release 2016.09.03

It's the same video player, the only difference is that the video player
is loaded differently, and certain metadata (title and description) is
not available under dr.dk/mu, so make it by default get that from some
of the html meta tags.

Skip the dr.dk/tv test

dr.dk/tv videos are only available for between 7 and 90 days due to
Danish law, and in certain cases may be readded. Skip this test as it is
no longer available.

.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 *2016.08.07*. 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 Issues with outdated version will be rejected.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 **2016.08.07**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.09.03*. 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 Issues with outdated version will be rejected.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 **2016.09.03**
 
 ### 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 2016.08.07
+[debug] youtube-dl version 2016.09.03
 [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: {}

AUTHORS

@@ -179,3 +179,7 @@ Jakub Adam Wieczorek
 Aleksandar Topuzović
 Nehal Patel
 Rob van Bekkum
+Petr Zvoníček
+Pratyush Singh
+Aleksander Nitecki
+Sebastian Blunt

CONTRIBUTING.md

@@ -46,7 +46,7 @@ Make sure that someone has not already opened the issue you're trying to open. S
 
 ###  Why are existing options not enough?
 
-Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#synopsis). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem.
+Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#options). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem.
 
 ###  Is there enough context in your bug report?
 

ChangeLog

@@ -1,3 +1,230 @@
+version 2016.09.03
+
+Core
+* Restore usage of NAME attribute from EXT-X-MEDIA tag for formats codes in
+  _extract_m3u8_formats (#10522)
+* Handle semicolon in mimetype2ext
+
+
+Extractors
++ [youtube] Add support for rental videos' previews (#10532)
+* [youtube:playlist] Fallback to video extraction for video/playlist URLs when
+  no playlist is actually served (#10537)
++ [drtv] Add support for dr.dk/nyheder (#10536)
++ [facebook:plugins:video] Add extractor (#10530)
++ [go] Add extractor for *.go.com sites
+* [adobepass] Check for authz_token expiration (#10527)
+* [nytimes] improve extraction
+* [thestar] Fix extraction (#10465)
+* [glide] Fix extraction (#10478)
+- [exfm] Remove extractor (#10482)
+* [youporn] Fix categories and tags extraction (#10521)
++ [curiositystream] Add extractor for app.curiositystream.com
+- [thvideo] Remove extractor (#10464)
+* [movingimage] Fix for the new site name (#10466)
++ [cbs] Add support for once formats (#10515)
+* [limelight] Skip ism snd duplicate manifests
++ [porncom] Extract categories and tags (#10510)
++ [facebook] Extract timestamp (#10508)
++ [yahoo] Extract more formats
+
+
+version 2016.08.31
+
+Extractors
+* [soundcloud] Fix URL regular expression to avoid clashes with sets (#10505)
+* [bandcamp:album] Fix title extraction (#10455)
+* [pyvideo] Fix extraction (#10468)
++ [ctv] Add support for tsn.ca, bnn.ca and thecomedynetwork.ca (#10016)
+* [9c9media] Extract more metadata
+* [9c9media] Fix multiple stacks extraction (#10016)
+* [adultswim] Improve video info extraction (#10492)
+* [vodplatform] Improve embed regular expression
+- [played] Remove extractor (#10470)
++ [tbs] Add extractor for tbs.com and tntdrama.com (#10222)
++ [cartoonnetwork] Add extractor for cartoonnetwork.com (#10110)
+* [adultswim] Rework in terms of turner extractor
+* [cnn] Rework in terms of turner extractor
+* [nba] Rework in terms of turner extractor
++ [turner] Add base extractor for Turner Broadcasting System based sites
+* [bilibili] Fix extraction (#10375)
+* [openload] Fix extraction (#10408)
+
+
+version 2016.08.28
+
+Core
++ Add warning message that ffmpeg doesn't support SOCKS
+* Improve thumbnail sorting
++ Extract formats from #EXT-X-MEDIA tags in _extract_m3u8_formats
+* Fill IV with leading zeros for IVs shorter than 16 octets in hlsnative
++ Add ac-3 to the list of audio codecs in parse_codecs
+
+Extractors
+* [periscope:user] Fix extraction (#10453)
+* [douyutv] Fix extraction (#10153, #10318, #10444)
++ [nhk:vod] Add extractor for www3.nhk.or.jp on demand (#4437, #10424)
+- [trutube] Remove extractor (#10438)
++ [usanetwork] Add extractor for usanetwork.com
+* [crackle] Fix extraction (#10333)
+* [spankbang] Fix description and uploader extraction (#10339)
+* [discoverygo] Detect cable provider restricted videos (#10425)
++ [cbc] Add support for watch.cbc.ca
+* [kickstarter] Silent the warning for og:description (#10415)
+* [mtvservices:embedded] Fix extraction for the new 'edge' player (#10363)
+
+
+version 2016.08.24.1
+
+Extractors
++ [pluralsight] Add support for subtitles (#9681)
+
+
+version 2016.08.24
+
+Extractors
+* [youtube] Fix authentication (#10392)
+* [openload] Fix extraction (#10408)
++ [bravotv] Add support for Adobe Pass (#10407)
+* [bravotv] Fix clip info extraction (#10407)
+* [eagleplatform] Improve embedded videos detection (#10409)
+* [awaan] Fix extraction
+* [mtvservices:embedded] Update config URL
++ [abc:iview] Add extractor (#6148)
+
+
+version 2016.08.22
+
+Core
+* Improve formats and subtitles extension auto calculation
++ Recognize full unit names in parse_filesize
++ Add support for m3u8 manifests in HTML5 multimedia tags
+* Fix octal/hexadecimal number detection in js_to_json
+
+Extractors
++ [ivi] Add support for 720p and 1080p
++ [charlierose] Add new extractor (#10382)
+* [1tv] Fix extraction (#9249)
+* [twitch] Renew authentication
+* [kaltura] Improve subtitles extension calculation
++ [zingmp3] Add support for video clips
+* [zingmp3] Fix extraction (#10041)
+* [kaltura] Improve subtitles extraction (#10279)
+* [cultureunplugged] Fix extraction (#10330)
++ [cnn] Add support for money.cnn.com (#2797)
+* [cbsnews] Fix extraction (#10362)
+* [cbs] Fix extraction (#10393)
++ [litv] Support 'promo' URLs (#10385)
+* [snotr] Fix extraction (#10338)
+* [n-tv.de] Fix extraction (#10331)
+* [globo:article] Relax URL and video id regular expressions (#10379)
+
+
+version 2016.08.19
+
+Core
+- Remove output template description from --help
+* Recognize lowercase units in parse_filesize
+
+Extractors
++ [porncom] Add extractor for porn.com (#2251, #10251)
++ [generic] Add support for DBTV embeds
+* [vk:wallpost] Fix audio extraction for new site layout
+* [vk] Fix authentication
++ [hgtvcom:show] Add extractor for hgtv.com shows (#10365)
++ [discoverygo] Add support for another GO network sites
+
+
+version 2016.08.17
+
+Core
++ Add _get_netrc_login_info
+
+Extractors
+* [mofosex] Extract all formats (#10335)
++ [generic] Add support for vbox7 embeds
++ [vbox7] Add support for embed URLs
++ [viafree] Add extractor (#10358)
++ [mtg] Add support for viafree URLs (#10358)
+* [theplatform] Extract all subtitles per language
++ [xvideos] Fix HLS extraction (#10356)
++ [amcnetworks] Add extractor
++ [bbc:playlist] Add support for pagination (#10349)
++ [fxnetworks] Add extractor (#9462)
+* [cbslocal] Fix extraction for SendtoNews-based videos
+* [sendtonews] Fix extraction
+* [jwplatform] Extract video id from JWPlayer data
+- [zippcast] Remove extractor (#10332)
++ [viceland] Add extractor (#8799)
++ [adobepass] Add base extractor for Adobe Pass Authentication
+* [life:embed] Improve extraction
+* [vgtv] Detect geo restricted videos (#10348)
++ [uplynk] Add extractor
+* [xiami] Fix extraction (#10342)
+
+
+version 2016.08.13
+
+Core
+* Show progress for curl external downloader
+* Forward more options to curl external downloader
+
+Extractors
+* [pbs] Fix description extraction
+* [franceculture] Fix extraction (#10324)
+* [pornotube] Fix extraction (#10322)
+* [4tube] Fix metadata extraction (#10321)
+* [imgur] Fix width and height extraction (#10325)
+* [expotv] Improve extraction
++ [vbox7] Fix extraction (#10309)
+- [tapely] Remove extractor (#10323)
+* [muenchentv] Fix extraction (#10313)
++ [24video] Add support for .me and .xxx TLDs
+* [24video] Fix comment count extraction
+* [sunporno] Add support for embed URLs
+* [sunporno] Fix metadata extraction (#10316)
++ [hgtv] Add extractor for hgtv.ca (#3999)
+- [pbs] Remove request to unavailable API
++ [pbs] Add support for high quality HTTP formats
++ [crunchyroll] Add support for HLS formats (#10301)
+
+
+version 2016.08.12
+
+Core
+* Subtitles are now written as is. Newline conversions are disabled. (#10268)
++ Recognize more formats in unified_timestamp
+
+Extractors
+- [goldenmoustache] Remove extractor (#10298)
+* [drtuber] Improve title extraction
+* [drtuber] Make dislike count optional (#10297)
+* [chirbit] Fix extraction (#10296)
+* [francetvinfo] Relax URL regular expression
+* [rtlnl] Relax URL regular expression (#10282)
+* [formula1] Relax URL regular expression (#10283)
+* [wat] Improve extraction (#10281)
+* [ctsnews] Fix extraction
+
+
+version 2016.08.10
+
+Core
+* Make --metadata-from-title non fatal when title does not match the pattern
+* Introduce options for randomized sleep before each download
+  --min-sleep-interval and --max-sleep-interval (#9930)
+* Respect default in _search_json_ld
+
+Extractors
++ [uol] Add extractor for uol.com.br (#4263)
+* [rbmaradio] Fix extraction and extract all formats (#10242)
++ [sonyliv] Add extractor for sonyliv.com (#10258)
+* [aparat] Fix extraction
+* [cwtv] Extract HTTP formats
++ [rozhlas] Add extractor for prehravac.rozhlas.cz (#10253)
+* [kuwo:singer] Fix extraction
+
+
 version 2016.08.07
 
 Core

README.md

@@ -201,32 +201,8 @@ which means you can modify it, redistribute it or use it however you like.
     -a, --batch-file FILE            File containing URLs to download ('-' for
                                      stdin)
     --id                             Use only video ID in file name
-    -o, --output TEMPLATE            Output filename template. Use %(title)s to
-                                     get the title, %(uploader)s for the
-                                     uploader name, %(uploader_id)s for the
-                                     uploader nickname if different,
-                                     %(autonumber)s to get an automatically
-                                     incremented number, %(ext)s for the
-                                     filename extension, %(format)s for the
-                                     format description (like "22 - 1280x720" or
-                                     "HD"), %(format_id)s for the unique id of
-                                     the format (like YouTube's itags: "137"),
-                                     %(upload_date)s for the upload date
-                                     (YYYYMMDD), %(extractor)s for the provider
-                                     (youtube, metacafe, etc), %(id)s for the
-                                     video id, %(playlist_title)s,
-                                     %(playlist_id)s, or %(playlist)s (=title if
-                                     present, ID otherwise) for the playlist the
-                                     video is in, %(playlist_index)s for the
-                                     position in the playlist. %(height)s and
-                                     %(width)s for the width and height of the
-                                     video format. %(resolution)s for a textual
-                                     description of the resolution of the video
-                                     format. %% for a literal percent. Use - to
-                                     output to stdout. Can also be used to
-                                     download to a different directory, for
-                                     example with -o '/my/downloads/%(uploader)s
-                                     /%(title)s-%(id)s.%(ext)s' .
+    -o, --output TEMPLATE            Output filename template, see the "OUTPUT
+                                     TEMPLATE" for all the info
     --autonumber-size NUMBER         Specify the number of digits in
                                      %(autonumber)s when it is present in output
                                      filename template or --auto-number option
@@ -330,7 +306,15 @@ which means you can modify it, redistribute it or use it however you like.
                                      bidirectional text support. Requires bidiv
                                      or fribidi executable in PATH
     --sleep-interval SECONDS         Number of seconds to sleep before each
-                                     download.
+                                     download when used alone or a lower bound
+                                     of a range for randomized sleep before each
+                                     download (minimum possible number of
+                                     seconds to sleep) when used along with
+                                     --max-sleep-interval.
+    --max-sleep-interval SECONDS     Upper bound of a range for randomized sleep
+                                     before each download (maximum possible
+                                     number of seconds to sleep). Must only be
+                                     used along with --min-sleep-interval.
 
 ## Video Format Options:
     -f, --format FORMAT              Video format code, see the "FORMAT
@@ -428,11 +412,19 @@ You can configure youtube-dl by placing any supported command line option to a c
 
 For example, with the following configuration file youtube-dl will always extract the audio, not copy the mtime, use a proxy and save all videos under `Movies` directory in your home directory:
 ```
--x
---no-mtime
---proxy 127.0.0.1:3128
--o ~/Movies/%(title)s.%(ext)s
 # Lines starting with # are comments
+
+# Always extract audio
+-x
+
+# Do not copy the mtime
+--no-mtime
+
+# Use this proxy
+--proxy 127.0.0.1:3128
+
+# Save all videos under Movies directory in your home directory
+-o ~/Movies/%(title)s.%(ext)s
 ```
 
 Note that options in configuration file are just the same options aka switches used in regular command line calls thus there **must be no whitespace** after `-` or `--`, e.g. `-o` or `--proxy` but not `- o` or `-- proxy`.
@@ -661,7 +653,11 @@ $ youtube-dl -f 'best[filesize<50M]'
 
 # Download best format available via direct link over HTTP/HTTPS protocol
 $ youtube-dl -f '(bestvideo+bestaudio/best)[protocol^=http]'
+
+# Download the best video format and the best audio format without merging them
+$ youtube-dl -f 'bestvideo,bestaudio' -o '%(title)s.f%(format_id)s.%(ext)s'
 ```
+Note that in the last example, an output template is recommended as bestvideo and bestaudio may have the same file name.
 
 
 # VIDEO SELECTION
@@ -742,7 +738,7 @@ Videos or video formats streamed via RTMP protocol can only be downloaded when [
 
 ### I have downloaded a video but how can I play it?
 
-Once the video is fully downloaded, use any video player, such as [mpv](https://mpv.io/), [vlc](http://www.videolan.org) or [mplayer](http://www.mplayerhq.hu/).
+Once the video is fully downloaded, use any video player, such as [mpv](https://mpv.io/), [vlc](http://www.videolan.org/) or [mplayer](http://www.mplayerhq.hu/).
 
 ### I extracted a video URL with `-g`, but it does not play on another machine / in my webbrowser.
 
@@ -824,10 +820,32 @@ Either prepend `http://www.youtube.com/watch?v=` or separate the ID from the opt
 
 ### How do I pass cookies to youtube-dl?
 
-Use the `--cookies` option, for example `--cookies /path/to/cookies/file.txt`. 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.
+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.
 
 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).
 
+### How do I stream directly to media player?
+
+You will first need to tell youtube-dl to stream media to stdout with `-o -`, and also tell your media player to read from stdin (it must be capable of this for streaming) and then pipe former to latter. For example, streaming to [vlc](http://www.videolan.org/) can be achieved with:
+
+    youtube-dl -o - "http://www.youtube.com/watch?v=BaW_jenozKcj" | vlc -
+
+### How do I download only new videos from a playlist?
+
+Use download-archive feature. With this feature you should initially download the complete playlist with `--download-archive /path/to/download/archive/file.txt` that will record identifiers of all the videos in a special file. Each subsequent run with the same `--download-archive` will download only new videos and skip all videos that have been downloaded before. Note that only successful downloads are recorded in the file.
+
+For example, at first,
+
+    youtube-dl --download-archive archive.txt "https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re"
+
+will download the complete `PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re` playlist and create a file `archive.txt`. Each subsequent run will only download new videos if any:
+
+    youtube-dl --download-archive archive.txt "https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re"
+
 ### Can you add support for this anime video site, or site which shows current movies for free?
 
 As a matter of policy (as well as legality), youtube-dl does not include support for services that specialize in infringing copyright. As a rule of thumb, if you cannot easily find a video that the service is quite obviously allowed to distribute (i.e. that has been uploaded by the creator, the creator's distributor, or is published under a free license), the service is probably unfit for inclusion to youtube-dl.
@@ -1196,7 +1214,7 @@ Make sure that someone has not already opened the issue you're trying to open. S
 
 ###  Why are existing options not enough?
 
-Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#synopsis). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem.
+Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#options). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem.
 
 ###  Is there enough context in your bug report?
 

devscripts/prepare_manpage.py

@@ -54,17 +54,21 @@ def filter_options(readme):
 
         if in_options:
             if line.lstrip().startswith('-'):
-                option, description = re.split(r'\s{2,}', line.lstrip())
-                split_option = option.split(' ')
+                split = re.split(r'\s{2,}', line.lstrip())
+                # Description string may start with `-` as well. If there is
+                # only one piece then it's a description bit not an option.
+                if len(split) > 1:
+                    option, description = split
+                    split_option = option.split(' ')
 
-                if not split_option[-1].startswith('-'):  # metavar
-                    option = ' '.join(split_option[:-1] + ['*%s*' % split_option[-1]])
+                    if not split_option[-1].startswith('-'):  # metavar
+                        option = ' '.join(split_option[:-1] + ['*%s*' % split_option[-1]])
 
-                # Pandoc's definition_lists. See http://pandoc.org/README.html
-                # for more information.
-                ret += '\n%s\n:   %s\n' % (option, description)
-            else:
-                ret += line.lstrip() + '\n'
+                    # Pandoc's definition_lists. See http://pandoc.org/README.html
+                    # for more information.
+                    ret += '\n%s\n:   %s\n' % (option, description)
+                    continue
+            ret += line.lstrip() + '\n'
         else:
             ret += line + '\n'
 

docs/supportedsites.md

@@ -13,9 +13,12 @@
  - **5min**
  - **8tracks**
  - **91porn**
+ - **9c9media**
+ - **9c9media:stack**
  - **9gag**
  - **9now.com.au**
  - **abc.net.au**
+ - **abc.net.au:iview**
  - **Abc7News**
  - **abcnews**
  - **abcnews:video**
@@ -35,6 +38,7 @@
  - **AlJazeera**
  - **Allocine**
  - **AlphaPorno**
+ - **AMCNetworks**
  - **AnimeOnDemand**
  - **anitube.se**
  - **AnySex**
@@ -65,6 +69,10 @@
  - **audiomack**
  - **audiomack:album**
  - **auroravid**: AuroraVid
+ - **AWAAN**
+ - **awaan:live**
+ - **awaan:season**
+ - **awaan:video**
  - **Azubu**
  - **AzubuLive**
  - **BaiduVideo**: 百度视频
@@ -109,8 +117,11 @@
  - **Canvas**
  - **CarambaTV**
  - **CarambaTVPage**
- - **CBC**
- - **CBCPlayer**
+ - **CartoonNetwork**
+ - **cbc.ca**
+ - **cbc.ca:player**
+ - **cbc.ca:watch**
+ - **cbc.ca:watch:video**
  - **CBS**
  - **CBSInteractive**
  - **CBSLocal**
@@ -120,6 +131,7 @@
  - **CDA**
  - **CeskaTelevize**
  - **channel9**: Channel 9
+ - **CharlieRose**
  - **Chaturbate**
  - **Chilloutzone**
  - **chirbit**
@@ -159,6 +171,8 @@
  - **CTVNews**
  - **culturebox.francetvinfo.fr**
  - **CultureUnplugged**
+ - **curiositystream**
+ - **curiositystream:collection**
  - **CWTV**
  - **DailyMail**
  - **dailymotion**
@@ -170,10 +184,6 @@
  - **daum.net:playlist**
  - **daum.net:user**
  - **DBTV**
- - **DCN**
- - **dcn:live**
- - **dcn:season**
- - **dcn:video**
  - **DctpTv**
  - **DeezerPlaylist**
  - **defense.gouv.fr**
@@ -215,11 +225,11 @@
  - **EsriVideo**
  - **Europa**
  - **EveryonesMixtape**
- - **exfm**: ex.fm
  - **ExpoTV**
  - **ExtremeTube**
  - **EyedoTV**
  - **facebook**
+ - **FacebookPluginsVideo**
  - **faz.net**
  - **fc2**
  - **Fczenit**
@@ -238,7 +248,6 @@
  - **FoxSports**
  - **france2.fr:generation-quoi**
  - **FranceCulture**
- - **FranceCultureEmission**
  - **FranceInter**
  - **francetv**: France 2, 3, 4, 5 and Ô
  - **francetvinfo.fr**
@@ -248,6 +257,7 @@
  - **Funimation**
  - **FunnyOrDie**
  - **Fusion**
+ - **FXNetworks**
  - **GameInformer**
  - **GameOne**
  - **gameone:playlist**
@@ -263,9 +273,9 @@
  - **Glide**: Glide mobile video messages (glide.me)
  - **Globo**
  - **GloboArticle**
+ - **Go**
  - **GodTube**
  - **GodTV**
- - **GoldenMoustache**
  - **Golem**
  - **GoogleDrive**
  - **Goshgay**
@@ -278,6 +288,8 @@
  - **HellPorno**
  - **Helsinki**: helsinki.fi
  - **HentaiStigma**
+ - **HGTV**
+ - **hgtv.com:show**
  - **HistoricFilms**
  - **history:topic**: History.com Topic
  - **hitbox**
@@ -397,8 +409,10 @@
  - **MovieClips**
  - **MovieFap**
  - **Moviezine**
+ - **MovingImage**
  - **MPORA**
  - **MSN**
+ - **mtg**: MTG services
  - **MTV**
  - **mtv.de**
  - **mtvservices:embedded**
@@ -443,6 +457,7 @@
  - **NextMediaActionNews**: 蘋果日報 - 動新聞
  - **nfb**: National Film Board of Canada
  - **nfl.com**
+ - **NhkVod**
  - **nhl.com**
  - **nhl.com:news**: NHL news
  - **nhl.com:videocenter**
@@ -451,7 +466,6 @@
  - **nick.de**
  - **niconico**: ニコニコ動画
  - **NiconicoPlaylist**
- - **NineCNineMedia**
  - **Nintendo**
  - **njoy**: N-JOY
  - **njoy:embed**
@@ -509,7 +523,6 @@
  - **Pinkbike**
  - **Pladform**
  - **play.fm**
- - **played.to**
  - **PlaysTV**
  - **Playtvak**: Playtvak.cz, iDNES.cz and Lidovky.cz
  - **Playvid**
@@ -521,6 +534,7 @@
  - **podomatic**
  - **Pokemon**
  - **PolskieRadio**
+ - **PornCom**
  - **PornHd**
  - **PornHub**: PornHub and Thumbzilla
  - **PornHubPlaylist**
@@ -564,6 +578,7 @@
  - **RoosterTeeth**
  - **RottenTomatoes**
  - **Roxwel**
+ - **Rozhlas**
  - **RTBF**
  - **rte**: Raidió Teilifís Éireann TV
  - **rte:radio**: Raidió Teilifís Éireann radio
@@ -621,6 +636,7 @@
  - **smotri:user**: Smotri.com user videos
  - **Snotr**
  - **Sohu**
+ - **SonyLIV**
  - **soundcloud**
  - **soundcloud:playlist**
  - **soundcloud:search**: Soundcloud search
@@ -647,7 +663,6 @@
  - **sr:mediathek**: Saarländischer Rundfunk
  - **SRGSSR**
  - **SRGSSRPlay**: srf.ch, rts.ch, rsi.ch, rtr.ch and swissinfo.ch play sites
- - **SSA**
  - **stanfordoc**: Stanford Open ClassRoom
  - **Steam**
  - **Stitcher**
@@ -663,8 +678,8 @@
  - **SztvHu**
  - **Tagesschau**
  - **tagesschau:player**
- - **Tapely**
  - **Tass**
+ - **TBS**
  - **TDSLifeway**
  - **teachertube**: teachertube.com videos
  - **teachertube:user:collection**: teachertube.com user and collection videos
@@ -690,8 +705,6 @@
  - **TheStar**
  - **ThisAmericanLife**
  - **ThisAV**
- - **THVideo**
- - **THVideoPlaylist**
  - **tinypic**: tinypic.com videos
  - **tlc.de**
  - **TMZ**
@@ -706,7 +719,6 @@
  - **TrailerAddict** (Currently broken)
  - **Trilulilu**
  - **trollvids**
- - **TruTube**
  - **Tube8**
  - **TubiTv**
  - **tudou**
@@ -731,7 +743,6 @@
  - **tvp**: Telewizja Polska
  - **tvp:embed**: Telewizja Polska
  - **tvp:series**
- - **TVPlay**: TV3Play and related services
  - **Tweakers**
  - **twitch:chapter**
  - **twitch:clips**
@@ -747,8 +758,12 @@
  - **udemy:course**
  - **UDNEmbed**: 聯合影音
  - **Unistra**
+ - **uol.com.br**
+ - **uplynk**
+ - **uplynk:preplay**
  - **Urort**: NRK P3 Urørt
  - **URPlay**
+ - **USANetwork**
  - **USAToday**
  - **ustream**
  - **ustream:channel**
@@ -764,7 +779,9 @@
  - **VevoPlaylist**
  - **VGTV**: VGTV, BTTV, FTV, Aftenposten and Aftonbladet
  - **vh1.com**
+ - **Viafree**
  - **Vice**
+ - **Viceland**
  - **ViceShow**
  - **Vidbit**
  - **Viddler**
@@ -884,6 +901,4 @@
  - **Zapiks**
  - **ZDF**
  - **ZDFChannel**
- - **zingmp3:album**: mp3.zing.vn albums
- - **zingmp3:song**: mp3.zing.vn songs
- - **ZippCast**
+ - **zingmp3**: mp3.zing.vn

test/test_utils.py

@@ -39,6 +39,7 @@ from youtube_dl.utils import (
     is_html,
     js_to_json,
     limit_length,
+    mimetype2ext,
     ohdave_rsa_encrypt,
     OnDemandPagedList,
     orderedSet,
@@ -625,6 +626,14 @@ class TestUtil(unittest.TestCase):
             limit_length('foo bar baz asd', 12).startswith('foo bar'))
         self.assertTrue('...' in limit_length('foo bar baz asd', 12))
 
+    def test_mimetype2ext(self):
+        self.assertEqual(mimetype2ext(None), None)
+        self.assertEqual(mimetype2ext('video/x-flv'), 'flv')
+        self.assertEqual(mimetype2ext('application/x-mpegURL'), 'm3u8')
+        self.assertEqual(mimetype2ext('text/vtt'), 'vtt')
+        self.assertEqual(mimetype2ext('text/vtt;charset=utf-8'), 'vtt')
+        self.assertEqual(mimetype2ext('text/html; charset=utf-8'), 'html')
+
     def test_parse_codecs(self):
         self.assertEqual(parse_codecs(''), {})
         self.assertEqual(parse_codecs('avc1.77.30, mp4a.40.2'), {
@@ -712,6 +721,9 @@ class TestUtil(unittest.TestCase):
         inp = '''{"foo":101}'''
         self.assertEqual(js_to_json(inp), '''{"foo":101}''')
 
+        inp = '''{"duration": "00:01:07"}'''
+        self.assertEqual(js_to_json(inp), '''{"duration": "00:01:07"}''')
+
     def test_js_to_json_edgecases(self):
         on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
         self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
@@ -817,7 +829,10 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(parse_filesize('2 MiB'), 2097152)
         self.assertEqual(parse_filesize('5 GB'), 5000000000)
         self.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
+        self.assertEqual(parse_filesize('1.2tb'), 1200000000000)
         self.assertEqual(parse_filesize('1,24 KB'), 1240)
+        self.assertEqual(parse_filesize('1,24 kb'), 1240)
+        self.assertEqual(parse_filesize('8.5 megabytes'), 8500000)
 
     def test_parse_count(self):
         self.assertEqual(parse_count(None), None)
@@ -968,6 +983,7 @@ The first line
         self.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128'])
         self.assertEqual(cli_option({'proxy': None}, '--proxy', 'proxy'), [])
         self.assertEqual(cli_option({}, '--proxy', 'proxy'), [])
+        self.assertEqual(cli_option({'retries': 10}, '--retries', 'retries'), ['--retries', '10'])
 
     def test_cli_valueless_option(self):
         self.assertEqual(cli_valueless_option(

test/test_verbose_output.py

@@ -22,10 +22,10 @@ class TestVerboseOutput(unittest.TestCase):
                 '--password', 'secret',
             ], cwd=rootDir, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
         sout, serr = outp.communicate()
-        self.assertTrue('--username' in serr)
-        self.assertTrue('johnsmith' not in serr)
-        self.assertTrue('--password' in serr)
-        self.assertTrue('secret' not in serr)
+        self.assertTrue(b'--username' in serr)
+        self.assertTrue(b'johnsmith' not in serr)
+        self.assertTrue(b'--password' in serr)
+        self.assertTrue(b'secret' not in serr)
 
     def test_private_info_shortarg(self):
         outp = subprocess.Popen(
@@ -35,10 +35,10 @@ class TestVerboseOutput(unittest.TestCase):
                 '-p', 'secret',
             ], cwd=rootDir, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
         sout, serr = outp.communicate()
-        self.assertTrue('-u' in serr)
-        self.assertTrue('johnsmith' not in serr)
-        self.assertTrue('-p' in serr)
-        self.assertTrue('secret' not in serr)
+        self.assertTrue(b'-u' in serr)
+        self.assertTrue(b'johnsmith' not in serr)
+        self.assertTrue(b'-p' in serr)
+        self.assertTrue(b'secret' not in serr)
 
     def test_private_info_eq(self):
         outp = subprocess.Popen(
@@ -48,10 +48,10 @@ class TestVerboseOutput(unittest.TestCase):
                 '--password=secret',
             ], cwd=rootDir, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
         sout, serr = outp.communicate()
-        self.assertTrue('--username' in serr)
-        self.assertTrue('johnsmith' not in serr)
-        self.assertTrue('--password' in serr)
-        self.assertTrue('secret' not in serr)
+        self.assertTrue(b'--username' in serr)
+        self.assertTrue(b'johnsmith' not in serr)
+        self.assertTrue(b'--password' in serr)
+        self.assertTrue(b'secret' not in serr)
 
     def test_private_info_shortarg_eq(self):
         outp = subprocess.Popen(
@@ -61,10 +61,10 @@ class TestVerboseOutput(unittest.TestCase):
                 '-p=secret',
             ], cwd=rootDir, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
         sout, serr = outp.communicate()
-        self.assertTrue('-u' in serr)
-        self.assertTrue('johnsmith' not in serr)
-        self.assertTrue('-p' in serr)
-        self.assertTrue('secret' not in serr)
+        self.assertTrue(b'-u' in serr)
+        self.assertTrue(b'johnsmith' not in serr)
+        self.assertTrue(b'-p' in serr)
+        self.assertTrue(b'secret' not in serr)
 
 if __name__ == '__main__':
     unittest.main()

youtube_dl/YoutubeDL.py

@@ -249,7 +249,16 @@ class YoutubeDL(object):
     source_address:    (Experimental) Client-side IP address to bind to.
     call_home:         Boolean, true iff we are allowed to contact the
                        youtube-dl servers for debugging.
-    sleep_interval:    Number of seconds to sleep before each download.
+    sleep_interval:    Number of seconds to sleep before each download when
+                       used alone or a lower bound of a range for randomized
+                       sleep before each download (minimum possible number
+                       of seconds to sleep) when used along with
+                       max_sleep_interval.
+    max_sleep_interval:Upper bound of a range for randomized sleep before each
+                       download (maximum possible number of seconds to sleep).
+                       Must only be used along with sleep_interval.
+                       Actual sleep time will be a random float from range
+                       [sleep_interval; max_sleep_interval].
     listformats:       Print an overview of available video formats and exit.
     list_thumbnails:   Print a table of all thumbnails and exit.
     match_filter:      A function that gets called with the info_dict of
@@ -1247,8 +1256,10 @@ class YoutubeDL(object):
                 info_dict['thumbnails'] = thumbnails = [{'url': thumbnail}]
         if thumbnails:
             thumbnails.sort(key=lambda t: (
-                t.get('preference'), t.get('width'), t.get('height'),
-                t.get('id'), t.get('url')))
+                t.get('preference') if t.get('preference') is not None else -1,
+                t.get('width') if t.get('width') is not None else -1,
+                t.get('height') if t.get('height') is not None else -1,
+                t.get('id') if t.get('id') is not None else '', t.get('url')))
             for i, t in enumerate(thumbnails):
                 t['url'] = sanitize_url(t['url'])
                 if t.get('width') and t.get('height'):
@@ -1290,7 +1301,7 @@ class YoutubeDL(object):
                 for subtitle_format in subtitle:
                     if subtitle_format.get('url'):
                         subtitle_format['url'] = sanitize_url(subtitle_format['url'])
-                    if 'ext' not in subtitle_format:
+                    if subtitle_format.get('ext') is None:
                         subtitle_format['ext'] = determine_ext(subtitle_format['url']).lower()
 
         if self.params.get('listsubtitles', False):
@@ -1345,7 +1356,7 @@ class YoutubeDL(object):
                     note=' ({0})'.format(format['format_note']) if format.get('format_note') is not None else '',
                 )
             # Automatically determine file extension if missing
-            if 'ext' not in format:
+            if format.get('ext') is None:
                 format['ext'] = determine_ext(format['url']).lower()
             # Automatically determine protocol if missing (useful for format
             # selection purposes)
@@ -1594,7 +1605,9 @@ class YoutubeDL(object):
                         self.to_screen('[info] Video subtitle %s.%s is already_present' % (sub_lang, sub_format))
                     else:
                         self.to_screen('[info] Writing video subtitles to: ' + sub_filename)
-                        with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile:
+                        # Use newline='' to prevent conversion of newline characters
+                        # See https://github.com/rg3/youtube-dl/issues/10268
+                        with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8', newline='') as subfile:
                             subfile.write(sub_data)
                 except (OSError, IOError):
                     self.report_error('Cannot write subtitles file ' + sub_filename)

youtube_dl/__init__.py

@@ -145,6 +145,16 @@ def _real_main(argv=None):
         if numeric_limit is None:
             parser.error('invalid max_filesize specified')
         opts.max_filesize = numeric_limit
+    if opts.sleep_interval is not None:
+        if opts.sleep_interval < 0:
+            parser.error('sleep interval must be positive or 0')
+    if opts.max_sleep_interval is not None:
+        if opts.max_sleep_interval < 0:
+            parser.error('max sleep interval must be positive or 0')
+        if opts.max_sleep_interval < opts.sleep_interval:
+            parser.error('max sleep interval must be greater than or equal to min sleep interval')
+    else:
+        opts.max_sleep_interval = opts.sleep_interval
 
     def parse_retries(retries):
         if retries in ('inf', 'infinite'):
@@ -370,6 +380,7 @@ def _real_main(argv=None):
         'source_address': opts.source_address,
         'call_home': opts.call_home,
         'sleep_interval': opts.sleep_interval,
+        'max_sleep_interval': opts.max_sleep_interval,
         'external_downloader': opts.external_downloader,
         'list_thumbnails': opts.list_thumbnails,
         'playlist_items': opts.playlist_items,

youtube_dl/downloader/common.py

@@ -4,6 +4,7 @@ import os
 import re
 import sys
 import time
+import random
 
 from ..compat import compat_os_name
 from ..utils import (
@@ -342,8 +343,11 @@ class FileDownloader(object):
             })
             return True
 
-        sleep_interval = self.params.get('sleep_interval')
-        if sleep_interval:
+        min_sleep_interval = self.params.get('sleep_interval')
+        if min_sleep_interval:
+            max_sleep_interval = self.params.get('max_sleep_interval', min_sleep_interval)
+            print(min_sleep_interval, max_sleep_interval)
+            sleep_interval = random.uniform(min_sleep_interval, max_sleep_interval)
             self.to_screen('[download] Sleeping %s seconds...' % sleep_interval)
             time.sleep(sleep_interval)
 

youtube_dl/downloader/external.py

@@ -96,6 +96,12 @@ class CurlFD(ExternalFD):
         cmd = [self.exe, '--location', '-o', tmpfilename]
         for key, val in info_dict['http_headers'].items():
             cmd += ['--header', '%s: %s' % (key, val)]
+        cmd += self._bool_option('--continue-at', 'continuedl', '-', '0')
+        cmd += self._valueless_option('--silent', 'noprogress')
+        cmd += self._valueless_option('--verbose', 'verbose')
+        cmd += self._option('--limit-rate', 'ratelimit')
+        cmd += self._option('--retry', 'retries')
+        cmd += self._option('--max-filesize', 'max_filesize')
         cmd += self._option('--interface', 'source_address')
         cmd += self._option('--proxy', 'proxy')
         cmd += self._valueless_option('--insecure', 'nocheckcertificate')
@@ -103,6 +109,16 @@ class CurlFD(ExternalFD):
         cmd += ['--', info_dict['url']]
         return cmd
 
+    def _call_downloader(self, tmpfilename, info_dict):
+        cmd = [encodeArgument(a) for a in self._make_cmd(tmpfilename, info_dict)]
+
+        self._debug_cmd(cmd)
+
+        # curl writes the progress to stderr so don't capture it.
+        p = subprocess.Popen(cmd)
+        p.communicate()
+        return p.returncode
+
 
 class AxelFD(ExternalFD):
     AVAILABLE_OPT = '-V'
@@ -204,6 +220,12 @@ class FFmpegFD(ExternalFD):
         if proxy:
             if not re.match(r'^[\da-zA-Z]+://', proxy):
                 proxy = 'http://%s' % proxy
+
+            if proxy.startswith('socks'):
+                self.report_warning(
+                    '%s does not support SOCKS proxies. Downloading is likely to fail. '
+                    'Consider adding --hls-prefer-native to your command.' % self.get_basename())
+
             # Since December 2015 ffmpeg supports -http_proxy option (see
             # http://git.videolan.org/?p=ffmpeg.git;a=commit;h=b4eb1f29ebddd60c41a2eb39f5af701e38e0d3fd)
             # We could switch to the following code if we are able to detect version properly

youtube_dl/downloader/hls.py

@@ -20,6 +20,7 @@ from ..utils import (
     encodeFilename,
     sanitize_open,
     parse_m3u8_attributes,
+    update_url_query,
 )
 
 
@@ -82,6 +83,10 @@ class HlsFD(FragmentFD):
 
         self._prepare_and_start_frag_download(ctx)
 
+        extra_query = None
+        extra_param_to_segment_url = info_dict.get('extra_param_to_segment_url')
+        if extra_param_to_segment_url:
+            extra_query = compat_urlparse.parse_qs(extra_param_to_segment_url)
         i = 0
         media_sequence = 0
         decrypt_info = {'METHOD': 'NONE'}
@@ -95,6 +100,8 @@ class HlsFD(FragmentFD):
                         if re.match(r'^https?://', line)
                         else compat_urlparse.urljoin(man_url, line))
                     frag_filename = '%s-Frag%d' % (ctx['tmpfilename'], i)
+                    if extra_query:
+                        frag_url = update_url_query(frag_url, extra_query)
                     success = ctx['dl'].download(frag_filename, {'url': frag_url})
                     if not success:
                         return False
@@ -116,10 +123,12 @@ class HlsFD(FragmentFD):
                     decrypt_info = parse_m3u8_attributes(line[11:])
                     if decrypt_info['METHOD'] == 'AES-128':
                         if 'IV' in decrypt_info:
-                            decrypt_info['IV'] = binascii.unhexlify(decrypt_info['IV'][2:])
+                            decrypt_info['IV'] = binascii.unhexlify(decrypt_info['IV'][2:].zfill(32))
                         if not re.match(r'^https?://', decrypt_info['URI']):
                             decrypt_info['URI'] = compat_urlparse.urljoin(
                                 man_url, decrypt_info['URI'])
+                        if extra_query:
+                            decrypt_info['URI'] = update_url_query(decrypt_info['URI'], extra_query)
                         decrypt_info['KEY'] = self.ydl.urlopen(decrypt_info['URI']).read()
                 elif line.startswith('#EXT-X-MEDIA-SEQUENCE'):
                     media_sequence = int(line[22:])

youtube_dl/extractor/abc.py

@@ -7,6 +7,7 @@ from ..utils import (
     ExtractorError,
     js_to_json,
     int_or_none,
+    parse_iso8601,
 )
 
 
@@ -93,3 +94,57 @@ class ABCIE(InfoExtractor):
             'description': self._og_search_description(webpage),
             'thumbnail': self._og_search_thumbnail(webpage),
         }
+
+
+class ABCIViewIE(InfoExtractor):
+    IE_NAME = 'abc.net.au:iview'
+    _VALID_URL = r'https?://iview\.abc\.net\.au/programs/[^/]+/(?P<id>[^/?#]+)'
+
+    _TESTS = [{
+        'url': 'http://iview.abc.net.au/programs/gardening-australia/FA1505V024S00',
+        'md5': '979d10b2939101f0d27a06b79edad536',
+        'info_dict': {
+            'id': 'FA1505V024S00',
+            'ext': 'mp4',
+            'title': 'Series 27 Ep 24',
+            'description': 'md5:b28baeae7504d1148e1d2f0e3ed3c15d',
+            'upload_date': '20160820',
+            'uploader_id': 'abc1',
+            'timestamp': 1471719600,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        video_params = self._parse_json(self._search_regex(
+            r'videoParams\s*=\s*({.+?});', webpage, 'video params'), video_id)
+        title = video_params['title']
+        stream = next(s for s in video_params['playlist'] if s.get('type') == 'program')
+
+        formats = self._extract_akamai_formats(stream['hds-unmetered'], video_id)
+        self._sort_formats(formats)
+
+        subtitles = {}
+        src_vtt = stream.get('captions', {}).get('src-vtt')
+        if src_vtt:
+            subtitles['en'] = [{
+                'url': src_vtt,
+                'ext': 'vtt',
+            }]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': self._html_search_meta(['og:description', 'twitter:description'], webpage),
+            'thumbnail': self._html_search_meta(['og:image', 'twitter:image:src'], webpage),
+            'duration': int_or_none(video_params.get('eventDuration')),
+            'timestamp': parse_iso8601(video_params.get('pubDate'), ' '),
+            'series': video_params.get('seriesTitle'),
+            'series_id': video_params.get('seriesHouseNumber') or video_id[:7],
+            'episode_number': int_or_none(self._html_search_meta('episodeNumber', webpage)),
+            'episode': self._html_search_meta('episode_title', webpage),
+            'uploader_id': video_params.get('channel'),
+            'formats': formats,
+            'subtitles': subtitles,
+        }

youtube_dl/extractor/adobepass.py

@@ -0,0 +1,137 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import re
+import time
+import xml.etree.ElementTree as etree
+
+from .common import InfoExtractor
+from ..utils import (
+    unescapeHTML,
+    urlencode_postdata,
+    unified_timestamp,
+)
+
+
+class AdobePassIE(InfoExtractor):
+    _SERVICE_PROVIDER_TEMPLATE = 'https://sp.auth.adobe.com/adobe-services/%s'
+    _USER_AGENT = 'Mozilla/5.0 (X11; Linux i686; rv:47.0) Gecko/20100101 Firefox/47.0'
+
+    @staticmethod
+    def _get_mvpd_resource(provider_id, title, guid, rating):
+        channel = etree.Element('channel')
+        channel_title = etree.SubElement(channel, 'title')
+        channel_title.text = provider_id
+        item = etree.SubElement(channel, 'item')
+        resource_title = etree.SubElement(item, 'title')
+        resource_title.text = title
+        resource_guid = etree.SubElement(item, 'guid')
+        resource_guid.text = guid
+        resource_rating = etree.SubElement(item, 'media:rating')
+        resource_rating.attrib = {'scheme': 'urn:v-chip'}
+        resource_rating.text = rating
+        return '<rss version="2.0" xmlns:media="http://search.yahoo.com/mrss/">' + etree.tostring(channel).decode() + '</rss>'
+
+    def _extract_mvpd_auth(self, url, video_id, requestor_id, resource):
+        def xml_text(xml_str, tag):
+            return self._search_regex(
+                '<%s>(.+?)</%s>' % (tag, tag), xml_str, tag)
+
+        def is_expired(token, date_ele):
+            token_expires = unified_timestamp(re.sub(r'[_ ]GMT', '', xml_text(token, date_ele)))
+            return token_expires and token_expires <= int(time.time())
+
+        mvpd_headers = {
+            'ap_42': 'anonymous',
+            'ap_11': 'Linux i686',
+            'ap_z': self._USER_AGENT,
+            'User-Agent': self._USER_AGENT,
+        }
+
+        guid = xml_text(resource, 'guid')
+        requestor_info = self._downloader.cache.load('mvpd', requestor_id) or {}
+        authn_token = requestor_info.get('authn_token')
+        if authn_token and is_expired(authn_token, 'simpleTokenExpires'):
+            authn_token = None
+        if not authn_token:
+            # TODO add support for other TV Providers
+            mso_id = 'DTV'
+            username, password = self._get_netrc_login_info(mso_id)
+            if not username or not password:
+                return ''
+
+            def post_form(form_page, note, data={}):
+                post_url = self._html_search_regex(r'<form[^>]+action=(["\'])(?P<url>.+?)\1', form_page, 'post url', group='url')
+                return self._download_webpage(
+                    post_url, video_id, note, data=urlencode_postdata(data or self._hidden_inputs(form_page)), headers={
+                        'Content-Type': 'application/x-www-form-urlencoded',
+                    })
+
+            provider_redirect_page = self._download_webpage(
+                self._SERVICE_PROVIDER_TEMPLATE % 'authenticate/saml', video_id,
+                'Downloading Provider Redirect Page', query={
+                    'noflash': 'true',
+                    'mso_id': mso_id,
+                    'requestor_id': requestor_id,
+                    'no_iframe': 'false',
+                    'domain_name': 'adobe.com',
+                    'redirect_url': url,
+                })
+            provider_login_page = post_form(
+                provider_redirect_page, 'Downloading Provider Login Page')
+            mvpd_confirm_page = post_form(provider_login_page, 'Logging in', {
+                'username': username,
+                'password': password,
+            })
+            post_form(mvpd_confirm_page, 'Confirming Login')
+
+            session = self._download_webpage(
+                self._SERVICE_PROVIDER_TEMPLATE % 'session', video_id,
+                'Retrieving Session', data=urlencode_postdata({
+                    '_method': 'GET',
+                    'requestor_id': requestor_id,
+                }), headers=mvpd_headers)
+            if '<pendingLogout' in session:
+                self._downloader.cache.store('mvpd', requestor_id, {})
+                return self._extract_mvpd_auth(url, video_id, requestor_id, resource)
+            authn_token = unescapeHTML(xml_text(session, 'authnToken'))
+            requestor_info['authn_token'] = authn_token
+            self._downloader.cache.store('mvpd', requestor_id, requestor_info)
+
+        authz_token = requestor_info.get(guid)
+        if authz_token and is_expired(authz_token, 'simpleTokenTTL'):
+            authz_token = None
+        if not authz_token:
+            authorize = self._download_webpage(
+                self._SERVICE_PROVIDER_TEMPLATE % 'authorize', video_id,
+                'Retrieving Authorization Token', data=urlencode_postdata({
+                    'resource_id': resource,
+                    'requestor_id': requestor_id,
+                    'authentication_token': authn_token,
+                    'mso_id': xml_text(authn_token, 'simpleTokenMsoID'),
+                    'userMeta': '1',
+                }), headers=mvpd_headers)
+            if '<pendingLogout' in authorize:
+                self._downloader.cache.store('mvpd', requestor_id, {})
+                return self._extract_mvpd_auth(url, video_id, requestor_id, resource)
+            authz_token = unescapeHTML(xml_text(authorize, 'authzToken'))
+            requestor_info[guid] = authz_token
+            self._downloader.cache.store('mvpd', requestor_id, requestor_info)
+
+        mvpd_headers.update({
+            'ap_19': xml_text(authn_token, 'simpleSamlNameID'),
+            'ap_23': xml_text(authn_token, 'simpleSamlSessionIndex'),
+        })
+
+        short_authorize = self._download_webpage(
+            self._SERVICE_PROVIDER_TEMPLATE % 'shortAuthorize',
+            video_id, 'Retrieving Media Token', data=urlencode_postdata({
+                'authz_token': authz_token,
+                'requestor_id': requestor_id,
+                'session_guid': xml_text(authn_token, 'simpleTokenAuthenticationGuid'),
+                'hashed_guid': 'false',
+            }), headers=mvpd_headers)
+        if '<pendingLogout' in short_authorize:
+            self._downloader.cache.store('mvpd', requestor_id, {})
+            return self._extract_mvpd_auth(url, video_id, requestor_id, resource)
+        return short_authorize

youtube_dl/extractor/adultswim.py

@@ -3,16 +3,14 @@ from __future__ import unicode_literals
 
 import re
 
-from .common import InfoExtractor
+from .turner import TurnerBaseIE
 from ..utils import (
-    determine_ext,
     ExtractorError,
-    float_or_none,
-    xpath_text,
+    int_or_none,
 )
 
 
-class AdultSwimIE(InfoExtractor):
+class AdultSwimIE(TurnerBaseIE):
     _VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<is_playlist>playlists/)?(?P<show_path>[^/]+)/(?P<episode_path>[^/?#]+)/?'
 
     _TESTS = [{
@@ -96,7 +94,8 @@ class AdultSwimIE(InfoExtractor):
         'params': {
             # m3u8 download
             'skip_download': True,
-        }
+        },
+        'expected_warnings': ['Unable to download f4m manifest'],
     }]
 
     @staticmethod
@@ -148,7 +147,10 @@ class AdultSwimIE(InfoExtractor):
                 if bootstrapped_data.get('slugged_video', {}).get('slug') == episode_path:
                     video_info = bootstrapped_data['slugged_video']
             if not video_info:
-                video_info = bootstrapped_data.get('heroMetadata', {}).get('trailer').get('video')
+                video_info = bootstrapped_data.get(
+                    'heroMetadata', {}).get('trailer', {}).get('video')
+            if not video_info:
+                video_info = bootstrapped_data.get('onlineOriginals', [None])[0]
             if not video_info:
                 raise ExtractorError('Unable to find video info')
 
@@ -162,70 +164,38 @@ class AdultSwimIE(InfoExtractor):
             elif video_info.get('videoPlaybackID'):
                 segment_ids = [video_info['videoPlaybackID']]
             else:
-                raise ExtractorError(
-                    'This video is only available via cable service provider subscription that'
-                    ' is not currently supported. You may want to use --cookies.'
-                    if video_info.get('auth') is True else 'Unable to find stream or clips',
-                    expected=True)
+                if video_info.get('auth') is True:
+                    raise ExtractorError(
+                        'This video is only available via cable service provider subscription that'
+                        ' is not currently supported. You may want to use --cookies.', expected=True)
+                else:
+                    raise ExtractorError('Unable to find stream or clips')
 
         episode_id = video_info['id']
         episode_title = video_info['title']
-        episode_description = video_info['description']
-        episode_duration = video_info.get('duration')
+        episode_description = video_info.get('description')
+        episode_duration = int_or_none(video_info.get('duration'))
+        view_count = int_or_none(video_info.get('views'))
 
         entries = []
         for part_num, segment_id in enumerate(segment_ids):
-            segment_url = 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=desktop' % segment_id
-
+            segement_info = self._extract_cvp_info(
+                'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=desktop' % segment_id,
+                segment_id, {
+                    'secure': {
+                        'media_src': 'http://androidhls-secure.cdn.turner.com/adultswim/big',
+                        'tokenizer_src': 'http://www.adultswim.com/astv/mvpd/processors/services/token_ipadAdobe.do',
+                    },
+                })
             segment_title = '%s - %s' % (show_title, episode_title)
             if len(segment_ids) > 1:
                 segment_title += ' Part %d' % (part_num + 1)
-
-            idoc = self._download_xml(
-                segment_url, segment_title,
-                'Downloading segment information', 'Unable to download segment information')
-
-            segment_duration = float_or_none(
-                xpath_text(idoc, './/trt', 'segment duration').strip())
-
-            formats = []
-            file_els = idoc.findall('.//files/file') or idoc.findall('./files/file')
-
-            unique_urls = []
-            unique_file_els = []
-            for file_el in file_els:
-                media_url = file_el.text
-                if not media_url or determine_ext(media_url) == 'f4m':
-                    continue
-                if file_el.text not in unique_urls:
-                    unique_urls.append(file_el.text)
-                    unique_file_els.append(file_el)
-
-            for file_el in unique_file_els:
-                bitrate = file_el.attrib.get('bitrate')
-                ftype = file_el.attrib.get('type')
-                media_url = file_el.text
-                if determine_ext(media_url) == 'm3u8':
-                    formats.extend(self._extract_m3u8_formats(
-                        media_url, segment_title, 'mp4', preference=0,
-                        m3u8_id='hls', fatal=False))
-                else:
-                    formats.append({
-                        'format_id': '%s_%s' % (bitrate, ftype),
-                        'url': file_el.text.strip(),
-                        # The bitrate may not be a number (for example: 'iphone')
-                        'tbr': int(bitrate) if bitrate.isdigit() else None,
-                    })
-
-            self._sort_formats(formats)
-
-            entries.append({
+            segement_info.update({
                 'id': segment_id,
                 'title': segment_title,
-                'formats': formats,
-                'duration': segment_duration,
-                'description': episode_description
+                'description': episode_description,
             })
+            entries.append(segement_info)
 
         return {
             '_type': 'playlist',
@@ -234,5 +204,6 @@ class AdultSwimIE(InfoExtractor):
             'entries': entries,
             'title': '%s - %s' % (show_title, episode_title),
             'description': episode_description,
-            'duration': episode_duration
+            'duration': episode_duration,
+            'view_count': view_count,
         }

youtube_dl/extractor/aenetworks.py

@@ -109,7 +109,10 @@ class AENetworksIE(AENetworksBaseIE):
         info = self._parse_theplatform_metadata(theplatform_metadata)
         if theplatform_metadata.get('AETN$isBehindWall'):
             requestor_id = self._DOMAIN_TO_REQUESTOR_ID[domain]
-            resource = '<rss version="2.0" xmlns:media="http://search.yahoo.com/mrss/"><channel><title>%s</title><item><title>%s</title><guid>%s</guid><media:rating scheme="urn:v-chip">%s</media:rating></item></channel></rss>' % (requestor_id, theplatform_metadata['title'], theplatform_metadata['AETN$PPL_pplProgramId'], theplatform_metadata['ratings'][0]['rating'])
+            resource = self._get_mvpd_resource(
+                requestor_id, theplatform_metadata['title'],
+                theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'),
+                theplatform_metadata['ratings'][0]['rating'])
             query['auth'] = self._extract_mvpd_auth(
                 url, video_id, requestor_id, resource)
         info.update(self._search_json_ld(webpage, video_id, fatal=False))

youtube_dl/extractor/amcnetworks.py

@@ -0,0 +1,91 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .theplatform import ThePlatformIE
+from ..utils import (
+    update_url_query,
+    parse_age_limit,
+    int_or_none,
+)
+
+
+class AMCNetworksIE(ThePlatformIE):
+    _VALID_URL = r'https?://(?:www\.)?(?:amc|bbcamerica|ifc|wetv)\.com/(?:movies/|shows/[^/]+/(?:full-episodes/)?season-\d+/episode-\d+(?:-(?:[^/]+/)?|/))(?P<id>[^/?#]+)'
+    _TESTS = [{
+        'url': 'http://www.ifc.com/shows/maron/season-04/episode-01/step-1',
+        'md5': '',
+        'info_dict': {
+            'id': 's3MX01Nl4vPH',
+            'ext': 'mp4',
+            'title': 'Maron - Season 4 - Step 1',
+            'description': 'In denial about his current situation, Marc is reluctantly convinced by his friends to enter rehab. Starring Marc Maron and Constance Zimmer.',
+            'age_limit': 17,
+            'upload_date': '20160505',
+            'timestamp': 1462468831,
+            'uploader': 'AMCN',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://www.bbcamerica.com/shows/the-hunt/full-episodes/season-1/episode-01-the-hardest-challenge',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.amc.com/shows/preacher/full-episodes/season-01/episode-00/pilot',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.wetv.com/shows/million-dollar-matchmaker/season-01/episode-06-the-dumped-dj-and-shallow-hal',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.ifc.com/movies/chaos',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        query = {
+            'mbr': 'true',
+            'manifest': 'm3u',
+        }
+        media_url = self._search_regex(r'window\.platformLinkURL\s*=\s*[\'"]([^\'"]+)', webpage, 'media url')
+        theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
+            r'https?://link.theplatform.com/s/([^?]+)', media_url, 'theplatform_path'), display_id)
+        info = self._parse_theplatform_metadata(theplatform_metadata)
+        video_id = theplatform_metadata['pid']
+        title = theplatform_metadata['title']
+        rating = theplatform_metadata['ratings'][0]['rating']
+        auth_required = self._search_regex(r'window\.authRequired\s*=\s*(true|false);', webpage, 'auth required')
+        if auth_required == 'true':
+            requestor_id = self._search_regex(r'window\.requestor_id\s*=\s*[\'"]([^\'"]+)', webpage, 'requestor id')
+            resource = self._get_mvpd_resource(requestor_id, title, video_id, rating)
+            query['auth'] = self._extract_mvpd_auth(url, video_id, requestor_id, resource)
+        media_url = update_url_query(media_url, query)
+        formats, subtitles = self._extract_theplatform_smil(media_url, video_id)
+        self._sort_formats(formats)
+        info.update({
+            'id': video_id,
+            'subtitles': subtitles,
+            'formats': formats,
+            'age_limit': parse_age_limit(parse_age_limit(rating)),
+        })
+        ns_keys = theplatform_metadata.get('$xmlns', {}).keys()
+        if ns_keys:
+            ns = list(ns_keys)[0]
+            series = theplatform_metadata.get(ns + '$show')
+            season_number = int_or_none(theplatform_metadata.get(ns + '$season'))
+            episode = theplatform_metadata.get(ns + '$episodeTitle')
+            episode_number = int_or_none(theplatform_metadata.get(ns + '$episode'))
+            if season_number:
+                title = 'Season %d - %s' % (season_number, title)
+            if series:
+                title = '%s - %s' % (series, title)
+            info.update({
+                'title': title,
+                'series': series,
+                'season_number': season_number,
+                'episode': episode,
+                'episode_number': episode_number,
+            })
+        return info

youtube_dl/extractor/aol.py

@@ -123,6 +123,10 @@ class AolFeaturesIE(InfoExtractor):
             'title': 'What To Watch - February 17, 2016',
         },
         'add_ie': ['FiveMin'],
+        'params': {
+            # encrypted m3u8 download
+            'skip_download': True,
+        },
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/aparat.py

@@ -1,8 +1,6 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
@@ -15,7 +13,7 @@ class AparatIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://www.aparat.com/v/wP8On',
-        'md5': '6714e0af7e0d875c5a39c4dc4ab46ad1',
+        'md5': '131aca2e14fe7c4dcb3c4877ba300c89',
         'info_dict': {
             'id': 'wP8On',
             'ext': 'mp4',
@@ -31,13 +29,13 @@ class AparatIE(InfoExtractor):
         # Note: There is an easier-to-parse configuration at
         # http://www.aparat.com/video/video/config/videohash/%video_id
         # but the URL in there does not work
-        embed_url = ('http://www.aparat.com/video/video/embed/videohash/' +
-                     video_id + '/vt/frame')
+        embed_url = 'http://www.aparat.com/video/video/embed/vt/frame/showvideo/yes/videohash/' + video_id
         webpage = self._download_webpage(embed_url, video_id)
 
-        video_urls = [video_url.replace('\\/', '/') for video_url in re.findall(
-            r'(?:fileList\[[0-9]+\]\s*=|"file"\s*:)\s*"([^"]+)"', webpage)]
-        for i, video_url in enumerate(video_urls):
+        file_list = self._parse_json(self._search_regex(
+            r'fileList\s*=\s*JSON\.parse\(\'([^\']+)\'\)', webpage, 'file list'), video_id)
+        for i, item in enumerate(file_list[0]):
+            video_url = item['file']
             req = HEADRequest(video_url)
             res = self._request_webpage(
                 req, video_id, note='Testing video URL %d' % i, errnote=False)

youtube_dl/extractor/awaan.py

@@ -12,46 +12,41 @@ from ..compat import (
 from ..utils import (
     int_or_none,
     parse_iso8601,
-    sanitized_Request,
     smuggle_url,
     unsmuggle_url,
     urlencode_postdata,
 )
 
 
-class DCNIE(InfoExtractor):
+class AWAANIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?show/(?P<show_id>\d+)/[^/]+(?:/(?P<video_id>\d+)/(?P<season_id>\d+))?'
 
     def _real_extract(self, url):
         show_id, video_id, season_id = re.match(self._VALID_URL, url).groups()
         if video_id and int(video_id) > 0:
             return self.url_result(
-                'http://www.dcndigital.ae/media/%s' % video_id, 'DCNVideo')
+                'http://awaan.ae/media/%s' % video_id, 'AWAANVideo')
         elif season_id and int(season_id) > 0:
             return self.url_result(smuggle_url(
-                'http://www.dcndigital.ae/program/season/%s' % season_id,
-                {'show_id': show_id}), 'DCNSeason')
+                'http://awaan.ae/program/season/%s' % season_id,
+                {'show_id': show_id}), 'AWAANSeason')
         else:
             return self.url_result(
-                'http://www.dcndigital.ae/program/%s' % show_id, 'DCNSeason')
+                'http://awaan.ae/program/%s' % show_id, 'AWAANSeason')
 
 
-class DCNBaseIE(InfoExtractor):
-    def _extract_video_info(self, video_data, video_id, is_live):
+class AWAANBaseIE(InfoExtractor):
+    def _parse_video_data(self, video_data, video_id, is_live):
         title = video_data.get('title_en') or video_data['title_ar']
         img = video_data.get('img')
-        thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None
-        duration = int_or_none(video_data.get('duration'))
-        description = video_data.get('description_en') or video_data.get('description_ar')
-        timestamp = parse_iso8601(video_data.get('create_time'), ' ')
 
         return {
             'id': video_id,
             'title': self._live_title(title) if is_live else title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'duration': duration,
-            'timestamp': timestamp,
+            'description': video_data.get('description_en') or video_data.get('description_ar'),
+            'thumbnail': 'http://admin.mangomolo.com/analytics/%s' % img if img else None,
+            'duration': int_or_none(video_data.get('duration')),
+            'timestamp': parse_iso8601(video_data.get('create_time'), ' '),
             'is_live': is_live,
         }
 
@@ -75,11 +70,12 @@ class DCNBaseIE(InfoExtractor):
         return formats
 
 
-class DCNVideoIE(DCNBaseIE):
-    IE_NAME = 'dcn:video'
+class AWAANVideoIE(AWAANBaseIE):
+    IE_NAME = 'awaan:video'
     _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?(?:video(?:/[^/]+)?|media|catchup/[^/]+/[^/]+)/(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://www.dcndigital.ae/#/video/%D8%B1%D8%AD%D9%84%D8%A9-%D8%A7%D9%84%D8%B9%D9%85%D8%B1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/17375',
+        'md5': '5f61c33bfc7794315c671a62d43116aa',
         'info_dict':
         {
             'id': '17375',
@@ -90,10 +86,6 @@ class DCNVideoIE(DCNBaseIE):
             'timestamp': 1227504126,
             'upload_date': '20081124',
         },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
     }, {
         'url': 'http://awaan.ae/video/26723981/%D8%AF%D8%A7%D8%B1-%D8%A7%D9%84%D8%B3%D9%84%D8%A7%D9%85:-%D8%AE%D9%8A%D8%B1-%D8%AF%D9%88%D8%B1-%D8%A7%D9%84%D8%A3%D9%86%D8%B5%D8%A7%D8%B1',
         'only_matching': True,
@@ -102,11 +94,10 @@ class DCNVideoIE(DCNBaseIE):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        request = sanitized_Request(
+        video_data = self._download_json(
             'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
-            headers={'Origin': 'http://www.dcndigital.ae'})
-        video_data = self._download_json(request, video_id)
-        info = self._extract_video_info(video_data, video_id, False)
+            video_id, headers={'Origin': 'http://awaan.ae'})
+        info = self._parse_video_data(video_data, video_id, False)
 
         webpage = self._download_webpage(
             'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' +
@@ -121,19 +112,31 @@ class DCNVideoIE(DCNBaseIE):
         return info
 
 
-class DCNLiveIE(DCNBaseIE):
-    IE_NAME = 'dcn:live'
+class AWAANLiveIE(AWAANBaseIE):
+    IE_NAME = 'awaan:live'
     _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?live/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://awaan.ae/live/6/dubai-tv',
+        'info_dict': {
+            'id': '6',
+            'ext': 'mp4',
+            'title': 're:Dubai Al Oula [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'upload_date': '20150107',
+            'timestamp': 1420588800,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
 
     def _real_extract(self, url):
         channel_id = self._match_id(url)
 
-        request = sanitized_Request(
+        channel_data = self._download_json(
             'http://admin.mangomolo.com/analytics/index.php/plus/getchanneldetails?channel_id=%s' % channel_id,
-            headers={'Origin': 'http://www.dcndigital.ae'})
-
-        channel_data = self._download_json(request, channel_id)
-        info = self._extract_video_info(channel_data, channel_id, True)
+            channel_id, headers={'Origin': 'http://awaan.ae'})
+        info = self._parse_video_data(channel_data, channel_id, True)
 
         webpage = self._download_webpage(
             'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' +
@@ -148,8 +151,8 @@ class DCNLiveIE(DCNBaseIE):
         return info
 
 
-class DCNSeasonIE(InfoExtractor):
-    IE_NAME = 'dcn:season'
+class AWAANSeasonIE(InfoExtractor):
+    IE_NAME = 'awaan:season'
     _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?program/(?:(?P<show_id>\d+)|season/(?P<season_id>\d+))'
     _TEST = {
         'url': 'http://dcndigital.ae/#/program/205024/%D9%85%D8%AD%D8%A7%D8%B6%D8%B1%D8%A7%D8%AA-%D8%A7%D9%84%D8%B4%D9%8A%D8%AE-%D8%A7%D9%84%D8%B4%D8%B9%D8%B1%D8%A7%D9%88%D9%8A',
@@ -170,21 +173,17 @@ class DCNSeasonIE(InfoExtractor):
             data['season'] = season_id
             show_id = smuggled_data.get('show_id')
             if show_id is None:
-                request = sanitized_Request(
+                season = self._download_json(
                     'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id=%s' % season_id,
-                    headers={'Origin': 'http://www.dcndigital.ae'})
-                season = self._download_json(request, season_id)
+                    season_id, headers={'Origin': 'http://awaan.ae'})
                 show_id = season['id']
         data['show_id'] = show_id
-        request = sanitized_Request(
+        show = self._download_json(
             'http://admin.mangomolo.com/analytics/index.php/plus/show',
-            urlencode_postdata(data),
-            {
-                'Origin': 'http://www.dcndigital.ae',
+            show_id, data=urlencode_postdata(data), headers={
+                'Origin': 'http://awaan.ae',
                 'Content-Type': 'application/x-www-form-urlencoded'
             })
-
-        show = self._download_json(request, show_id)
         if not season_id:
             season_id = show['default_season']
         for season in show['seasons']:
@@ -195,6 +194,6 @@ class DCNSeasonIE(InfoExtractor):
                 for video in show['videos']:
                     video_id = compat_str(video['id'])
                     entries.append(self.url_result(
-                        'http://www.dcndigital.ae/media/%s' % video_id, 'DCNVideo', video_id))
+                        'http://awaan.ae/media/%s' % video_id, 'AWAANVideo', video_id))
 
                 return self.playlist_result(entries, season_id, title)

youtube_dl/extractor/bandcamp.py

@@ -162,6 +162,15 @@ class BandcampAlbumIE(InfoExtractor):
             'uploader_id': 'dotscale',
         },
         'playlist_mincount': 7,
+    }, {
+        # with escaped quote in title
+        'url': 'https://jstrecords.bandcamp.com/album/entropy-ep',
+        'info_dict': {
+            'title': '"Entropy" EP',
+            'uploader_id': 'jstrecords',
+            'id': 'entropy-ep',
+        },
+        'playlist_mincount': 3,
     }]
 
     def _real_extract(self, url):
@@ -176,8 +185,11 @@ class BandcampAlbumIE(InfoExtractor):
         entries = [
             self.url_result(compat_urlparse.urljoin(url, t_path), ie=BandcampIE.ie_key())
             for t_path in tracks_paths]
-        title = self._search_regex(
-            r'album_title\s*:\s*"(.*?)"', webpage, 'title', fatal=False)
+        title = self._html_search_regex(
+            r'album_title\s*:\s*"((?:\\.|[^"\\])+?)"',
+            webpage, 'title', fatal=False)
+        if title:
+            title = title.replace(r'\"', '"')
         return {
             '_type': 'playlist',
             'uploader_id': uploader_id,

youtube_dl/extractor/bbc.py

@@ -2,6 +2,7 @@
 from __future__ import unicode_literals
 
 import re
+import itertools
 
 from .common import InfoExtractor
 from ..utils import (
@@ -17,6 +18,7 @@ from ..utils import (
 from ..compat import (
     compat_etree_fromstring,
     compat_HTTPError,
+    compat_urlparse,
 )
 
 
@@ -759,7 +761,7 @@ class BBCIE(BBCCoUkIE):
 
         webpage = self._download_webpage(url, playlist_id)
 
-        json_ld_info = self._search_json_ld(webpage, playlist_id, default=None)
+        json_ld_info = self._search_json_ld(webpage, playlist_id, default={})
         timestamp = json_ld_info.get('timestamp')
 
         playlist_title = json_ld_info.get('title')
@@ -1056,19 +1058,35 @@ class BBCCoUkArticleIE(InfoExtractor):
 
 
 class BBCCoUkPlaylistBaseIE(InfoExtractor):
+    def _entries(self, webpage, url, playlist_id):
+        single_page = 'page' in compat_urlparse.parse_qs(
+            compat_urlparse.urlparse(url).query)
+        for page_num in itertools.count(2):
+            for video_id in re.findall(
+                    self._VIDEO_ID_TEMPLATE % BBCCoUkIE._ID_REGEX, webpage):
+                yield self.url_result(
+                    self._URL_TEMPLATE % video_id, BBCCoUkIE.ie_key())
+            if single_page:
+                return
+            next_page = self._search_regex(
+                r'<li[^>]+class=(["\'])pagination_+next\1[^>]*><a[^>]+href=(["\'])(?P<url>(?:(?!\2).)+)\2',
+                webpage, 'next page url', default=None, group='url')
+            if not next_page:
+                break
+            webpage = self._download_webpage(
+                compat_urlparse.urljoin(url, next_page), playlist_id,
+                'Downloading page %d' % page_num, page_num)
+
     def _real_extract(self, url):
         playlist_id = self._match_id(url)
 
         webpage = self._download_webpage(url, playlist_id)
 
-        entries = [
-            self.url_result(self._URL_TEMPLATE % video_id, BBCCoUkIE.ie_key())
-            for video_id in re.findall(
-                self._VIDEO_ID_TEMPLATE % BBCCoUkIE._ID_REGEX, webpage)]
-
         title, description = self._extract_title_and_description(webpage)
 
-        return self.playlist_result(entries, playlist_id, title, description)
+        return self.playlist_result(
+            self._entries(webpage, url, playlist_id),
+            playlist_id, title, description)
 
 
 class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE):
@@ -1117,6 +1135,24 @@ class BBCCoUkPlaylistIE(BBCCoUkPlaylistBaseIE):
             'description': 'French thriller serial about a missing teenager.',
         },
         'playlist_mincount': 7,
+    }, {
+        # multipage playlist, explicit page
+        'url': 'http://www.bbc.co.uk/programmes/b00mfl7n/clips?page=1',
+        'info_dict': {
+            'id': 'b00mfl7n',
+            'title': 'Frozen Planet - Clips - BBC One',
+            'description': 'md5:65dcbf591ae628dafe32aa6c4a4a0d8c',
+        },
+        'playlist_mincount': 24,
+    }, {
+        # multipage playlist, all pages
+        'url': 'http://www.bbc.co.uk/programmes/b00mfl7n/clips',
+        'info_dict': {
+            'id': 'b00mfl7n',
+            'title': 'Frozen Planet - Clips - BBC One',
+            'description': 'md5:65dcbf591ae628dafe32aa6c4a4a0d8c',
+        },
+        'playlist_mincount': 142,
     }, {
         'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/broadcasts/2016/06',
         'only_matching': True,

youtube_dl/extractor/bet.py

@@ -2,7 +2,6 @@ from __future__ import unicode_literals
 
 from .mtv import MTVServicesInfoExtractor
 from ..utils import unified_strdate
-from ..compat import compat_urllib_parse_urlencode
 
 
 class BetIE(MTVServicesInfoExtractor):
@@ -53,9 +52,9 @@ class BetIE(MTVServicesInfoExtractor):
     _FEED_URL = "http://feeds.mtvnservices.com/od/feed/bet-mrss-player"
 
     def _get_feed_query(self, uri):
-        return compat_urllib_parse_urlencode({
+        return {
             'uuid': uri,
-        })
+        }
 
     def _extract_mgid(self, webpage):
         return self._search_regex(r'data-uri="([^"]+)', webpage, 'mgid')

youtube_dl/extractor/bigflix.py

@@ -11,15 +11,6 @@ from ..compat import compat_urllib_parse_unquote
 class BigflixIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?bigflix\.com/.+/(?P<id>[0-9]+)'
     _TESTS = [{
-        'url': 'http://www.bigflix.com/Hindi-movies/Action-movies/Singham-Returns/16537',
-        'md5': 'dc1b4aebb46e3a7077ecc0d9f43f61e3',
-        'info_dict': {
-            'id': '16537',
-            'ext': 'mp4',
-            'title': 'Singham Returns',
-            'description': 'md5:3d2ba5815f14911d5cc6a501ae0cf65d',
-        }
-    }, {
         # 2 formats
         'url': 'http://www.bigflix.com/Tamil-movies/Drama-movies/Madarasapatinam/16070',
         'info_dict': {

youtube_dl/extractor/bilibili.py

@@ -1,22 +1,15 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import calendar
-import datetime
+import hashlib
 import re
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_etree_fromstring,
-    compat_str,
-    compat_parse_qs,
-    compat_xml_parse_error,
-)
+from ..compat import compat_parse_qs
 from ..utils import (
-    ExtractorError,
     int_or_none,
     float_or_none,
-    xpath_text,
+    unified_timestamp,
 )
 
 
@@ -25,13 +18,13 @@ class BiliBiliIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.bilibili.tv/video/av1074402/',
-        'md5': '5f7d29e1a2872f3df0cf76b1f87d3788',
+        'md5': '9fa226fe2b8a9a4d5a69b4c6a183417e',
         'info_dict': {
-            'id': '1554319',
-            'ext': 'flv',
+            'id': '1074402',
+            'ext': 'mp4',
             'title': '【金坷垃】金泡沫',
             'description': 'md5:ce18c2a2d2193f0df2917d270f2e5923',
-            'duration': 308.067,
+            'duration': 308.315,
             'timestamp': 1398012660,
             'upload_date': '20140420',
             'thumbnail': 're:^https?://.+\.jpg',
@@ -42,76 +35,42 @@ class BiliBiliIE(InfoExtractor):
         'url': 'http://www.bilibili.com/video/av1041170/',
         'info_dict': {
             'id': '1041170',
+            'ext': 'mp4',
             'title': '【BD1080P】刀语【诸神&异域】',
             'description': '这是个神奇的故事~每个人不留弹幕不给走哦~切利哦！~',
+            'duration': 3382.259,
+            'timestamp': 1396530060,
+            'upload_date': '20140403',
+            'thumbnail': 're:^https?://.+\.jpg',
+            'uploader': '枫叶逝去',
+            'uploader_id': '520116',
         },
-        'playlist_count': 9,
     }, {
         'url': 'http://www.bilibili.com/video/av4808130/',
         'info_dict': {
             'id': '4808130',
+            'ext': 'mp4',
             'title': '【长篇】哆啦A梦443【钉铛】',
             'description': '(2016.05.27)来组合客人的脸吧&寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&illust_id=56912929',
+            'duration': 1493.995,
+            'timestamp': 1464564180,
+            'upload_date': '20160529',
+            'thumbnail': 're:^https?://.+\.jpg',
+            'uploader': '喜欢拉面',
+            'uploader_id': '151066',
         },
-        'playlist': [{
-            'md5': '55cdadedf3254caaa0d5d27cf20a8f9c',
-            'info_dict': {
-                'id': '4808130_part1',
-                'ext': 'flv',
-                'title': '【长篇】哆啦A梦443【钉铛】',
-                'description': '(2016.05.27)来组合客人的脸吧&寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&illust_id=56912929',
-                'timestamp': 1464564180,
-                'upload_date': '20160529',
-                'uploader': '喜欢拉面',
-                'uploader_id': '151066',
-            },
-        }, {
-            'md5': '926f9f67d0c482091872fbd8eca7ea3d',
-            'info_dict': {
-                'id': '4808130_part2',
-                'ext': 'flv',
-                'title': '【长篇】哆啦A梦443【钉铛】',
-                'description': '(2016.05.27)来组合客人的脸吧&寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&illust_id=56912929',
-                'timestamp': 1464564180,
-                'upload_date': '20160529',
-                'uploader': '喜欢拉面',
-                'uploader_id': '151066',
-            },
-        }, {
-            'md5': '4b7b225b968402d7c32348c646f1fd83',
-            'info_dict': {
-                'id': '4808130_part3',
-                'ext': 'flv',
-                'title': '【长篇】哆啦A梦443【钉铛】',
-                'description': '(2016.05.27)来组合客人的脸吧&寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&illust_id=56912929',
-                'timestamp': 1464564180,
-                'upload_date': '20160529',
-                'uploader': '喜欢拉面',
-                'uploader_id': '151066',
-            },
-        }, {
-            'md5': '7b795e214166501e9141139eea236e91',
-            'info_dict': {
-                'id': '4808130_part4',
-                'ext': 'flv',
-                'title': '【长篇】哆啦A梦443【钉铛】',
-                'description': '(2016.05.27)来组合客人的脸吧&寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&illust_id=56912929',
-                'timestamp': 1464564180,
-                'upload_date': '20160529',
-                'uploader': '喜欢拉面',
-                'uploader_id': '151066',
-            },
-        }],
     }, {
         # Missing upload time
         'url': 'http://www.bilibili.com/video/av1867637/',
         'info_dict': {
-            'id': '2880301',
-            'ext': 'flv',
+            'id': '1867637',
+            'ext': 'mp4',
             'title': '【HDTV】【喜剧】岳父岳母真难当 （2014）【法国票房冠军】',
             'description': '一个信奉天主教的法国旧式传统资产阶级家庭中有四个女儿。三个女儿却分别找了阿拉伯、犹太、中国丈夫，老夫老妻唯独期盼剩下未嫁的小女儿能找一个信奉天主教的法国白人，结果没想到小女儿找了一位非裔黑人……【这次应该不会跳帧了】',
+            'duration': 5760.0,
             'uploader': '黑夜为猫',
             'uploader_id': '610729',
+            'thumbnail': 're:^https?://.+\.jpg',
         },
         'params': {
             # Just to test metadata extraction
@@ -120,86 +79,61 @@ class BiliBiliIE(InfoExtractor):
         'expected_warnings': ['upload time'],
     }]
 
-    # BiliBili blocks keys from time to time. The current key is extracted from
-    # the Android client
-    # TODO: find the sign algorithm used in the flash player
-    _APP_KEY = '86385cdc024c0f6c'
+    _APP_KEY = '6f90a59ac58a4123'
+    _BILIBILI_KEY = '0bfd84cc3940035173f35e6777508326'
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
 
-        params = compat_parse_qs(self._search_regex(
+        cid = compat_parse_qs(self._search_regex(
             [r'EmbedPlayer\([^)]+,\s*"([^"]+)"\)',
              r'<iframe[^>]+src="https://secure\.bilibili\.com/secure,([^"]+)"'],
-            webpage, 'player parameters'))
-        cid = params['cid'][0]
+            webpage, 'player parameters'))['cid'][0]
 
-        info_xml_str = self._download_webpage(
-            'http://interface.bilibili.com/v_cdn_play',
-            cid, query={'appkey': self._APP_KEY, 'cid': cid},
-            note='Downloading video info page')
+        payload = 'appkey=%s&cid=%s&otype=json&quality=2&type=mp4' % (self._APP_KEY, cid)
+        sign = hashlib.md5((payload + self._BILIBILI_KEY).encode('utf-8')).hexdigest()
 
-        err_msg = None
-        durls = None
-        info_xml = None
-        try:
-            info_xml = compat_etree_fromstring(info_xml_str.encode('utf-8'))
-        except compat_xml_parse_error:
-            info_json = self._parse_json(info_xml_str, video_id, fatal=False)
-            err_msg = (info_json or {}).get('error_text')
-        else:
-            err_msg = xpath_text(info_xml, './message')
-
-        if info_xml is not None:
-            durls = info_xml.findall('./durl')
-        if not durls:
-            if err_msg:
-                raise ExtractorError('%s said: %s' % (self.IE_NAME, err_msg), expected=True)
-            else:
-                raise ExtractorError('No videos found!')
+        video_info = self._download_json(
+            'http://interface.bilibili.com/playurl?%s&sign=%s' % (payload, sign),
+            video_id, note='Downloading video info page')
 
         entries = []
 
-        for durl in durls:
-            size = xpath_text(durl, ['./filesize', './size'])
+        for idx, durl in enumerate(video_info['durl']):
             formats = [{
-                'url': durl.find('./url').text,
-                'filesize': int_or_none(size),
+                'url': durl['url'],
+                'filesize': int_or_none(durl['size']),
             }]
-            for backup_url in durl.findall('./backup_url/url'):
+            for backup_url in durl['backup_url']:
                 formats.append({
-                    'url': backup_url.text,
+                    'url': backup_url,
                     # backup URLs have lower priorities
-                    'preference': -2 if 'hd.mp4' in backup_url.text else -3,
+                    'preference': -2 if 'hd.mp4' in backup_url else -3,
                 })
 
             self._sort_formats(formats)
 
             entries.append({
-                'id': '%s_part%s' % (cid, xpath_text(durl, './order')),
-                'duration': int_or_none(xpath_text(durl, './length'), 1000),
+                'id': '%s_part%s' % (video_id, idx),
+                'duration': float_or_none(durl.get('length'), 1000),
                 'formats': formats,
             })
 
         title = self._html_search_regex('<h1[^>]+title="([^"]+)">', webpage, 'title')
         description = self._html_search_meta('description', webpage)
-        datetime_str = self._html_search_regex(
-            r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', fatal=False)
-        timestamp = None
-        if datetime_str:
-            timestamp = calendar.timegm(datetime.datetime.strptime(datetime_str, '%Y-%m-%dT%H:%M').timetuple())
+        timestamp = unified_timestamp(self._html_search_regex(
+            r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', fatal=False))
 
         # TODO 'view_count' requires deobfuscating Javascript
         info = {
-            'id': compat_str(cid),
+            'id': video_id,
             'title': title,
             'description': description,
             'timestamp': timestamp,
             'thumbnail': self._html_search_meta('thumbnailUrl', webpage),
-            'duration': float_or_none(xpath_text(info_xml, './timelength'), scale=1000),
+            'duration': float_or_none(video_info.get('timelength'), scale=1000),
         }
 
         uploader_mobj = re.search(

youtube_dl/extractor/biqle.py

@@ -24,7 +24,8 @@ class BIQLEIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Ребенок в шоке от автоматической мойки',
             'uploader': 'Dmitry Kotov',
-        }
+        },
+        'skip': ' This video was marked as adult.  Embedding adult videos on external sites is prohibited.',
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/bravotv.py

@@ -1,31 +1,74 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-from .common import InfoExtractor
-from ..utils import smuggle_url
+from .adobepass import AdobePassIE
+from ..utils import (
+    smuggle_url,
+    update_url_query,
+    int_or_none,
+)
 
 
-class BravoTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?bravotv\.com/(?:[^/]+/)+videos/(?P<id>[^/?]+)'
-    _TEST = {
+class BravoTVIE(AdobePassIE):
+    _VALID_URL = r'https?://(?:www\.)?bravotv\.com/(?:[^/]+/)+(?P<id>[^/?#]+)'
+    _TESTS = [{
         'url': 'http://www.bravotv.com/last-chance-kitchen/season-5/videos/lck-ep-12-fishy-finale',
-        'md5': 'd60cdf68904e854fac669bd26cccf801',
+        'md5': '9086d0b7ef0ea2aabc4781d75f4e5863',
         'info_dict': {
-            'id': 'LitrBdX64qLn',
+            'id': 'zHyk1_HU_mPy',
             'ext': 'mp4',
-            'title': 'Last Chance Kitchen Returns',
-            'description': 'S13: Last Chance Kitchen Returns for Top Chef Season 13',
-            'timestamp': 1448926740,
-            'upload_date': '20151130',
+            'title': 'LCK Ep 12: Fishy Finale',
+            'description': 'S13/E12: Two eliminated chefs have just 12 minutes to cook up a delicious fish dish.',
             'uploader': 'NBCU-BRAV',
+            'upload_date': '20160302',
+            'timestamp': 1456945320,
         }
-    }
+    }, {
+        'url': 'http://www.bravotv.com/below-deck/season-3/ep-14-reunion-part-1',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-        account_pid = self._search_regex(r'"account_pid"\s*:\s*"([^"]+)"', webpage, 'account pid')
-        release_pid = self._search_regex(r'"release_pid"\s*:\s*"([^"]+)"', webpage, 'release pid')
-        return self.url_result(smuggle_url(
-            'http://link.theplatform.com/s/%s/%s?mbr=true&switch=progressive' % (account_pid, release_pid),
-            {'force_smil_url': True}), 'ThePlatform', release_pid)
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        settings = self._parse_json(self._search_regex(
+            r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);', webpage, 'drupal settings'),
+            display_id)
+        info = {}
+        query = {
+            'mbr': 'true',
+        }
+        account_pid, release_pid = [None] * 2
+        tve = settings.get('sharedTVE')
+        if tve:
+            query['manifest'] = 'm3u'
+            account_pid = 'HNK2IC'
+            release_pid = tve['release_pid']
+            if tve.get('entitlement') == 'auth':
+                adobe_pass = settings.get('adobePass', {})
+                resource = self._get_mvpd_resource(
+                    adobe_pass.get('adobePassResourceId', 'bravo'),
+                    tve['title'], release_pid, tve.get('rating'))
+                query['auth'] = self._extract_mvpd_auth(
+                    url, release_pid, adobe_pass.get('adobePassRequestorId', 'bravo'), resource)
+        else:
+            shared_playlist = settings['shared_playlist']
+            account_pid = shared_playlist['account_pid']
+            metadata = shared_playlist['video_metadata'][shared_playlist['default_clip']]
+            release_pid = metadata['release_pid']
+            info.update({
+                'title': metadata['title'],
+                'description': metadata.get('description'),
+                'season_number': int_or_none(metadata.get('season_num')),
+                'episode_number': int_or_none(metadata.get('episode_num')),
+            })
+            query['switch'] = 'progressive'
+        info.update({
+            '_type': 'url_transparent',
+            'id': release_pid,
+            'url': smuggle_url(update_url_query(
+                'http://link.theplatform.com/s/%s/%s' % (account_pid, release_pid),
+                query), {'force_smil_url': True}),
+            'ie_key': 'ThePlatform',
+        })
+        return info

youtube_dl/extractor/cartoonnetwork.py

@@ -0,0 +1,36 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .turner import TurnerBaseIE
+
+
+class CartoonNetworkIE(TurnerBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?cartoonnetwork\.com/video/(?:[^/]+/)+(?P<id>[^/?#]+)-(?:clip|episode)\.html'
+    _TEST = {
+        'url': 'http://www.cartoonnetwork.com/video/teen-titans-go/starfire-the-cat-lady-clip.html',
+        'info_dict': {
+            'id': '8a250ab04ed07e6c014ef3f1e2f9016c',
+            'ext': 'mp4',
+            'title': 'Starfire the Cat Lady',
+            'description': 'Robin decides to become a cat so that Starfire will finally love him.',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        id_type, video_id = re.search(r"_cnglobal\.cvp(Video|Title)Id\s*=\s*'([^']+)';", webpage).groups()
+        query = ('id' if id_type == 'Video' else 'titleId') + '=' + video_id
+        return self._extract_cvp_info(
+            'http://www.cartoonnetwork.com/video-seo-svc/episodeservices/getCvpPlaylist?networkName=CN2&' + query, video_id, {
+                'secure': {
+                    'media_src': 'http://apple-secure.cdn.turner.com/toon/big',
+                    'tokenizer_src': 'http://www.cartoonnetwork.com/cntv/mvpd/processors/services/token_ipadAdobe.do',
+                },
+            })

youtube_dl/extractor/cbc.py

@@ -9,10 +9,19 @@ from ..utils import (
     js_to_json,
     smuggle_url,
     try_get,
+    xpath_text,
+    xpath_element,
+    xpath_with_ns,
+    find_xpath_attr,
+    parse_iso8601,
+    parse_age_limit,
+    int_or_none,
+    ExtractorError,
 )
 
 
 class CBCIE(InfoExtractor):
+    IE_NAME = 'cbc.ca'
     _VALID_URL = r'https?://(?:www\.)?cbc\.ca/(?!player/)(?:[^/]+/)+(?P<id>[^/?#]+)'
     _TESTS = [{
         # with mediaId
@@ -114,6 +123,7 @@ class CBCIE(InfoExtractor):
 
 
 class CBCPlayerIE(InfoExtractor):
+    IE_NAME = 'cbc.ca:player'
     _VALID_URL = r'(?:cbcplayer:|https?://(?:www\.)?cbc\.ca/(?:player/play/|i/caffeine/syndicate/\?mediaId=))(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://www.cbc.ca/player/play/2683190193',
@@ -167,3 +177,165 @@ class CBCPlayerIE(InfoExtractor):
                 }),
             'id': video_id,
         }
+
+
+class CBCWatchBaseIE(InfoExtractor):
+    _device_id = None
+    _device_token = None
+    _API_BASE_URL = 'https://api-cbc.cloud.clearleap.com/cloffice/client/'
+    _NS_MAP = {
+        'media': 'http://search.yahoo.com/mrss/',
+        'clearleap': 'http://www.clearleap.com/namespace/clearleap/1.0/',
+    }
+
+    def _call_api(self, path, video_id):
+        url = path if path.startswith('http') else self._API_BASE_URL + path
+        result = self._download_xml(url, video_id, headers={
+            'X-Clearleap-DeviceId': self._device_id,
+            'X-Clearleap-DeviceToken': self._device_token,
+        })
+        error_message = xpath_text(result, 'userMessage') or xpath_text(result, 'systemMessage')
+        if error_message:
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message))
+        return result
+
+    def _real_initialize(self):
+        if not self._device_id or not self._device_token:
+            device = self._downloader.cache.load('cbcwatch', 'device') or {}
+            self._device_id, self._device_token = device.get('id'), device.get('token')
+            if not self._device_id or not self._device_token:
+                result = self._download_xml(
+                    self._API_BASE_URL + 'device/register',
+                    None, data=b'<device><type>web</type></device>')
+                self._device_id = xpath_text(result, 'deviceId', fatal=True)
+                self._device_token = xpath_text(result, 'deviceToken', fatal=True)
+                self._downloader.cache.store(
+                    'cbcwatch', 'device', {
+                        'id': self._device_id,
+                        'token': self._device_token,
+                    })
+
+    def _parse_rss_feed(self, rss):
+        channel = xpath_element(rss, 'channel', fatal=True)
+
+        def _add_ns(path):
+            return xpath_with_ns(path, self._NS_MAP)
+
+        entries = []
+        for item in channel.findall('item'):
+            guid = xpath_text(item, 'guid', fatal=True)
+            title = xpath_text(item, 'title', fatal=True)
+
+            media_group = xpath_element(item, _add_ns('media:group'), fatal=True)
+            content = xpath_element(media_group, _add_ns('media:content'), fatal=True)
+            content_url = content.attrib['url']
+
+            thumbnails = []
+            for thumbnail in media_group.findall(_add_ns('media:thumbnail')):
+                thumbnail_url = thumbnail.get('url')
+                if not thumbnail_url:
+                    continue
+                thumbnails.append({
+                    'id': thumbnail.get('profile'),
+                    'url': thumbnail_url,
+                    'width': int_or_none(thumbnail.get('width')),
+                    'height': int_or_none(thumbnail.get('height')),
+                })
+
+            timestamp = None
+            release_date = find_xpath_attr(
+                item, _add_ns('media:credit'), 'role', 'releaseDate')
+            if release_date is not None:
+                timestamp = parse_iso8601(release_date.text)
+
+            entries.append({
+                '_type': 'url_transparent',
+                'url': content_url,
+                'id': guid,
+                'title': title,
+                'description': xpath_text(item, 'description'),
+                'timestamp': timestamp,
+                'duration': int_or_none(content.get('duration')),
+                'age_limit': parse_age_limit(xpath_text(item, _add_ns('media:rating'))),
+                'episode': xpath_text(item, _add_ns('clearleap:episode')),
+                'episode_number': int_or_none(xpath_text(item, _add_ns('clearleap:episodeInSeason'))),
+                'series': xpath_text(item, _add_ns('clearleap:series')),
+                'season_number': int_or_none(xpath_text(item, _add_ns('clearleap:season'))),
+                'thumbnails': thumbnails,
+                'ie_key': 'CBCWatchVideo',
+            })
+
+        return self.playlist_result(
+            entries, xpath_text(channel, 'guid'),
+            xpath_text(channel, 'title'),
+            xpath_text(channel, 'description'))
+
+
+class CBCWatchVideoIE(CBCWatchBaseIE):
+    IE_NAME = 'cbc.ca:watch:video'
+    _VALID_URL = r'https?://api-cbc\.cloud\.clearleap\.com/cloffice/client/web/play/?\?.*?\bcontentId=(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        result = self._call_api(url, video_id)
+
+        m3u8_url = xpath_text(result, 'url', fatal=True)
+        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')
+        # Despite metadata in m3u8 all video+audio formats are
+        # actually video-only (no audio)
+        for f in formats:
+            if f.get('acodec') != 'none' and f.get('vcodec') != 'none':
+                f['acodec'] = 'none'
+        self._sort_formats(formats)
+
+        info = {
+            'id': video_id,
+            'title': video_id,
+            'formats': formats,
+        }
+
+        rss = xpath_element(result, 'rss')
+        if rss:
+            info.update(self._parse_rss_feed(rss)['entries'][0])
+            del info['url']
+            del info['_type']
+            del info['ie_key']
+        return info
+
+
+class CBCWatchIE(CBCWatchBaseIE):
+    IE_NAME = 'cbc.ca:watch'
+    _VALID_URL = r'https?://watch\.cbc\.ca/(?:[^/]+/)+(?P<id>[0-9a-f-]+)'
+    _TESTS = [{
+        'url': 'http://watch.cbc.ca/doc-zone/season-6/customer-disservice/38e815a-009e3ab12e4',
+        'info_dict': {
+            'id': '38e815a-009e3ab12e4',
+            'ext': 'mp4',
+            'title': 'Customer (Dis)Service',
+            'description': 'md5:8bdd6913a0fe03d4b2a17ebe169c7c87',
+            'upload_date': '20160219',
+            'timestamp': 1455840000,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+            'format': 'bestvideo',
+        },
+        'skip': 'Geo-restricted to Canada',
+    }, {
+        'url': 'http://watch.cbc.ca/arthur/all/1ed4b385-cd84-49cf-95f0-80f004680057',
+        'info_dict': {
+            'id': '1ed4b385-cd84-49cf-95f0-80f004680057',
+            'title': 'Arthur',
+            'description': 'Arthur, the sweetest 8-year-old aardvark, and his pals solve all kinds of problems with humour, kindness and teamwork.',
+        },
+        'playlist_mincount': 30,
+        'skip': 'Geo-restricted to Canada',
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        rss = self._call_api('web/browse/' + video_id, video_id)
+        return self._parse_rss_feed(rss)

youtube_dl/extractor/cbs.py

@@ -4,6 +4,7 @@ from .theplatform import ThePlatformFeedIE
 from ..utils import (
     int_or_none,
     find_xpath_attr,
+    ExtractorError,
 )
 
 
@@ -17,19 +18,6 @@ class CBSBaseIE(ThePlatformFeedIE):
             }]
         } if closed_caption_e is not None and closed_caption_e.attrib.get('value') else []
 
-    def _extract_video_info(self, filter_query, video_id):
-        return self._extract_feed_info(
-            'dJ5BDC', 'VxxJg8Ymh8sE', filter_query, video_id, lambda entry: {
-                'series': entry.get('cbs$SeriesTitle'),
-                'season_number': int_or_none(entry.get('cbs$SeasonNumber')),
-                'episode': entry.get('cbs$EpisodeTitle'),
-                'episode_number': int_or_none(entry.get('cbs$EpisodeNumber')),
-            }, {
-                'StreamPack': {
-                    'manifest': 'm3u',
-                }
-            })
-
 
 class CBSIE(CBSBaseIE):
     _VALID_URL = r'(?:cbs:|https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/video|colbertlateshow\.com/(?:video|podcasts))/)(?P<id>[\w-]+)'
@@ -38,7 +26,6 @@ class CBSIE(CBSBaseIE):
         'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
         'info_dict': {
             'id': '_u7W953k6la293J7EPTd9oHkSPs6Xn6_',
-            'display_id': 'connect-chat-feat-garth-brooks',
             'ext': 'mp4',
             'title': 'Connect Chat feat. Garth Brooks',
             'description': 'Connect with country music singer Garth Brooks, as he chats with fans on Wednesday November 27, 2013. Be sure to tune in to Garth Brooks: Live from Las Vegas, Friday November 29, at 9/8c on CBS!',
@@ -47,7 +34,10 @@ class CBSIE(CBSBaseIE):
             'upload_date': '20131127',
             'uploader': 'CBSI-NEW',
         },
-        'expected_warnings': ['Failed to download m3u8 information'],
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
         '_skip': 'Blocked outside the US',
     }, {
         'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/',
@@ -56,8 +46,31 @@ class CBSIE(CBSBaseIE):
         'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
         'only_matching': True,
     }]
-    TP_RELEASE_URL_TEMPLATE = 'http://link.theplatform.com/s/dJ5BDC/%s?mbr=true'
+
+    def _extract_video_info(self, guid):
+        path = 'dJ5BDC/media/guid/2198311517/' + guid
+        smil_url = 'http://link.theplatform.com/s/%s?mbr=true' % path
+        formats, subtitles = self._extract_theplatform_smil(smil_url + '&manifest=m3u', guid)
+        for r in ('OnceURL&formats=M3U', 'HLS&formats=M3U', 'RTMP', 'WIFI', '3G'):
+            try:
+                tp_formats, _ = self._extract_theplatform_smil(smil_url + '&assetTypes=' + r, guid, 'Downloading %s SMIL data' % r.split('&')[0])
+                formats.extend(tp_formats)
+            except ExtractorError:
+                continue
+        self._sort_formats(formats)
+        metadata = self._download_theplatform_metadata(path, guid)
+        info = self._parse_theplatform_metadata(metadata)
+        info.update({
+            'id': guid,
+            'formats': formats,
+            'subtitles': subtitles,
+            'series': metadata.get('cbs$SeriesTitle'),
+            'season_number': int_or_none(metadata.get('cbs$SeasonNumber')),
+            'episode': metadata.get('cbs$EpisodeTitle'),
+            'episode_number': int_or_none(metadata.get('cbs$EpisodeNumber')),
+        })
+        return info
 
     def _real_extract(self, url):
         content_id = self._match_id(url)
-        return self._extract_video_info('byGuid=%s' % content_id, content_id)
+        return self._extract_video_info(content_id)

youtube_dl/extractor/cbslocal.py

@@ -41,13 +41,8 @@ class CBSLocalIE(AnvatoIE):
         'url': 'http://cleveland.cbslocal.com/2016/05/16/indians-score-season-high-15-runs-in-blowout-win-over-reds-rapid-reaction/',
         'info_dict': {
             'id': 'GxfCe0Zo7D-175909-5588',
-            'ext': 'mp4',
-            'title': 'Recap: CLE 15, CIN 6',
-            'description': '5/16/16: Indians\' bats explode for 15 runs in a win',
-            'upload_date': '20160516',
-            'timestamp': 1463433840,
-            'duration': 49,
         },
+        'playlist_count': 9,
         'params': {
             # m3u8 download
             'skip_download': True,
@@ -60,12 +55,11 @@ class CBSLocalIE(AnvatoIE):
 
         sendtonews_url = SendtoNewsIE._extract_url(webpage)
         if sendtonews_url:
-            info_dict = {
-                '_type': 'url_transparent',
-                'url': compat_urlparse.urljoin(url, sendtonews_url),
-            }
-        else:
-            info_dict = self._extract_anvato_videos(webpage, display_id)
+            return self.url_result(
+                compat_urlparse.urljoin(url, sendtonews_url),
+                ie=SendtoNewsIE.ie_key())
+
+        info_dict = self._extract_anvato_videos(webpage, display_id)
 
         time_str = self._html_search_regex(
             r'class="entry-date">([^<]+)<', webpage, 'released date', fatal=False)

youtube_dl/extractor/cbsnews.py

@@ -2,13 +2,13 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from .cbs import CBSBaseIE
+from .cbs import CBSIE
 from ..utils import (
     parse_duration,
 )
 
 
-class CBSNewsIE(CBSBaseIE):
+class CBSNewsIE(CBSIE):
     IE_DESC = 'CBS News'
     _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P<id>[\da-z_-]+)'
 
@@ -35,7 +35,8 @@ class CBSNewsIE(CBSBaseIE):
                 'ext': 'mp4',
                 'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
                 'description': 'md5:4a6983e480542d8b333a947bfc64ddc7',
-                'upload_date': '19700101',
+                'upload_date': '20140404',
+                'timestamp': 1396650660,
                 'uploader': 'CBSI-NEW',
                 'thumbnail': 're:^https?://.*\.jpg$',
                 'duration': 205,
@@ -63,14 +64,15 @@ class CBSNewsIE(CBSBaseIE):
 
         item = video_info['item'] if 'item' in video_info else video_info
         guid = item['mpxRefId']
-        return self._extract_video_info('byGuid=%s' % guid, guid)
+        return self._extract_video_info(guid)
 
 
 class CBSNewsLiveVideoIE(InfoExtractor):
     IE_DESC = 'CBS News Live Videos'
     _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/video/(?P<id>[\da-z_-]+)'
 
-    _TESTS = [{
+    # Live videos get deleted soon. See http://www.cbsnews.com/live/ for the latest examples
+    _TEST = {
         'url': 'http://www.cbsnews.com/live/video/clinton-sanders-prepare-to-face-off-in-nh/',
         'info_dict': {
             'id': 'clinton-sanders-prepare-to-face-off-in-nh',
@@ -78,15 +80,8 @@ class CBSNewsLiveVideoIE(InfoExtractor):
             'title': 'Clinton, Sanders Prepare To Face Off In NH',
             'duration': 334,
         },
-        'skip': 'Video gone, redirected to http://www.cbsnews.com/live/',
-    }, {
-        'url': 'http://www.cbsnews.com/live/video/video-shows-intense-paragliding-accident/',
-        'info_dict': {
-            'id': 'video-shows-intense-paragliding-accident',
-            'ext': 'flv',
-            'title': 'Video Shows Intense Paragliding Accident',
-        },
-    }]
+        'skip': 'Video gone',
+    }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

youtube_dl/extractor/cbssports.py

@@ -23,6 +23,9 @@ class CBSSportsIE(CBSBaseIE):
         }
     }]
 
+    def _extract_video_info(self, filter_query, video_id):
+        return self._extract_feed_info('dJ5BDC', 'VxxJg8Ymh8sE', filter_query, video_id)
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
         return self._extract_video_info('byId=%s' % video_id, video_id)

youtube_dl/extractor/charlierose.py

@@ -0,0 +1,51 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import remove_end
+
+
+class CharlieRoseIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?charlierose\.com/video(?:s|/player)/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://charlierose.com/videos/27996',
+        'md5': 'fda41d49e67d4ce7c2411fd2c4702e09',
+        'info_dict': {
+            'id': '27996',
+            'ext': 'mp4',
+            'title': 'Remembering Zaha Hadid',
+            'thumbnail': 're:^https?://.*\.jpg\?\d+',
+            'description': 'We revisit past conversations with Zaha Hadid, in memory of the world renowned Iraqi architect.',
+            'subtitles': {
+                'en': [{
+                    'ext': 'vtt',
+                }],
+            },
+        },
+    }, {
+        'url': 'https://charlierose.com/videos/27996',
+        'only_matching': True,
+    }]
+
+    _PLAYER_BASE = 'https://charlierose.com/video/player/%s'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(self._PLAYER_BASE % video_id, video_id)
+
+        title = remove_end(self._og_search_title(webpage), ' - Charlie Rose')
+
+        info_dict = self._parse_html5_media_entries(
+            self._PLAYER_BASE % video_id, webpage, video_id,
+            m3u8_entry_protocol='m3u8_native')[0]
+
+        self._sort_formats(info_dict['formats'])
+        self._remove_duplicate_formats(info_dict['formats'])
+
+        info_dict.update({
+            'id': video_id,
+            'title': title,
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'description': self._og_search_description(webpage),
+        })
+
+        return info_dict

youtube_dl/extractor/chaturbate.py

@@ -17,7 +17,8 @@ class ChaturbateIE(InfoExtractor):
         },
         'params': {
             'skip_download': True,
-        }
+        },
+        'skip': 'Room is offline',
     }, {
         'url': 'https://en.chaturbate.com/siswet19/',
         'only_matching': True,

youtube_dl/extractor/chirbit.py

@@ -1,30 +1,33 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import base64
+
 from .common import InfoExtractor
-from ..utils import (
-    parse_duration,
-    int_or_none,
-)
+from ..utils import parse_duration
 
 
 class ChirbitIE(InfoExtractor):
     IE_NAME = 'chirbit'
     _VALID_URL = r'https?://(?:www\.)?chirb\.it/(?:(?:wp|pl)/|fb_chirbit_player\.swf\?key=)?(?P<id>[\da-zA-Z]+)'
     _TESTS = [{
-        'url': 'http://chirb.it/PrIPv5',
-        'md5': '9847b0dad6ac3e074568bf2cfb197de8',
+        'url': 'http://chirb.it/be2abG',
         'info_dict': {
-            'id': 'PrIPv5',
+            'id': 'be2abG',
             'ext': 'mp3',
-            'title': 'Фасадстрой',
-            'duration': 52,
-            'view_count': int,
-            'comment_count': int,
+            'title': 'md5:f542ea253f5255240be4da375c6a5d7e',
+            'description': 'md5:f24a4e22a71763e32da5fed59e47c770',
+            'duration': 306,
+        },
+        'params': {
+            'skip_download': True,
         }
     }, {
         'url': 'https://chirb.it/fb_chirbit_player.swf?key=PrIPv5',
         'only_matching': True,
+    }, {
+        'url': 'https://chirb.it/wp/MN58c2',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -33,27 +36,30 @@ class ChirbitIE(InfoExtractor):
         webpage = self._download_webpage(
             'http://chirb.it/%s' % audio_id, audio_id)
 
-        audio_url = self._search_regex(
-            r'"setFile"\s*,\s*"([^"]+)"', webpage, 'audio url')
+        data_fd = self._search_regex(
+            r'data-fd=(["\'])(?P<url>(?:(?!\1).)+)\1',
+            webpage, 'data fd', group='url')
+
+        # Reverse engineered from https://chirb.it/js/chirbit.player.js (look
+        # for soundURL)
+        audio_url = base64.b64decode(
+            data_fd[::-1].encode('ascii')).decode('utf-8')
 
         title = self._search_regex(
-            r'itemprop="name">([^<]+)', webpage, 'title')
-        duration = parse_duration(self._html_search_meta(
-            'duration', webpage, 'duration', fatal=False))
-        view_count = int_or_none(self._search_regex(
-            r'itemprop="playCount"\s*>(\d+)', webpage,
-            'listen count', fatal=False))
-        comment_count = int_or_none(self._search_regex(
-            r'>(\d+) Comments?:', webpage,
-            'comment count', fatal=False))
+            r'class=["\']chirbit-title["\'][^>]*>([^<]+)', webpage, 'title')
+        description = self._search_regex(
+            r'<h3>Description</h3>\s*<pre[^>]*>([^<]+)</pre>',
+            webpage, 'description', default=None)
+        duration = parse_duration(self._search_regex(
+            r'class=["\']c-length["\'][^>]*>([^<]+)',
+            webpage, 'duration', fatal=False))
 
         return {
             'id': audio_id,
             'url': audio_url,
             'title': title,
+            'description': description,
             'duration': duration,
-            'view_count': view_count,
-            'comment_count': comment_count,
         }
 
 

youtube_dl/extractor/cnn.py

@@ -3,15 +3,12 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-    parse_duration,
-    url_basename,
-)
+from .turner import TurnerBaseIE
+from ..utils import url_basename
 
 
-class CNNIE(InfoExtractor):
-    _VALID_URL = r'''(?x)https?://(?:(?:edition|www)\.)?cnn\.com/video/(?:data/.+?|\?)/
+class CNNIE(TurnerBaseIE):
+    _VALID_URL = r'''(?x)https?://(?:(?P<sub_domain>edition|www|money)\.)?cnn\.com/(?:video/(?:data/.+?|\?)/)?videos?/
         (?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:[a-z\-]+)|(?=&)))'''
 
     _TESTS = [{
@@ -25,6 +22,7 @@ class CNNIE(InfoExtractor):
             'duration': 135,
             'upload_date': '20130609',
         },
+        'expected_warnings': ['Failed to download m3u8 information'],
     }, {
         'url': 'http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29',
         'md5': 'b5cc60c60a3477d185af8f19a2a26f4e',
@@ -34,7 +32,8 @@ class CNNIE(InfoExtractor):
             'title': "Student's epic speech stuns new freshmen",
             'description': "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"",
             'upload_date': '20130821',
-        }
+        },
+        'expected_warnings': ['Failed to download m3u8 information'],
     }, {
         'url': 'http://www.cnn.com/video/data/2.0/video/living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln.html',
         'md5': 'f14d02ebd264df951feb2400e2c25a1b',
@@ -44,80 +43,61 @@ class CNNIE(InfoExtractor):
             'title': 'Nashville Ep. 1: Hand crafted skateboards',
             'description': 'md5:e7223a503315c9f150acac52e76de086',
             'upload_date': '20141222',
-        }
+        },
+        'expected_warnings': ['Failed to download m3u8 information'],
+    }, {
+        'url': 'http://money.cnn.com/video/news/2016/08/19/netflix-stunning-stats.cnnmoney/index.html',
+        'md5': '52a515dc1b0f001cd82e4ceda32be9d1',
+        'info_dict': {
+            'id': '/video/news/2016/08/19/netflix-stunning-stats.cnnmoney',
+            'ext': 'mp4',
+            'title': '5 stunning stats about Netflix',
+            'description': 'Did you know that Netflix has more than 80 million members? Here are five facts about the online video distributor that you probably didn\'t know.',
+            'upload_date': '20160819',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
     }, {
         'url': 'http://cnn.com/video/?/video/politics/2015/03/27/pkg-arizona-senator-church-attendance-mandatory.ktvk',
         'only_matching': True,
     }, {
         'url': 'http://cnn.com/video/?/video/us/2015/04/06/dnt-baker-refuses-anti-gay-order.wkmg',
         'only_matching': True,
+    }, {
+        'url': 'http://edition.cnn.com/videos/arts/2016/04/21/olympic-games-cultural-a-z-brazil.cnn',
+        'only_matching': True,
     }]
 
+    _CONFIG = {
+        # http://edition.cnn.com/.element/apps/cvp/3.0/cfg/spider/cnn/expansion/config.xml
+        'edition': {
+            'data_src': 'http://edition.cnn.com/video/data/3.0/video/%s/index.xml',
+            'media_src': 'http://pmd.cdn.turner.com/cnn/big',
+        },
+        # http://money.cnn.com/.element/apps/cvp2/cfg/config.xml
+        'money': {
+            'data_src': 'http://money.cnn.com/video/data/4.0/video/%s.xml',
+            'media_src': 'http://ht3.cdn.turner.com/money/big',
+        },
+    }
+
+    def _extract_timestamp(self, video_data):
+        # TODO: fix timestamp extraction
+        return None
+
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        path = mobj.group('path')
-        page_title = mobj.group('title')
-        info_url = 'http://edition.cnn.com/video/data/3.0/%s/index.xml' % path
-        info = self._download_xml(info_url, page_title)
-
-        formats = []
-        rex = re.compile(r'''(?x)
-            (?P<width>[0-9]+)x(?P<height>[0-9]+)
-            (?:_(?P<bitrate>[0-9]+)k)?
-        ''')
-        for f in info.findall('files/file'):
-            video_url = 'http://ht.cdn.turner.com/cnn/big%s' % (f.text.strip())
-            fdct = {
-                'format_id': f.attrib['bitrate'],
-                'url': video_url,
-            }
-
-            mf = rex.match(f.attrib['bitrate'])
-            if mf:
-                fdct['width'] = int(mf.group('width'))
-                fdct['height'] = int(mf.group('height'))
-                fdct['tbr'] = int_or_none(mf.group('bitrate'))
-            else:
-                mf = rex.search(f.text)
-                if mf:
-                    fdct['width'] = int(mf.group('width'))
-                    fdct['height'] = int(mf.group('height'))
-                    fdct['tbr'] = int_or_none(mf.group('bitrate'))
-                else:
-                    mi = re.match(r'ios_(audio|[0-9]+)$', f.attrib['bitrate'])
-                    if mi:
-                        if mi.group(1) == 'audio':
-                            fdct['vcodec'] = 'none'
-                            fdct['ext'] = 'm4a'
-                        else:
-                            fdct['tbr'] = int(mi.group(1))
-
-            formats.append(fdct)
-
-        self._sort_formats(formats)
-
-        thumbnails = [{
-            'height': int(t.attrib['height']),
-            'width': int(t.attrib['width']),
-            'url': t.text,
-        } for t in info.findall('images/image')]
-
-        metas_el = info.find('metas')
-        upload_date = (
-            metas_el.attrib.get('version') if metas_el is not None else None)
-
-        duration_el = info.find('length')
-        duration = parse_duration(duration_el.text)
-
-        return {
-            'id': info.attrib['id'],
-            'title': info.find('headline').text,
-            'formats': formats,
-            'thumbnails': thumbnails,
-            'description': info.find('description').text,
-            'duration': duration,
-            'upload_date': upload_date,
-        }
+        sub_domain, path, page_title = re.match(self._VALID_URL, url).groups()
+        if sub_domain not in ('money', 'edition'):
+            sub_domain = 'edition'
+        config = self._CONFIG[sub_domain]
+        return self._extract_cvp_info(
+            config['data_src'] % path, page_title, {
+                'default': {
+                    'media_src': config['media_src'],
+                }
+            })
 
 
 class CNNBlogsIE(InfoExtractor):
@@ -132,6 +112,7 @@ class CNNBlogsIE(InfoExtractor):
             'description': 'Glenn Greenwald responds to comments made this week on Capitol Hill that journalists could be criminal accessories.',
             'upload_date': '20140209',
         },
+        'expected_warnings': ['Failed to download m3u8 information'],
         'add_ie': ['CNN'],
     }
 
@@ -146,7 +127,7 @@ class CNNBlogsIE(InfoExtractor):
 
 
 class CNNArticleIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?:edition|www)\.)?cnn\.com/(?!video/)'
+    _VALID_URL = r'https?://(?:(?:edition|www)\.)?cnn\.com/(?!videos?/)'
     _TEST = {
         'url': 'http://www.cnn.com/2014/12/21/politics/obama-north-koreas-hack-not-war-but-cyber-vandalism/',
         'md5': '689034c2a3d9c6dc4aa72d65a81efd01',
@@ -154,9 +135,10 @@ class CNNArticleIE(InfoExtractor):
             'id': 'bestoftv/2014/12/21/ip-north-korea-obama.cnn',
             'ext': 'mp4',
             'title': 'Obama: Cyberattack not an act of war',
-            'description': 'md5:51ce6750450603795cad0cdfbd7d05c5',
+            'description': 'md5:0a802a40d2376f60e6b04c8d5bcebc4b',
             'upload_date': '20141221',
         },
+        'expected_warnings': ['Failed to download m3u8 information'],
         'add_ie': ['CNN'],
     }
 

youtube_dl/extractor/common.py

@@ -662,6 +662,24 @@ class InfoExtractor(object):
         else:
             return res
 
+    def _get_netrc_login_info(self, netrc_machine=None):
+        username = None
+        password = None
+        netrc_machine = netrc_machine or self._NETRC_MACHINE
+
+        if self._downloader.params.get('usenetrc', False):
+            try:
+                info = netrc.netrc().authenticators(netrc_machine)
+                if info is not None:
+                    username = info[0]
+                    password = info[2]
+                else:
+                    raise netrc.NetrcParseError('No authenticators for %s' % netrc_machine)
+            except (IOError, netrc.NetrcParseError) as err:
+                self._downloader.report_warning('parsing .netrc: %s' % error_to_compat_str(err))
+
+        return (username, password)
+
     def _get_login_info(self):
         """
         Get the login info as (username, password)
@@ -679,16 +697,8 @@ class InfoExtractor(object):
         if downloader_params.get('username') is not None:
             username = downloader_params['username']
             password = downloader_params['password']
-        elif downloader_params.get('usenetrc', False):
-            try:
-                info = netrc.netrc().authenticators(self._NETRC_MACHINE)
-                if info is not None:
-                    username = info[0]
-                    password = info[2]
-                else:
-                    raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
-            except (IOError, netrc.NetrcParseError) as err:
-                self._downloader.report_warning('parsing .netrc: %s' % error_to_compat_str(err))
+        else:
+            username, password = self._get_netrc_login_info()
 
         return (username, password)
 
@@ -816,11 +826,14 @@ class InfoExtractor(object):
         json_ld = self._search_regex(
             r'(?s)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>',
             html, 'JSON-LD', group='json_ld', **kwargs)
+        default = kwargs.get('default', NO_DEFAULT)
         if not json_ld:
-            return {}
-        return self._json_ld(
-            json_ld, video_id, fatal=kwargs.get('fatal', True),
-            expected_type=expected_type)
+            return default if default is not NO_DEFAULT else {}
+        # JSON-LD may be malformed and thus `fatal` should be respected.
+        # At the same time `default` may be passed that assumes `fatal=False`
+        # for _search_regex. Let's simulate the same behavior here as well.
+        fatal = kwargs.get('fatal', True) if default == NO_DEFAULT else False
+        return self._json_ld(json_ld, video_id, fatal=fatal, expected_type=expected_type)
 
     def _json_ld(self, json_ld, video_id, fatal=True, expected_type=None):
         if isinstance(json_ld, compat_str):
@@ -1188,27 +1201,44 @@ class InfoExtractor(object):
                 'protocol': entry_protocol,
                 'preference': preference,
             }]
-        last_info = None
-        last_media = None
+        last_info = {}
+        last_media = {}
         for line in m3u8_doc.splitlines():
             if line.startswith('#EXT-X-STREAM-INF:'):
                 last_info = parse_m3u8_attributes(line)
             elif line.startswith('#EXT-X-MEDIA:'):
-                last_media = parse_m3u8_attributes(line)
+                media = parse_m3u8_attributes(line)
+                media_type = media.get('TYPE')
+                if media_type in ('VIDEO', 'AUDIO'):
+                    media_url = media.get('URI')
+                    if media_url:
+                        format_id = []
+                        for v in (media.get('GROUP-ID'), media.get('NAME')):
+                            if v:
+                                format_id.append(v)
+                        formats.append({
+                            'format_id': '-'.join(format_id),
+                            'url': format_url(media_url),
+                            'language': media.get('LANGUAGE'),
+                            'vcodec': 'none' if media_type == 'AUDIO' else None,
+                            'ext': ext,
+                            'protocol': entry_protocol,
+                            'preference': preference,
+                        })
+                    else:
+                        # When there is no URI in EXT-X-MEDIA let this tag's
+                        # data be used by regular URI lines below
+                        last_media = media
             elif line.startswith('#') or not line.strip():
                 continue
             else:
-                if last_info is None:
-                    formats.append({'url': format_url(line)})
-                    continue
-                tbr = int_or_none(last_info.get('BANDWIDTH'), scale=1000)
+                tbr = int_or_none(last_info.get('AVERAGE-BANDWIDTH') or last_info.get('BANDWIDTH'), scale=1000)
                 format_id = []
                 if m3u8_id:
                     format_id.append(m3u8_id)
-                last_media_name = last_media.get('NAME') if last_media and last_media.get('TYPE') not in ('SUBTITLES', 'CLOSED-CAPTIONS') else None
                 # Despite specification does not mention NAME attribute for
                 # EXT-X-STREAM-INF it still sometimes may be present
-                stream_name = last_info.get('NAME') or last_media_name
+                stream_name = last_info.get('NAME') or last_media.get('NAME')
                 # Bandwidth of live streams may differ over time thus making
                 # format_id unpredictable. So it's better to keep provided
                 # format_id intact.
@@ -1239,11 +1269,9 @@ class InfoExtractor(object):
                         'abr': abr,
                     })
                 f.update(parse_codecs(last_info.get('CODECS')))
-                if last_media is not None:
-                    f['m3u8_media'] = last_media
-                    last_media = None
                 formats.append(f)
                 last_info = {}
+                last_media = {}
         return formats
 
     @staticmethod
@@ -1682,7 +1710,7 @@ class InfoExtractor(object):
                         self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type)
         return formats
 
-    def _parse_html5_media_entries(self, base_url, webpage):
+    def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8'):
         def absolute_url(video_url):
             return compat_urlparse.urljoin(base_url, video_url)
 
@@ -1697,6 +1725,21 @@ class InfoExtractor(object):
                 return f
             return {}
 
+        def _media_formats(src, cur_media_type):
+            full_url = absolute_url(src)
+            if determine_ext(full_url) == 'm3u8':
+                is_plain_url = False
+                formats = self._extract_m3u8_formats(
+                    full_url, video_id, ext='mp4',
+                    entry_protocol=m3u8_entry_protocol, m3u8_id=m3u8_id)
+            else:
+                is_plain_url = True
+                formats = [{
+                    'url': full_url,
+                    'vcodec': 'none' if cur_media_type == 'audio' else None,
+                }]
+            return is_plain_url, formats
+
         entries = []
         for media_tag, media_type, media_content in re.findall(r'(?s)(<(?P<tag>video|audio)[^>]*>)(.*?)</(?P=tag)>', webpage):
             media_info = {
@@ -1706,10 +1749,8 @@ class InfoExtractor(object):
             media_attributes = extract_attributes(media_tag)
             src = media_attributes.get('src')
             if src:
-                media_info['formats'].append({
-                    'url': absolute_url(src),
-                    'vcodec': 'none' if media_type == 'audio' else None,
-                })
+                _, formats = _media_formats(src)
+                media_info['formats'].extend(formats)
             media_info['thumbnail'] = media_attributes.get('poster')
             if media_content:
                 for source_tag in re.findall(r'<source[^>]+>', media_content):
@@ -1717,12 +1758,13 @@ class InfoExtractor(object):
                     src = source_attributes.get('src')
                     if not src:
                         continue
-                    f = parse_content_type(source_attributes.get('type'))
-                    f.update({
-                        'url': absolute_url(src),
-                        'vcodec': 'none' if media_type == 'audio' else None,
-                    })
-                    media_info['formats'].append(f)
+                    is_plain_url, formats = _media_formats(src, media_type)
+                    if is_plain_url:
+                        f = parse_content_type(source_attributes.get('type'))
+                        f.update(formats[0])
+                        media_info['formats'].append(f)
+                    else:
+                        media_info['formats'].extend(formats)
                 for track_tag in re.findall(r'<track[^>]+>', media_content):
                     track_attributes = extract_attributes(track_tag)
                     kind = track_attributes.get('kind')
@@ -1738,6 +1780,18 @@ class InfoExtractor(object):
                 entries.append(media_info)
         return entries
 
+    def _extract_akamai_formats(self, manifest_url, video_id):
+        formats = []
+        f4m_url = re.sub(r'(https?://.+?)/i/', r'\1/z/', manifest_url).replace('/master.m3u8', '/manifest.f4m')
+        formats.extend(self._extract_f4m_formats(
+            update_url_query(f4m_url, {'hdcore': '3.7.0'}),
+            video_id, f4m_id='hds', fatal=False))
+        m3u8_url = re.sub(r'(https?://.+?)/z/', r'\1/i/', manifest_url).replace('/manifest.f4m', '/master.m3u8')
+        formats.extend(self._extract_m3u8_formats(
+            m3u8_url, video_id, 'mp4', 'm3u8_native',
+            m3u8_id='hls', fatal=False))
+        return formats
+
     def _live_title(self, name):
         """ Generate the title for a live video """
         now = datetime.datetime.now()

youtube_dl/extractor/condenast.py

@@ -143,7 +143,8 @@ class CondeNastIE(InfoExtractor):
             })
         self._sort_formats(formats)
 
-        info = self._search_json_ld(webpage, video_id) if url_type != 'embed' else {}
+        info = self._search_json_ld(
+            webpage, video_id, fatal=False) if url_type != 'embed' else {}
         info.update({
             'id': video_id,
             'formats': formats,

youtube_dl/extractor/crackle.py

@@ -1,5 +1,5 @@
 # coding: utf-8
-from __future__ import unicode_literals
+from __future__ import unicode_literals, division
 
 from .common import InfoExtractor
 from ..utils import int_or_none
@@ -8,12 +8,22 @@ from ..utils import int_or_none
 class CrackleIE(InfoExtractor):
     _VALID_URL = r'(?:crackle:|https?://(?:www\.)?crackle\.com/(?:playlist/\d+/|(?:[^/]+/)+))(?P<id>\d+)'
     _TEST = {
-        'url': 'http://www.crackle.com/the-art-of-more/2496419',
+        'url': 'http://www.crackle.com/comedians-in-cars-getting-coffee/2498934',
         'info_dict': {
-            'id': '2496419',
+            'id': '2498934',
             'ext': 'mp4',
-            'title': 'Heavy Lies the Head',
-            'description': 'md5:bb56aa0708fe7b9a4861535f15c3abca',
+            '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',
+            'duration': 906,
+            'series': 'Comedians In Cars Getting Coffee',
+            'season_number': 8,
+            'episode_number': 4,
+            'subtitles': {
+                'en-US': [{
+                    'ext': 'ttml',
+                }]
+            },
         },
         'params': {
             # m3u8 download
@@ -21,12 +31,8 @@ class CrackleIE(InfoExtractor):
         }
     }
 
-    # extracted from http://legacyweb-us.crackle.com/flash/QueryReferrer.ashx
-    _SUBTITLE_SERVER = 'http://web-us-az.crackle.com'
-    _UPLYNK_OWNER_ID = 'e8773f7770a44dbd886eee4fca16a66b'
-    _THUMBNAIL_TEMPLATE = 'http://images-us-am.crackle.com/%stnl_1920x1080.jpg?ts=20140107233116?c=635333335057637614'
-
     # 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,
@@ -48,16 +54,21 @@ class CrackleIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
+
+        config_doc = self._download_xml(
+            'http://legacyweb-us.crackle.com/flash/QueryReferrer.ashx?site=16',
+            video_id, 'Downloading config')
+
         item = self._download_xml(
             'http://legacyweb-us.crackle.com/app/revamp/vidwallcache.aspx?flags=-1&fm=%s' % video_id,
             video_id).find('i')
         title = item.attrib['t']
 
-        thumbnail = None
         subtitles = {}
         formats = self._extract_m3u8_formats(
-            'http://content.uplynk.com/ext/%s/%s.m3u8' % (self._UPLYNK_OWNER_ID, video_id),
+            'http://content.uplynk.com/ext/%s/%s.m3u8' % (config_doc.attrib['strUplynkOwnerId'], video_id),
             video_id, 'mp4', m3u8_id='hls', fatal=None)
+        thumbnail = None
         path = item.attrib.get('p')
         if path:
             thumbnail = self._THUMBNAIL_TEMPLATE % path
@@ -76,7 +87,7 @@ class CrackleIE(InfoExtractor):
                     if locale not in subtitles:
                         subtitles[locale] = []
                     subtitles[locale] = [{
-                        'url': '%s/%s%s_%s.xml' % (self._SUBTITLE_SERVER, path, locale, v),
+                        'url': '%s/%s%s_%s.xml' % (config_doc.attrib['strSubtitleServer'], path, locale, v),
                         'ext': 'ttml',
                     }]
         self._sort_formats(formats, ('width', 'height', 'tbr', 'format_id'))
@@ -85,7 +96,7 @@ class CrackleIE(InfoExtractor):
             'id': video_id,
             'title': title,
             'description': item.attrib.get('d'),
-            'duration': int(item.attrib.get('r'), 16) if item.attrib.get('r') else None,
+            'duration': int(item.attrib.get('r'), 16) / 1000 if item.attrib.get('r') else None,
             'series': item.attrib.get('sn'),
             'season_number': int_or_none(item.attrib.get('se')),
             'episode_number': int_or_none(item.attrib.get('ep')),

youtube_dl/extractor/crunchyroll.py

@@ -114,6 +114,21 @@ class CrunchyrollIE(CrunchyrollBaseIE):
             # rtmp
             'skip_download': True,
         },
+    }, {
+        'url': 'http://www.crunchyroll.com/rezero-starting-life-in-another-world-/episode-5-the-morning-of-our-promise-is-still-distant-702409',
+        'info_dict': {
+            'id': '702409',
+            '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$',
+            'uploader': 'TV TOKYO',
+            'upload_date': '20160508',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
     }, {
         'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
         'only_matching': True,
@@ -336,9 +351,18 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             if video_encode_id in video_encode_ids:
                 continue
             video_encode_ids.append(video_encode_id)
+
+            video_file = xpath_text(stream_info, './file')
+            if not video_file:
+                continue
+            if video_file.startswith('http'):
+                formats.extend(self._extract_m3u8_formats(
+                    video_file, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False))
+                continue
+
             video_url = xpath_text(stream_info, './host')
-            video_play_path = xpath_text(stream_info, './file')
-            if not video_url or not video_play_path:
+            if not video_url:
                 continue
             metadata = stream_info.find('./metadata')
             format_info = {
@@ -353,7 +377,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
                 parsed_video_url = compat_urlparse.urlparse(video_url)
                 direct_video_url = compat_urlparse.urlunparse(parsed_video_url._replace(
                     netloc='v.lvlt.crcdn.net',
-                    path='%s/%s' % (remove_end(parsed_video_url.path, '/'), video_play_path.split(':')[-1])))
+                    path='%s/%s' % (remove_end(parsed_video_url.path, '/'), video_file.split(':')[-1])))
                 if self._is_valid_url(direct_video_url, video_id, video_format):
                     format_info.update({
                         'url': direct_video_url,
@@ -363,7 +387,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
 
             format_info.update({
                 'url': video_url,
-                'play_path': video_play_path,
+                'play_path': video_file,
                 'ext': 'flv',
             })
             formats.append(format_info)

youtube_dl/extractor/ctsnews.py

@@ -1,13 +1,12 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import parse_iso8601, ExtractorError
+from ..utils import unified_timestamp
 
 
 class CtsNewsIE(InfoExtractor):
     IE_DESC = '華視新聞'
-    # https connection failed (Connection reset)
     _VALID_URL = r'https?://news\.cts\.com\.tw/[a-z]+/[a-z]+/\d+/(?P<id>\d+)\.html'
     _TESTS = [{
         'url': 'http://news.cts.com.tw/cts/international/201501/201501291578109.html',
@@ -16,7 +15,7 @@ class CtsNewsIE(InfoExtractor):
             'id': '201501291578109',
             'ext': 'mp4',
             'title': '以色列.真主黨交火 3人死亡',
-            'description': 'md5:95e9b295c898b7ff294f09d450178d7d',
+            'description': '以色列和黎巴嫩真主黨，爆發五年最嚴重衝突，雙方砲轟交火，兩名以軍死亡，還有一名西班牙籍的聯合國維和人...',
             'timestamp': 1422528540,
             'upload_date': '20150129',
         }
@@ -28,7 +27,7 @@ class CtsNewsIE(InfoExtractor):
             'id': '201309031304098',
             'ext': 'mp4',
             'title': '韓國31歲童顏男 貌如十多歲小孩',
-            'description': 'md5:f183feeba3752b683827aab71adad584',
+            '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$',
             'timestamp': 1378205880,
             'upload_date': '20130903',
@@ -36,8 +35,7 @@ class CtsNewsIE(InfoExtractor):
     }, {
         # With Youtube embedded video
         'url': 'http://news.cts.com.tw/cts/money/201501/201501291578003.html',
-        'md5': '1d842c771dc94c8c3bca5af2cc1db9c5',
-        'add_ie': ['Youtube'],
+        'md5': 'e4726b2ccd70ba2c319865e28f0a91d1',
         'info_dict': {
             'id': 'OVbfO7d0_hQ',
             'ext': 'mp4',
@@ -47,42 +45,37 @@ class CtsNewsIE(InfoExtractor):
             'upload_date': '20150128',
             'uploader_id': 'TBSCTS',
             'uploader': '中華電視公司',
-        }
+        },
+        'add_ie': ['Youtube'],
     }]
 
     def _real_extract(self, url):
         news_id = self._match_id(url)
         page = self._download_webpage(url, news_id)
 
-        if self._search_regex(r'(CTSPlayer2)', page, 'CTSPlayer2 identifier', default=None):
-            feed_url = self._html_search_regex(
-                r'(http://news\.cts\.com\.tw/action/mp4feed\.php\?news_id=\d+)',
-                page, 'feed url')
-            video_url = self._download_webpage(
-                feed_url, news_id, note='Fetching feed')
+        news_id = self._hidden_inputs(page).get('get_id')
+
+        if news_id:
+            mp4_feed = self._download_json(
+                'http://news.cts.com.tw/action/test_mp4feed.php',
+                news_id, note='Fetching feed', query={'news_id': news_id})
+            video_url = mp4_feed['source_url']
         else:
             self.to_screen('Not CTSPlayer video, trying Youtube...')
             youtube_url = self._search_regex(
-                r'src="(//www\.youtube\.com/embed/[^"]+)"', page, 'youtube url',
-                default=None)
-            if not youtube_url:
-                raise ExtractorError('The news includes no videos!', expected=True)
+                r'src="(//www\.youtube\.com/embed/[^"]+)"', page, 'youtube url')
 
-            return {
-                '_type': 'url',
-                'url': youtube_url,
-                'ie_key': 'Youtube',
-            }
+            return self.url_result(youtube_url, ie='Youtube')
 
         description = self._html_search_meta('description', page)
-        title = self._html_search_meta('title', page)
+        title = self._html_search_meta('title', page, fatal=True)
         thumbnail = self._html_search_meta('image', page)
 
         datetime_str = self._html_search_regex(
-            r'(\d{4}/\d{2}/\d{2} \d{2}:\d{2})', page, 'date and time')
-        # Transform into ISO 8601 format with timezone info
-        datetime_str = datetime_str.replace('/', '-') + ':00+0800'
-        timestamp = parse_iso8601(datetime_str, delimiter=' ')
+            r'(\d{4}/\d{2}/\d{2} \d{2}:\d{2})', page, 'date and time', fatal=False)
+        timestamp = None
+        if datetime_str:
+            timestamp = unified_timestamp(datetime_str) - 8 * 3600
 
         return {
             'id': news_id,

youtube_dl/extractor/ctv.py

@@ -1,11 +1,13 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 
 
 class CTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?ctv\.ca/video/player\?vid=(?P<id>[0-9.]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?P<domain>ctv|tsn|bnn|thecomedynetwork)\.ca/.*?(?:\bvid=|-vid|~|%7E)(?P<id>[0-9.]+)'
     _TESTS = [{
         'url': 'http://www.ctv.ca/video/player?vid=706966',
         'md5': 'ff2ebbeae0aa2dcc32a830c3fd69b7b0',
@@ -18,13 +20,27 @@ class CTVIE(InfoExtractor):
             'timestamp': 1442624700,
         },
         'expected_warnings': ['HTTP Error 404'],
+    }, {
+        'url': 'http://www.thecomedynetwork.ca/video/player?vid=923582',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.tsn.ca/video/expectations-high-for-milos-raonic-at-us-open~939549',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.bnn.ca/video/berman-s-call-part-two-viewer-questions~939654',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.ctv.ca/YourMorning/Video/S1E6-Monday-August-29-2016-vid938009',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        domain, video_id = re.match(self._VALID_URL, url).groups()
+        if domain == 'thecomedynetwork':
+            domain = 'comedy'
         return {
             '_type': 'url_transparent',
             'id': video_id,
-            'url': '9c9media:ctv_web:%s' % video_id,
+            'url': '9c9media:%s_web:%s' % (domain, video_id),
             'ie_key': 'NineCNineMedia',
         }

youtube_dl/extractor/cultureunplugged.py

@@ -1,9 +1,13 @@
 from __future__ import unicode_literals
 
 import re
+import time
 
 from .common import InfoExtractor
-from ..utils import int_or_none
+from ..utils import (
+    int_or_none,
+    HEADRequest,
+)
 
 
 class CultureUnpluggedIE(InfoExtractor):
@@ -32,6 +36,9 @@ class CultureUnpluggedIE(InfoExtractor):
         video_id = mobj.group('id')
         display_id = mobj.group('display_id') or video_id
 
+        # request setClientTimezone.php to get PHPSESSID cookie which is need to get valid json data in the next request
+        self._request_webpage(HEADRequest(
+            'http://www.cultureunplugged.com/setClientTimezone.php?timeOffset=%d' % -(time.timezone / 3600)), display_id)
         movie_data = self._download_json(
             'http://www.cultureunplugged.com/movie-data/cu-%s.json' % video_id, display_id)
 

youtube_dl/extractor/curiositystream.py

@@ -0,0 +1,120 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    urlencode_postdata,
+    compat_str,
+    ExtractorError,
+)
+
+
+class CuriosityStreamBaseIE(InfoExtractor):
+    _NETRC_MACHINE = 'curiositystream'
+    _auth_token = None
+    _API_BASE_URL = 'https://api.curiositystream.com/v1/'
+
+    def _handle_errors(self, result):
+        error = result.get('error', {}).get('message')
+        if error:
+            if isinstance(error, dict):
+                error = ', '.join(error.values())
+            raise ExtractorError(
+                '%s said: %s' % (self.IE_NAME, error), expected=True)
+
+    def _call_api(self, path, video_id):
+        headers = {}
+        if self._auth_token:
+            headers['X-Auth-Token'] = self._auth_token
+        result = self._download_json(
+            self._API_BASE_URL + path, video_id, headers=headers)
+        self._handle_errors(result)
+        return result['data']
+
+    def _real_initialize(self):
+        (email, password) = self._get_login_info()
+        if email is None:
+            return
+        result = self._download_json(
+            self._API_BASE_URL + 'login', None, data=urlencode_postdata({
+                'email': email,
+                'password': password,
+            }))
+        self._handle_errors(result)
+        self._auth_token = result['message']['auth_token']
+
+    def _extract_media_info(self, media):
+        video_id = compat_str(media['id'])
+        limelight_media_id = media['limelight_media_id']
+        title = media['title']
+
+        subtitles = {}
+        for closed_caption in media.get('closed_captions', []):
+            sub_url = closed_caption.get('file')
+            if not sub_url:
+                continue
+            lang = closed_caption.get('code') or closed_caption.get('language') or 'en'
+            subtitles.setdefault(lang, []).append({
+                'url': sub_url,
+            })
+
+        return {
+            '_type': 'url_transparent',
+            'id': video_id,
+            'url': 'limelight:media:' + limelight_media_id,
+            'title': title,
+            'description': media.get('description'),
+            'thumbnail': media.get('image_large') or media.get('image_medium') or media.get('image_small'),
+            'duration': int_or_none(media.get('duration')),
+            'tags': media.get('tags'),
+            'subtitles': subtitles,
+            'ie_key': 'LimelightMedia',
+        }
+
+
+class CuriosityStreamIE(CuriosityStreamBaseIE):
+    IE_NAME = 'curiositystream'
+    _VALID_URL = r'https?://app\.curiositystream\.com/video/(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://app.curiositystream.com/video/2',
+        'md5': 'a0074c190e6cddaf86900b28d3e9ee7a',
+        'info_dict': {
+            'id': '2',
+            'ext': 'mp4',
+            'title': 'How Did You Develop The Internet?',
+            'description': 'Vint Cerf, Google\'s Chief Internet Evangelist, describes how he and Bob Kahn created the internet.',
+            'timestamp': 1448388615,
+            'upload_date': '20151124',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        media = self._call_api('media/' + video_id, video_id)
+        return self._extract_media_info(media)
+
+
+class CuriosityStreamCollectionIE(CuriosityStreamBaseIE):
+    IE_NAME = 'curiositystream:collection'
+    _VALID_URL = r'https?://app\.curiositystream\.com/collection/(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://app.curiositystream.com/collection/2',
+        'info_dict': {
+            'id': '2',
+            'title': 'Curious Minds: The Internet',
+            'description': 'How is the internet shaping our lives in the 21st Century?',
+        },
+        'playlist_mincount': 17,
+    }
+
+    def _real_extract(self, url):
+        collection_id = self._match_id(url)
+        collection = self._call_api(
+            'collections/' + collection_id, collection_id)
+        entries = []
+        for media in collection.get('media', []):
+            entries.append(self._extract_media_info(media))
+        return self.playlist_result(
+            entries, collection_id,
+            collection.get('title'), collection.get('description'))

youtube_dl/extractor/cwtv.py

@@ -28,7 +28,8 @@ class CWTVIE(InfoExtractor):
         'params': {
             # m3u8 download
             'skip_download': True,
-        }
+        },
+        'skip': 'redirect to http://cwtv.com/shows/arrow/',
     }, {
         'url': 'http://www.cwseed.com/shows/whose-line-is-it-anyway/jeff-davis-4/?play=24282b12-ead2-42f2-95ad-26770c2c6088',
         'info_dict': {
@@ -44,10 +45,6 @@ class CWTVIE(InfoExtractor):
             'upload_date': '20151006',
             'timestamp': 1444107300,
         },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        }
     }, {
         'url': 'http://cwtv.com/thecw/chroniclesofcisco/?play=8adebe35-f447-465f-ab52-e863506ff6d6',
         'only_matching': True,
@@ -61,11 +58,30 @@ class CWTVIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        video_data = self._download_json(
-            'http://metaframe.digitalsmiths.tv/v2/CWtv/assets/%s/partner/132?format=json' % video_id, video_id)
-
-        formats = self._extract_m3u8_formats(
-            video_data['videos']['variantplaylist']['uri'], video_id, 'mp4')
+        video_data = None
+        formats = []
+        for partner in (154, 213):
+            vdata = self._download_json(
+                'http://metaframe.digitalsmiths.tv/v2/CWtv/assets/%s/partner/%d?format=json' % (video_id, partner), video_id, fatal=False)
+            if not vdata:
+                continue
+            video_data = vdata
+            for quality, quality_data in vdata.get('videos', {}).items():
+                quality_url = quality_data.get('uri')
+                if not quality_url:
+                    continue
+                if quality == 'variantplaylist':
+                    formats.extend(self._extract_m3u8_formats(
+                        quality_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
+                else:
+                    tbr = int_or_none(quality_data.get('bitrate'))
+                    format_id = 'http' + ('-%d' % tbr if tbr else '')
+                    if self._is_valid_url(quality_url, video_id, format_id):
+                        formats.append({
+                            'format_id': format_id,
+                            'url': quality_url,
+                            'tbr': tbr,
+                        })
         self._sort_formats(formats)
 
         thumbnails = [{

youtube_dl/extractor/dbtv.py

@@ -38,6 +38,12 @@ class DBTVIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    @staticmethod
+    def _extract_urls(webpage):
+        return [url for _, url in re.findall(
+            r'<iframe[^>]+src=(["\'])((?:https?:)?//(?:www\.)?dbtv\.no/(?:lazy)?player/\d+.*?)\1',
+            webpage)]
+
     def _real_extract(self, url):
         video_id, display_id = re.match(self._VALID_URL, url).groups()
 

youtube_dl/extractor/discoverygo.py

@@ -7,11 +7,22 @@ from ..utils import (
     int_or_none,
     parse_age_limit,
     unescapeHTML,
+    ExtractorError,
 )
 
 
 class DiscoveryGoIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?discoverygo\.com/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _VALID_URL = r'''(?x)https?://(?:www\.)?(?:
+            discovery|
+            investigationdiscovery|
+            discoverylife|
+            animalplanet|
+            ahctv|
+            destinationamerica|
+            sciencechannel|
+            tlc|
+            velocitychannel
+        )go\.com/(?:[^/]+/)*(?P<id>[^/?#&]+)'''
     _TEST = {
         'url': 'https://www.discoverygo.com/love-at-first-kiss/kiss-first-ask-questions-later/',
         'info_dict': {
@@ -43,7 +54,14 @@ class DiscoveryGoIE(InfoExtractor):
 
         title = video['name']
 
-        stream = video['stream']
+        stream = video.get('stream')
+        if not stream:
+            if video.get('authenticated') is True:
+                raise ExtractorError(
+                    'This video is only available via cable service provider subscription that'
+                    ' is not currently supported. You may want to use --cookies.', expected=True)
+            else:
+                raise ExtractorError('Unable to find stream')
         STREAM_URL_SUFFIX = 'streamUrl'
         formats = []
         for stream_kind in ('', 'hds'):

youtube_dl/extractor/dotsub.py

@@ -10,18 +10,18 @@ from ..utils import (
 class DotsubIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?dotsub\.com/view/(?P<id>[^/]+)'
     _TEST = {
-        'url': 'http://dotsub.com/view/aed3b8b2-1889-4df5-ae63-ad85f5572f27',
-        'md5': '0914d4d69605090f623b7ac329fea66e',
+        'url': 'https://dotsub.com/view/9c63db2a-fa95-4838-8e6e-13deafe47f09',
+        'md5': '21c7ff600f545358134fea762a6d42b6',
         'info_dict': {
-            'id': 'aed3b8b2-1889-4df5-ae63-ad85f5572f27',
+            'id': '9c63db2a-fa95-4838-8e6e-13deafe47f09',
             'ext': 'flv',
-            'title': 'Pyramids of Waste (2010), AKA The Lightbulb Conspiracy - Planned obsolescence documentary',
-            'description': 'md5:699a0f7f50aeec6042cb3b1db2d0d074',
-            'thumbnail': 're:^https?://dotsub.com/media/aed3b8b2-1889-4df5-ae63-ad85f5572f27/p',
-            'duration': 3169,
-            'uploader': '4v4l0n42',
-            'timestamp': 1292248482.625,
-            'upload_date': '20101213',
+            'title': 'MOTIVATION - "It\'s Possible" Best Inspirational Video Ever',
+            'description': 'md5:41af1e273edbbdfe4e216a78b9d34ac6',
+            'thumbnail': 're:^https?://dotsub.com/media/9c63db2a-fa95-4838-8e6e-13deafe47f09/p',
+            'duration': 198,
+            'uploader': 'liuxt',
+            'timestamp': 1385778501.104,
+            'upload_date': '20131130',
             'view_count': int,
         }
     }

youtube_dl/extractor/douyutv.py

@@ -3,9 +3,17 @@ from __future__ import unicode_literals
 
 import hashlib
 import time
+import uuid
+
 from .common import InfoExtractor
-from ..utils import (ExtractorError, unescapeHTML)
-from ..compat import (compat_str, compat_basestring)
+from ..compat import (
+    compat_str,
+    compat_urllib_parse_urlencode,
+)
+from ..utils import (
+    ExtractorError,
+    unescapeHTML,
+)
 
 
 class DouyuTVIE(InfoExtractor):
@@ -21,7 +29,6 @@ class DouyuTVIE(InfoExtractor):
             'description': 're:.*m7show@163\.com.*',
             'thumbnail': 're:^https?://.*\.jpg$',
             'uploader': '7师傅',
-            'uploader_id': '431925',
             'is_live': True,
         },
         'params': {
@@ -37,7 +44,6 @@ class DouyuTVIE(InfoExtractor):
             'description': 'md5:746a2f7a253966a06755a912f0acc0d2',
             'thumbnail': 're:^https?://.*\.jpg$',
             'uploader': 'douyu小漠',
-            'uploader_id': '3769985',
             'is_live': True,
         },
         'params': {
@@ -54,7 +60,6 @@ class DouyuTVIE(InfoExtractor):
             'description': 're:.*m7show@163\.com.*',
             'thumbnail': 're:^https?://.*\.jpg$',
             'uploader': '7师傅',
-            'uploader_id': '431925',
             'is_live': True,
         },
         'params': {
@@ -65,6 +70,10 @@ class DouyuTVIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    # Decompile core.swf in webpage by ffdec "Search SWFs in memory". core.swf
+    # is encrypted originally, but ffdec can dump memory to get the decrypted one.
+    _API_KEY = 'A12Svb&%1UUmf@hC'
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
@@ -75,74 +84,56 @@ class DouyuTVIE(InfoExtractor):
             room_id = self._html_search_regex(
                 r'"room_id"\s*:\s*(\d+),', page, 'room id')
 
-        config = None
-        # Douyu API sometimes returns error "Unable to load the requested class: eticket_redis_cache"
-        # Retry with different parameters - same parameters cause same errors
-        for i in range(5):
-            prefix = 'room/%s?aid=android&client_sys=android&time=%d' % (
-                room_id, int(time.time()))
-            auth = hashlib.md5((prefix + '1231').encode('ascii')).hexdigest()
+        room = self._download_json(
+            'http://m.douyu.com/html5/live?roomId=%s' % room_id, video_id,
+            note='Downloading room info')['data']
 
-            config_page = self._download_webpage(
-                'http://www.douyutv.com/api/v1/%s&auth=%s' % (prefix, auth),
-                video_id)
-            try:
-                config = self._parse_json(config_page, video_id, fatal=False)
-            except ExtractorError:
-                # Wait some time before retrying to get a different time() value
-                self._sleep(1, video_id, msg_template='%(video_id)s: Error occurs. '
-                                                      'Waiting for %(timeout)s seconds before retrying')
-                continue
-            else:
-                break
-        if config is None:
-            raise ExtractorError('Unable to fetch API result')
-
-        data = config['data']
-
-        error_code = config.get('error', 0)
-        if error_code is not 0:
-            error_desc = 'Server reported error %i' % error_code
-            if isinstance(data, (compat_str, compat_basestring)):
-                error_desc += ': ' + data
-            raise ExtractorError(error_desc, expected=True)
-
-        show_status = data.get('show_status')
         # 1 = live, 2 = offline
-        if show_status == '2':
+        if room.get('show_status') == '2':
+            raise ExtractorError('Live stream is offline', expected=True)
+
+        tt = compat_str(int(time.time() / 60))
+        did = uuid.uuid4().hex.upper()
+
+        sign_content = ''.join((room_id, did, self._API_KEY, tt))
+        sign = hashlib.md5((sign_content).encode('utf-8')).hexdigest()
+
+        flv_data = compat_urllib_parse_urlencode({
+            'cdn': 'ws',
+            'rate': '0',
+            'tt': tt,
+            'did': did,
+            'sign': sign,
+        })
+
+        video_info = self._download_json(
+            'http://www.douyu.com/lapi/live/getPlay/%s' % room_id, video_id,
+            data=flv_data, note='Downloading video info',
+            headers={'Content-Type': 'application/x-www-form-urlencoded'})
+
+        error_code = video_info.get('error', 0)
+        if error_code is not 0:
             raise ExtractorError(
-                'Live stream is offline', expected=True)
+                '%s reported error %i' % (self.IE_NAME, error_code),
+                expected=True)
 
-        base_url = data['rtmp_url']
-        live_path = data['rtmp_live']
+        base_url = video_info['data']['rtmp_url']
+        live_path = video_info['data']['rtmp_live']
 
-        title = self._live_title(unescapeHTML(data['room_name']))
-        description = data.get('show_details')
-        thumbnail = data.get('room_src')
+        video_url = '%s/%s' % (base_url, live_path)
 
-        uploader = data.get('nickname')
-        uploader_id = data.get('owner_uid')
-
-        multi_formats = data.get('rtmp_multi_bitrate')
-        if not isinstance(multi_formats, dict):
-            multi_formats = {}
-        multi_formats['live'] = live_path
-
-        formats = [{
-            'url': '%s/%s' % (base_url, format_path),
-            'format_id': format_id,
-            'preference': 1 if format_id == 'live' else 0,
-        } for format_id, format_path in multi_formats.items()]
-        self._sort_formats(formats)
+        title = self._live_title(unescapeHTML(room['room_name']))
+        description = room.get('notice')
+        thumbnail = room.get('room_src')
+        uploader = room.get('nickname')
 
         return {
             'id': room_id,
             'display_id': video_id,
+            'url': video_url,
             'title': title,
             'description': description,
             'thumbnail': thumbnail,
             'uploader': uploader,
-            'uploader_id': uploader_id,
-            'formats': formats,
             'is_live': True,
         }

youtube_dl/extractor/drtuber.py

@@ -3,7 +3,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import str_to_int
+from ..utils import (
+    NO_DEFAULT,
+    str_to_int,
+)
 
 
 class DrTuberIE(InfoExtractor):
@@ -17,7 +20,6 @@ class DrTuberIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'hot perky blonde naked golf',
             'like_count': int,
-            'dislike_count': int,
             'comment_count': int,
             'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
             'thumbnail': 're:https?://.*\.jpg$',
@@ -36,25 +38,29 @@ class DrTuberIE(InfoExtractor):
             r'<source src="([^"]+)"', webpage, 'video URL')
 
         title = self._html_search_regex(
-            [r'<p[^>]+class="title_substrate">([^<]+)</p>', r'<title>([^<]+) - \d+'],
+            (r'class="title_watch"[^>]*><p>([^<]+)<',
+             r'<p[^>]+class="title_substrate">([^<]+)</p>',
+             r'<title>([^<]+) - \d+'),
             webpage, 'title')
 
         thumbnail = self._html_search_regex(
             r'poster="([^"]+)"',
             webpage, 'thumbnail', fatal=False)
 
-        def extract_count(id_, name):
+        def extract_count(id_, name, default=NO_DEFAULT):
             return str_to_int(self._html_search_regex(
                 r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_,
-                webpage, '%s count' % name, fatal=False))
+                webpage, '%s count' % name, default=default, fatal=False))
 
         like_count = extract_count('rate_likes', 'like')
-        dislike_count = extract_count('rate_dislikes', 'dislike')
+        dislike_count = extract_count('rate_dislikes', 'dislike', default=None)
         comment_count = extract_count('comments_count', 'comment')
 
         cats_str = self._search_regex(
-            r'<div[^>]+class="categories_list">(.+?)</div>', webpage, 'categories', fatal=False)
-        categories = [] if not cats_str else re.findall(r'<a title="([^"]+)"', cats_str)
+            r'<div[^>]+class="categories_list">(.+?)</div>',
+            webpage, 'categories', fatal=False)
+        categories = [] if not cats_str else re.findall(
+            r'<a title="([^"]+)"', cats_str)
 
         return {
             'id': video_id,

youtube_dl/extractor/drtv.py

@@ -4,26 +4,45 @@ from __future__ import unicode_literals
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
+    int_or_none,
+    float_or_none,
+    mimetype2ext,
     parse_iso8601,
+    remove_end,
 )
 
 
 class DRTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
+    _VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv/se|nyheder)/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
 
-    _TEST = {
-        'url': 'https://www.dr.dk/tv/se/boern/ultra/panisk-paske/panisk-paske-5',
-        'md5': 'dc515a9ab50577fa14cc4e4b0265168f',
+    _TESTS = [{
+        'url': 'https://www.dr.dk/tv/se/boern/ultra/klassen-ultra/klassen-darlig-taber-10',
+        'md5': '25e659cccc9a2ed956110a299fdf5983',
         'info_dict': {
-            'id': 'panisk-paske-5',
+            'id': 'klassen-darlig-taber-10',
             'ext': 'mp4',
-            'title': 'Panisk Påske (5)',
-            'description': 'md5:ca14173c5ab24cd26b0fcc074dff391c',
-            'timestamp': 1426984612,
-            'upload_date': '20150322',
-            'duration': 1455,
+            'title': 'Klassen - Dårlig taber (10)',
+            'description': 'md5:815fe1b7fa656ed80580f31e8b3c79aa',
+            'timestamp': 1471991907,
+            'upload_date': '20160823',
+            'duration': 606.84,
         },
-    }
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.dr.dk/nyheder/indland/live-christianias-rydning-af-pusher-street-er-i-gang',
+        'md5': '2c37175c718155930f939ef59952474a',
+        'info_dict': {
+            'id': 'christiania-pusher-street-ryddes-drdkrjpo',
+            'ext': 'mp4',
+            'title': 'LIVE Christianias rydning af Pusher Street er i gang',
+            'description': '- Det er det fedeste, der er sket i 20 år, fortæller christianit til DR Nyheder.',
+            'timestamp': 1472800279,
+            'upload_date': '20160902',
+            'duration': 131.4,
+        },
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -35,7 +54,8 @@ class DRTVIE(InfoExtractor):
                 'Video %s is not available' % video_id, expected=True)
 
         video_id = self._search_regex(
-            r'data-(?:material-identifier|episode-slug)="([^"]+)"',
+            (r'data-(?:material-identifier|episode-slug)="([^"]+)"',
+                r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'),
             webpage, 'video id')
 
         programcard = self._download_json(
@@ -43,9 +63,12 @@ class DRTVIE(InfoExtractor):
             video_id, 'Downloading video JSON')
         data = programcard['Data'][0]
 
-        title = data['Title']
-        description = data['Description']
-        timestamp = parse_iso8601(data['CreatedTime'])
+        title = remove_end(self._og_search_title(
+            webpage, default=None), ' | TV | DR') or data['Title']
+        description = self._og_search_description(
+            webpage, default=None) or data.get('Description')
+
+        timestamp = parse_iso8601(data.get('CreatedTime'))
 
         thumbnail = None
         duration = None
@@ -56,16 +79,18 @@ class DRTVIE(InfoExtractor):
         subtitles = {}
 
         for asset in data['Assets']:
-            if asset['Kind'] == 'Image':
-                thumbnail = asset['Uri']
-            elif asset['Kind'] == 'VideoResource':
-                duration = asset['DurationInMilliseconds'] / 1000.0
-                restricted_to_denmark = asset['RestrictedToDenmark']
-                spoken_subtitles = asset['Target'] == 'SpokenSubtitles'
-                for link in asset['Links']:
-                    uri = link['Uri']
-                    target = link['Target']
-                    format_id = target
+            if asset.get('Kind') == 'Image':
+                thumbnail = asset.get('Uri')
+            elif asset.get('Kind') == 'VideoResource':
+                duration = float_or_none(asset.get('DurationInMilliseconds'), 1000)
+                restricted_to_denmark = asset.get('RestrictedToDenmark')
+                spoken_subtitles = asset.get('Target') == 'SpokenSubtitles'
+                for link in asset.get('Links', []):
+                    uri = link.get('Uri')
+                    if not uri:
+                        continue
+                    target = link.get('Target')
+                    format_id = target or ''
                     preference = None
                     if spoken_subtitles:
                         preference = -1
@@ -76,8 +101,8 @@ class DRTVIE(InfoExtractor):
                             video_id, preference, f4m_id=format_id))
                     elif target == 'HLS':
                         formats.extend(self._extract_m3u8_formats(
-                            uri, video_id, 'mp4', preference=preference,
-                            m3u8_id=format_id))
+                            uri, video_id, 'mp4', entry_protocol='m3u8_native',
+                            preference=preference, m3u8_id=format_id))
                     else:
                         bitrate = link.get('Bitrate')
                         if bitrate:
@@ -85,7 +110,7 @@ class DRTVIE(InfoExtractor):
                         formats.append({
                             'url': uri,
                             'format_id': format_id,
-                            'tbr': bitrate,
+                            'tbr': int_or_none(bitrate),
                             'ext': link.get('FileFormat'),
                         })
                 subtitles_list = asset.get('SubtitlesList')
@@ -94,12 +119,18 @@ class DRTVIE(InfoExtractor):
                         'Danish': 'da',
                     }
                     for subs in subtitles_list:
-                        lang = subs['Language']
-                        subtitles[LANGS.get(lang, lang)] = [{'url': subs['Uri'], 'ext': 'vtt'}]
+                        if not subs.get('Uri'):
+                            continue
+                        lang = subs.get('Language') or 'da'
+                        subtitles.setdefault(LANGS.get(lang, lang), []).append({
+                            'url': subs['Uri'],
+                            'ext': mimetype2ext(subs.get('MimeType')) or 'vtt'
+                        })
 
         if not formats and restricted_to_denmark:
-            raise ExtractorError(
-                'Unfortunately, DR is not allowed to show this program outside Denmark.', expected=True)
+            self.raise_geo_restricted(
+                'Unfortunately, DR is not allowed to show this program outside Denmark.',
+                expected=True)
 
         self._sort_formats(formats)
 

youtube_dl/extractor/eagleplatform.py

@@ -52,11 +52,24 @@ class EaglePlatformIE(InfoExtractor):
 
     @staticmethod
     def _extract_url(webpage):
+        # Regular iframe embedding
         mobj = re.search(
             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//.+?\.media\.eagleplatform\.com/index/player\?.+?)\1',
             webpage)
         if mobj is not None:
             return mobj.group('url')
+        # Basic usage embedding (see http://dultonmedia.github.io/eplayer/)
+        mobj = re.search(
+            r'''(?xs)
+                    <script[^>]+
+                        src=(?P<q1>["\'])(?:https?:)?//(?P<host>.+?\.media\.eagleplatform\.com)/player/player\.js(?P=q1)
+                    .+?
+                    <div[^>]+
+                        class=(?P<q2>["\'])eagleplayer(?P=q2)[^>]+
+                        data-id=["\'](?P<id>\d+)
+            ''', webpage)
+        if mobj is not None:
+            return 'eagleplatform:%(host)s:%(id)s' % mobj.groupdict()
 
     @staticmethod
     def _handle_error(response):

youtube_dl/extractor/exfm.py

@@ -1,58 +0,0 @@
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-
-
-class ExfmIE(InfoExtractor):
-    IE_NAME = 'exfm'
-    IE_DESC = 'ex.fm'
-    _VALID_URL = r'https?://(?:www\.)?ex\.fm/song/(?P<id>[^/]+)'
-    _SOUNDCLOUD_URL = r'http://(?:www\.)?api\.soundcloud\.com/tracks/([^/]+)/stream'
-    _TESTS = [
-        {
-            'url': 'http://ex.fm/song/eh359',
-            'md5': 'e45513df5631e6d760970b14cc0c11e7',
-            'info_dict': {
-                'id': '44216187',
-                'ext': 'mp3',
-                'title': 'Test House "Love Is Not Enough" (Extended Mix) DeadJournalist Exclusive',
-                'uploader': 'deadjournalist',
-                'upload_date': '20120424',
-                'description': 'Test House \"Love Is Not Enough\" (Extended Mix) DeadJournalist Exclusive',
-            },
-            'note': 'Soundcloud song',
-            'skip': 'The site is down too often',
-        },
-        {
-            'url': 'http://ex.fm/song/wddt8',
-            'md5': '966bd70741ac5b8570d8e45bfaed3643',
-            'info_dict': {
-                'id': 'wddt8',
-                'ext': 'mp3',
-                'title': 'Safe and Sound',
-                'uploader': 'Capital Cities',
-            },
-            'skip': 'The site is down too often',
-        },
-    ]
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        song_id = mobj.group('id')
-        info_url = 'http://ex.fm/api/v3/song/%s' % song_id
-        info = self._download_json(info_url, song_id)['song']
-        song_url = info['url']
-        if re.match(self._SOUNDCLOUD_URL, song_url) is not None:
-            self.to_screen('Soundcloud song detected')
-            return self.url_result(song_url.replace('/stream', ''), 'Soundcloud')
-        return {
-            'id': song_id,
-            'url': song_url,
-            'ext': 'mp3',
-            'title': info['title'],
-            'thumbnail': info['image']['large'],
-            'uploader': info['artist'],
-            'view_count': info['loved_count'],
-        }

youtube_dl/extractor/expotv.py

@@ -1,7 +1,5 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
@@ -12,23 +10,22 @@ from ..utils import (
 class ExpoTVIE(InfoExtractor):
     _VALID_URL = r'https?://www\.expotv\.com/videos/[^?#]*/(?P<id>[0-9]+)($|[?#])'
     _TEST = {
-        'url': 'http://www.expotv.com/videos/reviews/1/24/LinneCardscom/17561',
-        'md5': '2985e6d7a392b2f7a05e0ca350fe41d0',
+        'url': 'http://www.expotv.com/videos/reviews/3/40/NYX-Butter-lipstick/667916',
+        'md5': 'fe1d728c3a813ff78f595bc8b7a707a8',
         'info_dict': {
-            'id': '17561',
+            'id': '667916',
             'ext': 'mp4',
-            'upload_date': '20060212',
-            'title': 'My Favorite Online Scrapbook Store',
-            'view_count': int,
-            'description': 'You\'ll find most everything you need at this virtual store front.',
-            'uploader': 'Anna T.',
+            'title': 'NYX Butter Lipstick Little Susie',
+            'description': 'Goes on like butter, but looks better!',
             'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': 'Stephanie S.',
+            'upload_date': '20150520',
+            'view_count': int,
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
         player_key = self._search_regex(
@@ -66,7 +63,7 @@ class ExpoTVIE(InfoExtractor):
             fatal=False)
         upload_date = unified_strdate(self._search_regex(
             r'<h5>Reviewed on ([0-9/.]+)</h5>', webpage, 'upload date',
-            fatal=False))
+            fatal=False), day_first=False)
 
         return {
             'id': video_id,

youtube_dl/extractor/extractors.py

@@ -1,7 +1,10 @@
 # flake8: noqa
 from __future__ import unicode_literals
 
-from .abc import ABCIE
+from .abc import (
+    ABCIE,
+    ABCIViewIE,
+)
 from .abc7news import Abc7NewsIE
 from .abcnews import (
     AbcNewsIE,
@@ -29,6 +32,7 @@ from .aftonbladet import AftonbladetIE
 from .airmozilla import AirMozillaIE
 from .aljazeera import AlJazeeraIE
 from .alphaporno import AlphaPornoIE
+from .amcnetworks import AMCNetworksIE
 from .animeondemand import AnimeOnDemandIE
 from .anitube import AnitubeIE
 from .anysex import AnySexIE
@@ -67,6 +71,12 @@ from .atttechchannel import ATTTechChannelIE
 from .audimedia import AudiMediaIE
 from .audioboom import AudioBoomIE
 from .audiomack import AudiomackIE, AudiomackAlbumIE
+from .awaan import (
+    AWAANIE,
+    AWAANVideoIE,
+    AWAANLiveIE,
+    AWAANSeasonIE,
+)
 from .azubu import AzubuIE, AzubuLiveIE
 from .baidu import BaiduVideoIE
 from .bambuser import BambuserIE, BambuserChannelIE
@@ -117,9 +127,12 @@ from .carambatv import (
     CarambaTVIE,
     CarambaTVPageIE,
 )
+from .cartoonnetwork import CartoonNetworkIE
 from .cbc import (
     CBCIE,
     CBCPlayerIE,
+    CBCWatchVideoIE,
+    CBCWatchIE,
 )
 from .cbs import CBSIE
 from .cbslocal import CBSLocalIE
@@ -133,6 +146,7 @@ from .ccc import CCCIE
 from .cda import CDAIE
 from .ceskatelevize import CeskaTelevizeIE
 from .channel9 import Channel9IE
+from .charlierose import CharlieRoseIE
 from .chaturbate import ChaturbateIE
 from .chilloutzone import ChilloutzoneIE
 from .chirbit import (
@@ -180,6 +194,10 @@ from .ctsnews import CtsNewsIE
 from .ctv import CTVIE
 from .ctvnews import CTVNewsIE
 from .cultureunplugged import CultureUnpluggedIE
+from .curiositystream import (
+    CuriosityStreamIE,
+    CuriosityStreamCollectionIE,
+)
 from .cwtv import CWTVIE
 from .dailymail import DailyMailIE
 from .dailymotion import (
@@ -195,12 +213,6 @@ from .daum import (
     DaumUserIE,
 )
 from .dbtv import DBTVIE
-from .dcn import (
-    DCNIE,
-    DCNVideoIE,
-    DCNLiveIE,
-    DCNSeasonIE,
-)
 from .dctp import DctpTvIE
 from .deezer import DeezerPlaylistIE
 from .democracynow import DemocracynowIE
@@ -249,11 +261,13 @@ from .espn import ESPNIE
 from .esri import EsriVideoIE
 from .europa import EuropaIE
 from .everyonesmixtape import EveryonesMixtapeIE
-from .exfm import ExfmIE
 from .expotv import ExpoTVIE
 from .extremetube import ExtremeTubeIE
 from .eyedotv import EyedoTVIE
-from .facebook import FacebookIE
+from .facebook import (
+    FacebookIE,
+    FacebookPluginsVideoIE,
+)
 from .faz import FazIE
 from .fc2 import FC2IE
 from .fczenit import FczenitIE
@@ -272,10 +286,7 @@ from .fox import FOXIE
 from .foxgay import FoxgayIE
 from .foxnews import FoxNewsIE
 from .foxsports import FoxSportsIE
-from .franceculture import (
-    FranceCultureIE,
-    FranceCultureEmissionIE,
-)
+from .franceculture import FranceCultureIE
 from .franceinter import FranceInterIE
 from .francetv import (
     PluzzIE,
@@ -290,6 +301,7 @@ from .freevideo import FreeVideoIE
 from .funimation import FunimationIE
 from .funnyordie import FunnyOrDieIE
 from .fusion import FusionIE
+from .fxnetworks import FXNetworksIE
 from .gameinformer import GameInformerIE
 from .gameone import (
     GameOneIE,
@@ -309,9 +321,9 @@ from .globo import (
     GloboIE,
     GloboArticleIE,
 )
+from .go import GoIE
 from .godtube import GodTubeIE
 from .godtv import GodTVIE
-from .goldenmoustache import GoldenMoustacheIE
 from .golem import GolemIE
 from .googledrive import GoogleDriveIE
 from .googleplus import GooglePlusIE
@@ -326,6 +338,10 @@ from .heise import HeiseIE
 from .hellporno import HellPornoIE
 from .helsinki import HelsinkiIE
 from .hentaistigma import HentaiStigmaIE
+from .hgtv import (
+    HGTVIE,
+    HGTVComShowIE,
+)
 from .historicfilms import HistoricFilmsIE
 from .hitbox import HitboxIE, HitboxLiveIE
 from .hornbunny import HornBunnyIE
@@ -477,6 +493,7 @@ from .motherless import MotherlessIE
 from .motorsport import MotorsportIE
 from .movieclips import MovieClipsIE
 from .moviezine import MoviezineIE
+from .movingimage import MovingImageIE
 from .msn import MSNIE
 from .mtv import (
     MTVIE,
@@ -533,6 +550,7 @@ from .nextmedia import (
 )
 from .nfb import NFBIE
 from .nfl import NFLIE
+from .nhk import NhkVodIE
 from .nhl import (
     NHLVideocenterIE,
     NHLNewsIE,
@@ -544,7 +562,10 @@ from .nick import (
     NickDeIE,
 )
 from .niconico import NiconicoIE, NiconicoPlaylistIE
-from .ninecninemedia import NineCNineMediaIE
+from .ninecninemedia import (
+    NineCNineMediaStackIE,
+    NineCNineMediaIE,
+)
 from .ninegag import NineGagIE
 from .ninenow import NineNowIE
 from .nintendo import NintendoIE
@@ -626,7 +647,6 @@ from .phoenix import PhoenixIE
 from .photobucket import PhotobucketIE
 from .pinkbike import PinkbikeIE
 from .pladform import PladformIE
-from .played import PlayedIE
 from .playfm import PlayFMIE
 from .plays import PlaysTVIE
 from .playtvak import PlaytvakIE
@@ -640,6 +660,7 @@ from .podomatic import PodomaticIE
 from .pokemon import PokemonIE
 from .polskieradio import PolskieRadioIE
 from .porn91 import Porn91IE
+from .porncom import PornComIE
 from .pornhd import PornHdIE
 from .pornhub import (
     PornHubIE,
@@ -696,6 +717,7 @@ from .rockstargames import RockstarGamesIE
 from .roosterteeth import RoosterTeethIE
 from .rottentomatoes import RottenTomatoesIE
 from .roxwel import RoxwelIE
+from .rozhlas import RozhlasIE
 from .rtbf import RTBFIE
 from .rte import RteIE, RteRadioIE
 from .rtlnl import RtlNlIE
@@ -755,6 +777,7 @@ from .smotri import (
 )
 from .snotr import SnotrIE
 from .sohu import SohuIE
+from .sonyliv import SonyLIVIE
 from .soundcloud import (
     SoundcloudIE,
     SoundcloudSetIE,
@@ -791,7 +814,6 @@ from .srgssr import (
     SRGSSRPlayIE,
 )
 from .srmediathek import SRMediathekIE
-from .ssa import SSAIE
 from .stanfordoc import StanfordOpenClassroomIE
 from .steam import SteamIE
 from .streamable import StreamableIE
@@ -810,8 +832,8 @@ from .tagesschau import (
     TagesschauPlayerIE,
     TagesschauIE,
 )
-from .tapely import TapelyIE
 from .tass import TassIE
+from .tbs import TBSIE
 from .tdslifeway import TDSLifewayIE
 from .teachertube import (
     TeacherTubeIE,
@@ -854,16 +876,11 @@ from .tnaflix import (
     MovieFapIE,
 )
 from .toggle import ToggleIE
-from .thvideo import (
-    THVideoIE,
-    THVideoPlaylistIE
-)
 from .toutv import TouTvIE
 from .toypics import ToypicsUserIE, ToypicsIE
 from .traileraddict import TrailerAddictIE
 from .trilulilu import TriluliluIE
 from .trollvids import TrollvidsIE
-from .trutube import TruTubeIE
 from .tube8 import Tube8IE
 from .tubitv import TubiTvIE
 from .tudou import (
@@ -898,7 +915,10 @@ from .tvp import (
     TVPIE,
     TVPSeriesIE,
 )
-from .tvplay import TVPlayIE
+from .tvplay import (
+    TVPlayIE,
+    ViafreeIE,
+)
 from .tweakers import TweakersIE
 from .twentyfourvideo import TwentyFourVideoIE
 from .twentymin import TwentyMinutenIE
@@ -927,8 +947,14 @@ from .udemy import (
 from .udn import UDNEmbedIE
 from .digiteka import DigitekaIE
 from .unistra import UnistraIE
+from .uol import UOLIE
+from .uplynk import (
+    UplynkIE,
+    UplynkPreplayIE,
+)
 from .urort import UrortIE
 from .urplay import URPlayIE
+from .usanetwork import USANetworkIE
 from .usatoday import USATodayIE
 from .ustream import UstreamIE, UstreamChannelIE
 from .ustudio import (
@@ -955,6 +981,7 @@ from .vice import (
     ViceIE,
     ViceShowIE,
 )
+from .viceland import VicelandIE
 from .vidbit import VidbitIE
 from .viddler import ViddlerIE
 from .videodetective import VideoDetectiveIE
@@ -1101,8 +1128,4 @@ from .youtube import (
 )
 from .zapiks import ZapiksIE
 from .zdf import ZDFIE, ZDFChannelIE
-from .zingmp3 import (
-    ZingMp3SongIE,
-    ZingMp3AlbumIE,
-)
-from .zippcast import ZippCastIE
+from .zingmp3 import ZingMp3IE

youtube_dl/extractor/extremetube.py

@@ -1,20 +1,14 @@
 from __future__ import unicode_literals
 
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-    sanitized_Request,
-    str_to_int,
-)
+from ..utils import str_to_int
+from .keezmovies import KeezMoviesIE
 
 
-class ExtremeTubeIE(InfoExtractor):
+class ExtremeTubeIE(KeezMoviesIE):
     _VALID_URL = r'https?://(?:www\.)?extremetube\.com/(?:[^/]+/)?video/(?P<id>[^/#?&]+)'
     _TESTS = [{
         'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
-        'md5': '344d0c6d50e2f16b06e49ca011d8ac69',
+        'md5': '1fb9228f5e3332ec8c057d6ac36f33e0',
         'info_dict': {
             'id': 'music-video-14-british-euro-brit-european-cumshots-swallow-652431',
             'ext': 'mp4',
@@ -35,58 +29,22 @@ class ExtremeTubeIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        webpage, info = self._extract_info(url)
 
-        req = sanitized_Request(url)
-        req.add_header('Cookie', 'age_verified=1')
-        webpage = self._download_webpage(req, video_id)
+        if not info['title']:
+            info['title'] = self._search_regex(
+                r'<h1[^>]+title="([^"]+)"[^>]*>', webpage, 'title')
 
-        video_title = self._html_search_regex(
-            r'<h1 [^>]*?title="([^"]+)"[^>]*>', webpage, 'title')
         uploader = self._html_search_regex(
             r'Uploaded by:\s*</strong>\s*(.+?)\s*</div>',
             webpage, 'uploader', fatal=False)
-        view_count = str_to_int(self._html_search_regex(
+        view_count = str_to_int(self._search_regex(
             r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>',
             webpage, 'view count', fatal=False))
 
-        flash_vars = self._parse_json(
-            self._search_regex(
-                r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flash vars'),
-            video_id)
-
-        formats = []
-        for quality_key, video_url in flash_vars.items():
-            height = int_or_none(self._search_regex(
-                r'quality_(\d+)[pP]$', quality_key, 'height', default=None))
-            if not height:
-                continue
-            f = {
-                'url': video_url,
-            }
-            mobj = re.search(
-                r'/(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', video_url)
-            if mobj:
-                height = int(mobj.group('height'))
-                bitrate = int(mobj.group('bitrate'))
-                f.update({
-                    'format_id': '%dp-%dk' % (height, bitrate),
-                    'height': height,
-                    'tbr': bitrate,
-                })
-            else:
-                f.update({
-                    'format_id': '%dp' % height,
-                    'height': height,
-                })
-            formats.append(f)
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'title': video_title,
-            'formats': formats,
+        info.update({
             'uploader': uploader,
             'view_count': view_count,
-            'age_limit': 18,
-        }
+        })
+
+        return info

youtube_dl/extractor/facebook.py

@@ -15,6 +15,7 @@ from ..compat import (
 from ..utils import (
     error_to_compat_str,
     ExtractorError,
+    int_or_none,
     limit_length,
     sanitized_Request,
     urlencode_postdata,
@@ -62,6 +63,8 @@ class FacebookIE(InfoExtractor):
             'ext': 'mp4',
             'title': 're:Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam',
             'uploader': 'Tennis on Facebook',
+            'upload_date': '20140908',
+            'timestamp': 1410199200,
         }
     }, {
         'note': 'Video without discernible title',
@@ -71,6 +74,8 @@ class FacebookIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Facebook video #274175099429670',
             'uploader': 'Asif Nawab Butt',
+            'upload_date': '20140506',
+            'timestamp': 1399398998,
         },
         'expected_warnings': [
             'title'
@@ -78,12 +83,14 @@ class FacebookIE(InfoExtractor):
     }, {
         'note': 'Video with DASH manifest',
         'url': 'https://www.facebook.com/video.php?v=957955867617029',
-        'md5': '54706e4db4f5ad58fbad82dde1f1213f',
+        'md5': 'b2c28d528273b323abe5c6ab59f0f030',
         'info_dict': {
             'id': '957955867617029',
             'ext': 'mp4',
             'title': 'When you post epic content on instagram.com/433 8 million followers, this is ...',
             'uploader': 'Demy de Zeeuw',
+            'upload_date': '20160110',
+            'timestamp': 1452431627,
         },
     }, {
         'url': 'https://www.facebook.com/maxlayn/posts/10153807558977570',
@@ -306,12 +313,16 @@ class FacebookIE(InfoExtractor):
         if not video_title:
             video_title = 'Facebook video #%s' % video_id
         uploader = clean_html(get_element_by_id('fbPhotoPageAuthorName', webpage))
+        timestamp = int_or_none(self._search_regex(
+            r'<abbr[^>]+data-utime=["\'](\d+)', webpage,
+            'timestamp', default=None))
 
         info_dict = {
             'id': video_id,
             'title': video_title,
             'formats': formats,
             'uploader': uploader,
+            'timestamp': timestamp,
         }
 
         return webpage, info_dict
@@ -340,3 +351,32 @@ class FacebookIE(InfoExtractor):
                 self._VIDEO_PAGE_TEMPLATE % video_id,
                 video_id, fatal_if_no_video=True)
             return info_dict
+
+
+class FacebookPluginsVideoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:[\w-]+\.)?facebook\.com/plugins/video\.php\?.*?\bhref=(?P<id>https.+)'
+
+    _TESTS = [{
+        'url': 'https://www.facebook.com/plugins/video.php?href=https%3A%2F%2Fwww.facebook.com%2Fgov.sg%2Fvideos%2F10154383743583686%2F&show_text=0&width=560',
+        'md5': '5954e92cdfe51fe5782ae9bda7058a07',
+        'info_dict': {
+            'id': '10154383743583686',
+            'ext': 'mp4',
+            'title': 'What to do during the haze?',
+            'uploader': 'Gov.sg',
+            'upload_date': '20160826',
+            'timestamp': 1472184808,
+        },
+        'add_ie': [FacebookIE.ie_key()],
+    }, {
+        'url': 'https://www.facebook.com/plugins/video.php?href=https%3A%2F%2Fwww.facebook.com%2Fvideo.php%3Fv%3D10204634152394104',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.facebook.com/plugins/video.php?href=https://www.facebook.com/gov.sg/videos/10154383743583686/&show_text=0&width=560',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        return self.url_result(
+            compat_urllib_parse_unquote(self._match_id(url)),
+            FacebookIE.ie_key())

youtube_dl/extractor/firsttv.py

@@ -2,44 +2,40 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import compat_xpath
+from ..compat import compat_urlparse
 from ..utils import (
     int_or_none,
     qualities,
     unified_strdate,
-    xpath_attr,
-    xpath_element,
-    xpath_text,
-    xpath_with_ns,
 )
 
 
 class FirstTVIE(InfoExtractor):
     IE_NAME = '1tv'
     IE_DESC = 'Первый канал'
-    _VALID_URL = r'https?://(?:www\.)?1tv\.ru/(?:[^/]+/)+p?(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?1tv\.ru/(?:[^/]+/)+(?P<id>[^/?#]+)'
 
     _TESTS = [{
-        # single format via video_materials.json API
-        'url': 'http://www.1tv.ru/prj/inprivate/vypusk/35930',
-        'md5': '82a2777648acae812d58b3f5bd42882b',
+        # single format
+        'url': 'http://www.1tv.ru/shows/naedine-so-vsemi/vypuski/gost-lyudmila-senchina-naedine-so-vsemi-vypusk-ot-12-02-2015',
+        'md5': 'a1b6b60d530ebcf8daacf4565762bbaf',
         'info_dict': {
-            'id': '35930',
+            'id': '40049',
             'ext': 'mp4',
             'title': 'Гость Людмила Сенчина. Наедине со всеми. Выпуск от 12.02.2015',
-            'description': 'md5:357933adeede13b202c7c21f91b871b2',
+            'description': 'md5:36a39c1d19618fec57d12efe212a8370',
             'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
             'upload_date': '20150212',
             'duration': 2694,
         },
     }, {
-        # multiple formats via video_materials.json API
-        'url': 'http://www.1tv.ru/video_archive/projects/dobroeutro/p113641',
+        # multiple formats
+        'url': 'http://www.1tv.ru/shows/dobroe-utro/pro-zdorove/vesennyaya-allergiya-dobroe-utro-fragment-vypuska-ot-07042016',
         'info_dict': {
-            'id': '113641',
+            'id': '364746',
             'ext': 'mp4',
             'title': 'Весенняя аллергия. Доброе утро. Фрагмент выпуска от 07.04.2016',
-            'description': 'md5:8dcebb3dded0ff20fade39087fd1fee2',
+            'description': 'md5:a242eea0031fd180a4497d52640a9572',
             'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
             'upload_date': '20160407',
             'duration': 179,
@@ -48,84 +44,47 @@ class FirstTVIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
-    }, {
-        # single format only available via ONE_ONLINE_VIDEOS.archive_single_xml API
-        'url': 'http://www.1tv.ru/video_archive/series/f7552/p47038',
-        'md5': '519d306c5b5669761fd8906c39dbee23',
-        'info_dict': {
-            'id': '47038',
-            'ext': 'mp4',
-            'title': '"Побег". Второй сезон. 3 серия',
-            'description': 'md5:3abf8f6b9bce88201c33e9a3d794a00b',
-            'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
-            'upload_date': '20120516',
-            'duration': 3080,
-        },
-    }, {
-        'url': 'http://www.1tv.ru/videoarchive/9967',
-        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        display_id = self._match_id(url)
 
-        # Videos with multiple formats only available via this API
-        video = self._download_json(
-            'http://www.1tv.ru/video_materials.json?legacy_id=%s' % video_id,
-            video_id, fatal=False)
-
-        description, thumbnail, upload_date, duration = [None] * 4
-
-        if video:
-            item = video[0]
-            title = item['title']
-            quality = qualities(('ld', 'sd', 'hd', ))
-            formats = [{
-                'url': f['src'],
-                'format_id': f.get('name'),
-                'quality': quality(f.get('name')),
-            } for f in item['mbr'] if f.get('src')]
-            thumbnail = item.get('poster')
-        else:
-            # Some videos are not available via video_materials.json
-            video = self._download_xml(
-                'http://www.1tv.ru/owa/win/ONE_ONLINE_VIDEOS.archive_single_xml?pid=%s' % video_id,
-                video_id)
-
-            NS_MAP = {
-                'media': 'http://search.yahoo.com/mrss/',
-            }
-
-            item = xpath_element(video, './channel/item', fatal=True)
-            title = xpath_text(item, './title', fatal=True)
-            formats = [{
-                'url': content.attrib['url'],
-            } for content in item.findall(
-                compat_xpath(xpath_with_ns('./media:content', NS_MAP))) if content.attrib.get('url')]
-            thumbnail = xpath_attr(
-                item, xpath_with_ns('./media:thumbnail', NS_MAP), 'url')
+        webpage = self._download_webpage(url, display_id)
+        playlist_url = compat_urlparse.urljoin(url, self._search_regex(
+            r'data-playlist-url="([^"]+)', webpage, 'playlist url'))
 
+        item = self._download_json(playlist_url, display_id)[0]
+        video_id = item['id']
+        quality = qualities(('ld', 'sd', 'hd', ))
+        formats = []
+        for f in item.get('mbr', []):
+            src = f.get('src')
+            if not src:
+                continue
+            fname = f.get('name')
+            formats.append({
+                'url': src,
+                'format_id': fname,
+                'quality': quality(fname),
+            })
         self._sort_formats(formats)
 
-        webpage = self._download_webpage(url, video_id, 'Downloading page', fatal=False)
-        if webpage:
-            title = self._html_search_regex(
-                (r'<div class="tv_translation">\s*<h1><a href="[^"]+">([^<]*)</a>',
-                 r"'title'\s*:\s*'([^']+)'"),
-                webpage, 'title', default=None) or title
-            description = self._html_search_regex(
-                r'<div class="descr">\s*<div>&nbsp;</div>\s*<p>([^<]*)</p></div>',
-                webpage, 'description', default=None) or self._html_search_meta(
-                'description', webpage, 'description')
-            thumbnail = thumbnail or self._og_search_thumbnail(webpage)
-            duration = int_or_none(self._html_search_meta(
-                'video:duration', webpage, 'video duration', fatal=False))
-            upload_date = unified_strdate(self._html_search_meta(
-                'ya:ovs:upload_date', webpage, 'upload date', fatal=False))
+        title = self._html_search_regex(
+            (r'<div class="tv_translation">\s*<h1><a href="[^"]+">([^<]*)</a>',
+             r"'title'\s*:\s*'([^']+)'"),
+            webpage, 'title', default=None) or item['title']
+        description = self._html_search_regex(
+            r'<div class="descr">\s*<div>&nbsp;</div>\s*<p>([^<]*)</p></div>',
+            webpage, 'description', default=None) or self._html_search_meta(
+            'description', webpage, 'description')
+        duration = int_or_none(self._html_search_meta(
+            'video:duration', webpage, 'video duration', fatal=False))
+        upload_date = unified_strdate(self._html_search_meta(
+            'ya:ovs:upload_date', webpage, 'upload date', fatal=False))
 
         return {
             'id': video_id,
-            'thumbnail': thumbnail,
+            'thumbnail': item.get('poster') or self._og_search_thumbnail(webpage),
             'title': title,
             'description': description,
             'upload_date': upload_date,

youtube_dl/extractor/flipagram.py

@@ -48,7 +48,7 @@ class FlipagramIE(InfoExtractor):
         flipagram = video_data['flipagram']
         video = flipagram['video']
 
-        json_ld = self._search_json_ld(webpage, video_id, fatal=False)
+        json_ld = self._search_json_ld(webpage, video_id, default={})
         title = json_ld.get('title') or flipagram['captionText']
         description = json_ld.get('description') or flipagram.get('captionText')
 

youtube_dl/extractor/formula1.py

@@ -5,8 +5,8 @@ from .common import InfoExtractor
 
 
 class Formula1IE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?formula1\.com/content/fom-website/en/video/\d{4}/\d{1,2}/(?P<id>.+?)\.html'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?formula1\.com/(?:content/fom-website/)?en/video/\d{4}/\d{1,2}/(?P<id>.+?)\.html'
+    _TESTS = [{
         'url': 'http://www.formula1.com/content/fom-website/en/video/2016/5/Race_highlights_-_Spain_2016.html',
         'md5': '8c79e54be72078b26b89e0e111c0502b',
         'info_dict': {
@@ -15,7 +15,10 @@ class Formula1IE(InfoExtractor):
             'title': 'Race highlights - Spain 2016',
         },
         'add_ie': ['Ooyala'],
-    }
+    }, {
+        'url': 'http://www.formula1.com/en/video/2016/5/Race_highlights_-_Spain_2016.html',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)

youtube_dl/extractor/fourtube.py

@@ -43,14 +43,14 @@ class FourTubeIE(InfoExtractor):
             'uploadDate', webpage))
         thumbnail = self._html_search_meta('thumbnailUrl', webpage)
         uploader_id = self._html_search_regex(
-            r'<a class="img-avatar" href="[^"]+/channels/([^/"]+)" title="Go to [^"]+ page">',
+            r'<a class="item-to-subscribe" href="[^"]+/channels/([^/"]+)" title="Go to [^"]+ page">',
             webpage, 'uploader id', fatal=False)
         uploader = self._html_search_regex(
-            r'<a class="img-avatar" href="[^"]+/channels/[^/"]+" title="Go to ([^"]+) page">',
+            r'<a class="item-to-subscribe" href="[^"]+/channels/[^/"]+" title="Go to ([^"]+) page">',
             webpage, 'uploader', fatal=False)
 
         categories_html = self._search_regex(
-            r'(?s)><i class="icon icon-tag"></i>\s*Categories / Tags\s*.*?<ul class="list">(.*?)</ul>',
+            r'(?s)><i class="icon icon-tag"></i>\s*Categories / Tags\s*.*?<ul class="[^"]*?list[^"]*?">(.*?)</ul>',
             webpage, 'categories', fatal=False)
         categories = None
         if categories_html:
@@ -59,10 +59,10 @@ class FourTubeIE(InfoExtractor):
                     r'(?s)<li><a.*?>(.*?)</a>', categories_html)]
 
         view_count = str_to_int(self._search_regex(
-            r'<meta itemprop="interactionCount" content="UserPlays:([0-9,]+)">',
+            r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserPlays:([0-9,]+)">',
             webpage, 'view count', fatal=False))
         like_count = str_to_int(self._search_regex(
-            r'<meta itemprop="interactionCount" content="UserLikes:([0-9,]+)">',
+            r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserLikes:([0-9,]+)">',
             webpage, 'like count', fatal=False))
         duration = parse_duration(self._html_search_meta('duration', webpage))
 

youtube_dl/extractor/franceculture.py

@@ -2,104 +2,56 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_urlparse,
-)
 from ..utils import (
     determine_ext,
-    int_or_none,
-    ExtractorError,
+    unified_strdate,
 )
 
 
 class FranceCultureIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?franceculture\.fr/player/reecouter\?play=(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?franceculture\.fr/emissions/(?:[^/]+/)*(?P<id>[^/?#&]+)'
     _TEST = {
-        'url': 'http://www.franceculture.fr/player/reecouter?play=4795174',
+        'url': 'http://www.franceculture.fr/emissions/carnet-nomade/rendez-vous-au-pays-des-geeks',
         'info_dict': {
-            'id': '4795174',
+            'id': 'rendez-vous-au-pays-des-geeks',
+            'display_id': 'rendez-vous-au-pays-des-geeks',
             'ext': 'mp3',
             'title': 'Rendez-vous au pays des geeks',
-            'alt_title': 'Carnet nomade | 13-14',
-            'vcodec': 'none',
+            'thumbnail': 're:^https?://.*\\.jpg$',
             'upload_date': '20140301',
-            'thumbnail': r're:^http://static\.franceculture\.fr/.*/images/player/Carnet-nomade\.jpg$',
-            'description': 'startswith:Avec :Jean-Baptiste Péretié pour son documentaire sur Arte "La revanche',
-            'timestamp': 1393700400,
+            'vcodec': 'none',
         }
     }
 
-    def _extract_from_player(self, url, video_id):
-        webpage = self._download_webpage(url, video_id)
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
 
-        video_path = self._search_regex(
-            r'<a id="player".*?href="([^"]+)"', webpage, 'video path')
-        video_url = compat_urlparse.urljoin(url, video_path)
-        timestamp = int_or_none(self._search_regex(
-            r'<a id="player".*?data-date="([0-9]+)"',
+        webpage = self._download_webpage(url, display_id)
+
+        video_url = self._search_regex(
+            r'(?s)<div[^>]+class="[^"]*?title-zone-diffusion[^"]*?"[^>]*>.*?<a[^>]+href="([^"]+)"',
+            webpage, 'video path')
+
+        title = self._og_search_title(webpage)
+
+        upload_date = unified_strdate(self._search_regex(
+            '(?s)<div[^>]+class="date"[^>]*>.*?<span[^>]+class="inner"[^>]*>([^<]+)<',
             webpage, 'upload date', fatal=False))
         thumbnail = self._search_regex(
-            r'<a id="player".*?>\s+<img src="([^"]+)"',
+            r'(?s)<figure[^>]+itemtype="https://schema.org/ImageObject"[^>]*>.*?<img[^>]+data-pagespeed-(?:lazy|high-res)-src="([^"]+)"',
             webpage, 'thumbnail', fatal=False)
-
-        display_id = self._search_regex(
-            r'<span class="path-diffusion">emission-(.*?)</span>', webpage, 'display_id')
-
-        title = self._html_search_regex(
-            r'<span class="title-diffusion">(.*?)</span>', webpage, 'title')
-        alt_title = self._html_search_regex(
-            r'<span class="title">(.*?)</span>',
-            webpage, 'alt_title', fatal=False)
-        description = self._html_search_regex(
-            r'<span class="description">(.*?)</span>',
-            webpage, 'description', fatal=False)
-
         uploader = self._html_search_regex(
             r'(?s)<div id="emission".*?<span class="author">(.*?)</span>',
             webpage, 'uploader', default=None)
         vcodec = 'none' if determine_ext(video_url.lower()) == 'mp3' else None
 
         return {
-            'id': video_id,
+            'id': display_id,
+            'display_id': display_id,
             'url': video_url,
+            'title': title,
+            'thumbnail': thumbnail,
             'vcodec': vcodec,
             'uploader': uploader,
-            'timestamp': timestamp,
-            'title': title,
-            'alt_title': alt_title,
-            'thumbnail': thumbnail,
-            'description': description,
-            'display_id': display_id,
+            'upload_date': upload_date,
         }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        return self._extract_from_player(url, video_id)
-
-
-class FranceCultureEmissionIE(FranceCultureIE):
-    _VALID_URL = r'https?://(?:www\.)?franceculture\.fr/emission-(?P<id>[^?#]+)'
-    _TEST = {
-        'url': 'http://www.franceculture.fr/emission-les-carnets-de-la-creation-jean-gabriel-periot-cineaste-2015-10-13',
-        'info_dict': {
-            'title': 'Jean-Gabriel Périot, cinéaste',
-            'alt_title': 'Les Carnets de la création',
-            'id': '5093239',
-            'display_id': 'les-carnets-de-la-creation-jean-gabriel-periot-cineaste-2015-10-13',
-            'ext': 'mp3',
-            'timestamp': 1444762500,
-            'upload_date': '20151013',
-            'description': 'startswith:Aujourd\'hui dans "Les carnets de la création", le cinéaste',
-        },
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-        video_path = self._html_search_regex(
-            r'<a class="rf-player-open".*?href="([^"]+)"', webpage, 'video path', 'no_path_player')
-        if video_path == 'no_path_player':
-            raise ExtractorError('no player : no sound in this page.', expected=True)
-        new_id = self._search_regex('play=(?P<id>[0-9]+)', video_path, 'new_id', group='id')
-        video_url = compat_urlparse.urljoin(url, video_path)
-        return self._extract_from_player(video_url, new_id)

youtube_dl/extractor/francetv.py

@@ -131,7 +131,7 @@ class PluzzIE(FranceTVBaseInfoExtractor):
 
 class FranceTvInfoIE(FranceTVBaseInfoExtractor):
     IE_NAME = 'francetvinfo.fr'
-    _VALID_URL = r'https?://(?:www|mobile|france3-regions)\.francetvinfo\.fr/.*/(?P<title>.+)\.html'
+    _VALID_URL = r'https?://(?:www|mobile|france3-regions)\.francetvinfo\.fr/(?:[^/]+/)*(?P<title>[^/?#&.]+)'
 
     _TESTS = [{
         'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
@@ -206,6 +206,9 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
             'uploader_id': 'x2q2ez',
         },
         'add_ie': ['Dailymotion'],
+    }, {
+        'url': 'http://france3-regions.francetvinfo.fr/limousin/emissions/jt-1213-limousin',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/fxnetworks.py

@@ -0,0 +1,70 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .adobepass import AdobePassIE
+from ..utils import (
+    update_url_query,
+    extract_attributes,
+    parse_age_limit,
+    smuggle_url,
+)
+
+
+class FXNetworksIE(AdobePassIE):
+    _VALID_URL = r'https?://(?:www\.)?(?:fxnetworks|simpsonsworld)\.com/video/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://www.fxnetworks.com/video/719841347694',
+        'md5': '1447d4722e42ebca19e5232ab93abb22',
+        'info_dict': {
+            'id': '719841347694',
+            'ext': 'mp4',
+            'title': 'Vanpage',
+            'description': 'F*ck settling down. You\'re the Worst returns for an all new season August 31st on FXX.',
+            'age_limit': 14,
+            'uploader': 'NEWA-FNG-FX',
+            'upload_date': '20160706',
+            'timestamp': 1467844741,
+        },
+        'add_ie': ['ThePlatform'],
+    }, {
+        'url': 'http://www.simpsonsworld.com/video/716094019682',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        if 'The content you are trying to access is not available in your region.' in webpage:
+            self.raise_geo_restricted()
+        video_data = extract_attributes(self._search_regex(
+            r'(<a.+?rel="http://link\.theplatform\.com/s/.+?</a>)', webpage, 'video data'))
+        player_type = self._search_regex(r'playerType\s*=\s*[\'"]([^\'"]+)', webpage, 'player type', default=None)
+        release_url = video_data['rel']
+        title = video_data['data-title']
+        rating = video_data.get('data-rating')
+        query = {
+            'mbr': 'true',
+        }
+        if player_type == 'movies':
+            query.update({
+                'manifest': 'm3u',
+            })
+        else:
+            query.update({
+                'switch': 'http',
+            })
+        if video_data.get('data-req-auth') == '1':
+            resource = self._get_mvpd_resource(
+                video_data['data-channel'], title,
+                video_data.get('data-guid'), rating)
+            query['auth'] = self._extract_mvpd_auth(url, video_id, 'fx', resource)
+
+        return {
+            '_type': 'url_transparent',
+            'id': video_id,
+            'title': title,
+            'url': smuggle_url(update_url_query(release_url, query), {'force_smil_url': True}),
+            'thumbnail': video_data.get('data-large-thumb'),
+            'age_limit': parse_age_limit(rating),
+            'ie_key': 'ThePlatform',
+        }

youtube_dl/extractor/generic.py

@@ -72,6 +72,8 @@ from .kaltura import KalturaIE
 from .eagleplatform import EaglePlatformIE
 from .facebook import FacebookIE
 from .soundcloud import SoundcloudIE
+from .vbox7 import Vbox7IE
+from .dbtv import DBTVIE
 
 
 class GenericIE(InfoExtractor):
@@ -102,7 +104,8 @@ class GenericIE(InfoExtractor):
             },
             'expected_warnings': [
                 'URL could be a direct video link, returning it as such.'
-            ]
+            ],
+            'skip': 'URL invalid',
         },
         # Direct download with broken HEAD
         {
@@ -266,7 +269,8 @@ class GenericIE(InfoExtractor):
             'params': {
                 # m3u8 downloads
                 'skip_download': True,
-            }
+            },
+            'skip': 'video gone',
         },
         # m3u8 served with Content-Type: text/plain
         {
@@ -281,7 +285,8 @@ class GenericIE(InfoExtractor):
             'params': {
                 # m3u8 downloads
                 'skip_download': True,
-            }
+            },
+            'skip': 'video gone',
         },
         # google redirect
         {
@@ -366,6 +371,7 @@ class GenericIE(InfoExtractor):
                 'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
             },
             'add_ie': ['BrightcoveLegacy'],
+            'skip': 'video gone',
         },
         {
             'url': 'http://www.championat.com/video/football/v/87/87499.html',
@@ -419,6 +425,7 @@ class GenericIE(InfoExtractor):
             'params': {
                 'skip_download': True,
             },
+            'skip': 'movie expired',
         },
         # embed.ly video
         {
@@ -446,6 +453,8 @@ class GenericIE(InfoExtractor):
                 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
                 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
             },
+            # HEAD requests lead to endless 301, while GET is OK
+            'expected_warnings': ['301'],
         },
         # RUTV embed
         {
@@ -520,6 +529,9 @@ class GenericIE(InfoExtractor):
                 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
             },
             'playlist_mincount': 7,
+            # This forum does not allow <iframe> syntaxes anymore
+            # Now HTML tags are displayed as-is
+            'skip': 'No videos on this page',
         },
         # Embedded TED video
         {
@@ -568,7 +580,8 @@ class GenericIE(InfoExtractor):
             },
             'params': {
                 'skip_download': 'Requires rtmpdump'
-            }
+            },
+            'skip': 'video gone',
         },
         # francetv embed
         {
@@ -1373,6 +1386,27 @@ class GenericIE(InfoExtractor):
             },
             'add_ie': [ArkenaIE.ie_key()],
         },
+        {
+            'url': 'http://nova.bg/news/view/2016/08/16/156543/%D0%BD%D0%B0-%D0%BA%D0%BE%D1%81%D1%8A%D0%BC-%D0%BE%D1%82-%D0%B2%D0%B7%D1%80%D0%B8%D0%B2-%D0%BE%D1%82%D1%86%D0%B5%D0%BF%D0%B8%D1%85%D0%B0-%D1%86%D1%8F%D0%BB-%D0%BA%D0%B2%D0%B0%D1%80%D1%82%D0%B0%D0%BB-%D0%B7%D0%B0%D1%80%D0%B0%D0%B4%D0%B8-%D0%B8%D0%B7%D1%82%D0%B8%D1%87%D0%B0%D0%BD%D0%B5-%D0%BD%D0%B0-%D0%B3%D0%B0%D0%B7-%D0%B2-%D0%BF%D0%BB%D0%BE%D0%B2%D0%B4%D0%B8%D0%B2/',
+            'info_dict': {
+                'id': '1c7141f46c',
+                'ext': 'mp4',
+                'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
+            },
+            'params': {
+                'skip_download': True,
+            },
+            'add_ie': [Vbox7IE.ie_key()],
+        },
+        {
+            # DBTV embeds
+            'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
+            'info_dict': {
+                'id': '43254897',
+                'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
+            },
+            'playlist_mincount': 3,
+        },
         # {
         #     # TODO: find another test
         #     # http://schema.org/VideoObject
@@ -2209,11 +2243,11 @@ class GenericIE(InfoExtractor):
 
         # Look for VODPlatform embeds
         mobj = re.search(
-            r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vod-platform\.net/embed/[^/?#]+)',
+            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
             webpage)
         if mobj is not None:
             return self.url_result(
-                self._proto_relative_url(unescapeHTML(mobj.group(1))), 'VODPlatform')
+                self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
 
         # Look for Instagram embeds
         instagram_embed_url = InstagramIE._extract_embed_url(webpage)
@@ -2239,10 +2273,20 @@ class GenericIE(InfoExtractor):
                 'uploader': video_uploader,
             }
 
+        # Look for VBOX7 embeds
+        vbox7_url = Vbox7IE._extract_url(webpage)
+        if vbox7_url:
+            return self.url_result(vbox7_url, Vbox7IE.ie_key())
+
+        # Look for DBTV embeds
+        dbtv_urls = DBTVIE._extract_urls(webpage)
+        if dbtv_urls:
+            return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
+
         # Looking for http://schema.org/VideoObject
         json_ld = self._search_json_ld(
-            webpage, video_id, fatal=False, expected_type='VideoObject')
-        if json_ld and json_ld.get('url'):
+            webpage, video_id, default={}, expected_type='VideoObject')
+        if json_ld.get('url'):
             info_dict.update({
                 'title': video_title or info_dict['title'],
                 'description': video_description,

youtube_dl/extractor/glide.py

@@ -2,7 +2,6 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import unified_strdate
 
 
 class GlideIE(InfoExtractor):
@@ -14,10 +13,8 @@ class GlideIE(InfoExtractor):
         'info_dict': {
             'id': 'UZF8zlmuQbe4mr+7dCiQ0w==',
             'ext': 'mp4',
-            'title': 'Damon Timm\'s Glide message',
+            'title': "Damon's Glide message",
             'thumbnail': 're:^https?://.*?\.cloudfront\.net/.*\.jpg$',
-            'uploader': 'Damon Timm',
-            'upload_date': '20140919',
         }
     }
 
@@ -27,7 +24,8 @@ class GlideIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         title = self._html_search_regex(
-            r'<title>(.+?)</title>', webpage, 'title')
+            r'<title>(.+?)</title>', webpage,
+            'title', default=None) or self._og_search_title(webpage)
         video_url = self._proto_relative_url(self._search_regex(
             r'<source[^>]+src=(["\'])(?P<url>.+?)\1',
             webpage, 'video URL', default=None,
@@ -36,18 +34,10 @@ class GlideIE(InfoExtractor):
             r'<img[^>]+id=["\']video-thumbnail["\'][^>]+src=(["\'])(?P<url>.+?)\1',
             webpage, 'thumbnail url', default=None,
             group='url')) or self._og_search_thumbnail(webpage)
-        uploader = self._search_regex(
-            r'<div[^>]+class=["\']info-name["\'][^>]*>([^<]+)',
-            webpage, 'uploader', fatal=False)
-        upload_date = unified_strdate(self._search_regex(
-            r'<div[^>]+class="info-date"[^>]*>([^<]+)',
-            webpage, 'upload date', fatal=False))
 
         return {
             'id': video_id,
             'title': title,
             'url': video_url,
             'thumbnail': thumbnail,
-            'uploader': uploader,
-            'upload_date': upload_date,
         }

youtube_dl/extractor/globo.py

@@ -396,12 +396,12 @@ class GloboIE(InfoExtractor):
 
 
 class GloboArticleIE(InfoExtractor):
-    _VALID_URL = 'https?://.+?\.globo\.com/(?:[^/]+/)*(?P<id>[^/]+)\.html'
+    _VALID_URL = 'https?://.+?\.globo\.com/(?:[^/]+/)*(?P<id>[^/]+)(?:\.html)?'
 
     _VIDEOID_REGEXES = [
         r'\bdata-video-id=["\'](\d{7,})',
         r'\bdata-player-videosids=["\'](\d{7,})',
-        r'\bvideosIDs\s*:\s*["\'](\d{7,})',
+        r'\bvideosIDs\s*:\s*["\']?(\d{7,})',
         r'\bdata-id=["\'](\d{7,})',
         r'<div[^>]+\bid=["\'](\d{7,})',
     ]
@@ -423,6 +423,9 @@ class GloboArticleIE(InfoExtractor):
     }, {
         'url': 'http://gshow.globo.com/programas/tv-xuxa/O-Programa/noticia/2014/01/xuxa-e-junno-namoram-muuuito-em-luau-de-zeze-di-camargo-e-luciano.html',
         'only_matching': True,
+    }, {
+        'url': 'http://oglobo.globo.com/rio/a-amizade-entre-um-entregador-de-farmacia-um-piano-19946271',
+        'only_matching': True,
     }]
 
     @classmethod

youtube_dl/extractor/go.py

@@ -0,0 +1,101 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    determine_ext,
+    parse_age_limit,
+)
+
+
+class GoIE(InfoExtractor):
+    _BRANDS = {
+        'abc': '001',
+        'freeform': '002',
+        'watchdisneychannel': '004',
+        'watchdisneyjunior': '008',
+        'watchdisneyxd': '009',
+    }
+    _VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/.*?vdka(?P<id>\w+)' % '|'.join(_BRANDS.keys())
+    _TESTS = [{
+        'url': 'http://abc.go.com/shows/castle/video/most-recent/vdka0_g86w5onx',
+        'info_dict': {
+            'id': '0_g86w5onx',
+            'ext': 'mp4',
+            'title': 'Sneak Peek: Language Arts',
+            'description': 'md5:7dcdab3b2d17e5217c953256af964e9c',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://abc.go.com/shows/after-paradise/video/most-recent/vdka3335601',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        sub_domain, video_id = re.match(self._VALID_URL, url).groups()
+        video_data = self._download_json(
+            'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/-1/-1/%s/-1/-1.json' % (self._BRANDS[sub_domain], video_id),
+            video_id)['video'][0]
+        title = video_data['title']
+
+        formats = []
+        for asset in video_data.get('assets', {}).get('asset', []):
+            asset_url = asset.get('value')
+            if not asset_url:
+                continue
+            format_id = asset.get('format')
+            ext = determine_ext(asset_url)
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    asset_url, video_id, 'mp4', m3u8_id=format_id or 'hls', fatal=False))
+            else:
+                formats.append({
+                    'format_id': format_id,
+                    'url': asset_url,
+                    'ext': ext,
+                })
+        self._sort_formats(formats)
+
+        subtitles = {}
+        for cc in video_data.get('closedcaption', {}).get('src', []):
+            cc_url = cc.get('value')
+            if not cc_url:
+                continue
+            ext = determine_ext(cc_url)
+            if ext == 'xml':
+                ext = 'ttml'
+            subtitles.setdefault(cc.get('lang'), []).append({
+                'url': cc_url,
+                'ext': ext,
+            })
+
+        thumbnails = []
+        for thumbnail in video_data.get('thumbnails', {}).get('thumbnail', []):
+            thumbnail_url = thumbnail.get('value')
+            if not thumbnail_url:
+                continue
+            thumbnails.append({
+                'url': thumbnail_url,
+                'width': int_or_none(thumbnail.get('width')),
+                'height': int_or_none(thumbnail.get('height')),
+            })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': video_data.get('longdescription') or video_data.get('description'),
+            'duration': int_or_none(video_data.get('duration', {}).get('value'), 1000),
+            'age_limit': parse_age_limit(video_data.get('tvrating', {}).get('rating')),
+            'episode_number': int_or_none(video_data.get('episodenumber')),
+            'series': video_data.get('show', {}).get('title'),
+            'season_number': int_or_none(video_data.get('season', {}).get('num')),
+            'thumbnails': thumbnails,
+            'formats': formats,
+            'subtitles': subtitles,
+        }

youtube_dl/extractor/goldenmoustache.py

@@ -1,48 +0,0 @@
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-
-
-class GoldenMoustacheIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?goldenmoustache\.com/(?P<display_id>[\w-]+)-(?P<id>\d+)'
-    _TESTS = [{
-        'url': 'http://www.goldenmoustache.com/suricate-le-poker-3700/',
-        'md5': '0f904432fa07da5054d6c8beb5efb51a',
-        'info_dict': {
-            'id': '3700',
-            'ext': 'mp4',
-            'title': 'Suricate - Le Poker',
-            'description': 'md5:3d1f242f44f8c8cb0a106f1fd08e5dc9',
-            'thumbnail': 're:^https?://.*\.jpg$',
-        }
-    }, {
-        'url': 'http://www.goldenmoustache.com/le-lab-tout-effacer-mc-fly-et-carlito-55249/',
-        'md5': '27f0c50fb4dd5f01dc9082fc67cd5700',
-        'info_dict': {
-            'id': '55249',
-            'ext': 'mp4',
-            'title': 'Le LAB - Tout Effacer (Mc Fly et Carlito)',
-            'description': 'md5:9b7fbf11023fb2250bd4b185e3de3b2a',
-            'thumbnail': 're:^https?://.*\.(?:png|jpg)$',
-        }
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-
-        video_url = self._html_search_regex(
-            r'data-src-type="mp4" data-src="([^"]+)"', webpage, 'video URL')
-        title = self._html_search_regex(
-            r'<title>(.*?)(?: - Golden Moustache)?</title>', webpage, 'title')
-        thumbnail = self._og_search_thumbnail(webpage)
-        description = self._og_search_description(webpage)
-
-        return {
-            'id': video_id,
-            'url': video_url,
-            'ext': 'mp4',
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-        }

youtube_dl/extractor/hgtv.py

@@ -0,0 +1,79 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    js_to_json,
+    smuggle_url,
+)
+
+
+class HGTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?hgtv\.ca/[^/]+/video/(?P<id>[^/]+)/video.html'
+    _TEST = {
+        'url': 'http://www.hgtv.ca/homefree/video/overnight-success/video.html?v=738081859718&p=1&s=da#video',
+        'md5': '',
+        'info_dict': {
+            'id': 'aFH__I_5FBOX',
+            'ext': 'mp4',
+            'title': 'Overnight Success',
+            'description': 'After weeks of hard work, high stakes, breakdowns and pep talks, the final 2 contestants compete to win the ultimate dream.',
+            'uploader': 'SHWM-NEW',
+            'timestamp': 1470320034,
+            'upload_date': '20160804',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        embed_vars = self._parse_json(self._search_regex(
+            r'(?s)embed_vars\s*=\s*({.*?});',
+            webpage, 'embed vars'), display_id, js_to_json)
+        return {
+            '_type': 'url_transparent',
+            'url': smuggle_url(
+                'http://link.theplatform.com/s/dtjsEC/%s?mbr=true&manifest=m3u' % embed_vars['pid'], {
+                    'force_smil_url': True
+                }),
+            'series': embed_vars.get('show'),
+            'season_number': int_or_none(embed_vars.get('season')),
+            'episode_number': int_or_none(embed_vars.get('episode')),
+            'ie_key': 'ThePlatform',
+        }
+
+
+class HGTVComShowIE(InfoExtractor):
+    IE_NAME = 'hgtv.com:show'
+    _VALID_URL = r'https?://(?:www\.)?hgtv\.com/shows/[^/]+/(?P<id>[^/?#&]+)'
+    _TEST = {
+        'url': 'http://www.hgtv.com/shows/flip-or-flop/flip-or-flop-full-episodes-videos',
+        'info_dict': {
+            'id': 'flip-or-flop-full-episodes-videos',
+            'title': 'Flip or Flop Full Episodes',
+        },
+        'playlist_mincount': 15,
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        config = self._parse_json(
+            self._search_regex(
+                r'(?s)data-module=["\']video["\'][^>]*>.*?<script[^>]+type=["\']text/x-config["\'][^>]*>(.+?)</script',
+                webpage, 'video config'),
+            display_id)['channels'][0]
+
+        entries = [
+            self.url_result(video['releaseUrl'])
+            for video in config['videos'] if video.get('releaseUrl')]
+
+        return self.playlist_result(
+            entries, display_id, config.get('title'), config.get('description'))

youtube_dl/extractor/imdb.py

@@ -6,6 +6,7 @@ from .common import InfoExtractor
 from ..utils import (
     mimetype2ext,
     qualities,
+    remove_end,
 )
 
 
@@ -19,7 +20,7 @@ class ImdbIE(InfoExtractor):
         'info_dict': {
             'id': '2524815897',
             'ext': 'mp4',
-            'title': 'Ice Age: Continental Drift Trailer (No. 2) - IMDb',
+            'title': 'Ice Age: Continental Drift Trailer (No. 2)',
             'description': 'md5:9061c2219254e5d14e03c25c98e96a81',
         }
     }, {
@@ -83,10 +84,10 @@ class ImdbIE(InfoExtractor):
 
         return {
             'id': video_id,
-            'title': self._og_search_title(webpage),
+            'title': remove_end(self._og_search_title(webpage), ' - IMDb'),
             'formats': formats,
             'description': descr,
-            'thumbnail': format_info['slate'],
+            'thumbnail': format_info.get('slate'),
         }
 
 

youtube_dl/extractor/imgur.py

@@ -50,12 +50,10 @@ class ImgurIE(InfoExtractor):
         webpage = self._download_webpage(
             compat_urlparse.urljoin(url, video_id), video_id)
 
-        width = int_or_none(self._search_regex(
-            r'<param name="width" value="([0-9]+)"',
-            webpage, 'width', fatal=False))
-        height = int_or_none(self._search_regex(
-            r'<param name="height" value="([0-9]+)"',
-            webpage, 'height', fatal=False))
+        width = int_or_none(self._og_search_property(
+            'video:width', webpage, default=None))
+        height = int_or_none(self._og_search_property(
+            'video:height', webpage, default=None))
 
         video_elements = self._search_regex(
             r'(?s)<div class="video-elements">(.*?)</div>',

youtube_dl/extractor/ivi.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
@@ -8,7 +8,7 @@ from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     int_or_none,
-    sanitized_Request,
+    qualities,
 )
 
 
@@ -49,11 +49,27 @@ class IviIE(InfoExtractor):
                 'thumbnail': 're:^https?://.*\.jpg$',
             },
             'skip': 'Only works from Russia',
+        },
+        {
+            # with MP4-HD720 format
+            'url': 'http://www.ivi.ru/watch/146500',
+            'md5': 'd63d35cdbfa1ea61a5eafec7cc523e1e',
+            'info_dict': {
+                'id': '146500',
+                'ext': 'mp4',
+                'title': 'Кукла',
+                'description': 'md5:ffca9372399976a2d260a407cc74cce6',
+                'duration': 5599,
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+            'skip': 'Only works from Russia',
         }
     ]
 
     # Sorted by quality
-    _KNOWN_FORMATS = ['MP4-low-mobile', 'MP4-mobile', 'FLV-lo', 'MP4-lo', 'FLV-hi', 'MP4-hi', 'MP4-SHQ']
+    _KNOWN_FORMATS = (
+        'MP4-low-mobile', 'MP4-mobile', 'FLV-lo', 'MP4-lo', 'FLV-hi', 'MP4-hi',
+        'MP4-SHQ', 'MP4-HD720', 'MP4-HD1080')
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -69,10 +85,9 @@ class IviIE(InfoExtractor):
             ]
         }
 
-        request = sanitized_Request(
-            'http://api.digitalaccess.ru/api/json/', json.dumps(data))
         video_json = self._download_json(
-            request, video_id, 'Downloading video JSON')
+            'http://api.digitalaccess.ru/api/json/', video_id,
+            'Downloading video JSON', data=json.dumps(data))
 
         if 'error' in video_json:
             error = video_json['error']
@@ -84,11 +99,13 @@ class IviIE(InfoExtractor):
 
         result = video_json['result']
 
+        quality = qualities(self._KNOWN_FORMATS)
+
         formats = [{
             'url': x['url'],
-            'format_id': x['content_format'],
-            'preference': self._KNOWN_FORMATS.index(x['content_format']),
-        } for x in result['files'] if x['content_format'] in self._KNOWN_FORMATS]
+            'format_id': x.get('content_format'),
+            'quality': quality(x.get('content_format')),
+        } for x in result['files'] if x.get('url')]
 
         self._sort_formats(formats)
 
@@ -115,7 +132,7 @@ class IviIE(InfoExtractor):
             webpage, 'season number', default=None))
 
         episode_number = int_or_none(self._search_regex(
-            r'<meta[^>]+itemprop="episode"[^>]*>\s*<meta[^>]+itemprop="episodeNumber"[^>]+content="(\d+)',
+            r'[^>]+itemprop="episode"[^>]*>\s*<meta[^>]+itemprop="episodeNumber"[^>]+content="(\d+)',
             webpage, 'episode number', default=None))
 
         description = self._og_search_description(webpage, default=None) or self._html_search_meta(

youtube_dl/extractor/jwplatform.py

@@ -30,7 +30,7 @@ class JWPlatformBaseIE(InfoExtractor):
         return self._parse_jwplayer_data(
             jwplayer_data, video_id, *args, **kwargs)
 
-    def _parse_jwplayer_data(self, jwplayer_data, video_id, require_title=True, m3u8_id=None, rtmp_params=None, base_url=None):
+    def _parse_jwplayer_data(self, jwplayer_data, video_id=None, require_title=True, m3u8_id=None, rtmp_params=None, base_url=None):
         # JWPlayer backward compatibility: flattened playlists
         # https://github.com/jwplayer/jwplayer/blob/v7.4.3/src/js/api/config.js#L81-L96
         if 'playlist' not in jwplayer_data:
@@ -43,6 +43,8 @@ class JWPlatformBaseIE(InfoExtractor):
             if 'sources' not in video_data:
                 video_data['sources'] = [video_data]
 
+            this_video_id = video_id or video_data['mediaid']
+
             formats = []
             for source in video_data['sources']:
                 source_url = self._proto_relative_url(source['file'])
@@ -52,7 +54,7 @@ class JWPlatformBaseIE(InfoExtractor):
                 ext = mimetype2ext(source_type) or determine_ext(source_url)
                 if source_type == 'hls' or ext == 'm3u8':
                     formats.extend(self._extract_m3u8_formats(
-                        source_url, video_id, 'mp4', 'm3u8_native', m3u8_id=m3u8_id, fatal=False))
+                        source_url, this_video_id, 'mp4', 'm3u8_native', m3u8_id=m3u8_id, fatal=False))
                 # https://github.com/jwplayer/jwplayer/blob/master/src/js/providers/default.js#L67
                 elif source_type.startswith('audio') or ext in ('oga', 'aac', 'mp3', 'mpeg', 'vorbis'):
                     formats.append({
@@ -68,7 +70,7 @@ class JWPlatformBaseIE(InfoExtractor):
                         'ext': ext,
                     }
                     if source_url.startswith('rtmp'):
-                        a_format['ext'] = 'flv',
+                        a_format['ext'] = 'flv'
 
                         # See com/longtailvideo/jwplayer/media/RTMPMediaProvider.as
                         # of jwplayer.flash.swf
@@ -95,7 +97,7 @@ class JWPlatformBaseIE(InfoExtractor):
                         })
 
             entries.append({
-                'id': video_id,
+                'id': this_video_id,
                 'title': video_data['title'] if require_title else video_data.get('title'),
                 'description': video_data.get('description'),
                 'thumbnail': self._proto_relative_url(video_data.get('image')),

youtube_dl/extractor/kaltura.py

@@ -36,6 +36,12 @@ class KalturaIE(InfoExtractor):
                 '''
     _SERVICE_URL = 'http://cdnapi.kaltura.com'
     _SERVICE_BASE = '/api_v3/index.php'
+    # See https://github.com/kaltura/server/blob/master/plugins/content/caption/base/lib/model/enums/CaptionType.php
+    _CAPTION_TYPES = {
+        1: 'srt',
+        2: 'ttml',
+        3: 'vtt',
+    }
     _TESTS = [
         {
             'url': 'kaltura:269692:1_1jc2y3e4',
@@ -67,6 +73,27 @@ class KalturaIE(InfoExtractor):
             # video with subtitles
             'url': 'kaltura:111032:1_cw786r8q',
             'only_matching': True,
+        },
+        {
+            # video with ttml subtitles (no fileExt)
+            'url': 'kaltura:1926081:0_l5ye1133',
+            'info_dict': {
+                'id': '0_l5ye1133',
+                'ext': 'mp4',
+                'title': 'What Can You Do With Python?',
+                'upload_date': '20160221',
+                'uploader_id': 'stork',
+                'thumbnail': 're:^https?://.*/thumbnail/.*',
+                'timestamp': int,
+                'subtitles': {
+                    'en': [{
+                        'ext': 'ttml',
+                    }],
+                },
+            },
+            'params': {
+                'skip_download': True,
+            },
         }
     ]
 
@@ -122,18 +149,6 @@ class KalturaIE(InfoExtractor):
 
         return data
 
-    def _get_kaltura_signature(self, video_id, partner_id, service_url=None):
-        actions = [{
-            'apiVersion': '3.1',
-            'expiry': 86400,
-            'format': 1,
-            'service': 'session',
-            'action': 'startWidgetSession',
-            'widgetId': '_%s' % partner_id,
-        }]
-        return self._kaltura_api_call(
-            video_id, actions, service_url, note='Downloading Kaltura signature')['ks']
-
     def _get_video_info(self, video_id, partner_id, service_url=None):
         actions = [
             {
@@ -208,6 +223,17 @@ class KalturaIE(InfoExtractor):
                     reference_id)['entryResult']
                 info, flavor_assets = entry_data['meta'], entry_data['contextData']['flavorAssets']
                 entry_id = info['id']
+                # Unfortunately, data returned in kalturaIframePackageData lacks
+                # captions so we will try requesting the complete data using
+                # regular approach since we now know the entry_id
+                try:
+                    _, info, flavor_assets, captions = self._get_video_info(
+                        entry_id, partner_id)
+                except ExtractorError:
+                    # Regular scenario failed but we already have everything
+                    # extracted apart from captions and can process at least
+                    # with this
+                    pass
             else:
                 raise ExtractorError('Invalid URL', expected=True)
             ks = params.get('flashvars[ks]', [None])[0]
@@ -265,9 +291,12 @@ class KalturaIE(InfoExtractor):
                 # Continue if caption is not ready
                 if f.get('status') != 2:
                     continue
+                if not caption.get('id'):
+                    continue
+                caption_format = int_or_none(caption.get('format'))
                 subtitles.setdefault(caption.get('languageCode') or caption.get('language'), []).append({
                     'url': '%s/api_v3/service/caption_captionasset/action/serve/captionAssetId/%s' % (self._SERVICE_URL, caption['id']),
-                    'ext': caption.get('fileExt'),
+                    'ext': caption.get('fileExt') or self._CAPTION_TYPES.get(caption_format) or 'ttml',
                 })
 
         return {

youtube_dl/extractor/keezmovies.py

@@ -3,64 +3,126 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..aes import aes_decrypt_text
+from ..compat import (
+    compat_str,
+    compat_urllib_parse_unquote,
+)
 from ..utils import (
-    sanitized_Request,
-    url_basename,
+    determine_ext,
+    ExtractorError,
+    int_or_none,
+    str_to_int,
+    strip_or_none,
 )
 
 
 class KeezMoviesIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/.+?(?P<id>[0-9]+)(?:[/?&]|$)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/(?:(?P<display_id>[^/]+)-)?(?P<id>\d+)'
+    _TESTS = [{
         'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711',
         'md5': '1c1e75d22ffa53320f45eeb07bc4cdc0',
         'info_dict': {
             'id': '1214711',
+            'display_id': 'petite-asian-lady-mai-playing-in-bathtub',
             'ext': 'mp4',
             'title': 'Petite Asian Lady Mai Playing In Bathtub',
-            'age_limit': 18,
             'thumbnail': 're:^https?://.*\.jpg$',
+            'view_count': int,
+            'age_limit': 18,
         }
-    }
+    }, {
+        'url': 'http://www.keezmovies.com/video/1214711',
+        'only_matching': True,
+    }]
 
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
+    def _extract_info(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = (mobj.group('display_id')
+                      if 'display_id' in mobj.groupdict()
+                      else None) or mobj.group('id')
 
-        req = sanitized_Request(url)
-        req.add_header('Cookie', 'age_verified=1')
-        webpage = self._download_webpage(req, video_id)
-
-        # embedded video
-        mobj = re.search(r'href="([^"]+)"></iframe>', webpage)
-        if mobj:
-            embedded_url = mobj.group(1)
-            return self.url_result(embedded_url)
-
-        video_title = self._html_search_regex(
-            r'<h1 [^>]*>([^<]+)', webpage, 'title')
-        flashvars = self._parse_json(self._search_regex(
-            r'var\s+flashvars\s*=\s*([^;]+);', webpage, 'flashvars'), video_id)
+        webpage = self._download_webpage(
+            url, display_id, headers={'Cookie': 'age_verified=1'})
 
         formats = []
-        for height in (180, 240, 480):
-            if flashvars.get('quality_%dp' % height):
-                video_url = flashvars['quality_%dp' % height]
-                a_format = {
-                    'url': video_url,
-                    'height': height,
-                    'format_id': '%dp' % height,
-                }
-                filename_parts = url_basename(video_url).split('_')
-                if len(filename_parts) >= 2 and re.match(r'\d+[Kk]', filename_parts[1]):
-                    a_format['tbr'] = int(filename_parts[1][:-1])
-                formats.append(a_format)
+        format_urls = set()
 
-        age_limit = self._rta_search(webpage)
+        title = None
+        thumbnail = None
+        duration = None
+        encrypted = False
 
-        return {
+        def extract_format(format_url, height=None):
+            if not isinstance(format_url, compat_str) or not format_url.startswith('http'):
+                return
+            if format_url in format_urls:
+                return
+            format_urls.add(format_url)
+            tbr = int_or_none(self._search_regex(
+                r'[/_](\d+)[kK][/_]', format_url, 'tbr', default=None))
+            if not height:
+                height = int_or_none(self._search_regex(
+                    r'[/_](\d+)[pP][/_]', format_url, 'height', default=None))
+            if encrypted:
+                format_url = aes_decrypt_text(
+                    video_url, title, 32).decode('utf-8')
+            formats.append({
+                'url': format_url,
+                'format_id': '%dp' % height if height else None,
+                'height': height,
+                'tbr': tbr,
+            })
+
+        flashvars = self._parse_json(
+            self._search_regex(
+                r'flashvars\s*=\s*({.+?});', webpage,
+                'flashvars', default='{}'),
+            display_id, fatal=False)
+
+        if flashvars:
+            title = flashvars.get('video_title')
+            thumbnail = flashvars.get('image_url')
+            duration = int_or_none(flashvars.get('video_duration'))
+            encrypted = flashvars.get('encrypted') is True
+            for key, value in flashvars.items():
+                mobj = re.search(r'quality_(\d+)[pP]', key)
+                if mobj:
+                    extract_format(value, int(mobj.group(1)))
+            video_url = flashvars.get('video_url')
+            if video_url and determine_ext(video_url, None):
+                extract_format(video_url)
+
+        video_url = self._html_search_regex(
+            r'flashvars\.video_url\s*=\s*(["\'])(?P<url>http.+?)\1',
+            webpage, 'video url', default=None, group='url')
+        if video_url:
+            extract_format(compat_urllib_parse_unquote(video_url))
+
+        if not formats:
+            if 'title="This video is no longer available"' in webpage:
+                raise ExtractorError(
+                    'Video %s is no longer available' % video_id, expected=True)
+
+        self._sort_formats(formats)
+
+        if not title:
+            title = self._html_search_regex(
+                r'<h1[^>]*>([^<]+)', webpage, 'title')
+
+        return webpage, {
             'id': video_id,
-            'title': video_title,
+            'display_id': display_id,
+            'title': strip_or_none(title),
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'age_limit': 18,
             'formats': formats,
-            'age_limit': age_limit,
-            'thumbnail': flashvars.get('image_url')
         }
+
+    def _real_extract(self, url):
+        webpage, info = self._extract_info(url)
+        info['view_count'] = str_to_int(self._search_regex(
+            r'<b>([\d,.]+)</b> Views?', webpage, 'view count', fatal=False))
+        return info

youtube_dl/extractor/kickstarter.py

@@ -37,7 +37,6 @@ class KickStarterIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Power Drive 2000',
         },
-        'expected_warnings': ['OpenGraph description'],
     }]
 
     def _real_extract(self, url):
@@ -67,6 +66,6 @@ class KickStarterIE(InfoExtractor):
             'id': video_id,
             'url': video_url,
             'title': title,
-            'description': self._og_search_description(webpage),
+            'description': self._og_search_description(webpage, default=None),
             'thumbnail': thumbnail,
         }

youtube_dl/extractor/kusi.py

@@ -18,31 +18,20 @@ from ..utils import (
 class KUSIIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?kusi\.com/(?P<path>story/.+|video\?clipId=(?P<clipId>\d+))'
     _TESTS = [{
-        'url': 'http://www.kusi.com/story/31183873/turko-files-case-closed-put-on-hold',
-        'md5': 'f926e7684294cf8cb7bdf8858e1b3988',
+        'url': 'http://www.kusi.com/story/32849881/turko-files-refused-to-help-it-aint-right',
+        'md5': '4e76ce8e53660ce9697d06c0ba6fc47d',
         'info_dict': {
-            'id': '12203019',
+            'id': '12689020',
             'ext': 'mp4',
-            'title': 'Turko Files: Case Closed! & Put On Hold!',
-            'duration': 231.0,
-            'upload_date': '20160210',
-            'timestamp': 1455087571,
+            'title': "Turko Files: Refused to Help, It Ain't Right!",
+            'duration': 223.586,
+            'upload_date': '20160826',
+            'timestamp': 1472233118,
             'thumbnail': 're:^https?://.*\.jpg$'
         },
     }, {
         'url': 'http://kusi.com/video?clipId=12203019',
-        'info_dict': {
-            'id': '12203019',
-            'ext': 'mp4',
-            'title': 'Turko Files: Case Closed! & Put On Hold!',
-            'duration': 231.0,
-            'upload_date': '20160210',
-            'timestamp': 1455087571,
-            'thumbnail': 're:^https?://.*\.jpg$'
-        },
-        'params': {
-            'skip_download': True,  # Same as previous one
-        },
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/kuwo.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_urlparse
 from ..utils import (
     get_element_by_id,
     clean_html,
@@ -242,8 +243,9 @@ class KuwoSingerIE(InfoExtractor):
                 query={'artistId': artist_id, 'pn': page_num, 'rn': self.PAGE_SIZE})
 
             return [
-                self.url_result(song_url, 'Kuwo') for song_url in re.findall(
-                    r'<div[^>]+class="name"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)',
+                self.url_result(compat_urlparse.urljoin(url, song_url), 'Kuwo')
+                for song_url in re.findall(
+                    r'<div[^>]+class="name"><a[^>]+href="(/yinyue/\d+)',
                     webpage)
             ]
 

youtube_dl/extractor/lifenews.py

@@ -4,7 +4,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urlparse
+from ..compat import (
+    compat_str,
+    compat_urlparse,
+)
 from ..utils import (
     determine_ext,
     ExtractorError,
@@ -96,7 +99,7 @@ class LifeNewsIE(InfoExtractor):
             r'<video[^>]+><source[^>]+src=["\'](.+?)["\']', webpage)
 
         iframe_links = re.findall(
-            r'<iframe[^>]+src=["\']((?:https?:)?//embed\.life\.ru/embed/.+?)["\']',
+            r'<iframe[^>]+src=["\']((?:https?:)?//embed\.life\.ru/(?:embed|video)/.+?)["\']',
             webpage)
 
         if not video_urls and not iframe_links:
@@ -164,9 +167,9 @@ class LifeNewsIE(InfoExtractor):
 
 class LifeEmbedIE(InfoExtractor):
     IE_NAME = 'life:embed'
-    _VALID_URL = r'https?://embed\.life\.ru/embed/(?P<id>[\da-f]{32})'
+    _VALID_URL = r'https?://embed\.life\.ru/(?:embed|video)/(?P<id>[\da-f]{32})'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://embed.life.ru/embed/e50c2dec2867350528e2574c899b8291',
         'md5': 'b889715c9e49cb1981281d0e5458fbbe',
         'info_dict': {
@@ -175,30 +178,57 @@ class LifeEmbedIE(InfoExtractor):
             'title': 'e50c2dec2867350528e2574c899b8291',
             'thumbnail': 're:http://.*\.jpg',
         }
-    }
+    }, {
+        # with 1080p
+        'url': 'https://embed.life.ru/video/e50c2dec2867350528e2574c899b8291',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
 
+        thumbnail = None
         formats = []
-        for video_url in re.findall(r'"file"\s*:\s*"([^"]+)', webpage):
-            video_url = compat_urlparse.urljoin(url, video_url)
-            ext = determine_ext(video_url)
-            if ext == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(
-                    video_url, video_id, 'mp4',
-                    entry_protocol='m3u8_native', m3u8_id='m3u8'))
-            else:
-                formats.append({
-                    'url': video_url,
-                    'format_id': ext,
-                    'preference': 1,
-                })
+
+        def extract_m3u8(manifest_url):
+            formats.extend(self._extract_m3u8_formats(
+                manifest_url, video_id, 'mp4',
+                entry_protocol='m3u8_native', m3u8_id='m3u8'))
+
+        def extract_original(original_url):
+            formats.append({
+                'url': original_url,
+                'format_id': determine_ext(original_url, None),
+                'preference': 1,
+            })
+
+        playlist = self._parse_json(
+            self._search_regex(
+                r'options\s*=\s*({.+?});', webpage, 'options', default='{}'),
+            video_id).get('playlist', {})
+        if playlist:
+            master = playlist.get('master')
+            if isinstance(master, compat_str) and determine_ext(master) == 'm3u8':
+                extract_m3u8(compat_urlparse.urljoin(url, master))
+            original = playlist.get('original')
+            if isinstance(original, compat_str):
+                extract_original(original)
+            thumbnail = playlist.get('image')
+
+        # Old rendition fallback
+        if not formats:
+            for video_url in re.findall(r'"file"\s*:\s*"([^"]+)', webpage):
+                video_url = compat_urlparse.urljoin(url, video_url)
+                if determine_ext(video_url) == 'm3u8':
+                    extract_m3u8(video_url)
+                else:
+                    extract_original(video_url)
+
         self._sort_formats(formats)
 
-        thumbnail = self._search_regex(
+        thumbnail = thumbnail or self._search_regex(
             r'"image"\s*:\s*"([^"]+)', webpage, 'thumbnail', default=None)
 
         return {

youtube_dl/extractor/limelight.py

@@ -34,11 +34,12 @@ class LimelightBaseIE(InfoExtractor):
     def _extract_info(self, streams, mobile_urls, properties):
         video_id = properties['media_id']
         formats = []
-
+        urls = []
         for stream in streams:
             stream_url = stream.get('url')
-            if not stream_url or stream.get('drmProtected'):
+            if not stream_url or stream.get('drmProtected') or stream_url in urls:
                 continue
+            urls.append(stream_url)
             ext = determine_ext(stream_url)
             if ext == 'f4m':
                 formats.extend(self._extract_f4m_formats(
@@ -58,9 +59,11 @@ class LimelightBaseIE(InfoExtractor):
                     format_id = 'rtmp'
                     if stream.get('videoBitRate'):
                         format_id += '-%d' % int_or_none(stream['videoBitRate'])
+                    http_url = 'http://%s/%s' % (rtmp.group('host').replace('csl.', 'cpl.'), rtmp.group('playpath')[4:])
+                    urls.append(http_url)
                     http_fmt = fmt.copy()
                     http_fmt.update({
-                        'url': 'http://%s/%s' % (rtmp.group('host').replace('csl.', 'cpl.'), rtmp.group('playpath')[4:]),
+                        'url': http_url,
                         'format_id': format_id.replace('rtmp', 'http'),
                     })
                     formats.append(http_fmt)
@@ -76,8 +79,9 @@ class LimelightBaseIE(InfoExtractor):
         for mobile_url in mobile_urls:
             media_url = mobile_url.get('mobileUrl')
             format_id = mobile_url.get('targetMediaPlatform')
-            if not media_url or format_id == 'Widevine':
+            if not media_url or format_id in ('Widevine', 'SmoothStreaming') or media_url in urls:
                 continue
+            urls.append(media_url)
             ext = determine_ext(media_url)
             if ext == 'm3u8':
                 formats.extend(self._extract_m3u8_formats(

youtube_dl/extractor/litv.py

@@ -14,7 +14,7 @@ from ..utils import (
 
 
 class LiTVIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.litv\.tv/vod/[^/]+/content\.do\?.*?\bid=(?P<id>[^&]+)'
+    _VALID_URL = r'https?://www\.litv\.tv/(?:vod|promo)/[^/]+/(?:content\.do)?\?.*?\b(?:content_)?id=(?P<id>[^&]+)'
 
     _URL_TEMPLATE = 'https://www.litv.tv/vod/%s/content.do?id=%s'
 
@@ -27,6 +27,7 @@ class LiTVIE(InfoExtractor):
         'playlist_count': 50,
     }, {
         'url': 'https://www.litv.tv/vod/drama/content.do?brc_id=root&id=VOD00041610&isUHEnabled=true&autoPlay=1',
+        'md5': '969e343d9244778cb29acec608e53640',
         'info_dict': {
             'id': 'VOD00041610',
             'ext': 'mp4',
@@ -37,7 +38,16 @@ class LiTVIE(InfoExtractor):
         },
         'params': {
             'noplaylist': True,
-            'skip_download': True,  # m3u8 download
+        },
+        'skip': 'Georestricted to Taiwan',
+    }, {
+        'url': 'https://www.litv.tv/promo/miyuezhuan/?content_id=VOD00044841&',
+        'md5': '88322ea132f848d6e3e18b32a832b918',
+        'info_dict': {
+            'id': 'VOD00044841',
+            'ext': 'mp4',
+            'title': '芈月傳第1集　霸星芈月降世楚國',
+            'description': '楚威王二年，太史令唐昧夜觀星象，發現霸星即將現世。王后得知霸星的預言後，想盡辦法不讓孩子順利出生，幸得莒姬相護化解危機。沒想到眾人期待下出生的霸星卻是位公主，楚威王對此失望至極。楚王后命人將女嬰丟棄河中，居然奇蹟似的被少司命像攔下，楚威王認為此女非同凡響，為她取名芈月。',
         },
         'skip': 'Georestricted to Taiwan',
     }]
@@ -92,13 +102,18 @@ class LiTVIE(InfoExtractor):
         # endpoint gives the same result as the data embedded in the webpage.
         # If georestricted, there are no embedded data, so an extra request is
         # necessary to get the error code
+        if 'assetId' not in view_data:
+            view_data = self._download_json(
+                'https://www.litv.tv/vod/ajax/getProgramInfo', video_id,
+                query={'contentId': video_id},
+                headers={'Accept': 'application/json'})
         video_data = self._parse_json(self._search_regex(
             r'uiHlsUrl\s*=\s*testBackendData\(([^;]+)\);',
             webpage, 'video data', default='{}'), video_id)
         if not video_data:
             payload = {
                 'assetId': view_data['assetId'],
-                'watchDevices': vod_data['watchDevices'],
+                'watchDevices': view_data['watchDevices'],
                 'contentType': view_data['contentType'],
             }
             video_data = self._download_json(
@@ -115,7 +130,8 @@ class LiTVIE(InfoExtractor):
             raise ExtractorError('Unexpected result from %s' % self.IE_NAME)
 
         formats = self._extract_m3u8_formats(
-            video_data['fullpath'], video_id, ext='mp4', m3u8_id='hls')
+            video_data['fullpath'], video_id, ext='mp4',
+            entry_protocol='m3u8_native', m3u8_id='hls')
         for a_format in formats:
             # LiTV HLS segments doesn't like compressions
             a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = True

youtube_dl/extractor/miomio.py

@@ -25,10 +25,7 @@ class MioMioIE(InfoExtractor):
             'title': '【SKY】字幕 铠武昭和VS平成 假面骑士大战FEAT战队 魔星字幕组 字幕',
             'duration': 5923,
         },
-        'params': {
-            # The server provides broken file
-            'skip_download': True,
-        }
+        'skip': 'Unable to load videos',
     }, {
         'url': 'http://www.miomio.tv/watch/cc184024/',
         'info_dict': {
@@ -47,16 +44,12 @@ class MioMioIE(InfoExtractor):
         'skip': 'Unable to load videos',
     }, {
         # new 'h5' player
-        'url': 'http://www.miomio.tv/watch/cc273295/',
-        'md5': '',
+        'url': 'http://www.miomio.tv/watch/cc273997/',
+        'md5': '0b27a4b4495055d826813f8c3a6b2070',
         'info_dict': {
-            'id': '273295',
+            'id': '273997',
             'ext': 'mp4',
-            'title': 'アウト×デラックス 20160526',
-        },
-        'params': {
-            # intermittent HTTP 500
-            'skip_download': True,
+            'title': 'マツコの知らない世界【劇的進化SP！ビニール傘＆冷凍食品2016】 1_2 - 16 05 31',
         },
     }]
 
@@ -116,7 +109,7 @@ class MioMioIE(InfoExtractor):
             player_webpage = self._download_webpage(
                 player_url, video_id,
                 note='Downloading player webpage', headers={'Referer': url})
-            entries = self._parse_html5_media_entries(player_url, player_webpage)
+            entries = self._parse_html5_media_entries(player_url, player_webpage, video_id)
             http_headers = {'Referer': player_url}
         else:
             http_headers = {'Referer': 'http://www.miomio.tv%s' % mioplayer_path}

youtube_dl/extractor/mofosex.py

@@ -1,53 +1,56 @@
 from __future__ import unicode_literals
 
-import os
-import re
-
-from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse_unquote,
-    compat_urllib_parse_urlparse,
+from ..utils import (
+    int_or_none,
+    str_to_int,
+    unified_strdate,
 )
-from ..utils import sanitized_Request
+from .keezmovies import KeezMoviesIE
 
 
-class MofosexIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?(?P<url>mofosex\.com/videos/(?P<id>[0-9]+)/.*?\.html)'
-    _TEST = {
-        'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html',
-        'md5': '1b2eb47ac33cc75d4a80e3026b613c5a',
+class MofosexIE(KeezMoviesIE):
+    _VALID_URL = r'https?://(?:www\.)?mofosex\.com/videos/(?P<id>\d+)/(?P<display_id>[^/?#&.]+)\.html'
+    _TESTS = [{
+        'url': 'http://www.mofosex.com/videos/318131/amateur-teen-playing-and-masturbating-318131.html',
+        'md5': '39a15853632b7b2e5679f92f69b78e91',
         'info_dict': {
-            'id': '5018',
+            'id': '318131',
+            'display_id': 'amateur-teen-playing-and-masturbating-318131',
             'ext': 'mp4',
-            'title': 'Japanese Teen Music Video',
+            'title': 'amateur teen playing and masturbating',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'upload_date': '20121114',
+            'view_count': int,
+            'like_count': int,
+            'dislike_count': int,
             'age_limit': 18,
         }
-    }
+    }, {
+        # This video is no longer available
+        'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        url = 'http://www.' + mobj.group('url')
+        webpage, info = self._extract_info(url)
 
-        req = sanitized_Request(url)
-        req.add_header('Cookie', 'age_verified=1')
-        webpage = self._download_webpage(req, video_id)
+        view_count = str_to_int(self._search_regex(
+            r'VIEWS:</span>\s*([\d,.]+)', webpage, 'view count', fatal=False))
+        like_count = int_or_none(self._search_regex(
+            r'id=["\']amountLikes["\'][^>]*>(\d+)', webpage,
+            'like count', fatal=False))
+        dislike_count = int_or_none(self._search_regex(
+            r'id=["\']amountDislikes["\'][^>]*>(\d+)', webpage,
+            'like count', fatal=False))
+        upload_date = unified_strdate(self._html_search_regex(
+            r'Added:</span>([^<]+)', webpage, 'upload date', fatal=False))
 
-        video_title = self._html_search_regex(r'<h1>(.+?)<', webpage, 'title')
-        video_url = compat_urllib_parse_unquote(self._html_search_regex(r'flashvars.video_url = \'([^\']+)', webpage, 'video_url'))
-        path = compat_urllib_parse_urlparse(video_url).path
-        extension = os.path.splitext(path)[1][1:]
-        format = path.split('/')[5].split('_')[:2]
-        format = '-'.join(format)
+        info.update({
+            'view_count': view_count,
+            'like_count': like_count,
+            'dislike_count': dislike_count,
+            'upload_date': upload_date,
+            'thumbnail': self._og_search_thumbnail(webpage),
+        })
 
-        age_limit = self._rta_search(webpage)
-
-        return {
-            'id': video_id,
-            'title': video_title,
-            'url': video_url,
-            'ext': extension,
-            'format': format,
-            'format_id': format,
-            'age_limit': age_limit,
-        }
+        return info

youtube_dl/extractor/movingimage.py

@@ -7,22 +7,19 @@ from ..utils import (
 )
 
 
-class SSAIE(InfoExtractor):
-    _VALID_URL = r'https?://ssa\.nls\.uk/film/(?P<id>\d+)'
+class MovingImageIE(InfoExtractor):
+    _VALID_URL = r'https?://movingimage\.nls\.uk/film/(?P<id>\d+)'
     _TEST = {
-        'url': 'http://ssa.nls.uk/film/3561',
+        'url': 'http://movingimage.nls.uk/film/3561',
+        'md5': '4caa05c2b38453e6f862197571a7be2f',
         'info_dict': {
             'id': '3561',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'SHETLAND WOOL',
             'description': 'md5:c5afca6871ad59b4271e7704fe50ab04',
             'duration': 900,
             'thumbnail': 're:^https?://.*\.jpg$',
         },
-        'params': {
-            # rtmp download
-            'skip_download': True,
-        },
     }
 
     def _real_extract(self, url):
@@ -30,10 +27,9 @@ class SSAIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
-        streamer = self._search_regex(
-            r"'streamer'\s*,\S*'(rtmp[^']+)'", webpage, 'streamer')
-        play_path = self._search_regex(
-            r"'file'\s*,\s*'([^']+)'", webpage, 'file').rpartition('.')[0]
+        formats = self._extract_m3u8_formats(
+            self._html_search_regex(r'file\s*:\s*"([^"]+)"', webpage, 'm3u8 manifest URL'),
+            video_id, ext='mp4', entry_protocol='m3u8_native')
 
         def search_field(field_name, fatal=False):
             return self._search_regex(
@@ -44,13 +40,11 @@ class SSAIE(InfoExtractor):
         description = unescapeHTML(search_field('Description'))
         duration = parse_duration(search_field('Running time'))
         thumbnail = self._search_regex(
-            r"'image'\s*,\s*'([^']+)'", webpage, 'thumbnails', fatal=False)
+            r"image\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False)
 
         return {
             'id': video_id,
-            'url': streamer,
-            'play_path': play_path,
-            'ext': 'flv',
+            'formats': formats,
             'title': title,
             'description': description,
             'duration': duration,

youtube_dl/extractor/mtv.py

@@ -4,7 +4,6 @@ import re
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_urllib_parse_urlencode,
     compat_str,
     compat_xpath,
 )
@@ -14,12 +13,13 @@ from ..utils import (
     fix_xml_ampersands,
     float_or_none,
     HEADRequest,
+    RegexNotFoundError,
     sanitized_Request,
     strip_or_none,
     timeconvert,
     unescapeHTML,
+    update_url_query,
     url_basename,
-    RegexNotFoundError,
     xpath_text,
 )
 
@@ -36,6 +36,11 @@ class MTVServicesInfoExtractor(InfoExtractor):
     def _id_from_uri(uri):
         return uri.split(':')[-1]
 
+    @staticmethod
+    def _remove_template_parameter(url):
+        # Remove the templates, like &device={device}
+        return re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', url)
+
     # This was originally implemented for ComedyCentral, but it also works here
     @classmethod
     def _transform_rtmp_url(cls, rtmp_video_url):
@@ -117,9 +122,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
         video_id = self._id_from_uri(uri)
         self.report_extraction(video_id)
         content_el = itemdoc.find('%s/%s' % (_media_xml_tag('group'), _media_xml_tag('content')))
-        mediagen_url = content_el.attrib['url']
-        # Remove the templates, like &device={device}
-        mediagen_url = re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', mediagen_url)
+        mediagen_url = self._remove_template_parameter(content_el.attrib['url'])
         if 'acceptMethods' not in mediagen_url:
             mediagen_url += '&' if '?' in mediagen_url else '?'
             mediagen_url += 'acceptMethods=fms'
@@ -178,12 +181,12 @@ class MTVServicesInfoExtractor(InfoExtractor):
         data = {'uri': uri}
         if self._LANG:
             data['lang'] = self._LANG
-        return compat_urllib_parse_urlencode(data)
+        return data
 
     def _get_videos_info(self, uri):
         video_id = self._id_from_uri(uri)
         feed_url = self._get_feed_url(uri)
-        info_url = feed_url + '?' + self._get_feed_query(uri)
+        info_url = update_url_query(feed_url, self._get_feed_query(uri))
         return self._get_videos_info_from_url(info_url, video_id)
 
     def _get_videos_info_from_url(self, url, video_id):
@@ -256,13 +259,9 @@ class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):
 
     def _get_feed_url(self, uri):
         video_id = self._id_from_uri(uri)
-        site_id = uri.replace(video_id, '')
-        config_url = ('http://media.mtvnservices.com/pmt/e1/players/{0}/'
-                      'context4/context5/config.xml'.format(site_id))
-        config_doc = self._download_xml(config_url, video_id)
-        feed_node = config_doc.find('.//feed')
-        feed_url = feed_node.text.strip().split('?')[0]
-        return feed_url
+        config = self._download_json(
+            'http://media.mtvnservices.com/pmt/e1/access/index.html?uri=%s&configtype=edge' % uri, video_id)
+        return self._remove_template_parameter(config['feedWithQueryParams'])
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/muenchentv.py

@@ -36,7 +36,7 @@ class MuenchenTVIE(InfoExtractor):
         title = self._live_title(self._og_search_title(webpage))
 
         data_js = self._search_regex(
-            r'(?s)\nplaylist:\s*(\[.*?}\]),related:',
+            r'(?s)\nplaylist:\s*(\[.*?}\]),',
             webpage, 'playlist configuration')
         data_json = js_to_json(data_js)
         data = json.loads(data_json)[0]

youtube_dl/extractor/myvidster.py

@@ -13,7 +13,7 @@ class MyVidsterIE(InfoExtractor):
             'id': '3685814',
             'title': 'md5:7d8427d6d02c4fbcef50fe269980c749',
             'upload_date': '20141027',
-            'uploader_id': 'utkualp',
+            'uploader': 'utkualp',
             'ext': 'mp4',
             'age_limit': 18,
         },

youtube_dl/extractor/nationalgeographic.py

@@ -3,7 +3,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from .theplatform import ThePlatformIE
+from .adobepass import AdobePassIE
 from ..utils import (
     smuggle_url,
     url_basename,
@@ -65,7 +65,7 @@ class NationalGeographicVideoIE(InfoExtractor):
         }
 
 
-class NationalGeographicIE(ThePlatformIE):
+class NationalGeographicIE(AdobePassIE):
     IE_NAME = 'natgeo'
     _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?[^/]+/(?:videos|episodes)/(?P<id>[^/?]+)'
 
@@ -119,7 +119,7 @@ class NationalGeographicIE(ThePlatformIE):
             auth_resource_id = self._search_regex(
                 r"video_auth_resourceId\s*=\s*'([^']+)'",
                 webpage, 'auth resource id')
-            query['auth'] = self._extract_mvpd_auth(url, display_id, 'natgeo', auth_resource_id) or ''
+            query['auth'] = self._extract_mvpd_auth(url, display_id, 'natgeo', auth_resource_id)
 
         return {
             '_type': 'url_transparent',
@@ -131,7 +131,7 @@ class NationalGeographicIE(ThePlatformIE):
         }
 
 
-class NationalGeographicEpisodeGuideIE(ThePlatformIE):
+class NationalGeographicEpisodeGuideIE(InfoExtractor):
     IE_NAME = 'natgeo:episodeguide'
     _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?(?P<id>[^/]+)/episode-guide'
     _TESTS = [

youtube_dl/extractor/nba.py

@@ -1,25 +1,20 @@
 from __future__ import unicode_literals
 
 import functools
-import os.path
 import re
 
-from .common import InfoExtractor
+from .turner import TurnerBaseIE
 from ..compat import (
     compat_urllib_parse_urlencode,
     compat_urlparse,
 )
 from ..utils import (
-    int_or_none,
     OnDemandPagedList,
-    parse_duration,
     remove_start,
-    xpath_text,
-    xpath_attr,
 )
 
 
-class NBAIE(InfoExtractor):
+class NBAIE(TurnerBaseIE):
     _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?P<path>(?:[^/]+/)+(?P<id>[^?]*?))/?(?:/index\.html)?(?:\?.*)?$'
     _TESTS = [{
         'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html',
@@ -44,28 +39,30 @@ class NBAIE(InfoExtractor):
         'url': 'http://watch.nba.com/video/channels/playoffs/2015/05/20/0041400301-cle-atl-recap.nba',
         'md5': 'b2b39b81cf28615ae0c3360a3f9668c4',
         'info_dict': {
-            'id': '0041400301-cle-atl-recap',
+            'id': 'channels/playoffs/2015/05/20/0041400301-cle-atl-recap.nba',
             'ext': 'mp4',
             'title': 'Hawks vs. Cavaliers Game 1',
             'description': 'md5:8094c3498d35a9bd6b1a8c396a071b4d',
             'duration': 228,
             'timestamp': 1432134543,
             'upload_date': '20150520',
-        }
+        },
+        'expected_warnings': ['Unable to download f4m manifest'],
     }, {
         'url': 'http://www.nba.com/clippers/news/doc-rivers-were-not-trading-blake',
         'info_dict': {
-            'id': '1455672027478-Doc_Feb16_720',
+            'id': 'teams/clippers/2016/02/17/1455672027478-Doc_Feb16_720.mov-297324',
             'ext': 'mp4',
             'title': 'Practice: Doc Rivers - 2/16/16',
             'description': 'Head Coach Doc Rivers addresses the media following practice.',
-            'upload_date': '20160217',
+            'upload_date': '20160216',
             'timestamp': 1455672000,
         },
         'params': {
             # m3u8 download
             'skip_download': True,
         },
+        'expected_warnings': ['Unable to download f4m manifest'],
     }, {
         'url': 'http://www.nba.com/timberwolves/wiggins-shootaround#',
         'info_dict': {
@@ -80,7 +77,7 @@ class NBAIE(InfoExtractor):
     }, {
         'url': 'http://www.nba.com/timberwolves/wiggins-shootaround#',
         'info_dict': {
-            'id': 'Wigginsmp4',
+            'id': 'teams/timberwolves/2014/12/12/Wigginsmp4-3462601',
             'ext': 'mp4',
             'title': 'Shootaround Access - Dec. 12 | Andrew Wiggins',
             'description': 'Wolves rookie Andrew Wiggins addresses the media after Friday\'s shootaround.',
@@ -92,6 +89,7 @@ class NBAIE(InfoExtractor):
             # m3u8 download
             'skip_download': True,
         },
+        'expected_warnings': ['Unable to download f4m manifest'],
     }]
 
     _PAGE_SIZE = 30
@@ -145,53 +143,12 @@ class NBAIE(InfoExtractor):
             if path.startswith('video/teams'):
                 path = 'video/channels/proxy/' + path[6:]
 
-        video_info = self._download_xml('http://www.nba.com/%s.xml' % path, video_id)
-        video_id = os.path.splitext(xpath_text(video_info, 'slug'))[0]
-        title = xpath_text(video_info, 'headline')
-        description = xpath_text(video_info, 'description')
-        duration = parse_duration(xpath_text(video_info, 'length'))
-        timestamp = int_or_none(xpath_attr(video_info, 'dateCreated', 'uts'))
-
-        thumbnails = []
-        for image in video_info.find('images'):
-            thumbnails.append({
-                'id': image.attrib.get('cut'),
-                'url': image.text,
-                'width': int_or_none(image.attrib.get('width')),
-                'height': int_or_none(image.attrib.get('height')),
+        return self._extract_cvp_info(
+            'http://www.nba.com/%s.xml' % path, video_id, {
+                'default': {
+                    'media_src': 'http://nba.cdn.turner.com/nba/big',
+                },
+                'm3u8': {
+                    'media_src': 'http://nbavod-f.akamaihd.net',
+                },
             })
-
-        formats = []
-        for video_file in video_info.findall('.//file'):
-            video_url = video_file.text
-            if video_url.startswith('/'):
-                continue
-            if video_url.endswith('.m3u8'):
-                formats.extend(self._extract_m3u8_formats(video_url, video_id, ext='mp4', m3u8_id='hls', fatal=False))
-            elif video_url.endswith('.f4m'):
-                formats.extend(self._extract_f4m_formats(video_url + '?hdcore=3.4.1.1', video_id, f4m_id='hds', fatal=False))
-            else:
-                key = video_file.attrib.get('bitrate')
-                format_info = {
-                    'format_id': key,
-                    'url': video_url,
-                }
-                mobj = re.search(r'(\d+)x(\d+)(?:_(\d+))?', key)
-                if mobj:
-                    format_info.update({
-                        'width': int(mobj.group(1)),
-                        'height': int(mobj.group(2)),
-                        'tbr': int_or_none(mobj.group(3)),
-                    })
-                formats.append(format_info)
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'duration': duration,
-            'timestamp': timestamp,
-            'thumbnails': thumbnails,
-            'formats': formats,
-        }

youtube_dl/extractor/nhk.py

@@ -0,0 +1,50 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class NhkVodIE(InfoExtractor):
+    _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/en/vod/(?P<id>.+?)\.html'
+    _TEST = {
+        # Videos available only for a limited period of time. Visit
+        # http://www3.nhk.or.jp/nhkworld/en/vod/ for working samples.
+        'url': 'http://www3.nhk.or.jp/nhkworld/en/vod/tokyofashion/20160815.html',
+        'info_dict': {
+            'id': 'A1bnNiNTE6nY3jLllS-BIISfcC_PpvF5',
+            'ext': 'flv',
+            'title': 'TOKYO FASHION EXPRESS - The Kimono as Global Fashion',
+            'description': 'md5:db338ee6ce8204f415b754782f819824',
+            'series': 'TOKYO FASHION EXPRESS',
+            'episode': 'The Kimono as Global Fashion',
+        },
+        'skip': 'Videos available only for a limited period of time',
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        embed_code = self._search_regex(
+            r'nw_vod_ooplayer\([^,]+,\s*(["\'])(?P<id>(?:(?!\1).)+)\1',
+            webpage, 'ooyala embed code', group='id')
+
+        title = self._search_regex(
+            r'<div[^>]+class=["\']episode-detail["\']>\s*<h\d+>([^<]+)',
+            webpage, 'title', default=None)
+        description = self._html_search_regex(
+            r'(?s)<p[^>]+class=["\']description["\'][^>]*>(.+?)</p>',
+            webpage, 'description', default=None)
+        series = self._search_regex(
+            r'<h2[^>]+class=["\']detail-top-player-title[^>]+><a[^>]+>([^<]+)',
+            webpage, 'series', default=None)
+
+        return {
+            '_type': 'url_transparent',
+            'ie_key': 'Ooyala',
+            'url': 'ooyala:%s' % embed_code,
+            'title': '%s - %s' % (series, title) if series and title else title,
+            'description': description,
+            'series': series,
+            'episode': title,
+        }

youtube_dl/extractor/nick.py

@@ -2,7 +2,6 @@
 from __future__ import unicode_literals
 
 from .mtv import MTVServicesInfoExtractor
-from ..compat import compat_urllib_parse_urlencode
 from ..utils import update_url_query
 
 
@@ -59,10 +58,10 @@ class NickIE(MTVServicesInfoExtractor):
     }]
 
     def _get_feed_query(self, uri):
-        return compat_urllib_parse_urlencode({
+        return {
             'feed': 'nick_arc_player_prime',
             'mgid': uri,
-        })
+        }
 
     def _extract_mgid(self, webpage):
         return self._search_regex(r'data-contenturi="([^"]+)', webpage, 'mgid')

youtube_dl/extractor/ninecninemedia.py

@@ -4,40 +4,36 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
     parse_iso8601,
-    parse_duration,
-    ExtractorError
+    float_or_none,
+    ExtractorError,
+    int_or_none,
 )
 
 
-class NineCNineMediaIE(InfoExtractor):
-    _VALID_URL = r'9c9media:(?P<destination_code>[^:]+):(?P<id>\d+)'
+class NineCNineMediaBaseIE(InfoExtractor):
+    _API_BASE_TEMPLATE = 'http://capi.9c9media.com/destinations/%s/platforms/desktop/contents/%s/'
+
+
+class NineCNineMediaStackIE(NineCNineMediaBaseIE):
+    IE_NAME = '9c9media:stack'
+    _VALID_URL = r'9c9media:stack:(?P<destination_code>[^:]+):(?P<content_id>\d+):(?P<content_package>\d+):(?P<id>\d+)'
 
     def _real_extract(self, url):
-        destination_code, video_id = re.match(self._VALID_URL, url).groups()
-        api_base_url = 'http://capi.9c9media.com/destinations/%s/platforms/desktop/contents/%s/' % (destination_code, video_id)
-        content = self._download_json(api_base_url, video_id, query={
-            '$include': '[contentpackages]',
-        })
-        title = content['Name']
-        if len(content['ContentPackages']) > 1:
-            raise ExtractorError('multiple content packages')
-        content_package = content['ContentPackages'][0]
-        stacks_base_url = api_base_url + 'contentpackages/%s/stacks/' % content_package['Id']
-        stacks = self._download_json(stacks_base_url, video_id)['Items']
-        if len(stacks) > 1:
-            raise ExtractorError('multiple stacks')
-        stack = stacks[0]
-        stack_base_url = '%s%s/manifest.' % (stacks_base_url, stack['Id'])
+        destination_code, content_id, package_id, stack_id = re.match(self._VALID_URL, url).groups()
+        stack_base_url_template = self._API_BASE_TEMPLATE + 'contentpackages/%s/stacks/%s/manifest.'
+        stack_base_url = stack_base_url_template % (destination_code, content_id, package_id, stack_id)
+
         formats = []
         formats.extend(self._extract_m3u8_formats(
-            stack_base_url + 'm3u8', video_id, 'mp4',
+            stack_base_url + 'm3u8', stack_id, 'mp4',
             'm3u8_native', m3u8_id='hls', fatal=False))
         formats.extend(self._extract_f4m_formats(
-            stack_base_url + 'f4m', video_id,
+            stack_base_url + 'f4m', stack_id,
             f4m_id='hds', fatal=False))
-        mp4_url = self._download_webpage(stack_base_url + 'pd', video_id, fatal=False)
+        mp4_url = self._download_webpage(stack_base_url + 'pd', stack_id, fatal=False)
         if mp4_url:
             formats.append({
                 'url': mp4_url,
@@ -46,10 +42,86 @@ class NineCNineMediaIE(InfoExtractor):
         self._sort_formats(formats)
 
         return {
-            'id': video_id,
-            'title': title,
-            'description': content.get('Desc') or content.get('ShortDesc'),
-            'timestamp': parse_iso8601(content.get('BroadcastDateTime')),
-            'duration': parse_duration(content.get('BroadcastTime')),
+            'id': stack_id,
             'formats': formats,
         }
+
+
+class NineCNineMediaIE(NineCNineMediaBaseIE):
+    IE_NAME = '9c9media'
+    _VALID_URL = r'9c9media:(?P<destination_code>[^:]+):(?P<id>\d+)'
+
+    def _real_extract(self, url):
+        destination_code, content_id = re.match(self._VALID_URL, url).groups()
+        api_base_url = self._API_BASE_TEMPLATE % (destination_code, content_id)
+        content = self._download_json(api_base_url, content_id, query={
+            '$include': '[Media,Season,ContentPackages]',
+        })
+        title = content['Name']
+        if len(content['ContentPackages']) > 1:
+            raise ExtractorError('multiple content packages')
+        content_package = content['ContentPackages'][0]
+        package_id = content_package['Id']
+        content_package_url = api_base_url + 'contentpackages/%s/' % package_id
+        content_package = self._download_json(content_package_url, content_id)
+
+        if content_package.get('Constraints', {}).get('Security', {}).get('Type') == 'adobe-drm':
+            raise ExtractorError('This video is DRM protected.', expected=True)
+
+        stacks = self._download_json(content_package_url + 'stacks/', package_id)['Items']
+        multistacks = len(stacks) > 1
+
+        thumbnails = []
+        for image in content.get('Images', []):
+            image_url = image.get('Url')
+            if not image_url:
+                continue
+            thumbnails.append({
+                'url': image_url,
+                'width': int_or_none(image.get('Width')),
+                'height': int_or_none(image.get('Height')),
+            })
+
+        tags, categories = [], []
+        for source_name, container in (('Tags', tags), ('Genres', categories)):
+            for e in content.get(source_name, []):
+                e_name = e.get('Name')
+                if not e_name:
+                    continue
+                container.append(e_name)
+
+        description = content.get('Desc') or content.get('ShortDesc')
+        season = content.get('Season', {})
+        base_info = {
+            'description': description,
+            'timestamp': parse_iso8601(content.get('BroadcastDateTime')),
+            'episode_number': int_or_none(content.get('Episode')),
+            'season': season.get('Name'),
+            'season_number': season.get('Number'),
+            'season_id': season.get('Id'),
+            'series': content.get('Media', {}).get('Name'),
+            'tags': tags,
+            'categories': categories,
+        }
+
+        entries = []
+        for stack in stacks:
+            stack_id = compat_str(stack['Id'])
+            entry = {
+                '_type': 'url_transparent',
+                'url': '9c9media:stack:%s:%s:%s:%s' % (destination_code, content_id, package_id, stack_id),
+                'id': stack_id,
+                'title': '%s_part%s' % (title, stack['Name']) if multistacks else title,
+                'duration': float_or_none(stack.get('Duration')),
+                'ie_key': 'NineCNineMediaStack',
+            }
+            entry.update(base_info)
+            entries.append(entry)
+
+        return {
+            '_type': 'multi_video',
+            'id': content_id,
+            'title': title,
+            'description': description,
+            'entries': entries,
+        }

youtube_dl/extractor/nrk.py

@@ -14,16 +14,6 @@ from ..utils import (
 
 
 class NRKBaseIE(InfoExtractor):
-    def _extract_formats(self, manifest_url, video_id, fatal=True):
-        formats = []
-        formats.extend(self._extract_f4m_formats(
-            manifest_url + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81',
-            video_id, f4m_id='hds', fatal=fatal))
-        formats.extend(self._extract_m3u8_formats(manifest_url.replace(
-            'akamaihd.net/z/', 'akamaihd.net/i/').replace('/manifest.f4m', '/master.m3u8'),
-            video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=fatal))
-        return formats
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
@@ -45,7 +35,7 @@ class NRKBaseIE(InfoExtractor):
                 asset_url = asset.get('url')
                 if not asset_url:
                     continue
-                formats = self._extract_formats(asset_url, video_id, fatal=False)
+                formats = self._extract_akamai_formats(asset_url, video_id)
                 if not formats:
                     continue
                 self._sort_formats(formats)
@@ -69,7 +59,7 @@ class NRKBaseIE(InfoExtractor):
         if not entries:
             media_url = data.get('mediaUrl')
             if media_url:
-                formats = self._extract_formats(media_url, video_id)
+                formats = self._extract_akamai_formats(media_url, video_id)
                 self._sort_formats(formats)
                 duration = parse_duration(data.get('duration'))
                 entries = [{

youtube_dl/extractor/ntvde.py

@@ -1,6 +1,8 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..compat import compat_urlparse
 from ..utils import (
@@ -40,8 +42,8 @@ class NTVDeIE(InfoExtractor):
         timestamp = int_or_none(info.get('publishedDateAsUnixTimeStamp'))
         vdata = self._parse_json(self._search_regex(
             r'(?s)\$\(\s*"\#player"\s*\)\s*\.data\(\s*"player",\s*(\{.*?\})\);',
-            webpage, 'player data'),
-            video_id, transform_source=js_to_json)
+            webpage, 'player data'), video_id,
+            transform_source=lambda s: js_to_json(re.sub(r'advertising:\s*{[^}]+},', '', s)))
         duration = parse_duration(vdata.get('duration'))
 
         formats = []

youtube_dl/extractor/nytimes.py

@@ -1,26 +1,37 @@
 from __future__ import unicode_literals
 
+import hmac
+import hashlib
+import base64
+
 from .common import InfoExtractor
 from ..utils import (
     float_or_none,
     int_or_none,
     parse_iso8601,
+    mimetype2ext,
+    determine_ext,
 )
 
 
 class NYTimesBaseIE(InfoExtractor):
+    _SECRET = b'pX(2MbU2);4N{7J8)>YwKRJ+/pQ3JkiU2Q^V>mFYv6g6gYvt6v'
+
     def _extract_video_from_id(self, video_id):
-        video_data = self._download_json(
-            'http://www.nytimes.com/svc/video/api/v2/video/%s' % video_id,
-            video_id, 'Downloading video JSON')
+        # Authorization generation algorithm is reverse engineered from `signer` in
+        # http://graphics8.nytimes.com/video/vhs/vhs-2.x.min.js
+        path = '/svc/video/api/v3/video/' + video_id
+        hm = hmac.new(self._SECRET, (path + ':vhs').encode(), hashlib.sha512).hexdigest()
+        video_data = self._download_json('http://www.nytimes.com' + path, video_id, 'Downloading video JSON', headers={
+            'Authorization': 'NYTV ' + base64.b64encode(hm.encode()).decode(),
+            'X-NYTV': 'vhs',
+        }, fatal=False)
+        if not video_data:
+            video_data = self._download_json(
+                'http://www.nytimes.com/svc/video/api/v2/video/' + video_id,
+                video_id, 'Downloading video JSON')
 
         title = video_data['headline']
-        description = video_data.get('summary')
-        duration = float_or_none(video_data.get('duration'), 1000)
-
-        uploader = video_data.get('byline')
-        publication_date = video_data.get('publication_date')
-        timestamp = parse_iso8601(publication_date[:-8]) if publication_date else None
 
         def get_file_size(file_size):
             if isinstance(file_size, int):
@@ -28,35 +39,59 @@ class NYTimesBaseIE(InfoExtractor):
             elif isinstance(file_size, dict):
                 return int(file_size.get('value', 0))
             else:
-                return 0
+                return None
 
-        formats = [
-            {
-                'url': video['url'],
-                'format_id': video.get('type'),
-                'vcodec': video.get('video_codec'),
-                'width': int_or_none(video.get('width')),
-                'height': int_or_none(video.get('height')),
-                'filesize': get_file_size(video.get('fileSize')),
-            } for video in video_data['renditions'] if video.get('url')
-        ]
+        urls = []
+        formats = []
+        for video in video_data.get('renditions', []):
+            video_url = video.get('url')
+            format_id = video.get('type')
+            if not video_url or format_id == 'thumbs' or video_url in urls:
+                continue
+            urls.append(video_url)
+            ext = mimetype2ext(video.get('mimetype')) or determine_ext(video_url)
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    video_url, video_id, 'mp4', 'm3u8_native',
+                    m3u8_id=format_id or 'hls', fatal=False))
+            elif ext == 'mpd':
+                continue
+            #     formats.extend(self._extract_mpd_formats(
+            #         video_url, video_id, format_id or 'dash', fatal=False))
+            else:
+                formats.append({
+                    'url': video_url,
+                    'format_id': format_id,
+                    'vcodec': video.get('videoencoding') or video.get('video_codec'),
+                    'width': int_or_none(video.get('width')),
+                    'height': int_or_none(video.get('height')),
+                    'filesize': get_file_size(video.get('file_size') or video.get('fileSize')),
+                    'tbr': int_or_none(video.get('bitrate'), 1000),
+                    'ext': ext,
+                })
         self._sort_formats(formats)
 
-        thumbnails = [
-            {
-                'url': 'http://www.nytimes.com/%s' % image['url'],
+        thumbnails = []
+        for image in video_data.get('images', []):
+            image_url = image.get('url')
+            if not image_url:
+                continue
+            thumbnails.append({
+                'url': 'http://www.nytimes.com/' + image_url,
                 'width': int_or_none(image.get('width')),
                 'height': int_or_none(image.get('height')),
-            } for image in video_data.get('images', []) if image.get('url')
-        ]
+            })
+
+        publication_date = video_data.get('publication_date')
+        timestamp = parse_iso8601(publication_date[:-8]) if publication_date else None
 
         return {
             'id': video_id,
             'title': title,
-            'description': description,
+            'description': video_data.get('summary'),
             'timestamp': timestamp,
-            'uploader': uploader,
-            'duration': duration,
+            'uploader': video_data.get('byline'),
+            'duration': float_or_none(video_data.get('duration'), 1000),
             'formats': formats,
             'thumbnails': thumbnails,
         }
@@ -67,7 +102,7 @@ class NYTimesIE(NYTimesBaseIE):
 
     _TESTS = [{
         'url': 'http://www.nytimes.com/video/opinion/100000002847155/verbatim-what-is-a-photocopier.html?playlistId=100000001150263',
-        'md5': '18a525a510f942ada2720db5f31644c0',
+        'md5': 'd665342765db043f7e225cff19df0f2d',
         'info_dict': {
             'id': '100000002847155',
             'ext': 'mov',

youtube_dl/extractor/openload.py

@@ -1,12 +1,12 @@
 # coding: utf-8
 from __future__ import unicode_literals, division
 
-import math
-
 from .common import InfoExtractor
-from ..compat import compat_chr
+from ..compat import (
+    compat_chr,
+    compat_ord,
+)
 from ..utils import (
-    decode_png,
     determine_ext,
     ExtractorError,
 )
@@ -42,71 +42,28 @@ class OpenloadIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage('https://openload.co/embed/%s/' % video_id, video_id)
 
-        if 'File not found' in webpage:
+        if 'File not found' in webpage or 'deleted by the owner' in webpage:
             raise ExtractorError('File not found', expected=True)
 
-        # The following extraction logic is proposed by @Belderak and @gdkchan
-        # and declared to be used freely in youtube-dl
-        # See https://github.com/rg3/youtube-dl/issues/9706
+        # The following decryption algorithm is written by @yokrysty and
+        # declared to be freely used in youtube-dl
+        # See https://github.com/rg3/youtube-dl/issues/10408
+        enc_data = self._html_search_regex(
+            r'<span[^>]+id="hiddenurl"[^>]*>([^<]+)</span>', webpage, 'encrypted data')
 
-        numbers_js = self._download_webpage(
-            'https://openload.co/assets/js/obfuscator/n.js', video_id,
-            note='Downloading signature numbers')
-        signums = self._search_regex(
-            r'window\.signatureNumbers\s*=\s*[\'"](?P<data>[a-z]+)[\'"]',
-            numbers_js, 'signature numbers', group='data')
+        video_url_chars = []
 
-        linkimg_uri = self._search_regex(
-            r'<img[^>]+id="linkimg"[^>]+src="([^"]+)"', webpage, 'link image')
-        linkimg = self._request_webpage(
-            linkimg_uri, video_id, note=False).read()
+        for idx, c in enumerate(enc_data):
+            j = compat_ord(c)
+            if j >= 33 and j <= 126:
+                j = ((j + 14) % 94) + 33
+            if idx == len(enc_data) - 1:
+                j += 1
+            video_url_chars += compat_chr(j)
 
-        width, height, pixels = decode_png(linkimg)
-
-        output = ''
-        for y in range(height):
-            for x in range(width):
-                r, g, b = pixels[y][3 * x:3 * x + 3]
-                if r == 0 and g == 0 and b == 0:
-                    break
-                else:
-                    output += compat_chr(r)
-                    output += compat_chr(g)
-                    output += compat_chr(b)
-
-        img_str_length = len(output) // 200
-        img_str = [[0 for x in range(img_str_length)] for y in range(10)]
-
-        sig_str_length = len(signums) // 260
-        sig_str = [[0 for x in range(sig_str_length)] for y in range(10)]
-
-        for i in range(10):
-            for j in range(img_str_length):
-                begin = i * img_str_length * 20 + j * 20
-                img_str[i][j] = output[begin:begin + 20]
-            for j in range(sig_str_length):
-                begin = i * sig_str_length * 26 + j * 26
-                sig_str[i][j] = signums[begin:begin + 26]
-
-        parts = []
-        # TODO: find better names for str_, chr_ and sum_
-        str_ = ''
-        for i in [2, 3, 5, 7]:
-            str_ = ''
-            sum_ = float(99)
-            for j in range(len(sig_str[i])):
-                for chr_idx in range(len(img_str[i][j])):
-                    if sum_ > float(122):
-                        sum_ = float(98)
-                    chr_ = compat_chr(int(math.floor(sum_)))
-                    if sig_str[i][j][chr_idx] == chr_ and j >= len(str_):
-                        sum_ += float(2.5)
-                        str_ += img_str[i][j][chr_idx]
-            parts.append(str_.replace(',', ''))
-
-        video_url = 'https://openload.co/stream/%s~%s~%s~%s' % (parts[3], parts[1], parts[2], parts[0])
+        video_url = 'https://openload.co/stream/%s?mime=true' % ''.join(video_url_chars)
 
         title = self._og_search_title(webpage, default=None) or self._search_regex(
             r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,