ class ABCOTVSIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'East Bay museum celebrates vintage synthesizers',
                 'description': 'md5:a4f10fb2f2a02565c1749d4adbab4b10',
-                'thumbnail': 're:^https?://.*\.jpg$',
+                'thumbnail': r're:^https?://.*\.jpg$',
                 'timestamp': 1421123075,
                 'upload_date': '20150113',
                 'uploader': 'Jonathan Bloom',

youtube_dl/extractor/adobetv.py

@@ -30,7 +30,7 @@ class AdobeTVIE(AdobeTVBaseIE):
             'ext': 'mp4',
             'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop',
             'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311',
-            'thumbnail': 're:https?://.*\.jpg$',
+            'thumbnail': r're:https?://.*\.jpg$',
             'upload_date': '20110914',
             'duration': 60,
             'view_count': int,

youtube_dl/extractor/aenetworks.py

@@ -87,7 +87,7 @@ class AENetworksIE(AENetworksBaseIE):
                     self._html_search_meta('aetn:SeriesTitle', webpage))
             elif url_parts_len == 2:
                 entries = []
-                for episode_item in re.findall(r'(?s)<div[^>]+class="[^"]*episode-item[^"]*"[^>]*>', webpage):
+                for episode_item in re.findall(r'(?s)<[^>]+class="[^"]*(?:episode|program)-item[^"]*"[^>]*>', webpage):
                     episode_attributes = extract_attributes(episode_item)
                     episode_url = compat_urlparse.urljoin(
                         url, episode_attributes['data-canonical'])

youtube_dl/extractor/afreecatv.py

@@ -18,6 +18,7 @@ from ..utils import (
 
 
 class AfreecaTVIE(InfoExtractor):
+    IE_NAME = 'afreecatv'
     IE_DESC = 'afreecatv.com'
     _VALID_URL = r'''(?x)
                     https?://
@@ -143,3 +144,107 @@ class AfreecaTVIE(InfoExtractor):
                 expected=True)
 
         return info
+
+
+class AfreecaTVGlobalIE(AfreecaTVIE):
+    IE_NAME = 'afreecatv:global'
+    _VALID_URL = r'https?://(?:www\.)?afreeca\.tv/(?P<channel_id>\d+)(?:/v/(?P<video_id>\d+))?'
+    _TESTS = [{
+        'url': 'http://afreeca.tv/36853014/v/58301',
+        'info_dict': {
+            'id': '58301',
+            'title': 'tryhard top100',
+            'uploader_id': '36853014',
+            'uploader': 'makgi Hearthstone Live!',
+        },
+        'playlist_count': 3,
+    }]
+
+    def _real_extract(self, url):
+        channel_id, video_id = re.match(self._VALID_URL, url).groups()
+        video_type = 'video' if video_id else 'live'
+        query = {
+            'pt': 'view',
+            'bid': channel_id,
+        }
+        if video_id:
+            query['vno'] = video_id
+        video_data = self._download_json(
+            'http://api.afreeca.tv/%s/view_%s.php' % (video_type, video_type),
+            video_id or channel_id, query=query)['channel']
+
+        if video_data.get('result') != 1:
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, video_data['remsg']))
+
+        title = video_data['title']
+
+        info = {
+            'thumbnail': video_data.get('thumb'),
+            'view_count': int_or_none(video_data.get('vcnt')),
+            'age_limit': int_or_none(video_data.get('grade')),
+            'uploader_id': channel_id,
+            'uploader': video_data.get('cname'),
+        }
+
+        if video_id:
+            entries = []
+            for i, f in enumerate(video_data.get('flist', [])):
+                video_key = self.parse_video_key(f.get('key', ''))
+                f_url = f.get('file')
+                if not video_key or not f_url:
+                    continue
+                entries.append({
+                    'id': '%s_%s' % (video_id, video_key.get('part', i + 1)),
+                    'title': title,
+                    'upload_date': video_key.get('upload_date'),
+                    'duration': int_or_none(f.get('length')),
+                    'url': f_url,
+                    'protocol': 'm3u8_native',
+                    'ext': 'mp4',
+                })
+
+            info.update({
+                'id': video_id,
+                'title': title,
+                'duration': int_or_none(video_data.get('length')),
+            })
+            if len(entries) > 1:
+                info['_type'] = 'multi_video'
+                info['entries'] = entries
+            elif len(entries) == 1:
+                i = entries[0].copy()
+                i.update(info)
+                info = i
+        else:
+            formats = []
+            for s in video_data.get('strm', []):
+                s_url = s.get('purl')
+                if not s_url:
+                    continue
+                stype = s.get('stype')
+                if stype == 'HLS':
+                    formats.extend(self._extract_m3u8_formats(
+                        s_url, channel_id, 'mp4', m3u8_id=stype, fatal=False))
+                elif stype == 'RTMP':
+                    format_id = [stype]
+                    label = s.get('label')
+                    if label:
+                        format_id.append(label)
+                    formats.append({
+                        'format_id': '-'.join(format_id),
+                        'url': s_url,
+                        'tbr': int_or_none(s.get('bps')),
+                        'height': int_or_none(s.get('brt')),
+                        'ext': 'flv',
+                        'rtmp_live': True,
+                    })
+            self._sort_formats(formats)
+
+            info.update({
+                'id': channel_id,
+                'title': self._live_title(title),
+                'is_live': True,
+                'formats': formats,
+            })
+
+        return info

youtube_dl/extractor/airmozilla.py

@@ -20,7 +20,7 @@ class AirMozillaIE(InfoExtractor):
             'id': '6x4q2w',
             'ext': 'mp4',
             'title': 'Privacy Lab - a meetup for privacy minded people in San Francisco',
-            'thumbnail': 're:https?://vid\.ly/(?P<id>[0-9a-z-]+)/poster',
+            'thumbnail': r're:https?://vid\.ly/(?P<id>[0-9a-z-]+)/poster',
             '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',

youtube_dl/extractor/allocine.py

@@ -21,7 +21,7 @@ class AllocineIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Astérix - Le Domaine des Dieux Teaser VF',
             'description': 'md5:4a754271d9c6f16c72629a8a993ee884',
-            'thumbnail': 're:http://.*\.jpg',
+            'thumbnail': r're:http://.*\.jpg',
         },
     }, {
         'url': 'http://www.allocine.fr/video/player_gen_cmedia=19540403&cfilm=222257.html',
@@ -32,7 +32,7 @@ class AllocineIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Planes 2 Bande-annonce VF',
             'description': 'Regardez la bande annonce du film Planes 2 (Planes 2 Bande-annonce VF). Planes 2, un film de Roberts Gannaway',
-            'thumbnail': 're:http://.*\.jpg',
+            'thumbnail': r're:http://.*\.jpg',
         },
     }, {
         'url': 'http://www.allocine.fr/video/player_gen_cmedia=19544709&cfilm=181290.html',
@@ -43,7 +43,7 @@ class AllocineIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Dragons 2 - Bande annonce finale VF',
             'description': 'md5:6cdd2d7c2687d4c6aafe80a35e17267a',
-            'thumbnail': 're:http://.*\.jpg',
+            'thumbnail': r're:http://.*\.jpg',
         },
     }, {
         'url': 'http://www.allocine.fr/video/video-19550147/',
@@ -53,7 +53,7 @@ class AllocineIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Faux Raccord N°123 - Les gaffes de Cliffhanger',
             'description': 'md5:bc734b83ffa2d8a12188d9eb48bb6354',
-            'thumbnail': 're:http://.*\.jpg',
+            'thumbnail': r're:http://.*\.jpg',
         },
     }]
 

youtube_dl/extractor/alphaporno.py

@@ -19,7 +19,7 @@ class AlphaPornoIE(InfoExtractor):
             'display_id': 'sensual-striptease-porn-with-samantha-alexandra',
             'ext': 'mp4',
             'title': 'Sensual striptease porn with Samantha Alexandra',
-            'thumbnail': 're:https?://.*\.jpg$',
+            'thumbnail': r're:https?://.*\.jpg$',
             'timestamp': 1418694611,
             'upload_date': '20141216',
             'duration': 387,

youtube_dl/extractor/aol.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 class AolIE(InfoExtractor):
     IE_NAME = 'on.aol.com'
-    _VALID_URL = r'(?:aol-video:|https?://on\.aol\.com/(?:[^/]+/)*(?:[^/?#&]+-)?)(?P<id>[^/?#&]+)'
+    _VALID_URL = r'(?:aol-video:|https?://(?:(?:www|on)\.)?aol\.com/(?:[^/]+/)*(?:[^/?#&]+-)?)(?P<id>[^/?#&]+)'
 
     _TESTS = [{
         # video with 5min ID
@@ -33,7 +33,7 @@ class AolIE(InfoExtractor):
         }
     }, {
         # video with vidible ID
-        'url': 'http://on.aol.com/video/netflix-is-raising-rates-5707d6b8e4b090497b04f706?context=PC:homepage:PL1944:1460189336183',
+        'url': 'http://www.aol.com/video/view/netflix-is-raising-rates/5707d6b8e4b090497b04f706/',
         'info_dict': {
             'id': '5707d6b8e4b090497b04f706',
             'ext': 'mp4',
@@ -108,30 +108,3 @@ class AolIE(InfoExtractor):
             'uploader': video_data.get('videoOwner'),
             'formats': formats,
         }
-
-
-class AolFeaturesIE(InfoExtractor):
-    IE_NAME = 'features.aol.com'
-    _VALID_URL = r'https?://features\.aol\.com/video/(?P<id>[^/?#]+)'
-
-    _TESTS = [{
-        'url': 'http://features.aol.com/video/behind-secret-second-careers-late-night-talk-show-hosts',
-        'md5': '7db483bb0c09c85e241f84a34238cc75',
-        'info_dict': {
-            'id': '519507715',
-            'ext': 'mp4',
-            'title': 'What To Watch - February 17, 2016',
-        },
-        'add_ie': ['FiveMin'],
-        'params': {
-            # encrypted m3u8 download
-            'skip_download': True,
-        },
-    }]
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-        return self.url_result(self._search_regex(
-            r'<script type="text/javascript" src="(https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js[^"]+)"',
-            webpage, '5min embed url'), 'FiveMin')

youtube_dl/extractor/ard.py

@@ -253,7 +253,7 @@ class ARDIE(InfoExtractor):
             'duration': 2600,
             'title': 'Die Story im Ersten: Mission unter falscher Flagge',
             'upload_date': '20140804',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
         },
         'skip': 'HTTP Error 404: Not Found',
     }

youtube_dl/extractor/atresplayer.py

@@ -30,7 +30,7 @@ class AtresPlayerIE(InfoExtractor):
                 'title': 'Especial Solidario de Nochebuena',
                 'description': 'md5:e2d52ff12214fa937107d21064075bf1',
                 'duration': 5527.6,
-                'thumbnail': 're:^https?://.*\.jpg$',
+                'thumbnail': r're:^https?://.*\.jpg$',
             },
             'skip': 'This video is only available for registered users'
         },
@@ -43,7 +43,7 @@ class AtresPlayerIE(InfoExtractor):
                 'title': 'David Bustamante',
                 'description': 'md5:f33f1c0a05be57f6708d4dd83a3b81c6',
                 'duration': 1439.0,
-                'thumbnail': 're:^https?://.*\.jpg$',
+                'thumbnail': r're:^https?://.*\.jpg$',
             },
         },
         {

youtube_dl/extractor/atttechchannel.py

@@ -14,7 +14,7 @@ class ATTTechChannelIE(InfoExtractor):
             'ext': 'flv',
             'title': 'AT&T Archives : The UNIX System: Making Computers Easier to Use',
             'description': 'A 1982 film about UNIX is the foundation for software in use around Bell Labs and AT&T.',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'upload_date': '20140127',
         },
         'params': {

youtube_dl/extractor/audioboom.py

@@ -17,7 +17,7 @@ class AudioBoomIE(InfoExtractor):
             'description': 'Guest:   Nate Davis - NFL free agency,   Guest:   Stan Gans',
             'duration': 2245.72,
             'uploader': 'Steve Czaban',
-            'uploader_url': 're:https?://(?:www\.)?audioboom\.com/channel/steveczabanyahoosportsradio',
+            'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channel/steveczabanyahoosportsradio',
         }
     }, {
         'url': 'https://audioboom.com/posts/4279833-3-09-2016-czaban-hour-3?t=0',

youtube_dl/extractor/azmedien.py

@@ -0,0 +1,172 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from .kaltura import KalturaIE
+from ..utils import (
+    get_element_by_id,
+    strip_or_none,
+    urljoin,
+)
+
+
+class AZMedienBaseIE(InfoExtractor):
+    def _kaltura_video(self, partner_id, entry_id):
+        return self.url_result(
+            'kaltura:%s:%s' % (partner_id, entry_id), ie=KalturaIE.ie_key(),
+            video_id=entry_id)
+
+
+class AZMedienIE(AZMedienBaseIE):
+    IE_DESC = 'AZ Medien videos'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?
+                        (?:
+                            telezueri\.ch|
+                            telebaern\.tv|
+                            telem1\.ch
+                        )/
+                        [0-9]+-show-[^/\#]+
+                        (?:
+                            /[0-9]+-episode-[^/\#]+
+                            (?:
+                                /[0-9]+-segment-(?:[^/\#]+\#)?|
+                                \#
+                            )|
+                            \#
+                        )
+                        (?P<id>[^\#]+)
+                    '''
+
+    _TESTS = [{
+        # URL with 'segment'
+        'url': 'http://www.telezueri.ch/62-show-zuerinews/13772-episode-sonntag-18-dezember-2016/32419-segment-massenabweisungen-beim-hiltl-club-wegen-pelzboom',
+        'info_dict': {
+            'id': '1_2444peh4',
+            'ext': 'mov',
+            'title': 'Massenabweisungen beim Hiltl Club wegen Pelzboom',
+            'description': 'md5:9ea9dd1b159ad65b36ddcf7f0d7c76a8',
+            'uploader_id': 'TeleZ?ri',
+            'upload_date': '20161218',
+            'timestamp': 1482084490,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # URL with 'segment' and fragment:
+        'url': 'http://www.telebaern.tv/118-show-news/14240-episode-dienstag-17-januar-2017/33666-segment-achtung-gefahr#zu-wenig-pflegerinnen-und-pfleger',
+        'only_matching': True
+    }, {
+        # URL with 'episode' and fragment:
+        'url': 'http://www.telem1.ch/47-show-sonntalk/13986-episode-soldaten-fuer-grenzschutz-energiestrategie-obama-bilanz#soldaten-fuer-grenzschutz-energiestrategie-obama-bilanz',
+        'only_matching': True
+    }, {
+        # URL with 'show' and fragment:
+        'url': 'http://www.telezueri.ch/66-show-sonntalk#burka-plakate-trump-putin-china-besuch',
+        'only_matching': True
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        partner_id = self._search_regex(
+            r'<script[^>]+src=["\'](?:https?:)?//(?:[^/]+\.)?kaltura\.com(?:/[^/]+)*/(?:p|partner_id)/([0-9]+)',
+            webpage, 'kaltura partner id')
+        entry_id = self._html_search_regex(
+            r'<a[^>]+data-id=(["\'])(?P<id>(?:(?!\1).)+)\1[^>]+data-slug=["\']%s'
+            % re.escape(video_id), webpage, 'kaltura entry id', group='id')
+
+        return self._kaltura_video(partner_id, entry_id)
+
+
+class AZMedienPlaylistIE(AZMedienBaseIE):
+    IE_DESC = 'AZ Medien playlists'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?
+                        (?:
+                            telezueri\.ch|
+                            telebaern\.tv|
+                            telem1\.ch
+                        )/
+                        (?P<id>[0-9]+-
+                            (?:
+                                show|
+                                topic|
+                                themen
+                            )-[^/\#]+
+                            (?:
+                                /[0-9]+-episode-[^/\#]+
+                            )?
+                        )$
+                    '''
+
+    _TESTS = [{
+        # URL with 'episode'
+        'url': 'http://www.telebaern.tv/118-show-news/13735-episode-donnerstag-15-dezember-2016',
+        'info_dict': {
+            'id': '118-show-news/13735-episode-donnerstag-15-dezember-2016',
+            'title': 'News - Donnerstag, 15. Dezember 2016',
+        },
+        'playlist_count': 9,
+    }, {
+        # URL with 'themen'
+        'url': 'http://www.telem1.ch/258-themen-tele-m1-classics',
+        'info_dict': {
+            'id': '258-themen-tele-m1-classics',
+            'title': 'Tele M1 Classics',
+        },
+        'playlist_mincount': 15,
+    }, {
+        # URL with 'topic', contains nested playlists
+        'url': 'http://www.telezueri.ch/219-topic-aera-trump-hat-offiziell-begonnen',
+        'only_matching': True,
+    }, {
+        # URL with 'show' only
+        'url': 'http://www.telezueri.ch/86-show-talktaeglich',
+        'only_matching': True
+    }]
+
+    def _real_extract(self, url):
+        show_id = self._match_id(url)
+        webpage = self._download_webpage(url, show_id)
+
+        entries = []
+
+        partner_id = self._search_regex(
+            r'src=["\'](?:https?:)?//(?:[^/]+\.)kaltura\.com/(?:[^/]+/)*(?:p|partner_id)/(\d+)',
+            webpage, 'kaltura partner id', default=None)
+
+        if partner_id:
+            entries = [
+                self._kaltura_video(partner_id, m.group('id'))
+                for m in re.finditer(
+                    r'data-id=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage)]
+
+        if not entries:
+            entries = [
+                self.url_result(m.group('url'), ie=AZMedienIE.ie_key())
+                for m in re.finditer(
+                    r'<a[^>]+data-real=(["\'])(?P<url>http.+?)\1', webpage)]
+
+        if not entries:
+            entries = [
+                # May contain nested playlists (e.g. [1]) thus no explicit
+                # ie_key
+                # 1. http://www.telezueri.ch/219-topic-aera-trump-hat-offiziell-begonnen)
+                self.url_result(urljoin(url, m.group('url')))
+                for m in re.finditer(
+                    r'<a[^>]+name=[^>]+href=(["\'])(?P<url>/.+?)\1', webpage)]
+
+        title = self._search_regex(
+            r'episodeShareTitle\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1',
+            webpage, 'title',
+            default=strip_or_none(get_element_by_id(
+                'video-title', webpage)), group='title')
+
+        return self.playlist_result(entries, show_id, title)

youtube_dl/extractor/azubu.py

@@ -21,7 +21,7 @@ class AzubuIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': '2014 HOT6 CUP LAST BIG MATCH Ro8 Day 1',
                 'description': 'md5:d06bdea27b8cc4388a90ad35b5c66c01',
-                'thumbnail': 're:^https?://.*\.jpe?g',
+                'thumbnail': r're:^https?://.*\.jpe?g',
                 'timestamp': 1417523507.334,
                 'upload_date': '20141202',
                 'duration': 9988.7,
@@ -38,7 +38,7 @@ class AzubuIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'Fnatic at Worlds 2014: Toyz - "I love Rekkles, he has amazing mechanics"',
                 'description': 'md5:4a649737b5f6c8b5c5be543e88dc62af',
-                'thumbnail': 're:^https?://.*\.jpe?g',
+                'thumbnail': r're:^https?://.*\.jpe?g',
                 'timestamp': 1410530893.320,
                 'upload_date': '20140912',
                 'duration': 172.385,

youtube_dl/extractor/bandcamp.py

@@ -209,6 +209,15 @@ class BandcampAlbumIE(InfoExtractor):
             'id': 'entropy-ep',
         },
         'playlist_mincount': 3,
+    }, {
+        # not all tracks have songs
+        'url': 'https://insulters.bandcamp.com/album/we-are-the-plague',
+        'info_dict': {
+            'id': 'we-are-the-plague',
+            'title': 'WE ARE THE PLAGUE',
+            'uploader_id': 'insulters',
+        },
+        'playlist_count': 2,
     }]
 
     def _real_extract(self, url):
@@ -217,12 +226,16 @@ class BandcampAlbumIE(InfoExtractor):
         album_id = mobj.group('album_id')
         playlist_id = album_id or uploader_id
         webpage = self._download_webpage(url, playlist_id)
-        tracks_paths = re.findall(r'<a href="(.*?)" itemprop="url">', webpage)
+        track_elements = re.findall(
-        if not tracks_paths:
+            r'(?s)<div[^>]*>(.*?<a[^>]+href="([^"]+?)"[^>]+itemprop="url"[^>]*>.*?)</div>', webpage)
+        if not track_elements:
             raise ExtractorError('The page doesn\'t contain any tracks')
+        # Only tracks with duration info have songs
         entries = [
             self.url_result(compat_urlparse.urljoin(url, t_path), ie=BandcampIE.ie_key())
-            for t_path in tracks_paths]
+            for elem_content, t_path in track_elements
+            if self._html_search_meta('duration', elem_content, default=None)]
+
         title = self._html_search_regex(
             r'album_title\s*:\s*"((?:\\.|[^"\\])+?)"',
             webpage, 'title', fatal=False)

youtube_dl/extractor/beampro.py

@@ -0,0 +1,73 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    clean_html,
+    compat_str,
+    int_or_none,
+    parse_iso8601,
+    try_get,
+)
+
+
+class BeamProLiveIE(InfoExtractor):
+    IE_NAME = 'Beam:live'
+    _VALID_URL = r'https?://(?:\w+\.)?beam\.pro/(?P<id>[^/?#&]+)'
+    _RATINGS = {'family': 0, 'teen': 13, '18+': 18}
+    _TEST = {
+        'url': 'http://www.beam.pro/niterhayven',
+        'info_dict': {
+            'id': '261562',
+            'ext': 'mp4',
+            'title': 'Introducing The Witcher 3 //  The Grind Starts Now!',
+            'description': 'md5:0b161ac080f15fe05d18a07adb44a74d',
+            'thumbnail': r're:https://.*\.jpg$',
+            'timestamp': 1483477281,
+            'upload_date': '20170103',
+            'uploader': 'niterhayven',
+            'uploader_id': '373396',
+            'age_limit': 18,
+            'is_live': True,
+            'view_count': int,
+        },
+        'skip': 'niterhayven is offline',
+        'params': {
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        channel_name = self._match_id(url)
+
+        chan = self._download_json(
+            'https://beam.pro/api/v1/channels/%s' % channel_name, channel_name)
+
+        if chan.get('online') is False:
+            raise ExtractorError(
+                '{0} is offline'.format(channel_name), expected=True)
+
+        channel_id = chan['id']
+
+        formats = self._extract_m3u8_formats(
+            'https://beam.pro/api/v1/channels/%s/manifest.m3u8' % channel_id,
+            channel_name, ext='mp4', m3u8_id='hls', fatal=False)
+        self._sort_formats(formats)
+
+        user_id = chan.get('userId') or try_get(chan, lambda x: x['user']['id'])
+
+        return {
+            'id': compat_str(chan.get('id') or channel_name),
+            'title': self._live_title(chan.get('name') or channel_name),
+            'description': clean_html(chan.get('description')),
+            'thumbnail': try_get(chan, lambda x: x['thumbnail']['url'], compat_str),
+            'timestamp': parse_iso8601(chan.get('updatedAt')),
+            'uploader': chan.get('token') or try_get(
+                chan, lambda x: x['user']['username'], compat_str),
+            'uploader_id': compat_str(user_id) if user_id else None,
+            'age_limit': self._RATINGS.get(chan.get('audience')),
+            'is_live': True,
+            'view_count': int_or_none(chan.get('viewersTotal')),
+            'formats': formats,
+        }

youtube_dl/extractor/bet.py

@@ -17,7 +17,7 @@ class BetIE(MTVServicesInfoExtractor):
                 'description': 'President Obama urges persistence in confronting racism and bias.',
                 'duration': 1534,
                 'upload_date': '20141208',
-                'thumbnail': 're:(?i)^https?://.*\.jpg$',
+                'thumbnail': r're:(?i)^https?://.*\.jpg$',
                 'subtitles': {
                     'en': 'mincount:2',
                 }
@@ -37,7 +37,7 @@ class BetIE(MTVServicesInfoExtractor):
                 'description': 'A BET News special.',
                 'duration': 1696,
                 'upload_date': '20141125',
-                'thumbnail': 're:(?i)^https?://.*\.jpg$',
+                'thumbnail': r're:(?i)^https?://.*\.jpg$',
                 'subtitles': {
                     'en': 'mincount:2',
                 }

youtube_dl/extractor/bild.py

@@ -19,7 +19,7 @@ class BildIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Das können die  neuen iPads',
             'description': 'md5:a4058c4fa2a804ab59c00d7244bbf62f',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'duration': 196,
         }
     }

youtube_dl/extractor/bilibili.py

@@ -5,19 +5,27 @@ import hashlib
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_parse_qs
+from ..compat import (
+    compat_parse_qs,
+    compat_urlparse,
+)
 from ..utils import (
+    ExtractorError,
     int_or_none,
     float_or_none,
+    parse_iso8601,
+    smuggle_url,
+    strip_jsonp,
     unified_timestamp,
+    unsmuggle_url,
     urlencode_postdata,
 )
 
 
 class BiliBiliIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.|bangumi\.|)bilibili\.(?:tv|com)/(?:video/av|anime/v/)(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.|bangumi\.|)bilibili\.(?:tv|com)/(?:video/av|anime/(?P<anime_id>\d+)/play#)(?P<id>\d+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.bilibili.tv/video/av1074402/',
         'md5': '9fa226fe2b8a9a4d5a69b4c6a183417e',
         'info_dict': {
@@ -28,29 +36,65 @@ class BiliBiliIE(InfoExtractor):
             'duration': 308.315,
             'timestamp': 1398012660,
             'upload_date': '20140420',
-            'thumbnail': 're:^https?://.+\.jpg',
+            'thumbnail': r're:^https?://.+\.jpg',
             'uploader': '菊子桑',
             'uploader_id': '156160',
         },
-    }
+    }, {
+        # Tested in BiliBiliBangumiIE
+        'url': 'http://bangumi.bilibili.com/anime/1869/play#40062',
+        'only_matching': True,
+    }, {
+        'url': 'http://bangumi.bilibili.com/anime/5802/play#100643',
+        'md5': '3f721ad1e75030cc06faf73587cfec57',
+        'info_dict': {
+            'id': '100643',
+            'ext': 'mp4',
+            'title': 'CHAOS;CHILD',
+            'description': '如果你是神明，并且能够让妄想成为现实。那你会进行怎么样的妄想？是淫靡的世界？独裁社会？毁灭性的制裁？还是……2015年，涩谷。从6年前发生的大灾害“涩谷地震”之后复兴了的这个街区里新设立的私立高中...',
+        },
+        'skip': 'Geo-restricted to China',
+    }]
 
-    _APP_KEY = '6f90a59ac58a4123'
+    _APP_KEY = '84956560bc028eb7'
-    _BILIBILI_KEY = '0bfd84cc3940035173f35e6777508326'
+    _BILIBILI_KEY = '94aba54af9065f71de72f5508f1cd42e'
+
+    def _report_error(self, result):
+        if 'message' in result:
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, result['message']), expected=True)
+        elif 'code' in result:
+            raise ExtractorError('%s returns error %d' % (self.IE_NAME, result['code']), expected=True)
+        else:
+            raise ExtractorError('Can\'t extract Bangumi episode ID')
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        url, smuggled_data = unsmuggle_url(url, {})
+
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        anime_id = mobj.group('anime_id')
         webpage = self._download_webpage(url, video_id)
 
-        if 'anime/v' not in url:
+        if 'anime/' not in url:
             cid = compat_parse_qs(self._search_regex(
                 [r'EmbedPlayer\([^)]+,\s*"([^"]+)"\)',
                  r'<iframe[^>]+src="https://secure\.bilibili\.com/secure,([^"]+)"'],
                 webpage, 'player parameters'))['cid'][0]
         else:
+            if 'no_bangumi_tip' not in smuggled_data:
+                self.to_screen('Downloading episode %s. To download all videos in anime %s, re-run youtube-dl with %s' % (
+                    video_id, anime_id, compat_urlparse.urljoin(url, '//bangumi.bilibili.com/anime/%s' % anime_id)))
+            headers = {
+                'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
+            }
+            headers.update(self.geo_verification_headers())
+
             js = self._download_json(
                 'http://bangumi.bilibili.com/web_api/get_source', video_id,
                 data=urlencode_postdata({'episode_id': video_id}),
-                headers={'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8'})
+                headers=headers)
+            if 'result' not in js:
+                self._report_error(js)
             cid = js['result']['cid']
 
         payload = 'appkey=%s&cid=%s&otype=json&quality=2&type=mp4' % (self._APP_KEY, cid)
@@ -58,7 +102,11 @@ class BiliBiliIE(InfoExtractor):
 
         video_info = self._download_json(
             'http://interface.bilibili.com/playurl?%s&sign=%s' % (payload, sign),
-            video_id, note='Downloading video info page')
+            video_id, note='Downloading video info page',
+            headers=self.geo_verification_headers())
+
+        if 'durl' not in video_info:
+            self._report_error(video_info)
 
         entries = []
 
@@ -85,7 +133,7 @@ class BiliBiliIE(InfoExtractor):
         title = self._html_search_regex('<h1[^>]+title="([^"]+)">', webpage, 'title')
         description = self._html_search_meta('description', webpage)
         timestamp = unified_timestamp(self._html_search_regex(
-            r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', fatal=False))
+            r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', default=None))
         thumbnail = self._html_search_meta(['og:image', 'thumbnailUrl'], webpage)
 
         # TODO 'view_count' requires deobfuscating Javascript
@@ -99,7 +147,7 @@ class BiliBiliIE(InfoExtractor):
         }
 
         uploader_mobj = re.search(
-            r'<a[^>]+href="https?://space\.bilibili\.com/(?P<id>\d+)"[^>]+title="(?P<name>[^"]+)"',
+            r'<a[^>]+href="(?:https?:)?//space\.bilibili\.com/(?P<id>\d+)"[^>]+title="(?P<name>[^"]+)"',
             webpage)
         if uploader_mobj:
             info.update({
@@ -123,3 +171,70 @@ class BiliBiliIE(InfoExtractor):
                 'description': description,
                 'entries': entries,
             }
+
+
+class BiliBiliBangumiIE(InfoExtractor):
+    _VALID_URL = r'https?://bangumi\.bilibili\.com/anime/(?P<id>\d+)'
+
+    IE_NAME = 'bangumi.bilibili.com'
+    IE_DESC = 'BiliBili番剧'
+
+    _TESTS = [{
+        'url': 'http://bangumi.bilibili.com/anime/1869',
+        'info_dict': {
+            'id': '1869',
+            'title': '混沌武士',
+            'description': 'md5:6a9622b911565794c11f25f81d6a97d2',
+        },
+        'playlist_count': 26,
+    }, {
+        'url': 'http://bangumi.bilibili.com/anime/1869',
+        'info_dict': {
+            'id': '1869',
+            'title': '混沌武士',
+            'description': 'md5:6a9622b911565794c11f25f81d6a97d2',
+        },
+        'playlist': [{
+            'md5': '91da8621454dd58316851c27c68b0c13',
+            'info_dict': {
+                'id': '40062',
+                'ext': 'mp4',
+                'title': '混沌武士',
+                'description': '故事发生在日本的江户时代。风是一个小酒馆的打工女。一日，酒馆里来了一群恶霸，虽然他们的举动令风十分不满，但是毕竟风只是一届女流，无法对他们采取什么行动，只能在心里嘟哝。这时，酒家里又进来了个“不良份子...',
+                'timestamp': 1414538739,
+                'upload_date': '20141028',
+                'episode': '疾风怒涛 Tempestuous Temperaments',
+                'episode_number': 1,
+            },
+        }],
+        'params': {
+            'playlist_items': '1',
+        },
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return False if BiliBiliIE.suitable(url) else super(BiliBiliBangumiIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        bangumi_id = self._match_id(url)
+
+        # Sometimes this API returns a JSONP response
+        season_info = self._download_json(
+            'http://bangumi.bilibili.com/jsonp/seasoninfo/%s.ver' % bangumi_id,
+            bangumi_id, transform_source=strip_jsonp)['result']
+
+        entries = [{
+            '_type': 'url_transparent',
+            'url': smuggle_url(episode['webplay_url'], {'no_bangumi_tip': 1}),
+            'ie_key': BiliBiliIE.ie_key(),
+            'timestamp': parse_iso8601(episode.get('update_time'), delimiter=' '),
+            'episode': episode.get('index_title'),
+            'episode_number': int_or_none(episode.get('index')),
+        } for episode in season_info['episodes']]
+
+        entries = sorted(entries, key=lambda entry: entry.get('episode_number'))
+
+        return self.playlist_result(
+            entries, bangumi_id,
+            season_info.get('bangumi_title'), season_info.get('evaluate'))

youtube_dl/extractor/biobiochiletv.py

@@ -19,7 +19,7 @@ class BioBioChileTVIE(InfoExtractor):
             'id': 'sobre-camaras-y-camarillas-parlamentarias',
             'ext': 'mp4',
             'title': 'Sobre Cámaras y camarillas parlamentarias',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': 'Fernando Atria',
         },
         'skip': 'URL expired and redirected to http://www.biobiochile.cl/portada/bbtv/index.html',
@@ -31,7 +31,7 @@ class BioBioChileTVIE(InfoExtractor):
             'id': 'natalia-valdebenito-repasa-a-diputado-hasbun-paso-a-la-categoria-de-hablar-brutalidades',
             'ext': 'mp4',
             'title': 'Natalia Valdebenito repasa a diputado Hasbún: Pasó a la categoría de hablar brutalidades',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': 'Piangella Obrador',
         },
         'params': {

youtube_dl/extractor/breakcom.py

@@ -1,9 +1,9 @@
 from __future__ import unicode_literals
 
 import re
-import json
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
     int_or_none,
     parse_age_limit,
@@ -11,7 +11,7 @@ from ..utils import (
 
 
 class BreakIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?break\.com/video/(?:[^/]+/)*.+-(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?(?P<site>break|screenjunkies)\.com/video/(?P<display_id>[^/]+?)(?:-(?P<id>\d+))?(?:[/?#&]|$)'
     _TESTS = [{
         'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056',
         'info_dict': {
@@ -20,45 +20,124 @@ class BreakIE(InfoExtractor):
             'title': 'When Girls Act Like D-Bags',
             'age_limit': 13,
         }
+    }, {
+        'url': 'http://www.screenjunkies.com/video/best-quentin-tarantino-movie-2841915',
+        'md5': '5c2b686bec3d43de42bde9ec047536b0',
+        'info_dict': {
+            'id': '2841915',
+            'display_id': 'best-quentin-tarantino-movie',
+            'ext': 'mp4',
+            'title': 'Best Quentin Tarantino Movie',
+            'thumbnail': r're:^https?://.*\.jpg',
+            'duration': 3671,
+            'age_limit': 13,
+            'tags': list,
+        },
+    }, {
+        'url': 'http://www.screenjunkies.com/video/honest-trailers-the-dark-knight',
+        'info_dict': {
+            'id': '2348808',
+            'display_id': 'honest-trailers-the-dark-knight',
+            'ext': 'mp4',
+            'title': 'Honest Trailers - The Dark Knight',
+            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
+            'age_limit': 10,
+            'tags': list,
+        },
+    }, {
+        # requires subscription but worked around
+        'url': 'http://www.screenjunkies.com/video/knocking-dead-ep-1-the-show-so-far-3003285',
+        'info_dict': {
+            'id': '3003285',
+            'display_id': 'knocking-dead-ep-1-the-show-so-far',
+            'ext': 'mp4',
+            'title': 'State of The Dead Recap: Knocking Dead Pilot',
+            'thumbnail': r're:^https?://.*\.jpg',
+            'duration': 3307,
+            'age_limit': 13,
+            'tags': list,
+        },
     }, {
         'url': 'http://www.break.com/video/ugc/baby-flex-2773063',
         'only_matching': True,
     }]
 
-    def _real_extract(self, url):
+    _DEFAULT_BITRATES = (48, 150, 320, 496, 864, 2240, 3264)
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(
-            'http://www.break.com/embed/%s' % video_id, video_id)
-        info = json.loads(self._search_regex(
-            r'var embedVars = ({.*})\s*?</script>',
-            webpage, 'info json', flags=re.DOTALL))
 
-        youtube_id = info.get('youtubeId')
+    def _real_extract(self, url):
+        site, display_id, video_id = re.match(self._VALID_URL, url).groups()
+
+        if not video_id:
+            webpage = self._download_webpage(url, display_id)
+            video_id = self._search_regex(
+                (r'src=["\']/embed/(\d+)', r'data-video-content-id=["\'](\d+)'),
+                webpage, 'video id')
+
+        webpage = self._download_webpage(
+            'http://www.%s.com/embed/%s' % (site, video_id),
+            display_id, 'Downloading video embed page')
+        embed_vars = self._parse_json(
+            self._search_regex(
+                r'(?s)embedVars\s*=\s*({.+?})\s*</script>', webpage, 'embed vars'),
+            display_id)
+
+        youtube_id = embed_vars.get('youtubeId')
         if youtube_id:
             return self.url_result(youtube_id, 'Youtube')
 
-        formats = [{
+        title = embed_vars['contentName']
-            'url': media['uri'] + '?' + info['AuthToken'],
-            'tbr': media['bitRate'],
-            'width': media['width'],
-            'height': media['height'],
-        } for media in info['media'] if media.get('mediaPurpose') == 'play']
 
-        if not formats:
+        formats = []
+        bitrates = []
+        for f in embed_vars.get('media', []):
+            if not f.get('uri') or f.get('mediaPurpose') != 'play':
+                continue
+            bitrate = int_or_none(f.get('bitRate'))
+            if bitrate:
+                bitrates.append(bitrate)
             formats.append({
-                'url': info['videoUri']
+                'url': f['uri'],
+                'format_id': 'http-%d' % bitrate if bitrate else 'http',
+                'width': int_or_none(f.get('width')),
+                'height': int_or_none(f.get('height')),
+                'tbr': bitrate,
+                'format': 'mp4',
             })
 
-        self._sort_formats(formats)
+        if not bitrates:
+            # When subscriptionLevel > 0, i.e. plus subscription is required
+            # media list will be empty. However, hds and hls uris are still
+            # available. We can grab them assuming bitrates to be default.
+            bitrates = self._DEFAULT_BITRATES
 
-        duration = int_or_none(info.get('videoLengthInSeconds'))
+        auth_token = embed_vars.get('AuthToken')
-        age_limit = parse_age_limit(info.get('audienceRating'))
+
+        def construct_manifest_url(base_url, ext):
+            pieces = [base_url]
+            pieces.extend([compat_str(b) for b in bitrates])
+            pieces.append('_kbps.mp4.%s?%s' % (ext, auth_token))
+            return ','.join(pieces)
+
+        if bitrates and auth_token:
+            hds_url = embed_vars.get('hdsUri')
+            if hds_url:
+                formats.extend(self._extract_f4m_formats(
+                    construct_manifest_url(hds_url, 'f4m'),
+                    display_id, f4m_id='hds', fatal=False))
+            hls_url = embed_vars.get('hlsUri')
+            if hls_url:
+                formats.extend(self._extract_m3u8_formats(
+                    construct_manifest_url(hls_url, 'm3u8'),
+                    display_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
-            'title': info['contentName'],
+            'display_id': display_id,
-            'thumbnail': info['thumbUri'],
+            'title': title,
-            'duration': duration,
+            'thumbnail': embed_vars.get('thumbUri'),
-            'age_limit': age_limit,
+            'duration': int_or_none(embed_vars.get('videoLengthInSeconds')) or None,
+            'age_limit': parse_age_limit(embed_vars.get('audienceRating')),
+            'tags': embed_vars.get('tags', '').split(','),
             'formats': formats,
         }

youtube_dl/extractor/brightcove.py

@@ -179,7 +179,7 @@ class BrightcoveLegacyIE(InfoExtractor):
 
         params = {}
 
-        playerID = find_param('playerID')
+        playerID = find_param('playerID') or find_param('playerId')
         if playerID is None:
             raise ExtractorError('Cannot find player ID')
         params['playerID'] = playerID
@@ -204,7 +204,7 @@ class BrightcoveLegacyIE(InfoExtractor):
         #   // build Brightcove <object /> XML
         # }
         m = re.search(
-            r'''(?x)customBC.\createVideo\(
+            r'''(?x)customBC\.createVideo\(
                 .*?                                                  # skipping width and height
                 ["\'](?P<playerID>\d+)["\']\s*,\s*                   # playerID
                 ["\'](?P<playerKey>AQ[^"\']{48})[^"\']*["\']\s*,\s*  # playerKey begins with AQ and is 50 characters

youtube_dl/extractor/byutv.py

@@ -16,7 +16,7 @@ class BYUtvIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Season 5 Episode 5',
             'description': 'md5:e07269172baff037f8e8bf9956bc9747',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'duration': 1486.486,
         },
         'params': {

youtube_dl/extractor/camdemy.py

@@ -26,7 +26,7 @@ class CamdemyIE(InfoExtractor):
             'id': '5181',
             'ext': 'mp4',
             'title': 'Ch1-1 Introduction, Signals (02-23-2012)',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'creator': 'ss11spring',
             'duration': 1591,
             'upload_date': '20130114',
@@ -41,7 +41,7 @@ class CamdemyIE(InfoExtractor):
             'id': '13885',
             'ext': 'mp4',
             'title': 'EverCam + Camdemy QuickStart',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'description': 'md5:2a9f989c2b153a2342acee579c6e7db6',
             'creator': 'evercam',
             'duration': 318,

youtube_dl/extractor/canalplus.py

@@ -27,6 +27,7 @@ class CanalplusIE(InfoExtractor):
                                     (?:www\.)?d8\.tv|
                                     (?:www\.)?c8\.fr|
                                     (?:www\.)?d17\.tv|
+                                    (?:(?:football|www)\.)?cstar\.fr|
                                     (?:www\.)?itele\.fr
                                 )/(?:(?:[^/]+/)*(?P<display_id>[^/?#&]+))?(?:\?.*\bvid=(?P<vid>\d+))?|
                                 player\.canalplus\.fr/#/(?P<id>\d+)
@@ -40,6 +41,7 @@ class CanalplusIE(InfoExtractor):
         'd8': 'd8',
         'c8': 'd8',
         'd17': 'd17',
+        'cstar': 'd17',
         'itele': 'itele',
     }
 
@@ -86,6 +88,19 @@ class CanalplusIE(InfoExtractor):
             'description': 'Chaque matin du lundi au vendredi, Michaël Darmon reçoit un invité politique à 8h25.',
             'upload_date': '20161014',
         },
+    }, {
+        'url': 'http://football.cstar.fr/cstar-minisite-foot/pid7566-feminines-videos.html?vid=1416769',
+        'info_dict': {
+            'id': '1416769',
+            'display_id': 'pid7566-feminines-videos',
+            'ext': 'mp4',
+            'title': 'France - Albanie : les temps forts de la soirée - 20/09/2016',
+            'description': 'md5:c3f30f2aaac294c1c969b3294de6904e',
+            'upload_date': '20160921',
+        },
+        'params': {
+            'skip_download': True,
+        },
     }, {
         'url': 'http://m.canalplus.fr/?vid=1398231',
         'only_matching': True,
@@ -107,7 +122,7 @@ class CanalplusIE(InfoExtractor):
             [r'<canal:player[^>]+?videoId=(["\'])(?P<id>\d+)',
              r'id=["\']canal_video_player(?P<id>\d+)',
              r'data-video=["\'](?P<id>\d+)'],
-            webpage, 'video id', group='id')
+            webpage, 'video id', default=mobj.group('vid'), group='id')
 
         info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
         video_data = self._download_json(info_url, video_id, 'Downloading video JSON')

youtube_dl/extractor/canvas.py

@@ -17,7 +17,7 @@ class CanvasIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'De afspraak veilt voor de Warmste Week',
             'description': 'md5:24cb860c320dc2be7358e0e5aa317ba6',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'duration': 49.02,
         }
     }, {
@@ -29,7 +29,7 @@ class CanvasIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Pieter 0167',
             'description': 'md5:943cd30f48a5d29ba02c3a104dc4ec4e',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'duration': 2553.08,
             'subtitles': {
                 'nl': [{
@@ -48,7 +48,7 @@ class CanvasIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Herbekijk Sorry voor alles',
             'description': 'md5:8bb2805df8164e5eb95d6a7a29dc0dd3',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'duration': 3788.06,
         },
         'params': {

youtube_dl/extractor/carambatv.py

@@ -21,7 +21,7 @@ class CarambaTVIE(InfoExtractor):
             'id': '191910501',
             'ext': 'mp4',
             'title': '[BadComedian] - Разборка в Маниле (Абсолютный обзор)',
-            'thumbnail': 're:^https?://.*\.jpg',
+            'thumbnail': r're:^https?://.*\.jpg',
             'duration': 2678.31,
         },
     }, {
@@ -69,7 +69,7 @@ class CarambaTVPageIE(InfoExtractor):
             'id': '475222',
             'ext': 'flv',
             'title': '[BadComedian] - Разборка в Маниле (Абсолютный обзор)',
-            'thumbnail': 're:^https?://.*\.jpg',
+            'thumbnail': r're:^https?://.*\.jpg',
             # duration reported by videomore is incorrect
             'duration': int,
         },

youtube_dl/extractor/cbc.py

@@ -90,19 +90,21 @@ class CBCIE(InfoExtractor):
             },
         }],
         'skip': 'Geo-restricted to Canada',
+    }, {
+        # multiple CBC.APP.Caffeine.initInstance(...)
+        'url': 'http://www.cbc.ca/news/canada/calgary/dog-indoor-exercise-winter-1.3928238',
+        'info_dict': {
+            'title': 'Keep Rover active during the deep freeze with doggie pushups and other fun indoor tasks',
+            'id': 'dog-indoor-exercise-winter-1.3928238',
+        },
+        'playlist_mincount': 6,
     }]
 
     @classmethod
     def suitable(cls, url):
         return False if CBCPlayerIE.suitable(url) else super(CBCIE, cls).suitable(url)
 
-    def _real_extract(self, url):
+    def _extract_player_init(self, player_init, display_id):
-        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-        player_init = self._search_regex(
-            r'CBC\.APP\.Caffeine\.initInstance\(({.+?})\);', webpage, 'player init',
-            default=None)
-        if player_init:
         player_info = self._parse_json(player_init, display_id, js_to_json)
         media_id = player_info.get('mediaId')
         if not media_id:
@@ -117,9 +119,20 @@ class CBCIE(InfoExtractor):
                     'http://feed.theplatform.com/f/h9dtGB/punlNGjMlc1F?fields=id&byContent=byReleases%3DbyId%253D' + clip_id,
                     clip_id)['entries'][0]['id'].split('/')[-1]
         return self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id)
-        else:
+
-            entries = [self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id) for media_id in re.findall(r'<iframe[^>]+src="[^"]+?mediaId=(\d+)"', webpage)]
+    def _real_extract(self, url):
-            return self.playlist_result(entries)
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        entries = [
+            self._extract_player_init(player_init, display_id)
+            for player_init in re.findall(r'CBC\.APP\.Caffeine\.initInstance\(({.+?})\);', webpage)]
+        entries.extend([
+            self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id)
+            for media_id in re.findall(r'<iframe[^>]+src="[^"]+?mediaId=(\d+)"', webpage)])
+        return self.playlist_result(
+            entries, display_id,
+            self._og_search_title(webpage, fatal=False),
+            self._og_search_description(webpage))
 
 
 class CBCPlayerIE(InfoExtractor):
@@ -283,6 +296,12 @@ class CBCWatchVideoIE(CBCWatchBaseIE):
         formats = self._extract_m3u8_formats(re.sub(r'/([^/]+)/[^/?]+\.m3u8', r'/\1/\1.m3u8', m3u8_url), video_id, 'mp4', fatal=False)
         if len(formats) < 2:
             formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4')
+        for f in formats:
+            format_id = f.get('format_id')
+            if format_id.startswith('AAC'):
+                f['acodec'] = 'aac'
+            elif format_id.startswith('AC3'):
+                f['acodec'] = 'ac-3'
         self._sort_formats(formats)
 
         info = {

youtube_dl/extractor/cbsnews.py

@@ -39,7 +39,7 @@ class CBSNewsIE(CBSIE):
                 'upload_date': '20140404',
                 'timestamp': 1396650660,
                 'uploader': 'CBSI-NEW',
-                'thumbnail': 're:^https?://.*\.jpg$',
+                'thumbnail': r're:^https?://.*\.jpg$',
                 'duration': 205,
                 'subtitles': {
                     'en': [{

youtube_dl/extractor/ccc.py

@@ -19,7 +19,7 @@ class CCCIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Introduction to Processor Design',
             'description': 'md5:df55f6d073d4ceae55aae6f2fd98a0ac',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'upload_date': '20131228',
             'timestamp': 1388188800,
             'duration': 3710,
@@ -32,7 +32,7 @@ class CCCIE(InfoExtractor):
     def _real_extract(self, url):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
-        event_id = self._search_regex("data-id='(\d+)'", webpage, 'event id')
+        event_id = self._search_regex(r"data-id='(\d+)'", webpage, 'event id')
         event_data = self._download_json('https://media.ccc.de/public/events/%s' % event_id, event_id)
 
         formats = []

youtube_dl/extractor/cctv.py

@@ -14,8 +14,9 @@ from ..utils import (
 
 class CCTVIE(InfoExtractor):
     IE_DESC = '央视网'
-    _VALID_URL = r'https?://(?:[^/]+)\.(?:cntv|cctv)\.(?:com|cn)/(?:[^/]+/)*?(?P<id>[^/?#&]+?)(?:/index)?(?:\.s?html|[?#&]|$)'
+    _VALID_URL = r'https?://(?:(?:[^/]+)\.(?:cntv|cctv)\.(?:com|cn)|(?:www\.)?ncpa-classic\.com)/(?:[^/]+/)*?(?P<id>[^/?#&]+?)(?:/index)?(?:\.s?html|[?#&]|$)'
     _TESTS = [{
+        # fo.addVariable("videoCenterId","id")
         'url': 'http://sports.cntv.cn/2016/02/12/ARTIaBRxv4rTT1yWf1frW2wi160212.shtml',
         'md5': 'd61ec00a493e09da810bf406a078f691',
         'info_dict': {
@@ -29,6 +30,7 @@ class CCTVIE(InfoExtractor):
             'upload_date': '20160212',
         },
     }, {
+        # var guid = "id"
         'url': 'http://tv.cctv.com/2016/02/05/VIDEUS7apq3lKrHG9Dncm03B160205.shtml',
         'info_dict': {
             'id': 'efc5d49e5b3b4ab2b34f3a502b73d3ae',
@@ -44,6 +46,7 @@ class CCTVIE(InfoExtractor):
             'skip_download': True,
         },
     }, {
+        # changePlayer('id')
         'url': 'http://english.cntv.cn/special/four_comprehensives/index.shtml',
         'info_dict': {
             'id': '4bb9bb4db7a6471ba85fdeda5af0381e',
@@ -59,6 +62,7 @@ class CCTVIE(InfoExtractor):
             'skip_download': True,
         },
     }, {
+        # loadvideo('id')
         'url': 'http://cctv.cntv.cn/lm/tvseries_russian/yilugesanghua/index.shtml',
         'info_dict': {
             'id': 'b15f009ff45c43968b9af583fc2e04b2',
@@ -73,6 +77,37 @@ class CCTVIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+    }, {
+        # var initMyAray = 'id'
+        'url': 'http://www.ncpa-classic.com/2013/05/22/VIDE1369219508996867.shtml',
+        'info_dict': {
+            'id': 'a194cfa7f18c426b823d876668325946',
+            'ext': 'mp4',
+            'title': '小泽征尔音乐塾 音乐梦想无国界',
+            'duration': 2173,
+            'timestamp': 1369248264,
+            'upload_date': '20130522',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # var ids = ["id"]
+        'url': 'http://www.ncpa-classic.com/clt/more/416/index.shtml',
+        'info_dict': {
+            'id': 'a8606119a4884588a79d81c02abecc16',
+            'ext': 'mp3',
+            'title': '来自维也纳的新年贺礼',
+            'description': 'md5:f13764ae8dd484e84dd4b39d5bcba2a7',
+            'duration': 1578,
+            'uploader': 'djy',
+            'timestamp': 1482942419,
+            'upload_date': '20161228',
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'expected_warnings': ['Failed to download m3u8 information'],
     }, {
         'url': 'http://ent.cntv.cn/2016/01/18/ARTIjprSSJH8DryTVr5Bx8Wb160118.shtml',
         'only_matching': True,
@@ -87,7 +122,7 @@ class CCTVIE(InfoExtractor):
         'only_matching': True,
     }, {
         'url': 'http://tv.cntv.cn/video/C39296/95cfac44cabd3ddc4a9438780a4e5c44',
-        'only_matching': True
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -97,8 +132,10 @@ class CCTVIE(InfoExtractor):
         video_id = self._search_regex(
             [r'var\s+guid\s*=\s*["\']([\da-fA-F]+)',
              r'videoCenterId["\']\s*,\s*["\']([\da-fA-F]+)',
-             r'"changePlayer\s*\(\s*["\']([\da-fA-F]+)',
+             r'changePlayer\s*\(\s*["\']([\da-fA-F]+)',
-             r'"load[Vv]ideo\s*\(\s*["\']([\da-fA-F]+)'],
+             r'load[Vv]ideo\s*\(\s*["\']([\da-fA-F]+)',
+             r'var\s+initMyAray\s*=\s*["\']([\da-fA-F]+)',
+             r'var\s+ids\s*=\s*\[["\']([\da-fA-F]+)'],
             webpage, 'video id')
 
         data = self._download_json(
@@ -138,7 +175,8 @@ class CCTVIE(InfoExtractor):
         self._sort_formats(formats)
 
         uploader = data.get('editer_name')
-        description = self._html_search_meta('description', webpage)
+        description = self._html_search_meta(
+            'description', webpage, default=None)
         timestamp = unified_timestamp(data.get('f_pgmtime'))
         duration = float_or_none(try_get(video, lambda x: x['totalLength']))
 

youtube_dl/extractor/cda.py

@@ -24,7 +24,7 @@ class CDAIE(InfoExtractor):
             'height': 720,
             'title': 'Oto dlaczego przed zakrętem należy zwolnić.',
             'description': 'md5:269ccd135d550da90d1662651fcb9772',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'average_rating': float,
             'duration': 39
         }
@@ -36,7 +36,7 @@ class CDAIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Lądowanie na lotnisku na Maderze',
             'description': 'md5:60d76b71186dcce4e0ba6d4bbdb13e1a',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': 'crash404',
             'view_count': int,
             'average_rating': float,

youtube_dl/extractor/ceskatelevize.py

@@ -25,7 +25,7 @@ class CeskaTelevizeIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Hyde Park Civilizace',
             'description': 'md5:fe93f6eda372d150759d11644ebbfb4a',
-            'thumbnail': 're:^https?://.*\.jpg',
+            'thumbnail': r're:^https?://.*\.jpg',
             'duration': 3350,
         },
         'params': {
@@ -39,7 +39,7 @@ class CeskaTelevizeIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Hyde Park Civilizace: Bonus 01 - En',
             'description': 'English Subtittles',
-            'thumbnail': 're:^https?://.*\.jpg',
+            'thumbnail': r're:^https?://.*\.jpg',
             'duration': 81.3,
         },
         'params': {
@@ -52,7 +52,7 @@ class CeskaTelevizeIE(InfoExtractor):
         'info_dict': {
             'id': 402,
             'ext': 'mp4',
-            'title': 're:^ČT Sport \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
+            'title': r're:^ČT Sport \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
             'is_live': True,
         },
         'params': {
@@ -80,7 +80,7 @@ class CeskaTelevizeIE(InfoExtractor):
                 'id': '61924494877068022',
                 'ext': 'mp4',
                 'title': 'Queer: Bogotart (Queer)',
-                'thumbnail': 're:^https?://.*\.jpg',
+                'thumbnail': r're:^https?://.*\.jpg',
                 'duration': 1558.3,
             },
         }],

youtube_dl/extractor/channel9.py

@@ -31,7 +31,7 @@ class Channel9IE(InfoExtractor):
             'title': 'Developer Kick-Off Session: Stuff We Love',
             'description': 'md5:c08d72240b7c87fcecafe2692f80e35f',
             'duration': 4576,
-            'thumbnail': 're:http://.*\.jpg',
+            'thumbnail': r're:http://.*\.jpg',
             'session_code': 'KOS002',
             'session_day': 'Day 1',
             'session_room': 'Arena 1A',
@@ -47,7 +47,7 @@ class Channel9IE(InfoExtractor):
             'title': 'Self-service BI with Power BI - nuclear testing',
             'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b',
             'duration': 1540,
-            'thumbnail': 're:http://.*\.jpg',
+            'thumbnail': r're:http://.*\.jpg',
             'authors': ['Mike Wilmot'],
         },
     }, {
@@ -59,7 +59,7 @@ class Channel9IE(InfoExtractor):
             'title': 'Ranges for the Standard Library',
             'description': 'md5:2e6b4917677af3728c5f6d63784c4c5d',
             'duration': 5646,
-            'thumbnail': 're:http://.*\.jpg',
+            'thumbnail': r're:http://.*\.jpg',
         },
         'params': {
             'skip_download': True,

youtube_dl/extractor/charlierose.py

@@ -13,7 +13,7 @@ class CharlieRoseIE(InfoExtractor):
             'id': '27996',
             'ext': 'mp4',
             'title': 'Remembering Zaha Hadid',
-            'thumbnail': 're:^https?://.*\.jpg\?\d+',
+            'thumbnail': r're:^https?://.*\.jpg\?\d+',
             'description': 'We revisit past conversations with Zaha Hadid, in memory of the world renowned Iraqi architect.',
             'subtitles': {
                 'en': [{

youtube_dl/extractor/chaturbate.py

@@ -1,5 +1,7 @@
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import ExtractorError
 
@@ -31,30 +33,35 @@ class ChaturbateIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
-        m3u8_url = self._search_regex(
+        m3u8_formats = [(m.group('id').lower(), m.group('url')) for m in re.finditer(
-            r'src=(["\'])(?P<url>http.+?\.m3u8.*?)\1', webpage,
+            r'hlsSource(?P<id>.+?)\s*=\s*(?P<q>["\'])(?P<url>http.+?)(?P=q)', webpage)]
-            'playlist', default=None, group='url')
 
-        if not m3u8_url:
+        if not m3u8_formats:
             error = self._search_regex(
                 [r'<span[^>]+class=(["\'])desc_span\1[^>]*>(?P<error>[^<]+)</span>',
                  r'<div[^>]+id=(["\'])defchat\1[^>]*>\s*<p><strong>(?P<error>[^<]+)<'],
                 webpage, 'error', group='error', default=None)
             if not error:
-                if any(p not in webpage for p in (
+                if any(p in webpage for p in (
                         self._ROOM_OFFLINE, 'offline_tipping', 'tip_offline')):
                     error = self._ROOM_OFFLINE
             if error:
                 raise ExtractorError(error, expected=True)
             raise ExtractorError('Unable to find stream URL')
 
-        formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
+        formats = []
+        for m3u8_id, m3u8_url in m3u8_formats:
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, video_id, ext='mp4',
+                # ffmpeg skips segments for fast m3u8
+                preference=-10 if m3u8_id == 'fast' else None,
+                m3u8_id=m3u8_id, fatal=False, live=True))
         self._sort_formats(formats)
 
         return {
             'id': video_id,
             'title': self._live_title(video_id),
-            'thumbnail': 'https://cdn-s.highwebmedia.com/uHK3McUtGCG3SMFcd4ZJsRv8/roomimage/%s.jpg' % video_id,
+            'thumbnail': 'https://roomimg.stream.highwebmedia.com/ri/%s.jpg' % video_id,
             'age_limit': self._rta_search(webpage),
             'is_live': True,
             'formats': formats,

youtube_dl/extractor/chirbit.py

@@ -19,6 +19,7 @@ class ChirbitIE(InfoExtractor):
             'title': 'md5:f542ea253f5255240be4da375c6a5d7e',
             'description': 'md5:f24a4e22a71763e32da5fed59e47c770',
             'duration': 306,
+            'uploader': 'Gerryaudio',
         },
         'params': {
             'skip_download': True,
@@ -54,6 +55,9 @@ class ChirbitIE(InfoExtractor):
         duration = parse_duration(self._search_regex(
             r'class=["\']c-length["\'][^>]*>([^<]+)',
             webpage, 'duration', fatal=False))
+        uploader = self._search_regex(
+            r'id=["\']chirbit-username["\'][^>]*>([^<]+)',
+            webpage, 'uploader', fatal=False)
 
         return {
             'id': audio_id,
@@ -61,6 +65,7 @@ class ChirbitIE(InfoExtractor):
             'title': title,
             'description': description,
             'duration': duration,
+            'uploader': uploader,
         }
 
 

youtube_dl/extractor/cliphunter.py

@@ -30,7 +30,7 @@ class CliphunterIE(InfoExtractor):
             'id': '1012420',
             'ext': 'flv',
             'title': 'Fun Jynx Maze solo',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'age_limit': 18,
         },
         'skip': 'Video gone',
@@ -41,7 +41,7 @@ class CliphunterIE(InfoExtractor):
             'id': '2019449',
             'ext': 'mp4',
             'title': 'ShesNew - My booty girlfriend, Victoria Paradice\'s pussy filled with jizz',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'age_limit': 18,
         },
     }]

youtube_dl/extractor/clipsyndicate.py

@@ -18,7 +18,7 @@ class ClipsyndicateIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Brick Briscoe',
             'duration': 612,
-            'thumbnail': 're:^https?://.+\.jpg',
+            'thumbnail': r're:^https?://.+\.jpg',
         },
     }, {
         'url': 'http://chic.clipsyndicate.com/video/play/5844117/shark_attack',

youtube_dl/extractor/clubic.py

@@ -19,7 +19,7 @@ class ClubicIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Clubic Week 2.0 : le FBI se lance dans la photo d\u0092identité',
             'description': 're:Gueule de bois chez Nokia. Le constructeur a indiqué cette.*',
-            'thumbnail': 're:^http://img\.clubic\.com/.*\.jpg$',
+            'thumbnail': r're:^http://img\.clubic\.com/.*\.jpg$',
         }
     }, {
         'url': 'http://www.clubic.com/video/video-clubic-week-2-0-apple-iphone-6s-et-plus-mais-surtout-le-pencil-469792.html',

youtube_dl/extractor/cmt.py

@@ -1,13 +1,11 @@
 from __future__ import unicode_literals
 
 from .mtv import MTVIE
-from ..utils import ExtractorError
 
 
 class CMTIE(MTVIE):
     IE_NAME = 'cmt.com'
-    _VALID_URL = r'https?://(?:www\.)?cmt\.com/(?:videos|shows)/(?:[^/]+/)*(?P<videoid>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?cmt\.com/(?:videos|shows|(?:full-)?episodes|video-clips)/(?P<id>[^/]+)'
-    _FEED_URL = 'http://www.cmt.com/sitewide/apps/player/embed/rss/'
 
     _TESTS = [{
         'url': 'http://www.cmt.com/videos/garth-brooks/989124/the-call-featuring-trisha-yearwood.jhtml#artist=30061',
@@ -33,17 +31,24 @@ class CMTIE(MTVIE):
     }, {
         'url': 'http://www.cmt.com/shows/party-down-south/party-down-south-ep-407-gone-girl/1738172/playlist/#id=1738172',
         'only_matching': True,
+    }, {
+        'url': 'http://www.cmt.com/full-episodes/537qb3/nashville-the-wayfaring-stranger-season-5-ep-501',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.cmt.com/video-clips/t9e4ci/nashville-juliette-in-2-minutes',
+        'only_matching': True,
     }]
 
-    @classmethod
-    def _transform_rtmp_url(cls, rtmp_video_url):
-        if 'error_not_available.swf' in rtmp_video_url:
-            raise ExtractorError(
-                '%s said: video is not available' % cls.IE_NAME, expected=True)
-
-        return super(CMTIE, cls)._transform_rtmp_url(rtmp_video_url)
-
     def _extract_mgid(self, webpage):
-        return self._search_regex(
+        mgid = self._search_regex(
             r'MTVN\.VIDEO\.contentUri\s*=\s*([\'"])(?P<mgid>.+?)\1',
-            webpage, 'mgid', group='mgid')
+            webpage, 'mgid', group='mgid', default=None)
+        if not mgid:
+            mgid = self._extract_triforce_mgid(webpage)
+        return mgid
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        mgid = self._extract_mgid(webpage)
+        return self.url_result('http://media.mtvnservices.com/embed/%s' % mgid)

youtube_dl/extractor/collegerama.py

@@ -21,7 +21,7 @@ class CollegeRamaIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'Een nieuwe wereld: waarden, bewustzijn en techniek van de mensheid 2.0.',
                 'description': '',
-                'thumbnail': 're:^https?://.*\.jpg$',
+                'thumbnail': r're:^https?://.*\.jpg$',
                 'duration': 7713.088,
                 'timestamp': 1413309600,
                 'upload_date': '20141014',

youtube_dl/extractor/comedycentral.py

@@ -48,15 +48,7 @@ class ComedyCentralFullEpisodesIE(MTVServicesInfoExtractor):
     def _real_extract(self, url):
         playlist_id = self._match_id(url)
         webpage = self._download_webpage(url, playlist_id)
-
+        mgid = self._extract_triforce_mgid(webpage, data_zone='t2_lc_promo1')
-        feed_json = self._search_regex(r'var triforceManifestFeed\s*=\s*(\{.+?\});\n', webpage, 'triforce feeed')
-        feed = self._parse_json(feed_json, playlist_id)
-        zones = feed['manifest']['zones']
-
-        video_zone = zones['t2_lc_promo1']
-        feed = self._download_json(video_zone['feed'], playlist_id)
-        mgid = feed['result']['data']['id']
-
         videos_info = self._get_videos_info(mgid)
         return videos_info
 
@@ -79,7 +71,7 @@ class ToshIE(MTVServicesInfoExtractor):
                 'ext': 'mp4',
                 'title': 'Tosh.0|June 9, 2077|2|211|Twitter Users Share Summer Plans',
                 'description': 'Tosh asked fans to share their summer plans.',
-                'thumbnail': 're:^https?://.*\.jpg',
+                'thumbnail': r're:^https?://.*\.jpg',
                 # It's really reported to be published on year 2077
                 'upload_date': '20770610',
                 'timestamp': 3390510600,
@@ -93,12 +85,6 @@ class ToshIE(MTVServicesInfoExtractor):
         'only_matching': True,
     }]
 
-    @classmethod
-    def _transform_rtmp_url(cls, rtmp_video_url):
-        new_urls = super(ToshIE, cls)._transform_rtmp_url(rtmp_video_url)
-        new_urls['rtmp'] = rtmp_video_url.replace('viacomccstrm', 'viacommtvstrm')
-        return new_urls
-
 
 class ComedyCentralTVIE(MTVServicesInfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/(?:staffeln|shows)/(?P<id>[^/?#&]+)'

youtube_dl/extractor/common.py

@@ -121,9 +121,19 @@ class InfoExtractor(object):
                                  download, lower-case.
                                  "http", "https", "rtsp", "rtmp", "rtmpe",
                                  "m3u8", "m3u8_native" or "http_dash_segments".
-                    * fragments  A list of fragments of the fragmented media,
+                    * fragment_base_url
-                                 with the following entries:
+                                 Base URL for fragments. Each fragment's path
-                                 * "url" (mandatory) - fragment's URL
+                                 value (if present) will be relative to
+                                 this URL.
+                    * fragments  A list of fragments of a fragmented media.
+                                 Each fragment entry must contain either an url
+                                 or a path. If an url is present it should be
+                                 considered by a client. Otherwise both path and
+                                 fragment_base_url must be present. Here is
+                                 the list of all potential fields:
+                                 * "url" - fragment's URL
+                                 * "path" - fragment's path relative to
+                                            fragment_base_url
                                  * "duration" (optional, int or float)
                                  * "filesize" (optional, int)
                     * preference Order number of this format. If this field is
@@ -1015,13 +1025,13 @@ class InfoExtractor(object):
                 unique_formats.append(f)
         formats[:] = unique_formats
 
-    def _is_valid_url(self, url, video_id, item='video'):
+    def _is_valid_url(self, url, video_id, item='video', headers={}):
         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)
+            self._request_webpage(url, video_id, 'Checking %s URL' % item, headers=headers)
             return True
         except ExtractorError as e:
             if isinstance(e.cause, compat_urllib_error.URLError):
@@ -1305,8 +1315,8 @@ class InfoExtractor(object):
                         'abr': abr,
                     })
                 f.update(parse_codecs(last_info.get('CODECS')))
-                if audio_in_video_stream.get(last_info.get('AUDIO')) is False:
+                if audio_in_video_stream.get(last_info.get('AUDIO')) is False and f['vcodec'] != 'none':
-                    # TODO: update acodec for for audio only formats with the same GROUP-ID
+                    # TODO: update acodec for audio only formats with the same GROUP-ID
                     f['acodec'] = 'none'
                 formats.append(f)
                 last_info = {}
@@ -1627,12 +1637,12 @@ class InfoExtractor(object):
                 segment_template = element.find(_add_ns('SegmentTemplate'))
                 if segment_template is not None:
                     extract_common(segment_template)
-                    media_template = segment_template.get('media')
+                    media = segment_template.get('media')
-                    if media_template:
+                    if media:
-                        ms_info['media_template'] = media_template
+                        ms_info['media'] = media
                     initialization = segment_template.get('initialization')
                     if initialization:
-                        ms_info['initialization_url'] = initialization
+                        ms_info['initialization'] = initialization
                     else:
                         extract_Initialization(segment_template)
             return ms_info
@@ -1676,6 +1686,7 @@ class InfoExtractor(object):
                         lang = representation_attrib.get('lang')
                         url_el = representation.find(_add_ns('BaseURL'))
                         filesize = int_or_none(url_el.attrib.get('{http://youtube.com/yt/2012/10/10}contentLength') if url_el is not None else None)
+                        bandwidth = int_or_none(representation_attrib.get('bandwidth'))
                         f = {
                             'format_id': '%s-%s' % (mpd_id, representation_id) if mpd_id else representation_id,
                             'url': base_url,
@@ -1683,7 +1694,7 @@ class InfoExtractor(object):
                             'ext': mimetype2ext(mime_type),
                             'width': int_or_none(representation_attrib.get('width')),
                             'height': int_or_none(representation_attrib.get('height')),
-                            'tbr': int_or_none(representation_attrib.get('bandwidth'), 1000),
+                            'tbr': int_or_none(bandwidth, 1000),
                             'asr': int_or_none(representation_attrib.get('audioSamplingRate')),
                             'fps': int_or_none(representation_attrib.get('frameRate')),
                             'language': lang if lang not in ('mul', 'und', 'zxx', 'mis') else None,
@@ -1692,13 +1703,32 @@ class InfoExtractor(object):
                         }
                         f.update(parse_codecs(representation_attrib.get('codecs')))
                         representation_ms_info = extract_multisegment_info(representation, adaption_set_ms_info)
-                        if 'segment_urls' not in representation_ms_info and 'media_template' in representation_ms_info:
 
-                            media_template = representation_ms_info['media_template']
+                        def prepare_template(template_name, identifiers):
-                            media_template = media_template.replace('$RepresentationID$', representation_id)
+                            t = representation_ms_info[template_name]
-                            media_template = re.sub(r'\$(Number|Bandwidth|Time)\$', r'%(\1)d', media_template)
+                            t = t.replace('$RepresentationID$', representation_id)
-                            media_template = re.sub(r'\$(Number|Bandwidth|Time)%([^$]+)\$', r'%(\1)\2', media_template)
+                            t = re.sub(r'\$(%s)\$' % '|'.join(identifiers), r'%(\1)d', t)
-                            media_template.replace('$$', '$')
+                            t = re.sub(r'\$(%s)%%([^$]+)\$' % '|'.join(identifiers), r'%(\1)\2', t)
+                            t.replace('$$', '$')
+                            return t
+
+                        # @initialization is a regular template like @media one
+                        # so it should be handled just the same way (see
+                        # https://github.com/rg3/youtube-dl/issues/11605)
+                        if 'initialization' in representation_ms_info:
+                            initialization_template = prepare_template(
+                                'initialization',
+                                # As per [1, 5.3.9.4.2, Table 15, page 54] $Number$ and
+                                # $Time$ shall not be included for @initialization thus
+                                # only $Bandwidth$ remains
+                                ('Bandwidth', ))
+                            representation_ms_info['initialization_url'] = initialization_template % {
+                                'Bandwidth': bandwidth,
+                            }
+
+                        if 'segment_urls' not in representation_ms_info and 'media' in representation_ms_info:
+
+                            media_template = prepare_template('media', ('Number', 'Bandwidth', 'Time'))
 
                             # As per [1, 5.3.9.4.4, Table 16, page 55] $Number$ and $Time$
                             # can't be used at the same time
@@ -1710,7 +1740,7 @@ class InfoExtractor(object):
                                 representation_ms_info['fragments'] = [{
                                     'url': media_template % {
                                         'Number': segment_number,
-                                        'Bandwidth': int_or_none(representation_attrib.get('bandwidth')),
+                                        'Bandwidth': bandwidth,
                                     },
                                     'duration': segment_duration,
                                 } for segment_number in range(
@@ -1728,7 +1758,7 @@ class InfoExtractor(object):
                                 def add_segment_url():
                                     segment_url = media_template % {
                                         'Time': segment_time,
-                                        'Bandwidth': int_or_none(representation_attrib.get('bandwidth')),
+                                        'Bandwidth': bandwidth,
                                         'Number': segment_number,
                                     }
                                     representation_ms_info['fragments'].append({
@@ -1751,14 +1781,16 @@ class InfoExtractor(object):
                             # Example: https://www.youtube.com/watch?v=iXZV5uAYMJI
                             # or any YouTube dashsegments video
                             fragments = []
-                            s_num = 0
+                            segment_index = 0
-                            for segment_url in representation_ms_info['segment_urls']:
+                            timescale = representation_ms_info['timescale']
-                                s = representation_ms_info['s'][s_num]
+                            for s in representation_ms_info['s']:
+                                duration = float_or_none(s['d'], timescale)
                                 for r in range(s.get('r', 0) + 1):
                                     fragments.append({
-                                        'url': segment_url,
+                                        'url': representation_ms_info['segment_urls'][segment_index],
-                                        'duration': float_or_none(s['d'], representation_ms_info['timescale']),
+                                        'duration': duration,
                                     })
+                                    segment_index += 1
                             representation_ms_info['fragments'] = fragments
                         # NB: MPD manifest may contain direct URLs to unfragmented media.
                         # No fragments key is present in this case.
@@ -1768,7 +1800,7 @@ class InfoExtractor(object):
                                 'protocol': 'http_dash_segments',
                             })
                             if 'initialization_url' in representation_ms_info:
-                                initialization_url = representation_ms_info['initialization_url'].replace('$RepresentationID$', representation_id)
+                                initialization_url = representation_ms_info['initialization_url']
                                 if not f.get('url'):
                                     f['url'] = initialization_url
                                 f['fragments'].append({'url': initialization_url})
@@ -1927,7 +1959,12 @@ class InfoExtractor(object):
         media_tags = [(media_tag, media_type, '')
                       for media_tag, media_type
                       in re.findall(r'(?s)(<(video|audio)[^>]*/>)', webpage)]
-        media_tags.extend(re.findall(r'(?s)(<(?P<tag>video|audio)[^>]*>)(.*?)</(?P=tag)>', webpage))
+        media_tags.extend(re.findall(
+            # We only allow video|audio followed by a whitespace or '>'.
+            # Allowing more characters may end up in significant slow down (see
+            # https://github.com/rg3/youtube-dl/issues/11979, example URL:
+            # http://www.porntrex.com/maps/videositemap.xml).
+            r'(?s)(<(?P<tag>video|audio)(?:\s+[^>]*)?>)(.*?)</(?P=tag)>', webpage))
         for media_tag, media_type, media_content in media_tags:
             media_info = {
                 'formats': [],
@@ -1967,10 +2004,13 @@ class InfoExtractor(object):
                 entries.append(media_info)
         return entries
 
-    def _extract_akamai_formats(self, manifest_url, video_id):
+    def _extract_akamai_formats(self, manifest_url, video_id, hosts={}):
         formats = []
         hdcore_sign = 'hdcore=3.7.0'
-        f4m_url = re.sub(r'(https?://.+?)/i/', r'\1/z/', manifest_url).replace('/master.m3u8', '/manifest.f4m')
+        f4m_url = re.sub(r'(https?://[^/+])/i/', r'\1/z/', manifest_url).replace('/master.m3u8', '/manifest.f4m')
+        hds_host = hosts.get('hds')
+        if hds_host:
+            f4m_url = re.sub(r'(https?://)[^/]+', r'\1' + hds_host, f4m_url)
         if 'hdcore=' not in f4m_url:
             f4m_url += ('&' if '?' in f4m_url else '?') + hdcore_sign
         f4m_formats = self._extract_f4m_formats(
@@ -1978,7 +2018,10 @@ class InfoExtractor(object):
         for entry in f4m_formats:
             entry.update({'extra_param_to_segment_url': hdcore_sign})
         formats.extend(f4m_formats)
-        m3u8_url = re.sub(r'(https?://.+?)/z/', r'\1/i/', manifest_url).replace('/manifest.f4m', '/master.m3u8')
+        m3u8_url = re.sub(r'(https?://[^/]+)/z/', r'\1/i/', manifest_url).replace('/manifest.f4m', '/master.m3u8')
+        hls_host = hosts.get('hls')
+        if hls_host:
+            m3u8_url = re.sub(r'(https?://)[^/]+', r'\1' + hls_host, m3u8_url)
         formats.extend(self._extract_m3u8_formats(
             m3u8_url, video_id, 'mp4', 'm3u8_native',
             m3u8_id='hls', fatal=False))

youtube_dl/extractor/coub.py

@@ -20,7 +20,7 @@ class CoubIE(InfoExtractor):
             'id': '5u5n1',
             'ext': 'mp4',
             'title': 'The Matrix Moonwalk',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'duration': 4.6,
             'timestamp': 1428527772,
             'upload_date': '20150408',

youtube_dl/extractor/crackle.py

@@ -6,7 +6,7 @@ from ..utils import int_or_none
 
 
 class CrackleIE(InfoExtractor):
-    _VALID_URL = r'(?:crackle:|https?://(?:www\.)?crackle\.com/(?:playlist/\d+/|(?:[^/]+/)+))(?P<id>\d+)'
+    _VALID_URL = r'(?:crackle:|https?://(?:(?:www|m)\.)?crackle\.com/(?:playlist/\d+/|(?:[^/]+/)+))(?P<id>\d+)'
     _TEST = {
         'url': 'http://www.crackle.com/comedians-in-cars-getting-coffee/2498934',
         'info_dict': {
@@ -14,7 +14,7 @@ class CrackleIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Everybody Respects A Bloody Nose',
             'description': 'Jerry is kaffeeklatsching in L.A. with funnyman J.B. Smoove (Saturday Night Live, Real Husbands of Hollywood). They’re headed for brew at 10 Speed Coffee in a 1964 Studebaker Avanti.',
-            'thumbnail': 're:^https?://.*\.jpg',
+            'thumbnail': r're:^https?://.*\.jpg',
             'duration': 906,
             'series': 'Comedians In Cars Getting Coffee',
             'season_number': 8,
@@ -31,8 +31,32 @@ class CrackleIE(InfoExtractor):
         }
     }
 
+    _THUMBNAIL_RES = [
+        (120, 90),
+        (208, 156),
+        (220, 124),
+        (220, 220),
+        (240, 180),
+        (250, 141),
+        (315, 236),
+        (320, 180),
+        (360, 203),
+        (400, 300),
+        (421, 316),
+        (460, 330),
+        (460, 460),
+        (462, 260),
+        (480, 270),
+        (587, 330),
+        (640, 480),
+        (700, 330),
+        (700, 394),
+        (854, 480),
+        (1024, 1024),
+        (1920, 1080),
+    ]
+
     # extracted from http://legacyweb-us.crackle.com/flash/ReferrerRedirect.ashx
-    _THUMBNAIL_TEMPLATE = 'http://images-us-am.crackle.com/%stnl_1920x1080.jpg?ts=20140107233116?c=635333335057637614'
     _MEDIA_FILE_SLOTS = {
         'c544.flv': {
             'width': 544,
@@ -61,17 +85,25 @@ class CrackleIE(InfoExtractor):
 
         item = self._download_xml(
             'http://legacyweb-us.crackle.com/app/revamp/vidwallcache.aspx?flags=-1&fm=%s' % video_id,
-            video_id).find('i')
+            video_id, headers=self.geo_verification_headers()).find('i')
         title = item.attrib['t']
 
         subtitles = {}
         formats = self._extract_m3u8_formats(
             'http://content.uplynk.com/ext/%s/%s.m3u8' % (config_doc.attrib['strUplynkOwnerId'], video_id),
             video_id, 'mp4', m3u8_id='hls', fatal=None)
-        thumbnail = None
+        thumbnails = []
         path = item.attrib.get('p')
         if path:
-            thumbnail = self._THUMBNAIL_TEMPLATE % path
+            for width, height in self._THUMBNAIL_RES:
+                res = '%dx%d' % (width, height)
+                thumbnails.append({
+                    'id': res,
+                    'url': 'http://images-us-am.crackle.com/%stnl_%s.jpg' % (path, res),
+                    'width': width,
+                    'height': height,
+                    'resolution': res,
+                })
             http_base_url = 'http://ahttp.crackle.com/' + path
             for mfs_path, mfs_info in self._MEDIA_FILE_SLOTS.items():
                 formats.append({
@@ -86,10 +118,11 @@ class CrackleIE(InfoExtractor):
                 if locale and v:
                     if locale not in subtitles:
                         subtitles[locale] = []
-                    subtitles[locale] = [{
+                    for url_ext, ext in (('vtt', 'vtt'), ('xml', 'tt')):
-                        'url': '%s/%s%s_%s.xml' % (config_doc.attrib['strSubtitleServer'], path, locale, v),
+                        subtitles.setdefault(locale, []).append({
-                        'ext': 'ttml',
+                            'url': '%s/%s%s_%s.%s' % (config_doc.attrib['strSubtitleServer'], path, locale, v, url_ext),
-                    }]
+                            'ext': ext,
+                        })
         self._sort_formats(formats, ('width', 'height', 'tbr', 'format_id'))
 
         return {
@@ -100,7 +133,7 @@ class CrackleIE(InfoExtractor):
             'series': item.attrib.get('sn'),
             'season_number': int_or_none(item.attrib.get('se')),
             'episode_number': int_or_none(item.attrib.get('ep')),
-            'thumbnail': thumbnail,
+            'thumbnails': thumbnails,
             'subtitles': subtitles,
             'formats': formats,
         }

youtube_dl/extractor/criterion.py

@@ -14,7 +14,7 @@ class CriterionIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Le Samouraï',
             'description': 'md5:a2b4b116326558149bef81f76dcbb93f',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
         }
     }
 

youtube_dl/extractor/crooksandliars.py

@@ -16,7 +16,7 @@ class CrooksAndLiarsIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!',
             'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
-            'thumbnail': 're:^https?://.*\.jpg',
+            'thumbnail': r're:^https?://.*\.jpg',
             'timestamp': 1428207000,
             'upload_date': '20150405',
             'uploader': 'Heather',

youtube_dl/extractor/crunchyroll.py

@@ -142,7 +142,7 @@ class CrunchyrollIE(CrunchyrollBaseIE):
             'ext': 'flv',
             'title': 'Culture Japan Episode 1 – Rebuilding Japan after the 3.11',
             'description': 'md5:2fbc01f90b87e8e9137296f37b461c12',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': 'Danny Choo Network',
             'upload_date': '20120213',
         },
@@ -158,7 +158,7 @@ class CrunchyrollIE(CrunchyrollBaseIE):
             'ext': 'mp4',
             'title': 'Re:ZERO -Starting Life in Another World- Episode 5 – The Morning of Our Promise Is Still Distant',
             'description': 'md5:97664de1ab24bbf77a9c01918cb7dca9',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': 'TV TOKYO',
             'upload_date': '20160508',
         },
@@ -166,6 +166,25 @@ class CrunchyrollIE(CrunchyrollBaseIE):
             # m3u8 download
             'skip_download': True,
         },
+    }, {
+        'url': 'http://www.crunchyroll.com/konosuba-gods-blessing-on-this-wonderful-world/episode-1-give-me-deliverance-from-this-judicial-injustice-727589',
+        'info_dict': {
+            'id': '727589',
+            'ext': 'mp4',
+            'title': "KONOSUBA -God's blessing on this wonderful world! 2 Episode 1 – Give Me Deliverance from this Judicial Injustice!",
+            'description': 'md5:cbcf05e528124b0f3a0a419fc805ea7d',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'uploader': 'Kadokawa Pictures Inc.',
+            'upload_date': '20170118',
+            'series': "KONOSUBA -God's blessing on this wonderful world!",
+            'season_number': 2,
+            'episode': 'Give Me Deliverance from this Judicial Injustice!',
+            'episode_number': 1,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
     }, {
         'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
         'only_matching': True,
@@ -236,8 +255,7 @@ class CrunchyrollIE(CrunchyrollBaseIE):
         output += 'WrapStyle: %s\n' % sub_root.attrib['wrap_style']
         output += 'PlayResX: %s\n' % sub_root.attrib['play_res_x']
         output += 'PlayResY: %s\n' % sub_root.attrib['play_res_y']
-        output += """ScaledBorderAndShadow: no
+        output += """
-
 [V4+ Styles]
 Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding
 """
@@ -439,6 +457,18 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
 
         subtitles = self.extract_subtitles(video_id, webpage)
 
+        # webpage provide more accurate data than series_title from XML
+        series = self._html_search_regex(
+            r'id=["\']showmedia_about_episode_num[^>]+>\s*<a[^>]+>([^<]+)',
+            webpage, 'series', default=xpath_text(metadata, 'series_title'))
+
+        episode = xpath_text(metadata, 'episode_title')
+        episode_number = int_or_none(xpath_text(metadata, 'episode_number'))
+
+        season_number = int_or_none(self._search_regex(
+            r'(?s)<h4[^>]+id=["\']showmedia_about_episode_num[^>]+>.+?</h4>\s*<h4>\s*Season (\d+)',
+            webpage, 'season number', default=None))
+
         return {
             'id': video_id,
             'title': video_title,
@@ -446,9 +476,10 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             'thumbnail': xpath_text(metadata, 'episode_image_url'),
             'uploader': video_uploader,
             'upload_date': video_upload_date,
-            'series': xpath_text(metadata, 'series_title'),
+            'series': series,
-            'episode': xpath_text(metadata, 'episode_title'),
+            'season_number': season_number,
-            'episode_number': int_or_none(xpath_text(metadata, 'episode_number')),
+            'episode': episode,
+            'episode_number': episode_number,
             'subtitles': subtitles,
             'formats': formats,
         }

youtube_dl/extractor/cspan.py

@@ -12,6 +12,7 @@ from ..utils import (
     ExtractorError,
 )
 from .senateisvp import SenateISVPIE
+from .ustream import UstreamIE
 
 
 class CSpanIE(InfoExtractor):
@@ -22,14 +23,13 @@ class CSpanIE(InfoExtractor):
         'md5': '94b29a4f131ff03d23471dd6f60b6a1d',
         'info_dict': {
             'id': '315139',
-            'ext': 'mp4',
             'title': 'Attorney General Eric Holder on Voting Rights Act Decision',
-            'description': 'Attorney General Eric Holder speaks to reporters following the Supreme Court decision in [Shelby County v. Holder], in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced.',
         },
+        'playlist_mincount': 2,
         'skip': 'Regularly fails on travis, for unknown reasons',
     }, {
         'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models',
-        'md5': '8e5fbfabe6ad0f89f3012a7943c1287b',
+        # md5 is unstable
         'info_dict': {
             'id': 'c4486943',
             'ext': 'mp4',
@@ -38,14 +38,11 @@ class CSpanIE(InfoExtractor):
         }
     }, {
         'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall',
-        'md5': '2ae5051559169baadba13fc35345ae74',
         'info_dict': {
             'id': '342759',
-            'ext': 'mp4',
             'title': 'General Motors Ignition Switch Recall',
-            'duration': 14848,
-            'description': 'md5:118081aedd24bf1d3b68b3803344e7f3'
         },
+        'playlist_mincount': 6,
     }, {
         # Video from senate.gov
         'url': 'http://www.c-span.org/video/?104517-1/immigration-reforms-needed-protect-skilled-american-workers',
@@ -57,12 +54,30 @@ class CSpanIE(InfoExtractor):
         'params': {
             'skip_download': True,  # m3u8 downloads
         }
+    }, {
+        # Ustream embedded video
+        'url': 'https://www.c-span.org/video/?114917-1/armed-services',
+        'info_dict': {
+            'id': '58428542',
+            'ext': 'flv',
+            'title': 'USHR07 Armed Services Committee',
+            'description': 'hsas00-2118-20150204-1000et-07\n\n\nUSHR07 Armed Services Committee',
+            'timestamp': 1423060374,
+            'upload_date': '20150204',
+            'uploader': 'HouseCommittee',
+            'uploader_id': '12987475',
+        },
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         video_type = None
         webpage = self._download_webpage(url, video_id)
+
+        ustream_url = UstreamIE._extract_url(webpage)
+        if ustream_url:
+            return self.url_result(ustream_url, UstreamIE.ie_key())
+
         # We first look for clipid, because clipprog always appears before
         patterns = [r'id=\'clip(%s)\'\s*value=\'([0-9]+)\'' % t for t in ('id', 'prog')]
         results = list(filter(None, (re.search(p, webpage) for p in patterns)))

youtube_dl/extractor/ctsnews.py

@@ -28,7 +28,7 @@ class CtsNewsIE(InfoExtractor):
             'ext': 'mp4',
             'title': '韓國31歲童顏男 貌如十多歲小孩',
             'description': '越有年紀的人，越希望看起來年輕一點，而南韓卻有一位31歲的男子，看起來像是11、12歲的小孩，身...',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'timestamp': 1378205880,
             'upload_date': '20130903',
         }
@@ -41,7 +41,7 @@ class CtsNewsIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'iPhone6熱銷 蘋果財報亮眼',
             'description': 'md5:f395d4f485487bb0f992ed2c4b07aa7d',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'upload_date': '20150128',
             'uploader_id': 'TBSCTS',
             'uploader': '中華電視公司',

youtube_dl/extractor/cultureunplugged.py

@@ -21,7 +21,7 @@ class CultureUnpluggedIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'The Next, Best West',
             'description': 'md5:0423cd00833dea1519cf014e9d0903b1',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'creator': 'Coldstream Creative',
             'duration': 2203,
             'view_count': int,

youtube_dl/extractor/dailymotion.py

@@ -58,7 +58,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
                 'ext': 'mp4',
                 'title': 'Steam Machine Models, Pricing Listed on Steam Store - IGN News',
                 'description': 'Several come bundled with the Steam Controller.',
-                'thumbnail': 're:^https?:.*\.(?:jpg|png)$',
+                'thumbnail': r're:^https?:.*\.(?:jpg|png)$',
                 'duration': 74,
                 'timestamp': 1425657362,
                 'upload_date': '20150306',

youtube_dl/extractor/daum.py

@@ -32,7 +32,7 @@ class DaumIE(InfoExtractor):
             'title': '마크 헌트 vs 안토니오 실바',
             'description': 'Mark Hunt vs Antonio Silva',
             'upload_date': '20131217',
-            'thumbnail': 're:^https?://.*\.(?:jpg|png)',
+            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
             'duration': 2117,
             'view_count': int,
             'comment_count': int,
@@ -45,7 +45,7 @@ class DaumIE(InfoExtractor):
             'title': '1297회, \'아빠 아들로 태어나길 잘 했어\' 민수, 감동의 눈물[아빠 어디가] 20150118',
             'description': 'md5:79794514261164ff27e36a21ad229fc5',
             'upload_date': '20150604',
-            'thumbnail': 're:^https?://.*\.(?:jpg|png)',
+            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
             'duration': 154,
             'view_count': int,
             'comment_count': int,
@@ -61,7 +61,7 @@ class DaumIE(InfoExtractor):
             'title': '01-Korean War ( Trouble on the horizon )',
             'description': '\nKorean War 01\nTrouble on the horizon\n전쟁의 먹구름',
             'upload_date': '20080223',
-            'thumbnail': 're:^https?://.*\.(?:jpg|png)',
+            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
             'duration': 249,
             'view_count': int,
             'comment_count': int,
@@ -139,7 +139,7 @@ class DaumClipIE(InfoExtractor):
             'title': 'DOTA 2GETHER 시즌2 6회 - 2부',
             'description': 'DOTA 2GETHER 시즌2 6회 - 2부',
             'upload_date': '20130831',
-            'thumbnail': 're:^https?://.*\.(?:jpg|png)',
+            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
             'duration': 3868,
             'view_count': int,
         },

youtube_dl/extractor/dbtv.py

@@ -17,7 +17,7 @@ class DBTVIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Skulle teste ut fornøyelsespark, men kollegaen var bare opptatt av bikinikroppen',
             'description': 'md5:1504a54606c4dde3e4e61fc97aa857e0',
-            'thumbnail': 're:https?://.*\.jpg',
+            'thumbnail': r're:https?://.*\.jpg',
             'timestamp': 1404039863,
             'upload_date': '20140629',
             'duration': 69.544,

youtube_dl/extractor/dctp.py

@@ -17,7 +17,7 @@ class DctpTvIE(InfoExtractor):
             'title': 'Videoinstallation für eine Kaufhausfassade',
             'description': 'Kurzfilm',
             'upload_date': '20110407',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
         },
     }
 

youtube_dl/extractor/deezer.py

@@ -19,7 +19,7 @@ class DeezerPlaylistIE(InfoExtractor):
             'id': '176747451',
             'title': 'Best!',
             'uploader': 'Anonymous',
-            'thumbnail': 're:^https?://cdn-images.deezer.com/images/cover/.*\.jpg$',
+            'thumbnail': r're:^https?://cdn-images.deezer.com/images/cover/.*\.jpg$',
         },
         'playlist_count': 30,
         'skip': 'Only available in .de',

youtube_dl/extractor/dhm.py

@@ -17,7 +17,7 @@ class DHMIE(InfoExtractor):
             'title': 'MARSHALL PLAN AT WORK IN WESTERN GERMANY, THE',
             'description': 'md5:1fabd480c153f97b07add61c44407c82',
             'duration': 660,
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
         },
     }, {
         'url': 'http://www.dhm.de/filmarchiv/02-mapping-the-wall/peter-g/rolle-1/',
@@ -26,7 +26,7 @@ class DHMIE(InfoExtractor):
             'id': 'rolle-1',
             'ext': 'flv',
             'title': 'ROLLE 1',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
         },
     }]
 

youtube_dl/extractor/digiteka.py

@@ -36,7 +36,7 @@ class DigitekaIE(InfoExtractor):
             'id': 's8uk0r',
             'ext': 'mp4',
             'title': 'Loi sur la fin de vie: le texte prévoit un renforcement des directives anticipées',
-            'thumbnail': 're:^https?://.*\.jpg',
+            'thumbnail': r're:^https?://.*\.jpg',
             'duration': 74,
             'upload_date': '20150317',
             'timestamp': 1426604939,
@@ -50,7 +50,7 @@ class DigitekaIE(InfoExtractor):
             'id': 'xvpfp8',
             'ext': 'mp4',
             'title': 'Two - C\'est La Vie (clip)',
-            'thumbnail': 're:^https?://.*\.jpg',
+            'thumbnail': r're:^https?://.*\.jpg',
             'duration': 233,
             'upload_date': '20150224',
             'timestamp': 1424760500,

youtube_dl/extractor/discoverygo.py

@@ -6,7 +6,6 @@ from ..utils import (
     extract_attributes,
     int_or_none,
     parse_age_limit,
-    unescapeHTML,
     ExtractorError,
 )
 
@@ -49,7 +48,7 @@ class DiscoveryGoIE(InfoExtractor):
                 webpage, 'video container'))
 
         video = self._parse_json(
-            unescapeHTML(container.get('data-video') or container.get('data-json')),
+            container.get('data-video') or container.get('data-json'),
             display_id)
 
         title = video['name']

youtube_dl/extractor/disney.py

@@ -0,0 +1,115 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    unified_strdate,
+    compat_str,
+    determine_ext,
+)
+
+
+class DisneyIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+        https?://(?P<domain>(?:[^/]+\.)?(?:disney\.[a-z]{2,3}(?:\.[a-z]{2})?|disney(?:(?:me|latino)\.com|turkiye\.com\.tr)|starwars\.com))/(?:embed/|(?:[^/]+/)+[\w-]+-)(?P<id>[a-z0-9]{24})'''
+    _TESTS = [{
+        'url': 'http://video.disney.com/watch/moana-trailer-545ed1857afee5a0ec239977',
+        'info_dict': {
+            'id': '545ed1857afee5a0ec239977',
+            'ext': 'mp4',
+            'title': 'Moana - Trailer',
+            'description': 'A fun adventure for the entire Family!  Bring home Moana on Digital HD Feb 21 & Blu-ray March 7',
+            'upload_date': '20170112',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
+    }, {
+        'url': 'http://videos.disneylatino.com/ver/spider-man-de-regreso-a-casa-primer-adelanto-543a33a1850bdcfcca13bae2',
+        'only_matching': True,
+    }, {
+        'url': 'http://video.en.disneyme.com/watch/future-worm/robo-carp-2001-544b66002aa7353cdd3f5114',
+        'only_matching': True,
+    }, {
+        'url': 'http://video.disneyturkiye.com.tr/izle/7c-7-cuceler/kimin-sesi-zaten-5456f3d015f6b36c8afdd0e2',
+        'only_matching': True,
+    }, {
+        'url': 'http://disneyjunior.disney.com/embed/546a4798ddba3d1612e4005d',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.starwars.com/embed/54690d1e6c42e5f09a0fb097',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        domain, video_id = re.match(self._VALID_URL, url).groups()
+        webpage = self._download_webpage(
+            'http://%s/embed/%s' % (domain, video_id), video_id)
+        video_data = self._parse_json(self._search_regex(
+            r'Disney\.EmbedVideo=({.+});', webpage, 'embed data'), video_id)['video']
+
+        for external in video_data.get('externals', []):
+            if external.get('source') == 'vevo':
+                return self.url_result('vevo:' + external['data_id'], 'Vevo')
+
+        title = video_data['title']
+
+        formats = []
+        for flavor in video_data.get('flavors', []):
+            flavor_format = flavor.get('format')
+            flavor_url = flavor.get('url')
+            if not flavor_url or not re.match(r'https?://', flavor_url):
+                continue
+            tbr = int_or_none(flavor.get('bitrate'))
+            if tbr == 99999:
+                formats.extend(self._extract_m3u8_formats(
+                    flavor_url, video_id, 'mp4', m3u8_id=flavor_format, fatal=False))
+                continue
+            format_id = []
+            if flavor_format:
+                format_id.append(flavor_format)
+            if tbr:
+                format_id.append(compat_str(tbr))
+            ext = determine_ext(flavor_url)
+            if flavor_format == 'applehttp' or ext == 'm3u8':
+                ext = 'mp4'
+            width = int_or_none(flavor.get('width'))
+            height = int_or_none(flavor.get('height'))
+            formats.append({
+                'format_id': '-'.join(format_id),
+                'url': flavor_url,
+                'width': width,
+                'height': height,
+                'tbr': tbr,
+                'ext': ext,
+                'vcodec': 'none' if (width == 0 and height == 0) else None,
+            })
+        self._sort_formats(formats)
+
+        subtitles = {}
+        for caption in video_data.get('captions', []):
+            caption_url = caption.get('url')
+            caption_format = caption.get('format')
+            if not caption_url or caption_format.startswith('unknown'):
+                continue
+            subtitles.setdefault(caption.get('language', 'en'), []).append({
+                'url': caption_url,
+                'ext': {
+                    'webvtt': 'vtt',
+                }.get(caption_format, caption_format),
+            })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': video_data.get('description') or video_data.get('short_desc'),
+            'thumbnail': video_data.get('thumb') or video_data.get('thumb_secure'),
+            'duration': int_or_none(video_data.get('duration_sec')),
+            'upload_date': unified_strdate(video_data.get('publish_date')),
+            'formats': formats,
+            'subtitles': subtitles,
+        }

youtube_dl/extractor/douyutv.py

@@ -18,7 +18,7 @@ from ..utils import (
 
 class DouyuTVIE(InfoExtractor):
     IE_DESC = '斗鱼'
-    _VALID_URL = r'https?://(?:www\.)?douyu(?:tv)?\.com/(?P<id>[A-Za-z0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?douyu(?:tv)?\.com/(?:[^/]+/)*(?P<id>[A-Za-z0-9]+)'
     _TESTS = [{
         'url': 'http://www.douyutv.com/iseven',
         'info_dict': {
@@ -26,8 +26,8 @@ class DouyuTVIE(InfoExtractor):
             '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}$',
-            'description': 're:.*m7show@163\.com.*',
+            'description': r're:.*m7show@163\.com.*',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': '7师傅',
             'is_live': True,
         },
@@ -42,7 +42,7 @@ class DouyuTVIE(InfoExtractor):
             'ext': 'flv',
             'title': 're:^小漠从零单排记！——CSOL2躲猫猫 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
             'description': 'md5:746a2f7a253966a06755a912f0acc0d2',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': 'douyu小漠',
             'is_live': True,
         },
@@ -57,8 +57,8 @@ class DouyuTVIE(InfoExtractor):
             'display_id': '17732',
             '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}$',
-            'description': 're:.*m7show@163\.com.*',
+            'description': r're:.*m7show@163\.com.*',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': '7师傅',
             'is_live': True,
         },
@@ -68,6 +68,10 @@ class DouyuTVIE(InfoExtractor):
     }, {
         'url': 'http://www.douyu.com/xiaocang',
         'only_matching': True,
+    }, {
+        # \"room_id\"
+        'url': 'http://www.douyu.com/t/lpl',
+        'only_matching': True,
     }]
 
     # Decompile core.swf in webpage by ffdec "Search SWFs in memory". core.swf
@@ -82,7 +86,7 @@ class DouyuTVIE(InfoExtractor):
         else:
             page = self._download_webpage(url, video_id)
             room_id = self._html_search_regex(
-                r'"room_id"\s*:\s*(\d+),', page, 'room id')
+                r'"room_id\\?"\s*:\s*(\d+),', page, 'room id')
 
         room = self._download_json(
             'http://m.douyu.com/html5/live?roomId=%s' % room_id, video_id,

youtube_dl/extractor/dramafever.py

@@ -66,7 +66,7 @@ class DramaFeverBaseIE(AMPIE):
 
 class DramaFeverIE(DramaFeverBaseIE):
     IE_NAME = 'dramafever'
-    _VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+/[0-9]+)(?:/|$)'
+    _VALID_URL = r'https?://(?:www\.)?dramafever\.com/(?:[^/]+/)?drama/(?P<id>[0-9]+/[0-9]+)(?:/|$)'
     _TESTS = [{
         'url': 'http://www.dramafever.com/drama/4512/1/Cooking_with_Shin/',
         'info_dict': {
@@ -76,7 +76,7 @@ class DramaFeverIE(DramaFeverBaseIE):
             'description': 'md5:a8eec7942e1664a6896fcd5e1287bfd0',
             'episode': 'Episode 1',
             'episode_number': 1,
-            'thumbnail': 're:^https?://.*\.jpg',
+            'thumbnail': r're:^https?://.*\.jpg',
             'timestamp': 1404336058,
             'upload_date': '20140702',
             'duration': 343,
@@ -94,7 +94,7 @@ class DramaFeverIE(DramaFeverBaseIE):
             'description': 'md5:3ff2ee8fedaef86e076791c909cf2e91',
             'episode': 'Mnet Asian Music Awards 2015 - Part 3',
             'episode_number': 4,
-            'thumbnail': 're:^https?://.*\.jpg',
+            'thumbnail': r're:^https?://.*\.jpg',
             'timestamp': 1450213200,
             'upload_date': '20151215',
             'duration': 5602,
@@ -103,6 +103,9 @@ class DramaFeverIE(DramaFeverBaseIE):
             # m3u8 download
             'skip_download': True,
         },
+    }, {
+        'url': 'https://www.dramafever.com/zh-cn/drama/4972/15/Doctor_Romantic/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -148,7 +151,7 @@ class DramaFeverIE(DramaFeverBaseIE):
 
 class DramaFeverSeriesIE(DramaFeverBaseIE):
     IE_NAME = 'dramafever:series'
-    _VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+)(?:/(?:(?!\d+(?:/|$)).+)?)?$'
+    _VALID_URL = r'https?://(?:www\.)?dramafever\.com/(?:[^/]+/)?drama/(?P<id>[0-9]+)(?:/(?:(?!\d+(?:/|$)).+)?)?$'
     _TESTS = [{
         'url': 'http://www.dramafever.com/drama/4512/Cooking_with_Shin/',
         'info_dict': {

youtube_dl/extractor/drbonanza.py

@@ -20,7 +20,7 @@ class DRBonanzaIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Talkshowet - Leonard Cohen',
             'description': 'md5:8f34194fb30cd8c8a30ad8b27b70c0ca',
-            'thumbnail': 're:^https?://.*\.(?:gif|jpg)$',
+            'thumbnail': r're:^https?://.*\.(?:gif|jpg)$',
             'timestamp': 1295537932,
             'upload_date': '20110120',
             'duration': 3664,
@@ -36,7 +36,7 @@ class DRBonanzaIE(InfoExtractor):
             'ext': 'mp3',
             'title': 'EM fodbold 1992 Danmark - Tyskland finale Transmission',
             'description': 'md5:501e5a195749480552e214fbbed16c4e',
-            'thumbnail': 're:^https?://.*\.(?:gif|jpg)$',
+            'thumbnail': r're:^https?://.*\.(?:gif|jpg)$',
             'timestamp': 1223274900,
             'upload_date': '20081006',
             'duration': 7369,

youtube_dl/extractor/dreisat.py

@@ -2,10 +2,19 @@ from __future__ import unicode_literals
 
 import re
 
-from .zdf import ZDFIE
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    unified_strdate,
+    xpath_text,
+    determine_ext,
+    qualities,
+    float_or_none,
+    ExtractorError,
+)
 
 
-class DreiSatIE(ZDFIE):
+class DreiSatIE(InfoExtractor):
     IE_NAME = '3sat'
     _VALID_URL = r'(?:https?://)?(?:www\.)?3sat\.de/mediathek/(?:index\.php|mediathek\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
     _TESTS = [
@@ -31,6 +40,163 @@ class DreiSatIE(ZDFIE):
         },
     ]
 
+    def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None):
+        param_groups = {}
+        for param_group in smil.findall(self._xpath_ns('./head/paramGroup', namespace)):
+            group_id = param_group.attrib.get(self._xpath_ns('id', 'http://www.w3.org/XML/1998/namespace'))
+            params = {}
+            for param in param_group:
+                params[param.get('name')] = param.get('value')
+            param_groups[group_id] = params
+
+        formats = []
+        for video in smil.findall(self._xpath_ns('.//video', namespace)):
+            src = video.get('src')
+            if not src:
+                continue
+            bitrate = float_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000)
+            group_id = video.get('paramGroup')
+            param_group = param_groups[group_id]
+            for proto in param_group['protocols'].split(','):
+                formats.append({
+                    'url': '%s://%s' % (proto, param_group['host']),
+                    'app': param_group['app'],
+                    'play_path': src,
+                    'ext': 'flv',
+                    'format_id': '%s-%d' % (proto, bitrate),
+                    'tbr': bitrate,
+                })
+        self._sort_formats(formats)
+        return formats
+
+    def extract_from_xml_url(self, video_id, xml_url):
+        doc = self._download_xml(
+            xml_url, video_id,
+            note='Downloading video info',
+            errnote='Failed to download video info')
+
+        status_code = 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)
+
+        title = doc.find('.//information/title').text
+        description = xpath_text(doc, './/information/detail', 'description')
+        duration = int_or_none(xpath_text(doc, './/details/lengthSec', 'duration'))
+        uploader = xpath_text(doc, './/details/originChannelTitle', 'uploader')
+        uploader_id = xpath_text(doc, './/details/originChannelId', 'uploader id')
+        upload_date = unified_strdate(xpath_text(doc, './/details/airtime', 'upload date'))
+
+        def xml_to_thumbnails(fnode):
+            thumbnails = []
+            for node in fnode:
+                thumbnail_url = node.text
+                if not thumbnail_url:
+                    continue
+                thumbnail = {
+                    'url': thumbnail_url,
+                }
+                if 'key' in node.attrib:
+                    m = re.match('^([0-9]+)x([0-9]+)$', node.attrib['key'])
+                    if m:
+                        thumbnail['width'] = int(m.group(1))
+                        thumbnail['height'] = int(m.group(2))
+                thumbnails.append(thumbnail)
+            return thumbnails
+
+        thumbnails = xml_to_thumbnails(doc.findall('.//teaserimages/teaserimage'))
+
+        format_nodes = doc.findall('.//formitaeten/formitaet')
+        quality = qualities(['veryhigh', 'high', 'med', 'low'])
+
+        def get_quality(elem):
+            return quality(xpath_text(elem, 'quality'))
+        format_nodes.sort(key=get_quality)
+        format_ids = []
+        formats = []
+        for fnode in format_nodes:
+            video_url = fnode.find('url').text
+            is_available = 'http://www.metafilegenerator' not in video_url
+            if not is_available:
+                continue
+            format_id = fnode.attrib['basetype']
+            quality = xpath_text(fnode, './quality', 'quality')
+            format_m = re.match(r'''(?x)
+                (?P<vcodec>[^_]+)_(?P<acodec>[^_]+)_(?P<container>[^_]+)_
+                (?P<proto>[^_]+)_(?P<index>[^_]+)_(?P<indexproto>[^_]+)
+            ''', format_id)
+
+            ext = determine_ext(video_url, None) or format_m.group('container')
+            if ext not in ('smil', 'f4m', 'm3u8'):
+                format_id = format_id + '-' + quality
+            if format_id in format_ids:
+                continue
+
+            if ext == 'meta':
+                continue
+            elif ext == 'smil':
+                formats.extend(self._extract_smil_formats(
+                    video_url, video_id, fatal=False))
+            elif ext == 'm3u8':
+                # the certificates are misconfigured (see
+                # https://github.com/rg3/youtube-dl/issues/8665)
+                if video_url.startswith('https://'):
+                    continue
+                formats.extend(self._extract_m3u8_formats(
+                    video_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
+            elif ext == 'f4m':
+                formats.extend(self._extract_f4m_formats(
+                    video_url, video_id, f4m_id=format_id, fatal=False))
+            else:
+                proto = format_m.group('proto').lower()
+
+                abr = int_or_none(xpath_text(fnode, './audioBitrate', 'abr'), 1000)
+                vbr = int_or_none(xpath_text(fnode, './videoBitrate', 'vbr'), 1000)
+
+                width = int_or_none(xpath_text(fnode, './width', 'width'))
+                height = int_or_none(xpath_text(fnode, './height', 'height'))
+
+                filesize = int_or_none(xpath_text(fnode, './filesize', 'filesize'))
+
+                format_note = ''
+                if not format_note:
+                    format_note = None
+
+                formats.append({
+                    'format_id': format_id,
+                    'url': video_url,
+                    'ext': ext,
+                    'acodec': format_m.group('acodec'),
+                    'vcodec': format_m.group('vcodec'),
+                    'abr': abr,
+                    'vbr': vbr,
+                    'width': width,
+                    'height': height,
+                    'filesize': filesize,
+                    'format_note': format_note,
+                    'protocol': proto,
+                    '_available': is_available,
+                })
+            format_ids.append(format_id)
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'thumbnails': thumbnails,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'upload_date': upload_date,
+            'formats': formats,
+        }
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')

youtube_dl/extractor/drtuber.py

@@ -22,7 +22,7 @@ class DrTuberIE(InfoExtractor):
             'like_count': int,
             'comment_count': int,
             'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
-            'thumbnail': 're:https?://.*\.jpg$',
+            'thumbnail': r're:https?://.*\.jpg$',
             'age_limit': 18,
         }
     }, {

youtube_dl/extractor/drtv.py

@@ -9,12 +9,13 @@ from ..utils import (
     mimetype2ext,
     parse_iso8601,
     remove_end,
+    update_url_query,
 )
 
 
 class DRTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv/se|nyheder)/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
+    _VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv/se|nyheder|radio/ondemand)/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
-
+    IE_NAME = 'drtv'
     _TESTS = [{
         'url': 'https://www.dr.dk/tv/se/boern/ultra/klassen-ultra/klassen-darlig-taber-10',
         'md5': '25e659cccc9a2ed956110a299fdf5983',
@@ -79,9 +80,10 @@ class DRTVIE(InfoExtractor):
         subtitles = {}
 
         for asset in data['Assets']:
-            if asset.get('Kind') == 'Image':
+            kind = asset.get('Kind')
+            if kind == 'Image':
                 thumbnail = asset.get('Uri')
-            elif asset.get('Kind') == 'VideoResource':
+            elif kind in ('VideoResource', 'AudioResource'):
                 duration = float_or_none(asset.get('DurationInMilliseconds'), 1000)
                 restricted_to_denmark = asset.get('RestrictedToDenmark')
                 spoken_subtitles = asset.get('Target') == 'SpokenSubtitles'
@@ -96,9 +98,13 @@ class DRTVIE(InfoExtractor):
                         preference = -1
                         format_id += '-spoken-subtitles'
                     if target == 'HDS':
-                        formats.extend(self._extract_f4m_formats(
+                        f4m_formats = self._extract_f4m_formats(
                             uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43',
-                            video_id, preference, f4m_id=format_id))
+                            video_id, preference, f4m_id=format_id)
+                        if kind == 'AudioResource':
+                            for f in f4m_formats:
+                                f['vcodec'] = 'none'
+                        formats.extend(f4m_formats)
                     elif target == 'HLS':
                         formats.extend(self._extract_m3u8_formats(
                             uri, video_id, 'mp4', entry_protocol='m3u8_native',
@@ -112,6 +118,7 @@ class DRTVIE(InfoExtractor):
                             'format_id': format_id,
                             'tbr': int_or_none(bitrate),
                             'ext': link.get('FileFormat'),
+                            'vcodec': 'none' if kind == 'AudioResource' else None,
                         })
                 subtitles_list = asset.get('SubtitlesList')
                 if isinstance(subtitles_list, list):
@@ -144,3 +151,58 @@ class DRTVIE(InfoExtractor):
             'formats': formats,
             'subtitles': subtitles,
         }
+
+
+class DRTVLiveIE(InfoExtractor):
+    IE_NAME = 'drtv:live'
+    _VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv|TV)/live/(?P<id>[\da-z-]+)'
+    _TEST = {
+        'url': 'https://www.dr.dk/tv/live/dr1',
+        'info_dict': {
+            'id': 'dr1',
+            'ext': 'mp4',
+            'title': 're:^DR1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        channel_id = self._match_id(url)
+        channel_data = self._download_json(
+            'https://www.dr.dk/mu-online/api/1.0/channel/' + channel_id,
+            channel_id)
+        title = self._live_title(channel_data['Title'])
+
+        formats = []
+        for streaming_server in channel_data.get('StreamingServers', []):
+            server = streaming_server.get('Server')
+            if not server:
+                continue
+            link_type = streaming_server.get('LinkType')
+            for quality in streaming_server.get('Qualities', []):
+                for stream in quality.get('Streams', []):
+                    stream_path = stream.get('Stream')
+                    if not stream_path:
+                        continue
+                    stream_url = update_url_query(
+                        '%s/%s' % (server, stream_path), {'b': ''})
+                    if link_type == 'HLS':
+                        formats.extend(self._extract_m3u8_formats(
+                            stream_url, channel_id, 'mp4',
+                            m3u8_id=link_type, fatal=False, live=True))
+                    elif link_type == 'HDS':
+                        formats.extend(self._extract_f4m_formats(update_url_query(
+                            '%s/%s' % (server, stream_path), {'hdcore': '3.7.0'}),
+                            channel_id, f4m_id=link_type, fatal=False))
+        self._sort_formats(formats)
+
+        return {
+            'id': channel_id,
+            'title': title,
+            'thumbnail': channel_data.get('PrimaryImageUri'),
+            'formats': formats,
+            'is_live': True,
+        }

youtube_dl/extractor/dumpert.py

@@ -21,7 +21,7 @@ class DumpertIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Ik heb nieuws voor je',
             'description': 'Niet schrikken hoor',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
         }
     }, {
         'url': 'http://www.dumpert.nl/embed/6675421/dc440fe7/',

youtube_dl/extractor/eagleplatform.py

@@ -31,7 +31,7 @@ class EaglePlatformIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Навальный вышел на свободу',
             'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'duration': 87,
             'view_count': int,
             'age_limit': 0,
@@ -45,7 +45,7 @@ class EaglePlatformIE(InfoExtractor):
             'id': '12820',
             'ext': 'mp4',
             'title': "'O Sole Mio",
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'duration': 216,
             'view_count': int,
         },

youtube_dl/extractor/egghead.py

@@ -0,0 +1,39 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class EggheadCourseIE(InfoExtractor):
+    IE_DESC = 'egghead.io course'
+    IE_NAME = 'egghead:course'
+    _VALID_URL = r'https://egghead\.io/courses/(?P<id>[a-zA-Z_0-9-]+)'
+    _TEST = {
+        'url': 'https://egghead.io/courses/professor-frisby-introduces-composable-functional-javascript',
+        'playlist_count': 29,
+        'info_dict': {
+            'id': 'professor-frisby-introduces-composable-functional-javascript',
+            'title': 'Professor Frisby Introduces Composable Functional JavaScript',
+            'description': 're:(?s)^This course teaches the ubiquitous.*You\'ll start composing functionality before you know it.$',
+        },
+    }
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+
+        title = self._html_search_regex(r'<h1 class="title">([^<]+)</h1>', webpage, 'title')
+        ul = self._search_regex(r'(?s)<ul class="series-lessons-list">(.*?)</ul>', webpage, 'session list')
+
+        found = re.findall(r'(?s)<a class="[^"]*"\s*href="([^"]+)">\s*<li class="item', ul)
+        entries = [self.url_result(m) for m in found]
+
+        return {
+            '_type': 'playlist',
+            'id': playlist_id,
+            'title': title,
+            'description': self._og_search_description(webpage),
+            'entries': entries,
+        }

youtube_dl/extractor/einthusan.py

@@ -19,7 +19,7 @@ class EinthusanIE(InfoExtractor):
                 'id': '2447',
                 'ext': 'mp4',
                 'title': 'Ek Villain',
-                'thumbnail': 're:^https?://.*\.jpg$',
+                'thumbnail': r're:^https?://.*\.jpg$',
                 'description': 'md5:9d29fc91a7abadd4591fb862fa560d93',
             }
         },
@@ -30,7 +30,7 @@ class EinthusanIE(InfoExtractor):
                 'id': '1671',
                 'ext': 'mp4',
                 'title': 'Soodhu Kavvuum',
-                'thumbnail': 're:^https?://.*\.jpg$',
+                'thumbnail': r're:^https?://.*\.jpg$',
                 'description': 'md5:b40f2bf7320b4f9414f3780817b2af8c',
             }
         },

youtube_dl/extractor/elpais.py

@@ -2,7 +2,7 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import unified_strdate
+from ..utils import strip_jsonp, unified_strdate
 
 
 class ElPaisIE(InfoExtractor):
@@ -29,6 +29,16 @@ class ElPaisIE(InfoExtractor):
             'description': 'Que sí, que las cápsulas son cómodas. Pero si le pides algo más a la vida, quizá deberías aprender a usar bien la cafetera italiana. No tienes más que ver este vídeo y seguir sus siete normas básicas.',
             'upload_date': '20160303',
         }
+    }, {
+        'url': 'http://elpais.com/elpais/2017/01/26/ciencia/1485456786_417876.html',
+        'md5': '9c79923a118a067e1a45789e1e0b0f9c',
+        'info_dict': {
+            'id': '1485456786_417876',
+            'ext': 'mp4',
+            'title': 'Hallado un barco de la antigua Roma que naufragó en Baleares hace 1.800 años',
+            'description': 'La nave portaba cientos de ánforas y se hundió cerca de la isla de Cabrera por razones desconocidas',
+            'upload_date': '20170127',
+        },
     }]
 
     def _real_extract(self, url):
@@ -37,6 +47,13 @@ class ElPaisIE(InfoExtractor):
 
         prefix = self._html_search_regex(
             r'var\s+url_cache\s*=\s*"([^"]+)";', webpage, 'URL prefix')
+        id_multimedia = self._search_regex(
+            r"id_multimedia\s*=\s*'([^']+)'", webpage, 'ID multimedia', default=None)
+        if id_multimedia:
+            url_info = self._download_json(
+                'http://elpais.com/vdpep/1/?pepid=' + id_multimedia, video_id, transform_source=strip_jsonp)
+            video_suffix = url_info['mp4']
+        else:
             video_suffix = self._search_regex(
                 r"(?:URLMediaFile|urlVideo_\d+)\s*=\s*url_cache\s*\+\s*'([^']+)'", webpage, 'video URL')
         video_url = prefix + video_suffix

youtube_dl/extractor/eroprofile.py

@@ -22,7 +22,7 @@ class EroProfileIE(InfoExtractor):
             'display_id': 'sexy-babe-softcore',
             'ext': 'm4v',
             'title': 'sexy babe softcore',
-            'thumbnail': 're:https?://.*\.jpg',
+            'thumbnail': r're:https?://.*\.jpg',
             'age_limit': 18,
         }
     }, {
@@ -32,7 +32,7 @@ class EroProfileIE(InfoExtractor):
             'id': '1133519',
             'ext': 'm4v',
             'title': 'Try It On Pee_cut_2.wmv - 4shared.com - file sharing - download movie file',
-            'thumbnail': 're:https?://.*\.jpg',
+            'thumbnail': r're:https?://.*\.jpg',
             'age_limit': 18,
         },
         'skip': 'Requires login',

youtube_dl/extractor/escapist.py

@@ -45,7 +45,7 @@ class EscapistIE(InfoExtractor):
             '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.",
             'title': "Breaking Down Baldur's Gate",
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'duration': 264,
             'uploader': 'The Escapist',
         }
@@ -57,7 +57,7 @@ class EscapistIE(InfoExtractor):
             'ext': 'mp4',
             'description': 'This week, Zero Punctuation reviews Evolve.',
             'title': 'Evolve - One vs Multiplayer',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'duration': 304,
             'uploader': 'The Escapist',
         }

youtube_dl/extractor/esri.py

@@ -22,7 +22,7 @@ class EsriVideoIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'ArcGIS Online - Developing Applications',
             'description': 'Jeremy Bartley demonstrates how to develop applications with ArcGIS Online.',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'duration': 185,
             'upload_date': '20120419',
         }

youtube_dl/extractor/europa.py

@@ -23,7 +23,7 @@ class EuropaIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'TRADE - Wikileaks on TTIP',
             'description': 'NEW  LIVE EC Midday press briefing of 11/08/2015',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'upload_date': '20150811',
             'duration': 34,
             'view_count': int,

youtube_dl/extractor/expotv.py

@@ -17,7 +17,7 @@ class ExpoTVIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'NYX Butter Lipstick Little Susie',
             'description': 'Goes on like butter, but looks better!',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': 'Stephanie S.',
             'upload_date': '20150520',
             'view_count': int,

youtube_dl/extractor/extractors.py

@@ -30,7 +30,10 @@ from .aenetworks import (
     AENetworksIE,
     HistoryTopicIE,
 )
-from .afreecatv import AfreecaTVIE
+from .afreecatv import (
+    AfreecaTVIE,
+    AfreecaTVGlobalIE,
+)
 from .airmozilla import AirMozillaIE
 from .aljazeera import AlJazeeraIE
 from .alphaporno import AlphaPornoIE
@@ -38,10 +41,7 @@ from .amcnetworks import AMCNetworksIE
 from .animeondemand import AnimeOnDemandIE
 from .anitube import AnitubeIE
 from .anysex import AnySexIE
-from .aol import (
+from .aol import AolIE
-    AolIE,
-    AolFeaturesIE,
-)
 from .allocine import AllocineIE
 from .aparat import AparatIE
 from .appleconnect import AppleConnectIE
@@ -80,6 +80,10 @@ from .awaan import (
     AWAANLiveIE,
     AWAANSeasonIE,
 )
+from .azmedien import (
+    AZMedienIE,
+    AZMedienPlaylistIE,
+)
 from .azubu import AzubuIE, AzubuLiveIE
 from .baidu import BaiduVideoIE
 from .bambuser import BambuserIE, BambuserChannelIE
@@ -91,6 +95,7 @@ from .bbc import (
     BBCCoUkPlaylistIE,
     BBCIE,
 )
+from .beampro import BeamProLiveIE
 from .beeg import BeegIE
 from .behindkink import BehindKinkIE
 from .bellmedia import BellMediaIE
@@ -98,7 +103,10 @@ from .beatport import BeatportIE
 from .bet import BetIE
 from .bigflix import BigflixIE
 from .bild import BildIE
-from .bilibili import BiliBiliIE
+from .bilibili import (
+    BiliBiliIE,
+    BiliBiliBangumiIE,
+)
 from .biobiochiletv import BioBioChileTVIE
 from .biqle import BIQLEIE
 from .bleacherreport import (
@@ -240,12 +248,16 @@ from .dramafever import (
 from .dreisat import DreiSatIE
 from .drbonanza import DRBonanzaIE
 from .drtuber import DrTuberIE
-from .drtv import DRTVIE
+from .drtv import (
+    DRTVIE,
+    DRTVLiveIE,
+)
 from .dvtv import DVTVIE
 from .dumpert import DumpertIE
 from .defense import DefenseGouvFrIE
 from .discovery import DiscoveryIE
 from .discoverygo import DiscoveryGoIE
+from .disney import DisneyIE
 from .dispeak import DigitallySpeakingIE
 from .dropbox import DropboxIE
 from .dw import (
@@ -255,6 +267,7 @@ from .dw import (
 from .eagleplatform import EaglePlatformIE
 from .ebaumsworld import EbaumsWorldIE
 from .echomsk import EchoMskIE
+from .egghead import EggheadCourseIE
 from .ehow import EHowIE
 from .eighttracks import EightTracksIE
 from .einthusan import EinthusanIE
@@ -289,6 +302,10 @@ from .fc2 import (
     FC2EmbedIE,
 )
 from .fczenit import FczenitIE
+from .filmon import (
+    FilmOnIE,
+    FilmOnChannelIE,
+)
 from .firstpost import FirstpostIE
 from .firsttv import FirstTVIE
 from .fivemin import FiveMinIE
@@ -332,6 +349,7 @@ from .gameone import (
 from .gamersyde import GamersydeIE
 from .gamespot import GameSpotIE
 from .gamestar import GameStarIE
+from .gaskrank import GaskrankIE
 from .gazeta import GazetaIE
 from .gdcvault import GDCVaultIE
 from .generic import GenericIE
@@ -369,6 +387,7 @@ from .hgtv import (
 )
 from .historicfilms import HistoricFilmsIE
 from .hitbox import HitboxIE, HitboxLiveIE
+from .hitrecord import HitRecordIE
 from .hornbunny import HornBunnyIE
 from .hotnewhiphop import HotNewHipHopIE
 from .hotstar import HotStarIE
@@ -396,6 +415,7 @@ from .imgur import (
     ImgurAlbumIE,
 )
 from .ina import InaIE
+from .inc import IncIE
 from .indavideo import (
     IndavideoIE,
     IndavideoEmbedIE,
@@ -406,6 +426,7 @@ from .internetvideoarchive import InternetVideoArchiveIE
 from .iprima import IPrimaIE
 from .iqiyi import IqiyiIE
 from .ir90tv import Ir90TvIE
+from .itv import ITVIE
 from .ivi import (
     IviIE,
     IviCompilationIE
@@ -544,6 +565,7 @@ from .mtv import (
     MTVVideoIE,
     MTVServicesEmbeddedIE,
     MTVDEIE,
+    MTV81IE,
 )
 from .muenchentv import MuenchenTVIE
 from .musicplayon import MusicPlayOnIE
@@ -593,6 +615,7 @@ from .nextmedia import (
     NextMediaIE,
     NextMediaActionNewsIE,
     AppleDailyIE,
+    NextTVIE,
 )
 from .nfb import NFBIE
 from .nfl import NFLIE
@@ -656,6 +679,7 @@ from .nrk import (
     NRKTVIE,
     NRKTVDirekteIE,
     NRKTVEpisodesIE,
+    NRKTVSeriesIE,
 )
 from .ntvde import NTVDeIE
 from .ntvru import NTVRuIE
@@ -719,6 +743,7 @@ from .polskieradio import (
 )
 from .porn91 import Porn91IE
 from .porncom import PornComIE
+from .pornflip import PornFlipIE
 from .pornhd import PornHdIE
 from .pornhub import (
     PornHubIE,
@@ -813,7 +838,7 @@ from .sbs import SBSIE
 from .scivee import SciVeeIE
 from .screencast import ScreencastIE
 from .screencastomatic import ScreencastOMaticIE
-from .screenjunkies import ScreenJunkiesIE
+from .scrippsnetworks import ScrippsNetworksWatchIE
 from .seeker import SeekerIE
 from .senateisvp import SenateISVPIE
 from .sendtonews import SendtoNewsIE
@@ -824,7 +849,6 @@ from .shared import (
     SharedIE,
     VivoIE,
 )
-from .sharesix import ShareSixIE
 from .showroomlive import ShowRoomLiveIE
 from .sina import SinaIE
 from .sixplay import SixPlayIE
@@ -869,12 +893,10 @@ from .spiegeltv import SpiegeltvIE
 from .spike import SpikeIE
 from .stitcher import StitcherIE
 from .sport5 import Sport5IE
-from .sportbox import (
+from .sportbox import SportBoxEmbedIE
-    SportBoxIE,
-    SportBoxEmbedIE,
-)
 from .sportdeutschland import SportDeutschlandIE
 from .sportschau import SportschauIE
+from .sprout import SproutIE
 from .srgssr import (
     SRGSSRIE,
     SRGSSRPlayIE,
@@ -976,6 +998,7 @@ from .tv2 import (
 )
 from .tv3 import TV3IE
 from .tv4 import TV4IE
+from .tva import TVAIE
 from .tvanouvelles import (
     TVANouvellesIE,
     TVANouvellesArticleIE,
@@ -1075,7 +1098,7 @@ from .videomore import (
     VideomoreSeasonIE,
 )
 from .videopremium import VideoPremiumIE
-from .videott import VideoTtIE
+from .videopress import VideoPressIE
 from .vidio import VidioIE
 from .vidme import (
     VidmeIE,
@@ -1120,7 +1143,10 @@ from .vk import (
     VKUserVideosIE,
     VKWallPostIE,
 )
-from .vlive import VLiveIE
+from .vlive import (
+    VLiveIE,
+    VLiveChannelIE
+)
 from .vodlocker import VodlockerIE
 from .vodplatform import VODPlatformIE
 from .voicerepublic import VoiceRepublicIE

youtube_dl/extractor/facebook.py

@@ -12,14 +12,16 @@ from ..compat import (
     compat_urllib_parse_unquote_plus,
 )
 from ..utils import (
+    clean_html,
     error_to_compat_str,
     ExtractorError,
+    get_element_by_id,
     int_or_none,
+    js_to_json,
     limit_length,
     sanitized_Request,
+    try_get,
     urlencode_postdata,
-    get_element_by_id,
-    clean_html,
 )
 
 
@@ -71,7 +73,7 @@ class FacebookIE(InfoExtractor):
         'info_dict': {
             'id': '274175099429670',
             'ext': 'mp4',
-            'title': 'Facebook video #274175099429670',
+            'title': 'Asif Nawab Butt posted a video to his Timeline.',
             'uploader': 'Asif Nawab Butt',
             'upload_date': '20140506',
             'timestamp': 1399398998,
@@ -132,6 +134,20 @@ class FacebookIE(InfoExtractor):
             'upload_date': '20161030',
             'uploader': 'CNN',
         },
+    }, {
+        # bigPipe.onPageletArrive ... onPageletArrive pagelet_group_mall
+        'url': 'https://www.facebook.com/yaroslav.korpan/videos/1417995061575415/',
+        'info_dict': {
+            'id': '1417995061575415',
+            'ext': 'mp4',
+            'title': 'md5:a7b86ca673f51800cd54687b7f4012fe',
+            'timestamp': 1486648217,
+            'upload_date': '20170209',
+            'uploader': 'Yaroslav Korpan',
+        },
+        'params': {
+            'skip_download': True,
+        },
     }, {
         'url': 'https://www.facebook.com/video.php?v=10204634152394104',
         'only_matching': True,
@@ -243,14 +259,30 @@ class FacebookIE(InfoExtractor):
 
         video_data = None
 
-        server_js_data = self._parse_json(self._search_regex(
+        def extract_video_data(instances):
-            r'handleServerJS\(({.+})(?:\);|,")', webpage, 'server js data', default='{}'), video_id)
+            for item in instances:
-        for item in server_js_data.get('instances', []):
                 if item[1][0] == 'VideoConfig':
                     video_item = item[2][0]
                     if video_item.get('video_id') == video_id:
-                    video_data = video_item['videoData']
+                        return video_item['videoData']
-                    break
+
+        server_js_data = self._parse_json(self._search_regex(
+            r'handleServerJS\(({.+})(?:\);|,")', webpage,
+            'server js data', default='{}'), video_id, fatal=False)
+
+        if server_js_data:
+            video_data = extract_video_data(server_js_data.get('instances', []))
+
+        if not video_data:
+            server_js_data = self._parse_json(
+                self._search_regex(
+                    r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+(?:stream_pagelet|pagelet_group_mall)',
+                    webpage, 'js data', default='{}'),
+                video_id, transform_source=js_to_json, fatal=False)
+            if server_js_data:
+                video_data = extract_video_data(try_get(
+                    server_js_data, lambda x: x['jsmods']['instances'],
+                    list) or [])
 
         if not video_data:
             if not fatal_if_no_video:
@@ -300,10 +332,16 @@ class FacebookIE(InfoExtractor):
             video_title = self._html_search_regex(
                 r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>',
                 webpage, 'alternative title', default=None)
-            video_title = limit_length(video_title, 80)
         if not video_title:
+            video_title = self._html_search_meta(
+                'description', webpage, 'title')
+        if video_title:
+            video_title = limit_length(video_title, 80)
+        else:
             video_title = 'Facebook video #%s' % video_id
-        uploader = clean_html(get_element_by_id('fbPhotoPageAuthorName', webpage))
+        uploader = clean_html(get_element_by_id(
+            'fbPhotoPageAuthorName', webpage)) or self._search_regex(
+            r'ownerName\s*:\s*"([^"]+)"', webpage, 'uploader', fatal=False)
         timestamp = int_or_none(self._search_regex(
             r'<abbr[^>]+data-utime=["\'](\d+)', webpage,
             'timestamp', default=None))

youtube_dl/extractor/fc2.py

@@ -133,7 +133,7 @@ class FC2EmbedIE(InfoExtractor):
             'id': '201403223kCqB3Ez',
             'ext': 'flv',
             'title': 'プリズン･ブレイク S1-01 マイケル 【吹替】',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
         },
     }
 

youtube_dl/extractor/filmon.py

@@ -0,0 +1,178 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_str,
+    compat_HTTPError,
+)
+from ..utils import (
+    qualities,
+    strip_or_none,
+    int_or_none,
+    ExtractorError,
+)
+
+
+class FilmOnIE(InfoExtractor):
+    IE_NAME = 'filmon'
+    _VALID_URL = r'(?:https?://(?:www\.)?filmon\.com/vod/view/|filmon:)(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.filmon.com/vod/view/24869-0-plan-9-from-outer-space',
+        'info_dict': {
+            'id': '24869',
+            'ext': 'mp4',
+            'title': 'Plan 9 From Outer Space',
+            'description': 'Dead human, zombies and vampires',
+        },
+    }, {
+        'url': 'https://www.filmon.com/vod/view/2825-1-popeye-series-1',
+        'info_dict': {
+            'id': '2825',
+            'title': 'Popeye Series 1',
+            'description': 'The original series of Popeye.',
+        },
+        'playlist_mincount': 8,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        try:
+            response = self._download_json(
+                'https://www.filmon.com/api/vod/movie?id=%s' % video_id,
+                video_id)['response']
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError):
+                errmsg = self._parse_json(e.cause.read().decode(), video_id)['reason']
+                raise ExtractorError('%s said: %s' % (self.IE_NAME, errmsg), expected=True)
+            raise
+
+        title = response['title']
+        description = strip_or_none(response.get('description'))
+
+        if response.get('type_id') == 1:
+            entries = [self.url_result('filmon:' + episode_id) for episode_id in response.get('episodes', [])]
+            return self.playlist_result(entries, video_id, title, description)
+
+        QUALITY = qualities(('low', 'high'))
+        formats = []
+        for format_id, stream in response.get('streams', {}).items():
+            stream_url = stream.get('url')
+            if not stream_url:
+                continue
+            formats.append({
+                'format_id': format_id,
+                'url': stream_url,
+                'ext': 'mp4',
+                'quality': QUALITY(stream.get('quality')),
+                'protocol': 'm3u8_native',
+            })
+        self._sort_formats(formats)
+
+        thumbnails = []
+        poster = response.get('poster', {})
+        thumbs = poster.get('thumbs', {})
+        thumbs['poster'] = poster
+        for thumb_id, thumb in thumbs.items():
+            thumb_url = thumb.get('url')
+            if not thumb_url:
+                continue
+            thumbnails.append({
+                'id': thumb_id,
+                'url': thumb_url,
+                'width': int_or_none(thumb.get('width')),
+                'height': int_or_none(thumb.get('height')),
+            })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'description': description,
+            'thumbnails': thumbnails,
+        }
+
+
+class FilmOnChannelIE(InfoExtractor):
+    IE_NAME = 'filmon:channel'
+    _VALID_URL = r'https?://(?:www\.)?filmon\.com/(?:tv|channel)/(?P<id>[a-z0-9-]+)'
+    _TESTS = [{
+        # VOD
+        'url': 'http://www.filmon.com/tv/sports-haters',
+        'info_dict': {
+            'id': '4190',
+            'ext': 'mp4',
+            'title': 'Sports Haters',
+            'description': 'md5:dabcb4c1d9cfc77085612f1a85f8275d',
+        },
+    }, {
+        # LIVE
+        'url': 'https://www.filmon.com/channel/filmon-sports',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.filmon.com/tv/2894',
+        'only_matching': True,
+    }]
+
+    _THUMBNAIL_RES = [
+        ('logo', 56, 28),
+        ('big_logo', 106, 106),
+        ('extra_big_logo', 300, 300),
+    ]
+
+    def _real_extract(self, url):
+        channel_id = self._match_id(url)
+
+        try:
+            channel_data = self._download_json(
+                'http://www.filmon.com/api-v2/channel/' + channel_id, channel_id)['data']
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError):
+                errmsg = self._parse_json(e.cause.read().decode(), channel_id)['message']
+                raise ExtractorError('%s said: %s' % (self.IE_NAME, errmsg), expected=True)
+            raise
+
+        channel_id = compat_str(channel_data['id'])
+        is_live = not channel_data.get('is_vod') and not channel_data.get('is_vox')
+        title = channel_data['title']
+
+        QUALITY = qualities(('low', 'high'))
+        formats = []
+        for stream in channel_data.get('streams', []):
+            stream_url = stream.get('url')
+            if not stream_url:
+                continue
+            if not is_live:
+                formats.extend(self._extract_wowza_formats(
+                    stream_url, channel_id, skip_protocols=['dash', 'rtmp', 'rtsp']))
+                continue
+            quality = stream.get('quality')
+            formats.append({
+                'format_id': quality,
+                # this is an m3u8 stream, but we are deliberately not using _extract_m3u8_formats
+                # because it doesn't have bitrate variants anyway
+                'url': stream_url,
+                'ext': 'mp4',
+                'quality': QUALITY(quality),
+            })
+        self._sort_formats(formats)
+
+        thumbnails = []
+        for name, width, height in self._THUMBNAIL_RES:
+            thumbnails.append({
+                'id': name,
+                'url': 'http://static.filmon.com/assets/channels/%s/%s.png' % (channel_id, name),
+                'width': width,
+                'height': height,
+            })
+
+        return {
+            'id': channel_id,
+            'display_id': channel_data.get('alias'),
+            'title': self._live_title(title) if is_live else title,
+            'description': channel_data.get('description'),
+            'thumbnails': thumbnails,
+            'formats': formats,
+            'is_live': is_live,
+        }

youtube_dl/extractor/firsttv.py

@@ -26,7 +26,7 @@ class FirstTVIE(InfoExtractor):
             'id': '40049',
             'ext': 'mp4',
             'title': 'Гость Людмила Сенчина. Наедине со всеми. Выпуск от 12.02.2015',
-            'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
+            'thumbnail': r're:^https?://.*\.(?:jpg|JPG)$',
             'upload_date': '20150212',
             'duration': 2694,
         },
@@ -37,7 +37,7 @@ class FirstTVIE(InfoExtractor):
             'id': '364746',
             'ext': 'mp4',
             'title': 'Весенняя аллергия. Доброе утро. Фрагмент выпуска от 07.04.2016',
-            'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
+            'thumbnail': r're:^https?://.*\.(?:jpg|JPG)$',
             'upload_date': '20160407',
             'duration': 179,
             'formats': 'mincount:3',
@@ -86,18 +86,43 @@ class FirstTVIE(InfoExtractor):
             title = item['title']
             quality = qualities(QUALITIES)
             formats = []
+            path = None
             for f in item.get('mbr', []):
                 src = f.get('src')
                 if not src or not isinstance(src, compat_str):
                     continue
                 tbr = int_or_none(self._search_regex(
                     r'_(\d{3,})\.mp4', src, 'tbr', default=None))
+                if not path:
+                    path = self._search_regex(
+                        r'//[^/]+/(.+?)_\d+\.mp4', src,
+                        'm3u8 path', default=None)
                 formats.append({
                     'url': src,
                     'format_id': f.get('name'),
                     'tbr': tbr,
-                    'quality': quality(f.get('name')),
+                    'source_preference': quality(f.get('name')),
                 })
+            # m3u8 URL format is reverse engineered from [1] (search for
+            # master.m3u8). dashEdges (that is currently balancer-vod.1tv.ru)
+            # is taken from [2].
+            # 1. http://static.1tv.ru/player/eump1tv-current/eump-1tv.all.min.js?rnd=9097422834:formatted
+            # 2. http://static.1tv.ru/player/eump1tv-config/config-main.js?rnd=9097422834
+            if not path and len(formats) == 1:
+                path = self._search_regex(
+                    r'//[^/]+/(.+?$)', formats[0]['url'],
+                    'm3u8 path', default=None)
+            if path:
+                if len(formats) == 1:
+                    m3u8_path = ','
+                else:
+                    tbrs = [compat_str(t) for t in sorted(f['tbr'] for f in formats)]
+                    m3u8_path = '_,%s,%s' % (','.join(tbrs), '.mp4')
+                formats.extend(self._extract_m3u8_formats(
+                    'http://balancer-vod.1tv.ru/%s%s.urlset/master.m3u8'
+                    % (path, m3u8_path),
+                    display_id, 'mp4',
+                    entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
             self._sort_formats(formats)
 
             thumbnail = item.get('poster') or self._og_search_thumbnail(webpage)

youtube_dl/extractor/fivetv.py

@@ -25,7 +25,7 @@ class FiveTVIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Россияне выбрали имя для общенациональной платежной системы',
             'description': 'md5:a8aa13e2b7ad36789e9f77a74b6de660',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'duration': 180,
         },
     }, {
@@ -35,7 +35,7 @@ class FiveTVIE(InfoExtractor):
             'ext': 'mp4',
             'title': '3D принтер',
             'description': 'md5:d76c736d29ef7ec5c0cf7d7c65ffcb41',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'duration': 180,
         },
     }, {
@@ -44,7 +44,7 @@ class FiveTVIE(InfoExtractor):
             'id': 'glavnoe',
             'ext': 'mp4',
             'title': 'Итоги недели с 8 по 14 июня 2015 года',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
         },
     }, {
         'url': 'http://www.5-tv.ru/glavnoe/broadcasts/508645/',

youtube_dl/extractor/fktv.py

@@ -19,7 +19,7 @@ class FKTVIE(InfoExtractor):
             'id': '1',
             'ext': 'mp4',
             'title': 'Folge 1 vom 10. April 2007',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
         },
     }
 

youtube_dl/extractor/flipagram.py

@@ -81,7 +81,7 @@ class FlipagramIE(InfoExtractor):
             'filesize': int_or_none(cover.get('size')),
         } for cover in flipagram.get('covers', []) if cover.get('url')]
 
-        # Note that this only retrieves comments that are initally loaded.
+        # Note that this only retrieves comments that are initially loaded.
         # For videos with large amounts of comments, most won't be retrieved.
         comments = []
         for comment in video_data.get('comments', {}).get(video_id, {}).get('items', []):

youtube_dl/extractor/foxgay.py

@@ -20,7 +20,7 @@ class FoxgayIE(InfoExtractor):
             'title': 'Fuck Turkish-style',
             'description': 'md5:6ae2d9486921891efe89231ace13ffdf',
             'age_limit': 18,
-            'thumbnail': 're:https?://.*\.jpg$',
+            'thumbnail': r're:https?://.*\.jpg$',
         },
     }