release 2016.11.02

Closes #11073

In the provided link, SWF params give up to 720P, and VideoConfig
gives 1080P for both best and bestvideo. I guess all Facebook videos
supports HTML5 now, so I remove the old detection for SWF params

.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 *2016.08.01*. 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 Issues with outdated version will be rejected.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 **2016.08.01**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.11.02*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.11.02**
 
 ### 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 2016.08.01
+[debug] youtube-dl version 2016.11.02
 [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: {}
@@ -55,4 +55,4 @@ $ youtube-dl -v <your command line>
 ### Description of your *issue*, suggested solution and other information
 
 Explanation of your *issue* in arbitrary form goes here. Please make sure the [description is worded well enough to be understood](https://github.com/rg3/youtube-dl#is-the-description-of-the-issue-itself-sufficient). Provide as much context and examples as possible.
-If work on your *issue* required an account credentials please provide them or explain how one can obtain them.
+If work on your *issue* requires account credentials please provide them or explain how one can obtain them.

.github/ISSUE_TEMPLATE_tmpl.md

@@ -55,4 +55,4 @@ $ youtube-dl -v <your command line>
 ### Description of your *issue*, suggested solution and other information
 
 Explanation of your *issue* in arbitrary form goes here. Please make sure the [description is worded well enough to be understood](https://github.com/rg3/youtube-dl#is-the-description-of-the-issue-itself-sufficient). Provide as much context and examples as possible.
-If work on your *issue* required an account credentials please provide them or explain how one can obtain them.
+If work on your *issue* requires account credentials please provide them or explain how one can obtain them.

.github/PULL_REQUEST_TEMPLATE.md

@@ -10,8 +10,13 @@
 - [ ] At least skimmed through [adding new extractor tutorial](https://github.com/rg3/youtube-dl#adding-support-for-a-new-site) and [youtube-dl coding conventions](https://github.com/rg3/youtube-dl#youtube-dl-coding-conventions) sections
 - [ ] [Searched](https://github.com/rg3/youtube-dl/search?q=is%3Apr&type=Issues) the bugtracker for similar pull requests
 
+### In order to be accepted and merged into youtube-dl each piece of code must be in public domain or released under [Unlicense](http://unlicense.org/). Check one of the following options:
+- [ ] I am the original author of this code and I am willing to release it under [Unlicense](http://unlicense.org/)
+- [ ] I am not the original author of this code but it is in public domain or released under [Unlicense](http://unlicense.org/) (provide reliable evidence)
+
 ### What is the purpose of your *pull request*?
 - [ ] Bug fix
+- [ ] Improvement
 - [ ] New extractor
 - [ ] New feature
 

.gitignore

@@ -29,6 +29,7 @@ updates_key.pem
 *.m4a
 *.m4v
 *.mp3
+*.3gp
 *.part
 *.swp
 test/testdata

AUTHORS

@@ -26,7 +26,7 @@ Albert Kim
 Pierre Rudloff
 Huarong Huo
 Ismael Mejía
-Steffan 'Ruirize' James
+Steffan Donal
 Andras Elso
 Jelle van der Waa
 Marcin Cieślak
@@ -179,3 +179,14 @@ Jakub Adam Wieczorek
 Aleksandar Topuzović
 Nehal Patel
 Rob van Bekkum
+Petr Zvoníček
+Pratyush Singh
+Aleksander Nitecki
+Sebastian Blunt
+Matěj Cepl
+Xie Yanbo
+Philip Xu
+John Hawkinson
+Rich Leeper
+Zhong Jianxin
+Thor77

CONTRIBUTING.md

@@ -12,7 +12,7 @@ $ youtube-dl -v <your command line>
 [debug] Proxy map: {}
 ...
 ```
-**Do not post screenshots of verbose log only plain text is acceptable.**
+**Do not post screenshots of verbose logs; only plain text is acceptable.**
 
 The output (including the first lines) contains important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
 
@@ -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?
 
@@ -66,7 +66,7 @@ Only post features that you (or an incapacitated friend you can personally talk
 
 ###  Is your question about youtube-dl?
 
-It may sound strange, but some bug reports we receive are completely unrelated to youtube-dl and relate to a different or even the reporter's own application. Please make sure that you are actually using youtube-dl. If you are using a UI for youtube-dl, report the bug to the maintainer of the actual application providing the UI. On the other hand, if your UI for youtube-dl fails in some way you believe is related to youtube-dl, by all means, go ahead and report the bug.
+It may sound strange, but some bug reports we receive are completely unrelated to youtube-dl and relate to a different, or even the reporter's own, application. Please make sure that you are actually using youtube-dl. If you are using a UI for youtube-dl, report the bug to the maintainer of the actual application providing the UI. On the other hand, if your UI for youtube-dl fails in some way you believe is related to youtube-dl, by all means, go ahead and report the bug.
 
 # DEVELOPER INSTRUCTIONS
 
@@ -85,7 +85,7 @@ To run the test, simply invoke your favorite test runner, or execute a test file
 If you want to create a build of youtube-dl yourself, you'll need
 
 * python
-* make (both GNU make and BSD make are supported)
+* make (only GNU make is supported)
 * pandoc
 * zip
 * nosetests
@@ -167,19 +167,19 @@ In any case, thank you very much for your contributions!
 
 This section introduces a guide lines for writing idiomatic, robust and future-proof extractor code.
 
-Extractors are very fragile by nature since they depend on the layout of the source data provided by 3rd party media hoster out of your control and this layout tend to change. As an extractor implementer your task is not only to write code that will extract media links and metadata correctly but also to minimize code dependency on source's layout changes and even to make the code foresee potential future changes and be ready for that. This is important because it will allow extractor not to break on minor layout changes thus keeping old youtube-dl versions working. Even though this breakage issue is easily fixed by emitting a new version of youtube-dl with fix incorporated all the previous version become broken in all repositories and distros' packages that may not be so prompt in fetching the update from us. Needless to say some may never receive an update at all that is possible for non rolling release distros.
+Extractors are very fragile by nature since they depend on the layout of the source data provided by 3rd party media hosters out of your control and this layout tends to change. As an extractor implementer your task is not only to write code that will extract media links and metadata correctly but also to minimize dependency on the source's layout and even to make the code foresee potential future changes and be ready for that. This is important because it will allow the extractor not to break on minor layout changes thus keeping old youtube-dl versions working. Even though this breakage issue is easily fixed by emitting a new version of youtube-dl with a fix incorporated, all the previous versions become broken in all repositories and distros' packages that may not be so prompt in fetching the update from us. Needless to say, some non rolling release distros may never receive an update at all.
 
 ### Mandatory and optional metafields
 
-For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by [information dictionary](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L75-L257) or simply *info dict*. Only the following meta fields in *info dict* are considered mandatory for successful extraction process by youtube-dl:
+For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by an [information dictionary](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L75-L257) or simply *info dict*. Only the following meta fields in the *info dict* are considered mandatory for a successful extraction process by youtube-dl:
 
  - `id` (media identifier)
  - `title` (media title)
  - `url` (media download URL) or `formats`
 
-In fact only the last option is technically mandatory (i.e. if you can't figure out the download location of the media the extraction does not make any sense). But by convention youtube-dl also treats `id` and `title` to be mandatory. Thus aforementioned metafields are the critical data the extraction does not make any sense without and if any of them fail to be extracted then extractor is considered completely broken.
+In fact only the last option is technically mandatory (i.e. if you can't figure out the download location of the media the extraction does not make any sense). But by convention youtube-dl also treats `id` and `title` as mandatory. Thus the aforementioned metafields are the critical data that the extraction does not make any sense without and if any of them fail to be extracted then the extractor is considered completely broken.
 
-[Any field](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L149-L257) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerate** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields.
+[Any field](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L149-L257) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerant** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields.
 
 #### Example
 
@@ -199,7 +199,7 @@ Assume at this point `meta`'s layout is:
 }
 ```
 
-Assume you want to extract `summary` and put into resulting info dict as `description`. Since `description` is optional metafield you should be ready that this key may be missing from the `meta` dict, so that you should extract it like:
+Assume you want to extract `summary` and put it into the resulting info dict as `description`. Since `description` is an optional metafield you should be ready that this key may be missing from the `meta` dict, so that you should extract it like:
 
 ```python
 description = meta.get('summary')  # correct
@@ -211,7 +211,7 @@ and not like:
 description = meta['summary']  # incorrect
 ```
 
-The latter will break extraction process with `KeyError` if `summary` disappears from `meta` at some time later but with former approach extraction will just go ahead with `description` set to `None` that is perfectly fine (remember `None` is equivalent for absence of data). 
+The latter will break extraction process with `KeyError` if `summary` disappears from `meta` at some later time but with the former approach extraction will just go ahead with `description` set to `None` which is perfectly fine (remember `None` is equivalent to the absence of data).
 
 Similarly, you should pass `fatal=False` when extracting optional data from a webpage with `_search_regex`, `_html_search_regex` or similar methods, for instance:
 
@@ -231,21 +231,21 @@ description = self._search_regex(
     webpage, 'description', default=None)
 ```
 
-On failure this code will silently continue the extraction with `description` set to `None`. That is useful for metafields that are known to may or may not be present.
+On failure this code will silently continue the extraction with `description` set to `None`. That is useful for metafields that may or may not be present.
  
 ### Provide fallbacks
 
-When extracting metadata try to provide several scenarios for that. For example if `title` is present in several places/sources try extracting from at least some of them. This would make it more future-proof in case some of the sources became unavailable.
+When extracting metadata try to do so from multiple sources. For example if `title` is present in several places, try extracting from at least some of them. This makes it more future-proof in case some of the sources become unavailable.
 
 #### Example
 
-Say `meta` from previous example has a `title` and you are about to extract it. Since `title` is mandatory meta field you should end up with something like:
+Say `meta` from the previous example has a `title` and you are about to extract it. Since `title` is a mandatory meta field you should end up with something like:
 
 ```python
 title = meta['title']
 ```
 
-If `title` disappeares from `meta` in future due to some changes on hoster's side the extraction would fail since `title` is mandatory. That's expected.
+If `title` disappears from `meta` in future due to some changes on the hoster's side the extraction would fail since `title` is mandatory. That's expected.
 
 Assume that you have some another source you can extract `title` from, for example `og:title` HTML meta of a `webpage`. In this case you can provide a fallback scenario:
 
@@ -282,7 +282,7 @@ title = self._search_regex(
     webpage, 'title', group='title')
 ```
 
-Note how you tolerate potential changes in `style` attribute's value or switch from using double quotes to single for `class` attribute: 
+Note how you tolerate potential changes in the `style` attribute's value or switch from using double quotes to single for `class` attribute: 
 
 The code definitely should not look like:
 

ChangeLog

@@ -1,3 +1,641 @@
+version 2016.11.02
+
+Core
++ Add basic support for Smooth Streaming protocol (#8118, #10969)
+* Improve MPD manifest base URL extraction (#10909, #11079)
+* Fix --match-filter for int-like strings (#11082)
+
+Extractors
++ [mva] Add support for ISM formats
++ [msn] Add support for ISM formats
++ [onet] Add support for ISM formats
++ [tvp] Add support for ISM formats
++ [nicknight] Add support for nicknight sites (#10769)
+
+
+version 2016.10.30
+
+Extractors
+* [facebook] Improve 1080P video detection (#11073)
+* [imgur] Recognize /r/ URLs (#11071)
+* [beeg] Fix extraction (#11069)
+* [openload] Fix extraction (#10408)
+* [gvsearch] Modernize and fix search request (#11051)
+* [adultswim] Fix extraction (#10979)
++ [nobelprize] Add support for nobelprize.org (#9999)
+* [hornbunny] Fix extraction (#10981)
+* [tvp] Improve video id extraction (#10585)
+
+
+version 2016.10.26
+
+Extractors
++ [rentv] Add support for ren.tv (#10620)
++ [ard] Detect unavailable videos (#11018)
+* [vk] Fix extraction (#11022)
+
+
+version 2016.10.25
+
+Core
+* Running youtube-dl in the background is fixed (#10996, #10706, #955)
+
+Extractors
++ [jamendo] Add support for jamendo.com (#10132, #10736)
++ [pandatv] Add support for panda.tv (#10736)
++ [dotsub] Support Vimeo embed (#10964)
+* [litv] Fix extraction
++ [vimeo] Delegate ondemand redirects to ondemand extractor (#10994)
+* [vivo] Fix extraction (#11003)
++ [twitch:stream] Add support for rebroadcasts (#10995)
+* [pluralsight] Fix subtitles conversion (#10990)
+
+
+version 2016.10.21.1
+
+Extractors
++ [pluralsight] Process all clip URLs (#10984)
+
+
+version 2016.10.21
+
+Core
+- Disable thumbnails embedding in mkv
++ Add support for Comcast multiple-system operator (#10819)
+
+Extractors
+* [pluralsight] Adapt to new API (#10972)
+* [openload] Fix extraction (#10408, #10971)
++ [natgeo] Extract m3u8 formats (#10959)
+
+
+version 2016.10.19
+
+Core
++ [utils] Expose PACKED_CODES_RE
++ [extractor/common] Extract non smil wowza mpd manifests
++ [extractor/common] Detect f4m audio-only formats
+
+Extractors
+* [vidzi] Fix extraction (#10908, #10952)
+* [urplay] Fix subtitles extraction
++ [urplay] Add support for urskola.se (#10915)
++ [orf] Add subtitles support (#10939)
+* [youtube] Fix --no-playlist behavior for youtu.be/id URLs (#10896)
+* [nrk] Relax URL regular expression (#10928)
++ [nytimes] Add support for podcasts (#10926)
+* [pluralsight] Relax URL regular expression (#10941)
+
+
+version 2016.10.16
+
+Core
+* [postprocessor/ffmpeg] Return correct filepath and ext in updated information
+  in FFmpegExtractAudioPP (#10879)
+
+Extractors
++ [ruutu] Add support for supla.fi (#10849)
++ [theoperaplatform] Add support for theoperaplatform.eu (#10914)
+* [lynda] Fix height for prioritized streams
++ [lynda] Add fallback extraction scenario
+* [lynda] Switch to https (#10916)
++ [huajiao] New extractor (#10917)
+* [cmt] Fix mgid extraction (#10813)
++ [safari:course] Add support for techbus.safaribooksonline.com
+* [orf:tvthek] Fix extraction and modernize (#10898)
+* [chirbit] Fix extraction of user profile pages
+* [carambatv] Fix extraction
+* [canalplus] Fix extraction for some videos
+* [cbsinteractive] Fix extraction for cnet.com
+* [parliamentliveuk] Lower case URLs are now recognized (#10912)
+
+
+version 2016.10.12
+
+Core
++ Support HTML media elements without child nodes
+* [Makefile] Support for GNU make < 4 is fixed; BSD make dropped (#9387)
+
+Extractors
+* [dailymotion] Fix extraction (#10901)
+* [vimeo:review] Fix extraction (#10900)
+* [nhl] Correctly handle invalid formats (#10713)
+* [footyroom] Fix extraction (#10810)
+* [abc.net.au:iview] Fix for standalone (non series) videos (#10895)
++ [hbo] Add support for episode pages (#10892)
+* [allocine] Fix extraction (#10860)
++ [nextmedia] Recognize action news on AppleDaily
+* [lego] Improve info extraction and bypass geo restriction (#10872)
+
+
+version 2016.10.07
+
+Extractors
++ [iprima] Detect geo restriction
+* [facebook] Fix video extraction (#10846)
++ [commonprotocols] Support direct MMS links (#10838)
++ [generic] Add support for multiple vimeo embeds (#10862)
++ [nzz] Add support for nzz.ch (#4407)
++ [npo] Detect geo restriction
++ [npo] Add support for 2doc.nl (#10842)
++ [lego] Add support for lego.com (#10369)
++ [tonline] Add support for t-online.de (#10376)
+* [techtalks] Relax URL regular expression (#10840)
+* [youtube:live] Extend URL regular expression (#10839)
++ [theweatherchannel] Add support for weather.com (#7188)
++ [thisoldhouse] Add support for thisoldhouse.com (#10837)
++ [nhl] Add support for wch2016.com (#10833)
+* [pornoxo] Use JWPlatform to improve metadata extraction
+
+
+version 2016.10.02
+
+Core
+* Fix possibly lost extended attributes during post-processing
++ Support pyxattr as well as python-xattr for --xattrs and
+  --xattr-set-filesize (#9054)
+
+Extractors
++ [jwplatform] Support DASH streams in JWPlayer
++ [jwplatform] Support old-style JWPlayer playlists
++ [byutv:event] Add extractor
+* [periscope:user] Fix extraction (#10820)
+* [dctp] Fix extraction (#10734)
++ [instagram] Extract video dimensions (#10790)
++ [tvland] Extend URL regular expression (#10812)
++ [vgtv] Add support for tv.aftonbladet.se (#10800)
+- [aftonbladet] Remove extractor
+* [vk] Fix timestamp and view count extraction (#10760)
++ [vk] Add support for running and finished live streams (#10799)
++ [leeco] Recognize more Le Sports URLs (#10794)
++ [instagram] Extract comments (#10788)
++ [ketnet] Extract mzsource formats (#10770)
+* [limelight:media] Improve HTTP formats extraction
+
+
+version 2016.09.27
+
+Core
++ Add hdcore query parameter to akamai f4m formats
++ Delegate HLS live streams downloading to ffmpeg
++ Improved support for HTML5 subtitles
+
+Extractors
++ [vk] Add support for dailymotion embeds (#10661)
+* [promptfile] Fix extraction (#10634)
+* [kaltura] Speed up embed regular expressions (#10764)
++ [npo] Add support for anderetijden.nl (#10754)
++ [prosiebensat1] Add support for advopedia sites
+* [mwave] Relax URL regular expression (#10735, #10748)
+* [prosiebensat1] Fix playlist support (#10745)
++ [prosiebensat1] Add support for sat1gold sites (#10745)
++ [cbsnews:livevideo] Fix extraction and extract m3u8 formats
++ [brightcove:new] Add support for live streams
+* [soundcloud] Generalize playlist entries extraction (#10733)
++ [mtv] Add support for new URL schema (#8169, #9808)
+* [einthusan] Fix extraction (#10714)
++ [twitter] Support Periscope embeds (#10737)
++ [openload] Support subtitles (#10625)
+
+
+version 2016.09.24
+
+Core
++ Add support for watchTVeverywhere.com authentication provider based MSOs for
+  Adobe Pass authentication (#10709)
+
+Extractors
++ [soundcloud:playlist] Provide video id for early playlist entries (#10733)
++ [prosiebensat1] Add support for kabeleinsdoku (#10732)
+* [cbs] Extract info from thunder videoPlayerService (#10728)
+* [openload] Fix extraction (#10408)
++ [ustream] Support the new HLS streams (#10698)
++ [ooyala] Extract all HLS formats
++ [cartoonnetwork] Add support for Adobe Pass authentication
++ [soundcloud] Extract license metadata
++ [fox] Add support for Adobe Pass authentication (#8584)
++ [tbs] Add support for Adobe Pass authentication (#10642, #10222)
++ [trutv] Add support for Adobe Pass authentication (#10519)
++ [turner] Add support for Adobe Pass authentication
+
+
+version 2016.09.19
+
+Extractors
++ [crunchyroll] Check if already authenticated (#10700)
+- [twitch:stream] Remove fallback to profile extraction when stream is offline
+* [thisav] Improve title extraction (#10682)
+* [vyborymos] Improve station info extraction
+
+
+version 2016.09.18
+
+Core
++ Introduce manifest_url and fragments fields in formats dictionary for
+  fragmented media
++ Provide manifest_url field for DASH segments, HLS and HDS
++ Provide fragments field for DASH segments
+* Rework DASH segments downloader to use fragments field
++ Add helper method for Wowza Streaming Engine formats extraction
+
+Extractors
++ [vyborymos] Add extractor for vybory.mos.ru (#10692)
++ [xfileshare] Add title regular expression for streamin.to (#10646)
++ [globo:article] Add support for multiple videos (#10653)
++ [thisav] Recognize HTML5 videos (#10447)
+* [jwplatform] Improve JWPlayer detection
++ [mangomolo] Add support for Mangomolo embeds
++ [toutv] Add support for authentication (#10669)
+* [franceinter] Fix upload date extraction
+* [tv4] Fix HLS and HDS formats extraction (#10659)
+
+
+version 2016.09.15
+
+Core
+* Improve _hidden_inputs
++ Introduce improved explicit Adobe Pass support
++ Add --ap-mso to provide multiple-system operator identifier
++ Add --ap-username to provide MSO account username
++ Add --ap-password to provide MSO account password
++ Add --ap-list-mso to list all supported MSOs
++ Add support for Rogers Cable multiple-system operator (#10606)
+
+Extractors
+* [crunchyroll] Fix authentication (#10655)
+* [twitch] Fix API calls (#10654, #10660)
++ [bellmedia] Add support for more Bell Media Television sites
+* [franceinter] Fix extraction (#10538, #2105)
+* [kuwo] Improve error detection (#10650)
++ [go] Add support for free full episodes (#10439)
+* [bilibili] Fix extraction for specific videos (#10647)
+* [nhk] Fix extraction (#10633)
+* [kaltura] Improve audio detection
+* [kaltura] Skip chun format
++ [vimeo:ondemand] Pass Referer along with embed URL (#10624)
++ [nbc] Add support for NBC Olympics (#10361)
+
+
+version 2016.09.11.1
+
+Extractors
++ [tube8] Extract categories and tags (#10579)
++ [pornhub] Extract categories and tags (#10499)
+* [openload] Temporary fix (#10408)
++ [foxnews] Add support Fox News articles (#10598)
+* [viafree] Improve video id extraction (#10615)
+* [iwara] Fix extraction after relaunch (#10462, #3215)
++ [tfo] Add extractor for tfo.org
+* [lrt] Fix audio extraction (#10566)
+* [9now] Fix extraction (#10561)
++ [canalplus] Add support for c8.fr (#10577)
+* [newgrounds] Fix uploader extraction (#10584)
++ [polskieradio:category] Add support for category lists (#10576)
++ [ketnet] Add extractor for ketnet.be (#10343)
++ [canvas] Add support for een.be (#10605)
++ [telequebec] Add extractor for telequebec.tv (#1999)
+* [parliamentliveuk] Fix extraction (#9137)
+
+
+version 2016.09.08
+
+Extractors
++ [jwplatform] Extract height from format label
++ [yahoo] Extract Brightcove Legacy Studio embeds (#9345)
+* [videomore] Fix extraction (#10592)
+* [foxgay] Fix extraction (#10480)
++ [rmcdecouverte] Add extractor for rmcdecouverte.bfmtv.com (#9709)
+* [gamestar] Fix metadata extraction (#10479)
+* [puls4] Fix extraction (#10583)
++ [cctv] Add extractor for CCTV and CNTV (#8153)
++ [lci] Add extractor for lci.fr (#10573)
++ [wat] Extract DASH formats
++ [viafree] Improve video id detection (#10569)
++ [trutv] Add extractor for trutv.com (#10519)
++ [nick] Add support for nickelodeon.nl (#10559)
++ [abcotvs:clips] Add support for clips.abcotvs.com
++ [abcotvs] Add support for ABC Owned Television Stations sites (#9551)
++ [miaopai] Add extractor for miaopai.com (#10556)
+* [gamestar] Fix metadata extraction (#10479)
++ [bilibili] Add support for episodes (#10190)
++ [tvnoe] Add extractor for tvnoe.cz (#10524)
+
+
+version 2016.09.04.1
+
+Core
+* In DASH downloader if the first segment fails, abort the whole download
+  process to prevent throttling (#10497)
++ Add support for --skip-unavailable-fragments and --fragment retries in
+  hlsnative downloader (#10165, #10448).
++ Add support for --skip-unavailable-fragments in DASH downloader
++ Introduce --skip-unavailable-fragments option for fragment based downloaders
+  that allows to skip fragments unavailable due to a HTTP error
+* Fix extraction of video/audio entries with src attribute in
+  _parse_html5_media_entries (#10540)
+
+Extractors
+* [theplatform] Relax URL regular expression (#10546)
+* [youtube:playlist] Extend URL regular expression
+* [rottentomatoes] Delegate extraction to internetvideoarchive extractor
+* [internetvideoarchive] Extract all formats
+* [pornvoisines] Fix extraction (#10469)
+* [rottentomatoes] Fix extraction (#10467)
+* [espn] Extend URL regular expression (#10549)
+* [vimple] Extend URL regular expression (#10547)
+* [youtube:watchlater] Fix extraction (#10544)
+* [youjizz] Fix extraction (#10437)
++ [foxnews] Add support for FoxNews Insider (#10445)
++ [fc2] Recognize Flash player URLs (#10512)
+
+
+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
++ Add support for TV Parental Guidelines ratings in parse_age_limit
++ Add decode_png (#9706)
++ Add support for partOfTVSeries in JSON-LD
+* Lower master M3U8 manifest preference for better format sorting
+
+Extractors
++ [discoverygo] Add extractor (#10245)
+* [flipagram] Make JSON-LD extraction non fatal
+* [generic] Make JSON-LD extraction non fatal
++ [bbc] Add support for morph embeds (#10239)
+* [tnaflixnetworkbase] Improve title extraction
+* [tnaflix] Fix metadata extraction (#10249)
+* [fox] Fix theplatform release URL query
+* [openload] Fix extraction (#9706)
+* [bbc] Skip duplicate manifest URLs
+* [bbc] Improve format code
++ [bbc] Add support for DASH and F4M
+* [bbc] Improve format sorting and listing
+* [bbc] Improve playlist extraction
++ [pokemon] Add extractor (#10093)
++ [condenast] Add fallback scenario for video info extraction
+
+
+version 2016.08.06
+
+Core
+* Add support for JSON-LD root list entries (#10203)
+* Improve unified_timestamp
+* Lower preference of RTSP formats in generic sorting
++ Add support for multiple properties in _og_search_property
+* Improve password hiding from verbose output
+
+Extractors
++ [adultswim] Add support for trailers (#10235)
+* [archiveorg] Improve extraction (#10219)
++ [jwplatform] Add support for playlists
++ [jwplatform] Add support for relative URLs
+* [jwplatform] Improve audio detection
++ [tvplay] Capture and output native error message
++ [tvplay] Extract series metadata
++ [tvplay] Add support for subtitles (#10194)
+* [tvp] Improve extraction (#7799)
+* [cbslocal] Fix timestamp parsing (#10213)
++ [naver] Add support for subtitles (#8096)
+* [naver] Improve extraction
+* [condenast] Improve extraction
+* [engadget] Relax URL regular expression
+* [5min] Fix extraction
++ [nationalgeographic] Add support for Episode Guide
++ [kaltura] Add support for subtitles
+* [kaltura] Optimize network requests
++ [vodplatform] Add extractor for vod-platform.net
+- [gamekings] Remove extractor
+* [limelight] Extract HTTP formats
+* [ntvru] Fix extraction
++ [comedycentral] Re-add :tds and :thedailyshow shortnames
+
+
 version 2016.08.01
 
 Fixed/improved extractors
@@ -7,6 +645,7 @@ Fixed/improved extractors
 - [safari] Relax regular expressions for URL matching (#10202)
 - [cwtv] Add support for cwtvpr.com (#10196)
 
+
 version 2016.07.30
 
 Fixed/improved extractors

Makefile

@@ -1,7 +1,7 @@
 all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish supportedsites
 
 clean:
-	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish youtube_dl/extractor/lazy_extractors.py *.dump *.part *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.jpg *.png CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe
+	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish youtube_dl/extractor/lazy_extractors.py *.dump *.part* *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.3gp *.jpg *.png CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe
 	find . -name "*.pyc" -delete
 	find . -name "*.class" -delete
 
@@ -12,7 +12,7 @@ SHAREDIR ?= $(PREFIX)/share
 PYTHON ?= /usr/bin/env python
 
 # set SYSCONFDIR to /etc if PREFIX=/usr or PREFIX=/usr/local
-SYSCONFDIR != if [ $(PREFIX) = /usr -o $(PREFIX) = /usr/local ]; then echo /etc; else echo $(PREFIX)/etc; fi
+SYSCONFDIR = $(shell if [ $(PREFIX) = /usr -o $(PREFIX) = /usr/local ]; then echo /etc; else echo $(PREFIX)/etc; fi)
 
 install: youtube-dl youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
 	install -d $(DESTDIR)$(BINDIR)
@@ -90,7 +90,7 @@ fish-completion: youtube-dl.fish
 
 lazy-extractors: youtube_dl/extractor/lazy_extractors.py
 
-_EXTRACTOR_FILES != find youtube_dl/extractor -iname '*.py' -and -not -iname 'lazy_extractors.py'
+_EXTRACTOR_FILES = $(shell find youtube_dl/extractor -iname '*.py' -and -not -iname 'lazy_extractors.py')
 youtube_dl/extractor/lazy_extractors.py: devscripts/make_lazy_extractors.py devscripts/lazy_load_template.py $(_EXTRACTOR_FILES)
 	$(PYTHON) devscripts/make_lazy_extractors.py $@
 

README.md

@@ -89,6 +89,8 @@ which means you can modify it, redistribute it or use it however you like.
     --mark-watched                   Mark videos watched (YouTube only)
     --no-mark-watched                Do not mark videos watched (YouTube only)
     --no-color                       Do not emit color codes in output
+    --abort-on-unavailable-fragment  Abort downloading when some fragment is not
+                                     available
 
 ## Network Options:
     --proxy URL                      Use the specified HTTP/HTTPS/SOCKS proxy.
@@ -173,7 +175,10 @@ which means you can modify it, redistribute it or use it however you like.
     -R, --retries RETRIES            Number of retries (default is 10), or
                                      "infinite".
     --fragment-retries RETRIES       Number of retries for a fragment (default
-                                     is 10), or "infinite" (DASH only)
+                                     is 10), or "infinite" (DASH and hlsnative
+                                     only)
+    --skip-unavailable-fragments     Skip unavailable fragments (DASH and
+                                     hlsnative only)
     --buffer-size SIZE               Size of download buffer (e.g. 1024 or 16K)
                                      (default is 1024)
     --no-resize-buffer               Do not automatically adjust the buffer
@@ -201,32 +206,8 @@ 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 +311,15 @@ 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
@@ -369,6 +358,17 @@ which means you can modify it, redistribute it or use it however you like.
     -n, --netrc                      Use .netrc authentication data
     --video-password PASSWORD        Video password (vimeo, smotri, youku)
 
+## Adobe Pass Options:
+    --ap-mso MSO                     Adobe Pass multiple-system operator (TV
+                                     provider) identifier, use --ap-list-mso for
+                                     a list of available MSOs
+    --ap-username USERNAME           Multiple-system operator account login
+    --ap-password PASSWORD           Multiple-system operator account password.
+                                     If this option is left out, youtube-dl will
+                                     ask interactively.
+    --ap-list-mso                    List all supported multiple-system
+                                     operators
+
 ## Post-processing Options:
     -x, --extract-audio              Convert video files to audio-only files
                                      (requires ffmpeg or avconv and ffprobe or
@@ -428,11 +428,19 @@ 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`.
@@ -441,12 +449,12 @@ You can use `--ignore-config` if you want to disable the configuration file for
 
 ### Authentication with `.netrc` file
 
-You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every youtube-dl execution and prevent tracking plain text passwords in the shell command history. You can achieve this using a [`.netrc` file](http://stackoverflow.com/tags/.netrc/info) on per extractor basis. For that you will need to create a `.netrc` file in your `$HOME` and restrict permissions to read/write by you only:
+You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every youtube-dl execution and prevent tracking plain text passwords in the shell command history. You can achieve this using a [`.netrc` file](http://stackoverflow.com/tags/.netrc/info) on a per extractor basis. For that you will need to create a `.netrc` file in your `$HOME` and restrict permissions to read/write by only you:
 ```
 touch $HOME/.netrc
 chmod a-rwx,u+rw $HOME/.netrc
 ```
-After that you can add credentials for extractor in the following format, where *extractor* is the name of extractor in lowercase:
+After that you can add credentials for an extractor in the following format, where *extractor* is the name of the extractor in lowercase:
 ```
 machine <extractor> login <login> password <password>
 ```
@@ -542,13 +550,13 @@ Available for the media that is a track or a part of a music album:
  - `disc_number`: Number of the disc or other physical medium the track belongs to
  - `release_year`: Year (YYYY) when the album was released
 
-Each aforementioned sequence when referenced in output template will be replaced by the actual value corresponding to the sequence name. Note that some of the sequences are not guaranteed to be present since they depend on the metadata obtained by particular extractor, such sequences will be replaced with `NA`.
+Each aforementioned sequence when referenced in an output template will be replaced by the actual value corresponding to the sequence name. Note that some of the sequences are not guaranteed to be present since they depend on the metadata obtained by a particular extractor. Such sequences will be replaced with `NA`.
 
-For example for `-o %(title)s-%(id)s.%(ext)s` and mp4 video with title `youtube-dl test video` and id `BaW_jenozKcj` this will result in a `youtube-dl test video-BaW_jenozKcj.mp4` file created in the current directory.
+For example for `-o %(title)s-%(id)s.%(ext)s` and an mp4 video with title `youtube-dl test video` and id `BaW_jenozKcj`, this will result in a `youtube-dl test video-BaW_jenozKcj.mp4` file created in the current directory.
 
-Output template can also contain arbitrary hierarchical path, e.g. `-o '%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s'` that will result in downloading each video in a directory corresponding to this path template. Any missing directory will be automatically created for you.
+Output templates can also contain arbitrary hierarchical path, e.g. `-o '%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s'` which will result in downloading each video in a directory corresponding to this path template. Any missing directory will be automatically created for you.
 
-To specify percent literal in output template use `%%`. To output to stdout use `-o -`.
+To use percent literals in an output template use `%%`. To output to stdout use `-o -`.
 
 The current default template is `%(title)s-%(id)s.%(ext)s`.
 
@@ -556,7 +564,7 @@ In some cases, you don't want special characters such as 中, spaces, or &, such
 
 #### Output template and Windows batch files
 
-If you are using output template inside a Windows batch file then you must escape plain percent characters (`%`) by doubling, so that `-o "%(title)s-%(id)s.%(ext)s"` should become `-o "%%(title)s-%%(id)s.%%(ext)s"`. However you should not touch `%`'s that are not plain characters, e.g. environment variables for expansion should stay intact: `-o "C:\%HOMEPATH%\Desktop\%%(title)s.%%(ext)s"`.
+If you are using an output template inside a Windows batch file then you must escape plain percent characters (`%`) by doubling, so that `-o "%(title)s-%(id)s.%(ext)s"` should become `-o "%%(title)s-%%(id)s.%%(ext)s"`. However you should not touch `%`'s that are not plain characters, e.g. environment variables for expansion should stay intact: `-o "C:\%HOMEPATH%\Desktop\%%(title)s.%%(ext)s"`.
 
 #### Output template examples
 
@@ -589,7 +597,7 @@ $ youtube-dl -o - BaW_jenozKc
 
 By default youtube-dl tries to download the best available quality, i.e. if you want the best quality you **don't need** to pass any special options, youtube-dl will guess it for you by **default**.
 
-But sometimes you may want to download in a different format, for example when you are on a slow or intermittent connection. The key mechanism for achieving this is so called *format selection* based on which you can explicitly specify desired format, select formats based on some criterion or criteria, setup precedence and much more.
+But sometimes you may want to download in a different format, for example when you are on a slow or intermittent connection. The key mechanism for achieving this is so-called *format selection* based on which you can explicitly specify desired format, select formats based on some criterion or criteria, setup precedence and much more.
 
 The general syntax for format selection is `--format FORMAT` or shorter `-f FORMAT` where `FORMAT` is a *selector expression*, i.e. an expression that describes format or formats you would like to download.
 
@@ -597,21 +605,21 @@ The general syntax for format selection is `--format FORMAT` or shorter `-f FORM
 
 The simplest case is requesting a specific format, for example with `-f 22` you can download the format with format code equal to 22. You can get the list of available format codes for particular video using `--list-formats` or `-F`. Note that these format codes are extractor specific. 
 
-You can also use a file extension (currently `3gp`, `aac`, `flv`, `m4a`, `mp3`, `mp4`, `ogg`, `wav`, `webm` are supported) to download best quality format of particular file extension served as a single file, e.g. `-f webm` will download best quality format with `webm` extension served as a single file.
+You can also use a file extension (currently `3gp`, `aac`, `flv`, `m4a`, `mp3`, `mp4`, `ogg`, `wav`, `webm` are supported) to download the best quality format of a particular file extension served as a single file, e.g. `-f webm` will download the best quality format with the `webm` extension served as a single file.
 
-You can also use special names to select particular edge case format:
- - `best`: Select best quality format represented by single file with video and audio
- - `worst`: Select worst quality format represented by single file with video and audio
- - `bestvideo`: Select best quality video only format (e.g. DASH video), may not be available
- - `worstvideo`: Select worst quality video only format, may not be available
- - `bestaudio`: Select best quality audio only format, may not be available
- - `worstaudio`: Select worst quality audio only format, may not be available
+You can also use special names to select particular edge case formats:
+ - `best`: Select the best quality format represented by a single file with video and audio.
+ - `worst`: Select the worst quality format represented by a single file with video and audio.
+ - `bestvideo`: Select the best quality video-only format (e.g. DASH video). May not be available.
+ - `worstvideo`: Select the worst quality video-only format. May not be available.
+ - `bestaudio`: Select the best quality audio only-format. May not be available.
+ - `worstaudio`: Select the worst quality audio only-format. May not be available.
 
-For example, to download worst quality video only format you can use `-f worstvideo`.
+For example, to download the worst quality video-only format you can use `-f worstvideo`.
 
 If you want to download multiple videos and they don't have the same formats available, you can specify the order of preference using slashes. Note that slash is left-associative, i.e. formats on the left hand side are preferred, for example `-f 22/17/18` will download format 22 if it's available, otherwise it will download format 17 if it's available, otherwise it will download format 18 if it's available, otherwise it will complain that no suitable formats are available for download.
 
-If you want to download several formats of the same video use comma as a separator, e.g. `-f 22,17,18` will download all these three formats, of course if they are available. Or more sophisticated example combined with precedence feature `-f 136/137/mp4/bestvideo,140/m4a/bestaudio`.
+If you want to download several formats of the same video use a comma as a separator, e.g. `-f 22,17,18` will download all these three formats, of course if they are available. Or a more sophisticated example combined with the precedence feature: `-f 136/137/mp4/bestvideo,140/m4a/bestaudio`.
 
 You can also filter the video formats by putting a condition in brackets, as in `-f "best[height=720]"` (or `-f "[filesize>10M]"`).
 
@@ -633,15 +641,15 @@ Also filtering work for comparisons `=` (equals), `!=` (not equals), `^=` (begin
  - `protocol`: The protocol that will be used for the actual download, lower-case. `http`, `https`, `rtsp`, `rtmp`, `rtmpe`, `m3u8`, or `m3u8_native`
  - `format_id`: A short description of the format
 
-Note that none of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by video hoster.
+Note that none of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by the video hoster.
 
 Formats for which the value is not known are excluded unless you put a question mark (`?`) after the operator. You can combine format filters, so `-f "[height <=? 720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s.
 
-You can merge the video and audio of two formats into a single file using `-f <video-format>+<audio-format>` (requires ffmpeg or avconv installed), for example `-f bestvideo+bestaudio` will download best video only format, best audio only format and mux them together with ffmpeg/avconv.
+You can merge the video and audio of two formats into a single file using `-f <video-format>+<audio-format>` (requires ffmpeg or avconv installed), for example `-f bestvideo+bestaudio` will download the best video-only format, the best audio-only format and mux them together with ffmpeg/avconv.
 
 Format selectors can also be grouped using parentheses, for example if you want to download the best mp4 and webm formats with a height lower than 480 you can use `-f '(mp4,webm)[height<480]'`.
 
-Since the end of April 2015 and version 2015.04.26 youtube-dl uses `-f bestvideo+bestaudio/best` as default format selection (see [#5447](https://github.com/rg3/youtube-dl/issues/5447), [#5456](https://github.com/rg3/youtube-dl/issues/5456)). If ffmpeg or avconv are installed this results in downloading `bestvideo` and `bestaudio` separately and muxing them together into a single file giving the best overall quality available. Otherwise it falls back to `best` and results in downloading the best available quality served as a single file. `best` is also needed for videos that don't come from YouTube because they don't provide the audio and video in two different files. If you want to only download some DASH formats (for example if you are not interested in getting videos with a resolution higher than 1080p), you can add `-f bestvideo[height<=?1080]+bestaudio/best` to your configuration file. Note that if you use youtube-dl to stream to `stdout` (and most likely to pipe it to your media player then), i.e. you explicitly specify output template as `-o -`, youtube-dl still uses `-f best` format selection in order to start content delivery immediately to your player and not to wait until `bestvideo` and `bestaudio` are downloaded and muxed.
+Since the end of April 2015 and version 2015.04.26, youtube-dl uses `-f bestvideo+bestaudio/best` as the default format selection (see [#5447](https://github.com/rg3/youtube-dl/issues/5447), [#5456](https://github.com/rg3/youtube-dl/issues/5456)). If ffmpeg or avconv are installed this results in downloading `bestvideo` and `bestaudio` separately and muxing them together into a single file giving the best overall quality available. Otherwise it falls back to `best` and results in downloading the best available quality served as a single file. `best` is also needed for videos that don't come from YouTube because they don't provide the audio and video in two different files. If you want to only download some DASH formats (for example if you are not interested in getting videos with a resolution higher than 1080p), you can add `-f bestvideo[height<=?1080]+bestaudio/best` to your configuration file. Note that if you use youtube-dl to stream to `stdout` (and most likely to pipe it to your media player then), i.e. you explicitly specify output template as `-o -`, youtube-dl still uses `-f best` format selection in order to start content delivery immediately to your player and not to wait until `bestvideo` and `bestaudio` are downloaded and muxed.
 
 If you want to preserve the old format selection behavior (prior to youtube-dl 2015.04.26), i.e. you want to download the best available quality media served as a single file, you should explicitly specify your choice with `-f best`. You may want to add it to the [configuration file](#configuration) in order not to type it every time you run youtube-dl.
 
@@ -661,7 +669,11 @@ $ 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
@@ -716,7 +728,7 @@ Add a file exclusion for `youtube-dl.exe` in Windows Defender settings.
 
 YouTube changed their playlist format in March 2014 and later on, so you'll need at least youtube-dl 2014.07.25 to download all YouTube videos.
 
-If you have installed youtube-dl with a package manager, pip, setup.py or a tarball, please use that to update. Note that Ubuntu packages do not seem to get updated anymore. Since we are not affiliated with Ubuntu, there is little we can do. Feel free to [report bugs](https://bugs.launchpad.net/ubuntu/+source/youtube-dl/+filebug) to the [Ubuntu packaging guys](mailto:ubuntu-motu@lists.ubuntu.com?subject=outdated%20version%20of%20youtube-dl) - all they have to do is update the package to a somewhat recent version. See above for a way to update.
+If you have installed youtube-dl with a package manager, pip, setup.py or a tarball, please use that to update. Note that Ubuntu packages do not seem to get updated anymore. Since we are not affiliated with Ubuntu, there is little we can do. Feel free to [report bugs](https://bugs.launchpad.net/ubuntu/+source/youtube-dl/+filebug) to the [Ubuntu packaging people](mailto:ubuntu-motu@lists.ubuntu.com?subject=outdated%20version%20of%20youtube-dl) - all they have to do is update the package to a somewhat recent version. See above for a way to update.
 
 ### I'm getting an error when trying to use output template: `error: using output template conflicts with using title, video ID or auto number`
 
@@ -742,7 +754,7 @@ 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 +836,42 @@ 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"
+
+### Should I add `--hls-prefer-native` into my config?
+
+When youtube-dl detects an HLS video, it can download it either with the built-in downloader or ffmpeg. Since many HLS streams are slightly invalid and ffmpeg/youtube-dl each handle some invalid cases better than the other, there is an option to switch the downloader if needed.
+
+When youtube-dl knows that one particular downloader works better for a given website, that downloader will be picked. Otherwise, youtube-dl will pick the best downloader for general compatibility, which at the moment happens to be ffmpeg. This choice may change in future versions of youtube-dl, with improvements of the built-in downloader and/or ffmpeg.
+
+In particular, the generic extractor (used when your website is not in the [list of supported sites by youtube-dl](http://rg3.github.io/youtube-dl/supportedsites.html) cannot mandate one specific downloader.
+
+If you put either `--hls-prefer-native` or `--hls-prefer-ffmpeg` into your configuration, a different subset of videos will fail to download correctly. Instead, it is much better to [file an issue](https://yt-dl.org/bug) or a pull request which details why the native or the ffmpeg HLS downloader is a better choice for your use case.
+
 ### 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.
@@ -858,7 +902,7 @@ If you want to find out whether a given URL is supported, simply call youtube-dl
 
 # Why do I need to go through that much red tape when filing bugs?
 
-Before we had the issue template, despite our extensive [bug reporting instructions](#bugs), about 80% of the issue reports we got were useless, for instance because people used ancient versions hundreds of releases old, because of simple syntactic errors (not in youtube-dl but in general shell usage), because the problem was alrady reported multiple times before, because people did not actually read an error message, even if it said "please install ffmpeg", because people did not mention the URL they were trying to download and many more simple, easy-to-avoid problems, many of whom were totally unrelated to youtube-dl.
+Before we had the issue template, despite our extensive [bug reporting instructions](#bugs), about 80% of the issue reports we got were useless, for instance because people used ancient versions hundreds of releases old, because of simple syntactic errors (not in youtube-dl but in general shell usage), because the problem was already reported multiple times before, because people did not actually read an error message, even if it said "please install ffmpeg", because people did not mention the URL they were trying to download and many more simple, easy-to-avoid problems, many of whom were totally unrelated to youtube-dl.
 
 youtube-dl is an open-source project manned by too few volunteers, so we'd rather spend time fixing bugs where we are certain none of those simple problems apply, and where we can be reasonably confident to be able to reproduce the issue without asking the reporter repeatedly. As such, the output of `youtube-dl -v YOUR_URL_HERE` is really all that's required to file an issue. The issue template also guides you through some basic steps you can do, such as checking that your version of youtube-dl is current.
 
@@ -879,7 +923,7 @@ To run the test, simply invoke your favorite test runner, or execute a test file
 If you want to create a build of youtube-dl yourself, you'll need
 
 * python
-* make (both GNU make and BSD make are supported)
+* make (only GNU make is supported)
 * pandoc
 * zip
 * nosetests
@@ -961,19 +1005,19 @@ In any case, thank you very much for your contributions!
 
 This section introduces a guide lines for writing idiomatic, robust and future-proof extractor code.
 
-Extractors are very fragile by nature since they depend on the layout of the source data provided by 3rd party media hoster out of your control and this layout tend to change. As an extractor implementer your task is not only to write code that will extract media links and metadata correctly but also to minimize code dependency on source's layout changes and even to make the code foresee potential future changes and be ready for that. This is important because it will allow extractor not to break on minor layout changes thus keeping old youtube-dl versions working. Even though this breakage issue is easily fixed by emitting a new version of youtube-dl with fix incorporated all the previous version become broken in all repositories and distros' packages that may not be so prompt in fetching the update from us. Needless to say some may never receive an update at all that is possible for non rolling release distros.
+Extractors are very fragile by nature since they depend on the layout of the source data provided by 3rd party media hosters out of your control and this layout tends to change. As an extractor implementer your task is not only to write code that will extract media links and metadata correctly but also to minimize dependency on the source's layout and even to make the code foresee potential future changes and be ready for that. This is important because it will allow the extractor not to break on minor layout changes thus keeping old youtube-dl versions working. Even though this breakage issue is easily fixed by emitting a new version of youtube-dl with a fix incorporated, all the previous versions become broken in all repositories and distros' packages that may not be so prompt in fetching the update from us. Needless to say, some non rolling release distros may never receive an update at all.
 
 ### Mandatory and optional metafields
 
-For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by [information dictionary](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L75-L257) or simply *info dict*. Only the following meta fields in *info dict* are considered mandatory for successful extraction process by youtube-dl:
+For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by an [information dictionary](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L75-L257) or simply *info dict*. Only the following meta fields in the *info dict* are considered mandatory for a successful extraction process by youtube-dl:
 
  - `id` (media identifier)
  - `title` (media title)
  - `url` (media download URL) or `formats`
 
-In fact only the last option is technically mandatory (i.e. if you can't figure out the download location of the media the extraction does not make any sense). But by convention youtube-dl also treats `id` and `title` to be mandatory. Thus aforementioned metafields are the critical data the extraction does not make any sense without and if any of them fail to be extracted then extractor is considered completely broken.
+In fact only the last option is technically mandatory (i.e. if you can't figure out the download location of the media the extraction does not make any sense). But by convention youtube-dl also treats `id` and `title` as mandatory. Thus the aforementioned metafields are the critical data that the extraction does not make any sense without and if any of them fail to be extracted then the extractor is considered completely broken.
 
-[Any field](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L149-L257) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerate** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields.
+[Any field](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L149-L257) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerant** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields.
 
 #### Example
 
@@ -993,7 +1037,7 @@ Assume at this point `meta`'s layout is:
 }
 ```
 
-Assume you want to extract `summary` and put into resulting info dict as `description`. Since `description` is optional metafield you should be ready that this key may be missing from the `meta` dict, so that you should extract it like:
+Assume you want to extract `summary` and put it into the resulting info dict as `description`. Since `description` is an optional metafield you should be ready that this key may be missing from the `meta` dict, so that you should extract it like:
 
 ```python
 description = meta.get('summary')  # correct
@@ -1005,7 +1049,7 @@ and not like:
 description = meta['summary']  # incorrect
 ```
 
-The latter will break extraction process with `KeyError` if `summary` disappears from `meta` at some time later but with former approach extraction will just go ahead with `description` set to `None` that is perfectly fine (remember `None` is equivalent for absence of data). 
+The latter will break extraction process with `KeyError` if `summary` disappears from `meta` at some later time but with the former approach extraction will just go ahead with `description` set to `None` which is perfectly fine (remember `None` is equivalent to the absence of data).
 
 Similarly, you should pass `fatal=False` when extracting optional data from a webpage with `_search_regex`, `_html_search_regex` or similar methods, for instance:
 
@@ -1025,21 +1069,21 @@ description = self._search_regex(
     webpage, 'description', default=None)
 ```
 
-On failure this code will silently continue the extraction with `description` set to `None`. That is useful for metafields that are known to may or may not be present.
+On failure this code will silently continue the extraction with `description` set to `None`. That is useful for metafields that may or may not be present.
  
 ### Provide fallbacks
 
-When extracting metadata try to provide several scenarios for that. For example if `title` is present in several places/sources try extracting from at least some of them. This would make it more future-proof in case some of the sources became unavailable.
+When extracting metadata try to do so from multiple sources. For example if `title` is present in several places, try extracting from at least some of them. This makes it more future-proof in case some of the sources become unavailable.
 
 #### Example
 
-Say `meta` from previous example has a `title` and you are about to extract it. Since `title` is mandatory meta field you should end up with something like:
+Say `meta` from the previous example has a `title` and you are about to extract it. Since `title` is a mandatory meta field you should end up with something like:
 
 ```python
 title = meta['title']
 ```
 
-If `title` disappeares from `meta` in future due to some changes on hoster's side the extraction would fail since `title` is mandatory. That's expected.
+If `title` disappears from `meta` in future due to some changes on the hoster's side the extraction would fail since `title` is mandatory. That's expected.
 
 Assume that you have some another source you can extract `title` from, for example `og:title` HTML meta of a `webpage`. In this case you can provide a fallback scenario:
 
@@ -1076,7 +1120,7 @@ title = self._search_regex(
     webpage, 'title', group='title')
 ```
 
-Note how you tolerate potential changes in `style` attribute's value or switch from using double quotes to single for `class` attribute: 
+Note how you tolerate potential changes in the `style` attribute's value or switch from using double quotes to single for `class` attribute: 
 
 The code definitely should not look like:
 
@@ -1146,7 +1190,7 @@ with youtube_dl.YoutubeDL(ydl_opts) as ydl:
 
 # BUGS
 
-Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues>. Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. For discussions, join us in the IRC channel [#youtube-dl](irc://chat.freenode.net/#youtube-dl) on freenode ([webchat](http://webchat.freenode.net/?randomnick=1&channels=youtube-dl)).
+Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues>. Unless you were prompted to or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. For discussions, join us in the IRC channel [#youtube-dl](irc://chat.freenode.net/#youtube-dl) on freenode ([webchat](http://webchat.freenode.net/?randomnick=1&channels=youtube-dl)).
 
 **Please include the full output of youtube-dl when run with `-v`**, i.e. **add** `-v` flag to **your command line**, copy the **whole** output and post it in the issue body wrapped in \`\`\` for better formatting. It should look similar to this:
 ```
@@ -1162,7 +1206,7 @@ $ youtube-dl -v <your command line>
 [debug] Proxy map: {}
 ...
 ```
-**Do not post screenshots of verbose log only plain text is acceptable.**
+**Do not post screenshots of verbose logs; only plain text is acceptable.**
 
 The output (including the first lines) contains important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
 
@@ -1196,7 +1240,7 @@ 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?
 
@@ -1216,7 +1260,7 @@ Only post features that you (or an incapacitated friend you can personally talk
 
 ###  Is your question about youtube-dl?
 
-It may sound strange, but some bug reports we receive are completely unrelated to youtube-dl and relate to a different or even the reporter's own application. Please make sure that you are actually using youtube-dl. If you are using a UI for youtube-dl, report the bug to the maintainer of the actual application providing the UI. On the other hand, if your UI for youtube-dl fails in some way you believe is related to youtube-dl, by all means, go ahead and report the bug.
+It may sound strange, but some bug reports we receive are completely unrelated to youtube-dl and relate to a different, or even the reporter's own, application. Please make sure that you are actually using youtube-dl. If you are using a UI for youtube-dl, report the bug to the maintainer of the actual application providing the UI. On the other hand, if your UI for youtube-dl fails in some way you believe is related to youtube-dl, by all means, go ahead and report the bug.
 
 # COPYRIGHT
 

devscripts/lazy_load_template.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re

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'
 

devscripts/release.sh

@@ -60,6 +60,9 @@ if ! type pandoc >/dev/null 2>/dev/null; then echo 'ERROR: pandoc is missing'; e
 if ! python3 -c 'import rsa' 2>/dev/null; then echo 'ERROR: python3-rsa is missing'; exit 1; fi
 if ! python3 -c 'import wheel' 2>/dev/null; then echo 'ERROR: wheel is missing'; exit 1; fi
 
+read -p "Is ChangeLog up to date? (y/n) " -n 1
+if [[ ! $REPLY =~ ^[Yy]$ ]]; then exit 1; fi
+
 /bin/echo -e "\n### First of all, testing..."
 make clean
 if $skip_tests ; then

docs/conf.py

@@ -1,4 +1,4 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 #
 # youtube-dl documentation build configuration file, created by
 # sphinx-quickstart on Fri Mar 14 21:05:43 2014.

docs/supportedsites.md

@@ -13,12 +13,16 @@
  - **5min**
  - **8tracks**
  - **91porn**
+ - **9c9media**
+ - **9c9media:stack**
  - **9gag**
  - **9now.com.au**
  - **abc.net.au**
- - **Abc7News**
+ - **abc.net.au:iview**
  - **abcnews**
  - **abcnews:video**
+ - **abcotvs**: ABC Owned Television Stations
+ - **abcotvs:clips**
  - **AcademicEarth:Course**
  - **acast**
  - **acast:channel**
@@ -30,11 +34,12 @@
  - **AdultSwim**
  - **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network
  - **AfreecaTV**: afreecatv.com
- - **Aftonbladet**
  - **AirMozilla**
  - **AlJazeera**
  - **Allocine**
  - **AlphaPorno**
+ - **AMCNetworks**
+ - **anderetijden**: npo.nl and ntr.nl
  - **AnimeOnDemand**
  - **anitube.se**
  - **AnySex**
@@ -65,6 +70,10 @@
  - **audiomack**
  - **audiomack:album**
  - **auroravid**: AuroraVid
+ - **AWAAN**
+ - **awaan:live**
+ - **awaan:season**
+ - **awaan:video**
  - **Azubu**
  - **AzubuLive**
  - **BaiduVideo**: 百度视频
@@ -77,9 +86,10 @@
  - **bbc.co.uk:article**: BBC articles
  - **bbc.co.uk:iplayer:playlist**
  - **bbc.co.uk:playlist**
- - **BeatportPro**
+ - **Beatport**
  - **Beeg**
  - **BehindKink**
+ - **BellMedia**
  - **Bet**
  - **Bigflix**
  - **Bild**: Bild.de
@@ -101,6 +111,7 @@
  - **bt:vestlendingen**: Bergens Tidende - Vestlendingen
  - **BuzzFeed**
  - **BYUtv**
+ - **BYUtvEvent**
  - **Camdemy**
  - **CamdemyFolder**
  - **CamWithHer**
@@ -109,17 +120,22 @@
  - **Canvas**
  - **CarambaTV**
  - **CarambaTVPage**
- - **CBC**
- - **CBCPlayer**
+ - **CartoonNetwork**
+ - **cbc.ca**
+ - **cbc.ca:player**
+ - **cbc.ca:watch**
+ - **cbc.ca:watch:video**
  - **CBS**
  - **CBSInteractive**
  - **CBSLocal**
- - **CBSNews**: CBS News
- - **CBSNewsLiveVideo**: CBS News Live Videos
+ - **cbsnews**: CBS News
+ - **cbsnews:livevideo**: CBS News Live Videos
  - **CBSSports**
+ - **CCTV**
  - **CDA**
  - **CeskaTelevize**
  - **channel9**: Channel 9
+ - **CharlieRose**
  - **Chaturbate**
  - **Chilloutzone**
  - **chirbit**
@@ -142,6 +158,7 @@
  - **CollegeRama**
  - **ComCarCoff**
  - **ComedyCentral**
+ - **ComedyCentralShortname**
  - **ComedyCentralTV**
  - **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED
  - **Coub**
@@ -154,10 +171,11 @@
  - **CSNNE**
  - **CSpan**: C-SPAN
  - **CtsNews**: 華視新聞
- - **CTV**
  - **CTVNews**
  - **culturebox.francetvinfo.fr**
  - **CultureUnplugged**
+ - **curiositystream**
+ - **curiositystream:collection**
  - **CWTV**
  - **DailyMail**
  - **dailymotion**
@@ -169,10 +187,6 @@
  - **daum.net:playlist**
  - **daum.net:user**
  - **DBTV**
- - **DCN**
- - **dcn:live**
- - **dcn:season**
- - **dcn:video**
  - **DctpTv**
  - **DeezerPlaylist**
  - **defense.gouv.fr**
@@ -181,6 +195,7 @@
  - **DigitallySpeaking**
  - **Digiteka**
  - **Discovery**
+ - **DiscoveryGo**
  - **Dotsub**
  - **DouyuTV**: 斗鱼
  - **DPlay**
@@ -213,13 +228,14 @@
  - **EsriVideo**
  - **Europa**
  - **EveryonesMixtape**
- - **exfm**: ex.fm
  - **ExpoTV**
  - **ExtremeTube**
  - **EyedoTV**
  - **facebook**
+ - **FacebookPluginsVideo**
  - **faz.net**
  - **fc2**
+ - **fc2:embed**
  - **Fczenit**
  - **features.aol.com**
  - **fernsehkritik.tv**
@@ -232,11 +248,12 @@
  - **Formula1**
  - **FOX**
  - **Foxgay**
- - **FoxNews**: Fox News and Fox Business Video
+ - **foxnews**: Fox News and Fox Business Video
+ - **foxnews:article**
+ - **foxnews:insider**
  - **FoxSports**
  - **france2.fr:generation-quoi**
  - **FranceCulture**
- - **FranceCultureEmission**
  - **FranceInter**
  - **francetv**: France 2, 3, 4, 5 and Ô
  - **francetvinfo.fr**
@@ -246,8 +263,8 @@
  - **Funimation**
  - **FunnyOrDie**
  - **Fusion**
+ - **FXNetworks**
  - **GameInformer**
- - **Gamekings**
  - **GameOne**
  - **gameone:playlist**
  - **Gamersyde**
@@ -262,9 +279,9 @@
  - **Glide**: Glide mobile video messages (glide.me)
  - **Globo**
  - **GloboArticle**
+ - **Go**
  - **GodTube**
  - **GodTV**
- - **GoldenMoustache**
  - **Golem**
  - **GoogleDrive**
  - **Goshgay**
@@ -272,11 +289,14 @@
  - **Groupon**
  - **Hark**
  - **HBO**
+ - **HBOEpisode**
  - **HearThisAt**
  - **Heise**
  - **HellPorno**
  - **Helsinki**: helsinki.fi
  - **HentaiStigma**
+ - **HGTV**
+ - **hgtv.com:show**
  - **HistoricFilms**
  - **history:topic**: History.com Topic
  - **hitbox**
@@ -288,6 +308,7 @@
  - **HowStuffWorks**
  - **HRTi**
  - **HRTiPlaylist**
+ - **Huajiao**: 花椒直播
  - **HuffPost**: Huffington Post
  - **Hypem**
  - **Iconosquare**
@@ -309,7 +330,10 @@
  - **ivi**: ivi.ru
  - **ivi:compilation**: ivi.ru compilations
  - **ivideon**: Ivideon TV
+ - **Iwara**
  - **Izlesene**
+ - **Jamendo**
+ - **JamendoAlbum**
  - **JeuxVideo**
  - **Jove**
  - **jpopsuki.tv**
@@ -322,6 +346,7 @@
  - **KarriereVideos**
  - **keek**
  - **KeezMovies**
+ - **Ketnet**
  - **KhanAcademy**
  - **KickStarter**
  - **KonserthusetPlay**
@@ -337,11 +362,13 @@
  - **kuwo:song**: 酷我音乐
  - **la7.it**
  - **Laola1Tv**
+ - **LCI**
  - **Lcp**
  - **LcpPlay**
  - **Le**: 乐视网
  - **Learnr**
  - **Lecture2Go**
+ - **LEGO**
  - **Lemonde**
  - **LePlaylist**
  - **LetvCloud**: 乐视云
@@ -367,6 +394,8 @@
  - **mailru**: Видео@Mail.Ru
  - **MakersChannel**
  - **MakerTV**
+ - **mangomolo:live**
+ - **mangomolo:video**
  - **MatchTV**
  - **MDR**: MDR.DE and KiKA
  - **media.ccc.de**
@@ -375,6 +404,7 @@
  - **Metacritic**
  - **Mgoon**
  - **MGTV**: 芒果TV
+ - **MiaoPai**
  - **Minhateca**
  - **MinistryGrid**
  - **Minoto**
@@ -396,10 +426,13 @@
  - **MovieClips**
  - **MovieFap**
  - **Moviezine**
+ - **MovingImage**
  - **MPORA**
  - **MSN**
- - **MTV**
+ - **mtg**: MTG services
+ - **mtv**
  - **mtv.de**
+ - **mtv:video**
  - **mtvservices:embedded**
  - **MuenchenTV**: münchen.tv
  - **MusicPlayOn**
@@ -415,11 +448,13 @@
  - **MyVidster**
  - **n-tv.de**
  - **natgeo**
- - **natgeo:channel**
+ - **natgeo:episodeguide**
+ - **natgeo:video**
  - **Naver**
  - **NBA**
  - **NBC**
  - **NBCNews**
+ - **NBCOlympics**
  - **NBCSports**
  - **NBCSportsVPlayer**
  - **ndr**: NDR.de - Norddeutscher Rundfunk
@@ -441,18 +476,20 @@
  - **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**
  - **nhl.com:videocenter:category**: NHL videocenter category
  - **nick.com**
  - **nick.de**
+ - **nicknight**
  - **niconico**: ニコニコ動画
  - **NiconicoPlaylist**
- - **NineCNineMedia**
  - **Nintendo**
  - **njoy**: N-JOY
  - **njoy:embed**
+ - **NobelPrize**
  - **Noco**
  - **Normalboots**
  - **NosVideo**
@@ -477,6 +514,7 @@
  - **Nuvid**
  - **NYTimes**
  - **NYTimesArticle**
+ - **NZZ**
  - **ocw.mit.edu**
  - **OdaTV**
  - **Odnoklassniki**
@@ -493,6 +531,7 @@
  - **orf:iptv**: iptv.ORF.at
  - **orf:oe1**: Radio Österreich 1
  - **orf:tvthek**: ORF TVthek
+ - **PandaTV**: 熊猫TV
  - **pandora.tv**: 판도라TV
  - **parliamentlive.tv**: UK parliament videos
  - **Patreon**
@@ -507,7 +546,6 @@
  - **Pinkbike**
  - **Pladform**
  - **play.fm**
- - **played.to**
  - **PlaysTV**
  - **Playtvak**: Playtvak.cz, iDNES.cz and Lidovky.cz
  - **Playvid**
@@ -517,7 +555,10 @@
  - **plus.google**: Google Plus
  - **pluzz.francetv.fr**
  - **podomatic**
+ - **Pokemon**
  - **PolskieRadio**
+ - **PolskieRadioCategory**
+ - **PornCom**
  - **PornHd**
  - **PornHub**: PornHub and Thumbzilla
  - **PornHubPlaylist**
@@ -550,6 +591,8 @@
  - **RDS**: RDS.ca
  - **RedTube**
  - **RegioTV**
+ - **RENTV**
+ - **RENTVArticle**
  - **Restudy**
  - **Reuters**
  - **ReverbNation**
@@ -557,10 +600,12 @@
  - **revision3:embed**
  - **RICE**
  - **RingTV**
+ - **RMCDecouverte**
  - **RockstarGames**
  - **RoosterTeeth**
  - **RottenTomatoes**
  - **Roxwel**
+ - **Rozhlas**
  - **RTBF**
  - **rte**: Raidió Teilifís Éireann TV
  - **rte:radio**: Raidió Teilifís Éireann radio
@@ -603,7 +648,7 @@
  - **ServingSys**
  - **Sexu**
  - **Shahid**
- - **Shared**: shared.sx and vivo.sx
+ - **Shared**: shared.sx
  - **ShareSix**
  - **Sina**
  - **SixPlay**
@@ -618,6 +663,7 @@
  - **smotri:user**: Smotri.com user videos
  - **Snotr**
  - **Sohu**
+ - **SonyLIV**
  - **soundcloud**
  - **soundcloud:playlist**
  - **soundcloud:search**: Soundcloud search
@@ -644,7 +690,6 @@
  - **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**
@@ -658,10 +703,11 @@
  - **SWRMediathek**
  - **Syfy**
  - **SztvHu**
+ - **t-online.de**
  - **Tagesschau**
  - **tagesschau:player**
- - **Tapely**
  - **Tass**
+ - **TBS**
  - **TDSLifeway**
  - **teachertube**: teachertube.com videos
  - **teachertube:user:collection**: teachertube.com user and collection videos
@@ -676,19 +722,22 @@
  - **Telecinco**: telecinco.es, cuatro.com and mediaset.es
  - **Telegraaf**
  - **TeleMB**
+ - **TeleQuebec**
  - **TeleTask**
  - **Telewebion**
  - **TF1**
+ - **TFO**
  - **TheIntercept**
+ - **theoperaplatform**
  - **ThePlatform**
  - **ThePlatformFeed**
  - **TheScene**
  - **TheSixtyOne**
  - **TheStar**
+ - **TheWeatherChannel**
  - **ThisAmericanLife**
  - **ThisAV**
- - **THVideo**
- - **THVideoPlaylist**
+ - **ThisOldHouse**
  - **tinypic**: tinypic.com videos
  - **tlc.de**
  - **TMZ**
@@ -702,8 +751,7 @@
  - **ToypicsUser**: Toypics user profile
  - **TrailerAddict** (Currently broken)
  - **Trilulilu**
- - **trollvids**
- - **TruTube**
+ - **TruTV**
  - **Tube8**
  - **TubiTv**
  - **tudou**
@@ -725,9 +773,10 @@
  - **TVCArticle**
  - **tvigle**: Интернет-телевидение Tvigle.ru
  - **tvland.com**
+ - **TVNoe**
  - **tvp**: Telewizja Polska
+ - **tvp:embed**: Telewizja Polska
  - **tvp:series**
- - **TVPlay**: TV3Play and related services
  - **Tweakers**
  - **twitch:chapter**
  - **twitch:clips**
@@ -743,8 +792,12 @@
  - **udemy:course**
  - **UDNEmbed**: 聯合影音
  - **Unistra**
+ - **uol.com.br**
+ - **uplynk**
+ - **uplynk:preplay**
  - **Urort**: NRK P3 Urørt
  - **URPlay**
+ - **USANetwork**
  - **USAToday**
  - **ustream**
  - **ustream:channel**
@@ -760,7 +813,9 @@
  - **VevoPlaylist**
  - **VGTV**: VGTV, BTTV, FTV, Aftenposten and Aftonbladet
  - **vh1.com**
+ - **Viafree**
  - **Vice**
+ - **Viceland**
  - **ViceShow**
  - **Vidbit**
  - **Viddler**
@@ -800,11 +855,13 @@
  - **Vimple**: Vimple - one-click video hosting
  - **Vine**
  - **vine:user**
+ - **Vivo**: vivo.sx
  - **vk**: VK
  - **vk:uservideos**: VK - User's Videos
  - **vk:wallpost**
  - **vlive**
  - **Vodlocker**
+ - **VODPlatform**
  - **VoiceRepublic**
  - **VoxMedia**
  - **Vporn**
@@ -812,6 +869,7 @@
  - **VRT**
  - **vube**: Vube.com
  - **VuClip**
+ - **VyboryMos**
  - **Walla**
  - **washingtonpost**
  - **washingtonpost:article**
@@ -825,7 +883,7 @@
  - **wholecloud**: WholeCloud
  - **Wimp**
  - **Wistia**
- - **WNL**
+ - **wnl**: npo.nl and ntr.nl
  - **WorldStarHipHop**
  - **wrzuta.pl**
  - **wrzuta.pl:playlist**
@@ -879,6 +937,4 @@
  - **Zapiks**
  - **ZDF**
  - **ZDFChannel**
- - **zingmp3:album**: mp3.zing.vn albums
- - **zingmp3:song**: mp3.zing.vn songs
- - **ZippCast**
+ - **zingmp3**: mp3.zing.vn

setup.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*-
+# coding: utf-8
 
 from __future__ import print_function
 

test/test_InfoExtractor.py

@@ -48,6 +48,9 @@ class TestInfoExtractor(unittest.TestCase):
         self.assertEqual(ie._og_search_property('foobar', html), 'Foo')
         self.assertEqual(ie._og_search_property('test1', html), 'foo > < bar')
         self.assertEqual(ie._og_search_property('test2', html), 'foo >//< bar')
+        self.assertEqual(ie._og_search_property(('test0', 'test1'), html), 'foo > < bar')
+        self.assertRaises(RegexNotFoundError, ie._og_search_property, 'test0', html, None, fatal=True)
+        self.assertRaises(RegexNotFoundError, ie._og_search_property, ('test0', 'test00'), html, None, fatal=True)
 
     def test_html_search_meta(self):
         ie = self.ie

test/test_YoutubeDL.py

@@ -605,6 +605,7 @@ class TestYoutubeDL(unittest.TestCase):
             'extractor': 'TEST',
             'duration': 30,
             'filesize': 10 * 1024,
+            'playlist_id': '42',
         }
         second = {
             'id': '2',
@@ -614,6 +615,7 @@ class TestYoutubeDL(unittest.TestCase):
             'duration': 10,
             'description': 'foo',
             'filesize': 5 * 1024,
+            'playlist_id': '43',
         }
         videos = [first, second]
 
@@ -650,6 +652,10 @@ class TestYoutubeDL(unittest.TestCase):
         res = get_videos(f)
         self.assertEqual(res, ['1'])
 
+        f = match_filter_func('playlist_id = 42')
+        res = get_videos(f)
+        self.assertEqual(res, ['1'])
+
     def test_playlist_items_selection(self):
         entries = [{
             'id': compat_str(i),

test/test_http.py

@@ -87,7 +87,7 @@ class TestHTTP(unittest.TestCase):
 
         ydl = YoutubeDL({'logger': FakeLogger()})
         r = ydl.extract_info('http://localhost:%d/302' % self.port)
-        self.assertEqual(r['url'], 'http://localhost:%d/vid.mp4' % self.port)
+        self.assertEqual(r['entries'][0]['url'], 'http://localhost:%d/vid.mp4' % self.port)
 
 
 class TestHTTPS(unittest.TestCase):
@@ -111,7 +111,7 @@ class TestHTTPS(unittest.TestCase):
 
         ydl = YoutubeDL({'logger': FakeLogger(), 'nocheckcertificate': True})
         r = ydl.extract_info('https://localhost:%d/video.html' % self.port)
-        self.assertEqual(r['url'], 'https://localhost:%d/vid.mp4' % self.port)
+        self.assertEqual(r['entries'][0]['url'], 'https://localhost:%d/vid.mp4' % self.port)
 
 
 def _build_proxy_handler(name):

test/test_utils.py

@@ -39,9 +39,12 @@ from youtube_dl.utils import (
     is_html,
     js_to_json,
     limit_length,
+    mimetype2ext,
+    month_by_name,
     ohdave_rsa_encrypt,
     OnDemandPagedList,
     orderedSet,
+    parse_age_limit,
     parse_duration,
     parse_filesize,
     parse_count,
@@ -66,6 +69,7 @@ from youtube_dl.utils import (
     uppercase_escape,
     lowercase_escape,
     url_basename,
+    base_url,
     urlencode_postdata,
     urshift,
     update_url_query,
@@ -289,6 +293,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unified_strdate('25-09-2014'), '20140925')
         self.assertEqual(unified_strdate('27.02.2016 17:30'), '20160227')
         self.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None)
+        self.assertEqual(unified_strdate('Feb 7, 2016 at 6:35 pm'), '20160207')
 
     def test_unified_timestamps(self):
         self.assertEqual(unified_timestamp('December 21, 2010'), 1292889600)
@@ -308,6 +313,8 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unified_timestamp('25-09-2014'), 1411603200)
         self.assertEqual(unified_timestamp('27.02.2016 17:30'), 1456594200)
         self.assertEqual(unified_timestamp('UNKNOWN DATE FORMAT'), None)
+        self.assertEqual(unified_timestamp('May 16, 2016 11:15 PM'), 1463440500)
+        self.assertEqual(unified_timestamp('Feb 7, 2016 at 6:35 pm'), 1454870100)
 
     def test_determine_ext(self):
         self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
@@ -431,6 +438,27 @@ class TestUtil(unittest.TestCase):
             url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
             'trailer.mp4')
 
+    def test_base_url(self):
+        self.assertEqual(base_url('http://foo.de/'), 'http://foo.de/')
+        self.assertEqual(base_url('http://foo.de/bar'), 'http://foo.de/')
+        self.assertEqual(base_url('http://foo.de/bar/'), 'http://foo.de/bar/')
+        self.assertEqual(base_url('http://foo.de/bar/baz'), 'http://foo.de/bar/')
+        self.assertEqual(base_url('http://foo.de/bar/baz?x=z/x/c'), 'http://foo.de/bar/')
+
+    def test_parse_age_limit(self):
+        self.assertEqual(parse_age_limit(None), None)
+        self.assertEqual(parse_age_limit(False), None)
+        self.assertEqual(parse_age_limit('invalid'), None)
+        self.assertEqual(parse_age_limit(0), 0)
+        self.assertEqual(parse_age_limit(18), 18)
+        self.assertEqual(parse_age_limit(21), 21)
+        self.assertEqual(parse_age_limit(22), None)
+        self.assertEqual(parse_age_limit('18'), 18)
+        self.assertEqual(parse_age_limit('18+'), 18)
+        self.assertEqual(parse_age_limit('PG-13'), 13)
+        self.assertEqual(parse_age_limit('TV-14'), 14)
+        self.assertEqual(parse_age_limit('TV-MA'), 17)
+
     def test_parse_duration(self):
         self.assertEqual(parse_duration(None), None)
         self.assertEqual(parse_duration(False), None)
@@ -609,6 +637,22 @@ 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_month_by_name(self):
+        self.assertEqual(month_by_name(None), None)
+        self.assertEqual(month_by_name('December', 'en'), 12)
+        self.assertEqual(month_by_name('décembre', 'fr'), 12)
+        self.assertEqual(month_by_name('December'), 12)
+        self.assertEqual(month_by_name('décembre'), None)
+        self.assertEqual(month_by_name('Unknown', 'unknown'), None)
+
     def test_parse_codecs(self):
         self.assertEqual(parse_codecs(''), {})
         self.assertEqual(parse_codecs('avc1.77.30, mp4a.40.2'), {
@@ -696,6 +740,9 @@ 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"})
@@ -801,7 +848,10 @@ 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)
@@ -952,6 +1002,7 @@ 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

@@ -0,0 +1,70 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+from __future__ import unicode_literals
+
+import unittest
+
+import sys
+import os
+import subprocess
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+
+
+class TestVerboseOutput(unittest.TestCase):
+    def test_private_info_arg(self):
+        outp = subprocess.Popen(
+            [
+                sys.executable, 'youtube_dl/__main__.py', '-v',
+                '--username', 'johnsmith@gmail.com',
+                '--password', 'secret',
+            ], cwd=rootDir, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        sout, serr = outp.communicate()
+        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(
+            [
+                sys.executable, 'youtube_dl/__main__.py', '-v',
+                '-u', 'johnsmith@gmail.com',
+                '-p', 'secret',
+            ], cwd=rootDir, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        sout, serr = outp.communicate()
+        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(
+            [
+                sys.executable, 'youtube_dl/__main__.py', '-v',
+                '--username=johnsmith@gmail.com',
+                '--password=secret',
+            ], cwd=rootDir, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        sout, serr = outp.communicate()
+        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(
+            [
+                sys.executable, 'youtube_dl/__main__.py', '-v',
+                '-u=johnsmith@gmail.com',
+                '-p=secret',
+            ], cwd=rootDir, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        sout, serr = outp.communicate()
+        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

@@ -1,5 +1,5 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*-
+# coding: utf-8
 
 from __future__ import absolute_import, unicode_literals
 
@@ -131,6 +131,9 @@ class YoutubeDL(object):
     username:          Username for authentication purposes.
     password:          Password for authentication purposes.
     videopassword:     Password for accessing a video.
+    ap_mso:            Adobe Pass multiple-system operator identifier.
+    ap_username:       Multiple-system operator account username.
+    ap_password:       Multiple-system operator account password.
     usenetrc:          Use netrc for authentication instead.
     verbose:           Print additional info to stdout.
     quiet:             Do not print messages to stdout.
@@ -249,7 +252,16 @@ 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 +1259,10 @@ 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 +1304,7 @@ 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 +1359,7 @@ 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 +1608,9 @@ 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)
@@ -1642,7 +1658,7 @@ class YoutubeDL(object):
                         video_ext, audio_ext = audio.get('ext'), video.get('ext')
                         if video_ext and audio_ext:
                             COMPATIBLE_EXTS = (
-                                ('mp3', 'mp4', 'm4a', 'm4p', 'm4b', 'm4r', 'm4v'),
+                                ('mp3', 'mp4', 'm4a', 'm4p', 'm4b', 'm4r', 'm4v', 'ismv', 'isma'),
                                 ('webm')
                             )
                             for exts in COMPATIBLE_EXTS:

youtube_dl/__init__.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*-
+# coding: utf-8
 
 from __future__ import unicode_literals
 
@@ -34,12 +34,14 @@ from .utils import (
     setproctitle,
     std_headers,
     write_string,
+    render_table,
 )
 from .update import update_self
 from .downloader import (
     FileDownloader,
 )
 from .extractor import gen_extractors, list_extractors
+from .extractor.adobepass import MSO_INFO
 from .YoutubeDL import YoutubeDL
 
 
@@ -118,18 +120,26 @@ def _real_main(argv=None):
                 desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
             write_string(desc + '\n', out=sys.stdout)
         sys.exit(0)
+    if opts.ap_list_mso:
+        table = [[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()]
+        write_string('Supported TV Providers:\n' + render_table(['mso', 'mso name'], table) + '\n', out=sys.stdout)
+        sys.exit(0)
 
     # Conflicting, missing and erroneous options
     if opts.usenetrc and (opts.username is not None or opts.password is not None):
         parser.error('using .netrc conflicts with giving username/password')
     if opts.password is not None and opts.username is None:
         parser.error('account username missing\n')
+    if opts.ap_password is not None and opts.ap_username is None:
+        parser.error('TV Provider account username missing\n')
     if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
         parser.error('using output template conflicts with using title, video ID or auto number')
     if opts.usetitle and opts.useid:
         parser.error('using title conflicts with using video ID')
     if opts.username is not None and opts.password is None:
         opts.password = compat_getpass('Type account password and press [Return]: ')
+    if opts.ap_username is not None and opts.ap_password is None:
+        opts.ap_password = compat_getpass('Type TV provider account password and press [Return]: ')
     if opts.ratelimit is not None:
         numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
         if numeric_limit is None:
@@ -145,6 +155,18 @@ 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
+    if opts.ap_mso and opts.ap_mso not in MSO_INFO:
+        parser.error('Unsupported TV Provider, use --ap-list-mso to get a list of supported TV Providers')
 
     def parse_retries(retries):
         if retries in ('inf', 'infinite'):
@@ -244,8 +266,6 @@ def _real_main(argv=None):
         postprocessors.append({
             'key': 'FFmpegEmbedSubtitle',
         })
-    if opts.xattrs:
-        postprocessors.append({'key': 'XAttrMetadata'})
     if opts.embedthumbnail:
         already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
         postprocessors.append({
@@ -254,6 +274,10 @@ def _real_main(argv=None):
         })
         if not already_have_thumbnail:
             opts.writethumbnail = True
+    # XAttrMetadataPP should be run after post-processors that may change file
+    # contents
+    if opts.xattrs:
+        postprocessors.append({'key': 'XAttrMetadata'})
     # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
     # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
     if opts.exec_cmd:
@@ -261,12 +285,6 @@ def _real_main(argv=None):
             'key': 'ExecAfterDownload',
             'exec_cmd': opts.exec_cmd,
         })
-    if opts.xattr_set_filesize:
-        try:
-            import xattr
-            xattr  # Confuse flake8
-        except ImportError:
-            parser.error('setting filesize xattr requested but python-xattr is not available')
     external_downloader_args = None
     if opts.external_downloader_args:
         external_downloader_args = compat_shlex_split(opts.external_downloader_args)
@@ -283,6 +301,9 @@ def _real_main(argv=None):
         'password': opts.password,
         'twofactor': opts.twofactor,
         'videopassword': opts.videopassword,
+        'ap_mso': opts.ap_mso,
+        'ap_username': opts.ap_username,
+        'ap_password': opts.ap_password,
         'quiet': (opts.quiet or any_getting or any_printing),
         'no_warnings': opts.no_warnings,
         'forceurl': opts.geturl,
@@ -308,6 +329,7 @@ def _real_main(argv=None):
         'nooverwrites': opts.nooverwrites,
         'retries': opts.retries,
         'fragment_retries': opts.fragment_retries,
+        'skip_unavailable_fragments': opts.skip_unavailable_fragments,
         'buffersize': opts.buffersize,
         'noresizebuffer': opts.noresizebuffer,
         'continuedl': opts.continue_dl,
@@ -370,6 +392,7 @@ 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/__init__.py

@@ -7,6 +7,7 @@ from .http import HttpFD
 from .rtmp import RtmpFD
 from .dash import DashSegmentsFD
 from .rtsp import RtspFD
+from .ism import IsmFD
 from .external import (
     get_external_downloader,
     FFmpegFD,
@@ -24,6 +25,7 @@ PROTOCOL_MAP = {
     'rtsp': RtspFD,
     'f4m': F4mFD,
     'http_dash_segments': DashSegmentsFD,
+    'ism': IsmFD,
 }
 
 

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 +343,10 @@ 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)
+            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/dash.py

@@ -1,7 +1,6 @@
 from __future__ import unicode_literals
 
 import os
-import re
 
 from .fragment import FragmentFD
 from ..compat import compat_urllib_error
@@ -19,32 +18,32 @@ class DashSegmentsFD(FragmentFD):
     FD_NAME = 'dashsegments'
 
     def real_download(self, filename, info_dict):
-        base_url = info_dict['url']
-        segment_urls = [info_dict['segment_urls'][0]] if self.params.get('test', False) else info_dict['segment_urls']
-        initialization_url = info_dict.get('initialization_url')
+        segments = info_dict['fragments'][:1] if self.params.get(
+            'test', False) else info_dict['fragments']
 
         ctx = {
             'filename': filename,
-            'total_frags': len(segment_urls) + (1 if initialization_url else 0),
+            'total_frags': len(segments),
         }
 
         self._prepare_and_start_frag_download(ctx)
 
-        def combine_url(base_url, target_url):
-            if re.match(r'^https?://', target_url):
-                return target_url
-            return '%s%s%s' % (base_url, '' if base_url.endswith('/') else '/', target_url)
-
         segments_filenames = []
 
         fragment_retries = self.params.get('fragment_retries', 0)
+        skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
 
-        def append_url_to_file(target_url, tmp_filename, segment_name):
+        def process_segment(segment, tmp_filename, num):
+            segment_url = segment['url']
+            segment_name = 'Frag%d' % num
             target_filename = '%s-%s' % (tmp_filename, segment_name)
+            # In DASH, the first segment contains necessary headers to
+            # generate a valid MP4 file, so always abort for the first segment
+            fatal = num == 0 or not skip_unavailable_fragments
             count = 0
             while count <= fragment_retries:
                 try:
-                    success = ctx['dl'].download(target_filename, {'url': combine_url(base_url, target_url)})
+                    success = ctx['dl'].download(target_filename, {'url': segment_url})
                     if not success:
                         return False
                     down, target_sanitized = sanitize_open(target_filename, 'rb')
@@ -52,26 +51,27 @@ class DashSegmentsFD(FragmentFD):
                     down.close()
                     segments_filenames.append(target_sanitized)
                     break
-                except (compat_urllib_error.HTTPError, ) as err:
+                except compat_urllib_error.HTTPError as err:
                     # YouTube may often return 404 HTTP error for a fragment causing the
                     # whole download to fail. However if the same fragment is immediately
                     # retried with the same request data this usually succeeds (1-2 attemps
                     # is usually enough) thus allowing to download the whole file successfully.
-                    # So, we will retry all fragments that fail with 404 HTTP error for now.
-                    if err.code != 404:
-                        raise
-                    # Retry fragment
+                    # To be future-proof we will retry all fragments that fail with any
+                    # HTTP error.
                     count += 1
                     if count <= fragment_retries:
-                        self.report_retry_fragment(segment_name, count, fragment_retries)
+                        self.report_retry_fragment(err, segment_name, count, fragment_retries)
             if count > fragment_retries:
+                if not fatal:
+                    self.report_skip_fragment(segment_name)
+                    return True
                 self.report_error('giving up after %s fragment retries' % fragment_retries)
                 return False
+            return True
 
-        if initialization_url:
-            append_url_to_file(initialization_url, ctx['tmpfilename'], 'Init')
-        for i, segment_url in enumerate(segment_urls):
-            append_url_to_file(segment_url, ctx['tmpfilename'], 'Seg%d' % i)
+        for i, segment in enumerate(segments):
+            if not process_segment(segment, ctx['tmpfilename'], i):
+                return False
 
         self._finish_frag_download(ctx)
 

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/fragment.py

@@ -6,6 +6,7 @@ import time
 from .common import FileDownloader
 from .http import HttpFD
 from ..utils import (
+    error_to_compat_str,
     encodeFilename,
     sanitize_open,
 )
@@ -22,13 +23,19 @@ class FragmentFD(FileDownloader):
 
     Available options:
 
-    fragment_retries:   Number of times to retry a fragment for HTTP error (DASH only)
+    fragment_retries:   Number of times to retry a fragment for HTTP error (DASH
+                        and hlsnative only)
+    skip_unavailable_fragments:
+                        Skip unavailable fragments (DASH and hlsnative only)
     """
 
-    def report_retry_fragment(self, fragment_name, count, retries):
+    def report_retry_fragment(self, err, fragment_name, count, retries):
         self.to_screen(
-            '[download] Got server HTTP error. Retrying fragment %s (attempt %d of %s)...'
-            % (fragment_name, count, self.format_retries(retries)))
+            '[download] Got server HTTP error: %s. Retrying fragment %s (attempt %d of %s)...'
+            % (error_to_compat_str(err), fragment_name, count, self.format_retries(retries)))
+
+    def report_skip_fragment(self, fragment_name):
+        self.to_screen('[download] Skipping fragment %s...' % fragment_name)
 
     def _prepare_and_start_frag_download(self, ctx):
         self._prepare_frag_download(ctx)

youtube_dl/downloader/hls.py

@@ -13,6 +13,7 @@ from .fragment import FragmentFD
 from .external import FFmpegFD
 
 from ..compat import (
+    compat_urllib_error,
     compat_urlparse,
     compat_struct_pack,
 )
@@ -20,6 +21,7 @@ from ..utils import (
     encodeFilename,
     sanitize_open,
     parse_m3u8_attributes,
+    update_url_query,
 )
 
 
@@ -29,7 +31,7 @@ class HlsFD(FragmentFD):
     FD_NAME = 'hlsnative'
 
     @staticmethod
-    def can_download(manifest):
+    def can_download(manifest, info_dict):
         UNSUPPORTED_FEATURES = (
             r'#EXT-X-KEY:METHOD=(?!NONE|AES-128)',  # encrypted streams [1]
             r'#EXT-X-BYTERANGE',  # playlists composed of byte ranges of media files [2]
@@ -51,6 +53,7 @@ class HlsFD(FragmentFD):
         )
         check_results = [not re.search(feature, manifest) for feature in UNSUPPORTED_FEATURES]
         check_results.append(can_decrypt_frag or '#EXT-X-KEY:METHOD=AES-128' not in manifest)
+        check_results.append(not info_dict.get('is_live'))
         return all(check_results)
 
     def real_download(self, filename, info_dict):
@@ -60,7 +63,7 @@ class HlsFD(FragmentFD):
 
         s = manifest.decode('utf-8', 'ignore')
 
-        if not self.can_download(s):
+        if not self.can_download(s, info_dict):
             self.report_warning(
                 'hlsnative has detected features it does not support, '
                 'extraction will be delegated to ffmpeg')
@@ -82,6 +85,14 @@ class HlsFD(FragmentFD):
 
         self._prepare_and_start_frag_download(ctx)
 
+        fragment_retries = self.params.get('fragment_retries', 0)
+        skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
+        test = self.params.get('test', False)
+
+        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'}
@@ -94,13 +105,37 @@ class HlsFD(FragmentFD):
                         line
                         if re.match(r'^https?://', line)
                         else compat_urlparse.urljoin(man_url, line))
-                    frag_filename = '%s-Frag%d' % (ctx['tmpfilename'], i)
-                    success = ctx['dl'].download(frag_filename, {'url': frag_url})
-                    if not success:
+                    frag_name = 'Frag%d' % i
+                    frag_filename = '%s-%s' % (ctx['tmpfilename'], frag_name)
+                    if extra_query:
+                        frag_url = update_url_query(frag_url, extra_query)
+                    count = 0
+                    while count <= fragment_retries:
+                        try:
+                            success = ctx['dl'].download(frag_filename, {'url': frag_url})
+                            if not success:
+                                return False
+                            down, frag_sanitized = sanitize_open(frag_filename, 'rb')
+                            frag_content = down.read()
+                            down.close()
+                            break
+                        except compat_urllib_error.HTTPError as err:
+                            # Unavailable (possibly temporary) fragments may be served.
+                            # First we try to retry then either skip or abort.
+                            # See https://github.com/rg3/youtube-dl/issues/10165,
+                            # https://github.com/rg3/youtube-dl/issues/10448).
+                            count += 1
+                            if count <= fragment_retries:
+                                self.report_retry_fragment(err, frag_name, count, fragment_retries)
+                    if count > fragment_retries:
+                        if skip_unavailable_fragments:
+                            i += 1
+                            media_sequence += 1
+                            self.report_skip_fragment(frag_name)
+                            continue
+                        self.report_error(
+                            'giving up after %s fragment retries' % fragment_retries)
                         return False
-                    down, frag_sanitized = sanitize_open(frag_filename, 'rb')
-                    frag_content = down.read()
-                    down.close()
                     if decrypt_info['METHOD'] == 'AES-128':
                         iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence)
                         frag_content = AES.new(
@@ -108,7 +143,7 @@ class HlsFD(FragmentFD):
                     ctx['dest_stream'].write(frag_content)
                     frags_filenames.append(frag_sanitized)
                     # We only download the first fragment during the test
-                    if self.params.get('test', False):
+                    if test:
                         break
                     i += 1
                     media_sequence += 1
@@ -116,10 +151,12 @@ 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/downloader/http.py

@@ -13,6 +13,9 @@ from ..utils import (
     encodeFilename,
     sanitize_open,
     sanitized_Request,
+    write_xattr,
+    XAttrMetadataError,
+    XAttrUnavailableError,
 )
 
 
@@ -179,9 +182,8 @@ class HttpFD(FileDownloader):
 
                 if self.params.get('xattr_set_filesize', False) and data_len is not None:
                     try:
-                        import xattr
-                        xattr.setxattr(tmpfilename, 'user.ytdl.filesize', str(data_len))
-                    except(OSError, IOError, ImportError) as err:
+                        write_xattr(tmpfilename, 'user.ytdl.filesize', str(data_len).encode('utf-8'))
+                    except (XAttrUnavailableError, XAttrMetadataError) as err:
                         self.report_error('unable to set filesize xattr: %s' % str(err))
 
             try:

youtube_dl/downloader/ism.py

@@ -0,0 +1,273 @@
+from __future__ import unicode_literals
+
+import os
+import time
+import struct
+import binascii
+import io
+
+from .fragment import FragmentFD
+from ..compat import compat_urllib_error
+from ..utils import (
+    sanitize_open,
+    encodeFilename,
+)
+
+
+u8 = struct.Struct(b'>B')
+u88 = struct.Struct(b'>Bx')
+u16 = struct.Struct(b'>H')
+u1616 = struct.Struct(b'>Hxx')
+u32 = struct.Struct(b'>I')
+u64 = struct.Struct(b'>Q')
+
+s88 = struct.Struct(b'>bx')
+s16 = struct.Struct(b'>h')
+s1616 = struct.Struct(b'>hxx')
+s32 = struct.Struct(b'>i')
+
+unity_matrix = (s32.pack(0x10000) + s32.pack(0) * 3) * 2 + s32.pack(0x40000000)
+
+TRACK_ENABLED = 0x1
+TRACK_IN_MOVIE = 0x2
+TRACK_IN_PREVIEW = 0x4
+
+SELF_CONTAINED = 0x1
+
+
+def box(box_type, payload):
+    return u32.pack(8 + len(payload)) + box_type + payload
+
+
+def full_box(box_type, version, flags, payload):
+    return box(box_type, u8.pack(version) + u32.pack(flags)[1:] + payload)
+
+
+def write_piff_header(stream, params):
+    track_id = params['track_id']
+    fourcc = params['fourcc']
+    duration = params['duration']
+    timescale = params.get('timescale', 10000000)
+    language = params.get('language', 'und')
+    height = params.get('height', 0)
+    width = params.get('width', 0)
+    is_audio = width == 0 and height == 0
+    creation_time = modification_time = int(time.time())
+
+    ftyp_payload = b'isml'  # major brand
+    ftyp_payload += u32.pack(1)  # minor version
+    ftyp_payload += b'piff' + b'iso2'  # compatible brands
+    stream.write(box(b'ftyp', ftyp_payload))  # File Type Box
+
+    mvhd_payload = u64.pack(creation_time)
+    mvhd_payload += u64.pack(modification_time)
+    mvhd_payload += u32.pack(timescale)
+    mvhd_payload += u64.pack(duration)
+    mvhd_payload += s1616.pack(1)  # rate
+    mvhd_payload += s88.pack(1)  # volume
+    mvhd_payload += u16.pack(0)  # reserved
+    mvhd_payload += u32.pack(0) * 2  # reserved
+    mvhd_payload += unity_matrix
+    mvhd_payload += u32.pack(0) * 6  # pre defined
+    mvhd_payload += u32.pack(0xffffffff)  # next track id
+    moov_payload = full_box(b'mvhd', 1, 0, mvhd_payload)  # Movie Header Box
+
+    tkhd_payload = u64.pack(creation_time)
+    tkhd_payload += u64.pack(modification_time)
+    tkhd_payload += u32.pack(track_id)  # track id
+    tkhd_payload += u32.pack(0)  # reserved
+    tkhd_payload += u64.pack(duration)
+    tkhd_payload += u32.pack(0) * 2  # reserved
+    tkhd_payload += s16.pack(0)  # layer
+    tkhd_payload += s16.pack(0)  # alternate group
+    tkhd_payload += s88.pack(1 if is_audio else 0)  # volume
+    tkhd_payload += u16.pack(0)  # reserved
+    tkhd_payload += unity_matrix
+    tkhd_payload += u1616.pack(width)
+    tkhd_payload += u1616.pack(height)
+    trak_payload = full_box(b'tkhd', 1, TRACK_ENABLED | TRACK_IN_MOVIE | TRACK_IN_PREVIEW, tkhd_payload)  # Track Header Box
+
+    mdhd_payload = u64.pack(creation_time)
+    mdhd_payload += u64.pack(modification_time)
+    mdhd_payload += u32.pack(timescale)
+    mdhd_payload += u64.pack(duration)
+    mdhd_payload += u16.pack(((ord(language[0]) - 0x60) << 10) | ((ord(language[1]) - 0x60) << 5) | (ord(language[2]) - 0x60))
+    mdhd_payload += u16.pack(0)  # pre defined
+    mdia_payload = full_box(b'mdhd', 1, 0, mdhd_payload)  # Media Header Box
+
+    hdlr_payload = u32.pack(0)  # pre defined
+    hdlr_payload += b'soun' if is_audio else b'vide'  # handler type
+    hdlr_payload += u32.pack(0) * 3  # reserved
+    hdlr_payload += (b'Sound' if is_audio else b'Video') + b'Handler\0'  # name
+    mdia_payload += full_box(b'hdlr', 0, 0, hdlr_payload)  # Handler Reference Box
+
+    if is_audio:
+        smhd_payload = s88.pack(0)  # balance
+        smhd_payload = u16.pack(0)  # reserved
+        media_header_box = full_box(b'smhd', 0, 0, smhd_payload)  # Sound Media Header
+    else:
+        vmhd_payload = u16.pack(0)  # graphics mode
+        vmhd_payload += u16.pack(0) * 3  # opcolor
+        media_header_box = full_box(b'vmhd', 0, 1, vmhd_payload)  # Video Media Header
+    minf_payload = media_header_box
+
+    dref_payload = u32.pack(1)  # entry count
+    dref_payload += full_box(b'url ', 0, SELF_CONTAINED, b'')  # Data Entry URL Box
+    dinf_payload = full_box(b'dref', 0, 0, dref_payload)  # Data Reference Box
+    minf_payload += box(b'dinf', dinf_payload)  # Data Information Box
+
+    stsd_payload = u32.pack(1)  # entry count
+
+    sample_entry_payload = u8.pack(0) * 6  # reserved
+    sample_entry_payload += u16.pack(1)  # data reference index
+    if is_audio:
+        sample_entry_payload += u32.pack(0) * 2  # reserved
+        sample_entry_payload += u16.pack(params.get('channels', 2))
+        sample_entry_payload += u16.pack(params.get('bits_per_sample', 16))
+        sample_entry_payload += u16.pack(0)  # pre defined
+        sample_entry_payload += u16.pack(0)  # reserved
+        sample_entry_payload += u1616.pack(params['sampling_rate'])
+
+        if fourcc == 'AACL':
+            smaple_entry_box = box(b'mp4a', sample_entry_payload)
+    else:
+        sample_entry_payload = sample_entry_payload
+        sample_entry_payload += u16.pack(0)  # pre defined
+        sample_entry_payload += u16.pack(0)  # reserved
+        sample_entry_payload += u32.pack(0) * 3  # pre defined
+        sample_entry_payload += u16.pack(width)
+        sample_entry_payload += u16.pack(height)
+        sample_entry_payload += u1616.pack(0x48)  # horiz resolution 72 dpi
+        sample_entry_payload += u1616.pack(0x48)  # vert resolution 72 dpi
+        sample_entry_payload += u32.pack(0)  # reserved
+        sample_entry_payload += u16.pack(1)  # frame count
+        sample_entry_payload += u8.pack(0) * 32  # compressor name
+        sample_entry_payload += u16.pack(0x18)  # depth
+        sample_entry_payload += s16.pack(-1)  # pre defined
+
+        codec_private_data = binascii.unhexlify(params['codec_private_data'])
+        if fourcc in ('H264', 'AVC1'):
+            sps, pps = codec_private_data.split(u32.pack(1))[1:]
+            avcc_payload = u8.pack(1)  # configuration version
+            avcc_payload += sps[1]  # avc profile indication
+            avcc_payload += sps[2]  # profile compatibility
+            avcc_payload += sps[3]  # avc level indication
+            avcc_payload += u8.pack(0xfc | (params.get('nal_unit_length_field', 4) - 1))  # complete represenation (1) + reserved (11111) + length size minus one
+            avcc_payload += u8.pack(1)  # reserved (0) + number of sps (0000001)
+            avcc_payload += u16.pack(len(sps))
+            avcc_payload += sps
+            avcc_payload += u8.pack(1)  # number of pps
+            avcc_payload += u16.pack(len(pps))
+            avcc_payload += pps
+            sample_entry_payload += box(b'avcC', avcc_payload)  # AVC Decoder Configuration Record
+            smaple_entry_box = box(b'avc1', sample_entry_payload)  # AVC Simple Entry
+    stsd_payload += smaple_entry_box
+
+    stbl_payload = full_box(b'stsd', 0, 0, stsd_payload)  # Sample Description Box
+
+    stts_payload = u32.pack(0)  # entry count
+    stbl_payload += full_box(b'stts', 0, 0, stts_payload)  # Decoding Time to Sample Box
+
+    stsc_payload = u32.pack(0)  # entry count
+    stbl_payload += full_box(b'stsc', 0, 0, stsc_payload)  # Sample To Chunk Box
+
+    stco_payload = u32.pack(0)  # entry count
+    stbl_payload += full_box(b'stco', 0, 0, stco_payload)  # Chunk Offset Box
+
+    minf_payload += box(b'stbl', stbl_payload)  # Sample Table Box
+
+    mdia_payload += box(b'minf', minf_payload)  # Media Information Box
+
+    trak_payload += box(b'mdia', mdia_payload)  # Media Box
+
+    moov_payload += box(b'trak', trak_payload)  # Track Box
+
+    mehd_payload = u64.pack(duration)
+    mvex_payload = full_box(b'mehd', 1, 0, mehd_payload)  # Movie Extends Header Box
+
+    trex_payload = u32.pack(track_id)  # track id
+    trex_payload += u32.pack(1)  # default sample description index
+    trex_payload += u32.pack(0)  # default sample duration
+    trex_payload += u32.pack(0)  # default sample size
+    trex_payload += u32.pack(0)  # default sample flags
+    mvex_payload += full_box(b'trex', 0, 0, trex_payload)  # Track Extends Box
+
+    moov_payload += box(b'mvex', mvex_payload)  # Movie Extends Box
+    stream.write(box(b'moov', moov_payload))  # Movie Box
+
+
+def extract_box_data(data, box_sequence):
+    data_reader = io.BytesIO(data)
+    while True:
+        box_size = u32.unpack(data_reader.read(4))[0]
+        box_type = data_reader.read(4)
+        if box_type == box_sequence[0]:
+            box_data = data_reader.read(box_size - 8)
+            if len(box_sequence) == 1:
+                return box_data
+            return extract_box_data(box_data, box_sequence[1:])
+        data_reader.seek(box_size - 8, 1)
+
+
+class IsmFD(FragmentFD):
+    """
+    Download segments in a ISM manifest
+    """
+
+    FD_NAME = 'ism'
+
+    def real_download(self, filename, info_dict):
+        segments = info_dict['fragments'][:1] if self.params.get(
+            'test', False) else info_dict['fragments']
+
+        ctx = {
+            'filename': filename,
+            'total_frags': len(segments),
+        }
+
+        self._prepare_and_start_frag_download(ctx)
+
+        segments_filenames = []
+
+        fragment_retries = self.params.get('fragment_retries', 0)
+        skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
+
+        track_written = False
+        for i, segment in enumerate(segments):
+            segment_url = segment['url']
+            segment_name = 'Frag%d' % i
+            target_filename = '%s-%s' % (ctx['tmpfilename'], segment_name)
+            count = 0
+            while count <= fragment_retries:
+                try:
+                    success = ctx['dl'].download(target_filename, {'url': segment_url})
+                    if not success:
+                        return False
+                    down, target_sanitized = sanitize_open(target_filename, 'rb')
+                    down_data = down.read()
+                    if not track_written:
+                        tfhd_data = extract_box_data(down_data, [b'moof', b'traf', b'tfhd'])
+                        info_dict['_download_params']['track_id'] = u32.unpack(tfhd_data[4:8])[0]
+                        write_piff_header(ctx['dest_stream'], info_dict['_download_params'])
+                        track_written = True
+                    ctx['dest_stream'].write(down_data)
+                    down.close()
+                    segments_filenames.append(target_sanitized)
+                    break
+                except compat_urllib_error.HTTPError as err:
+                    count += 1
+                    if count <= fragment_retries:
+                        self.report_retry_fragment(err, segment_name, count, fragment_retries)
+            if count > fragment_retries:
+                if skip_unavailable_fragments:
+                    self.report_skip_fragment(segment_name)
+                    continue
+                self.report_error('giving up after %s fragment retries' % fragment_retries)
+                return False
+
+        self._finish_frag_download(ctx)
+
+        for segment_file in segments_filenames:
+            os.remove(encodeFilename(segment_file))
+
+        return True

youtube_dl/extractor/abc.py

@@ -7,12 +7,13 @@ from ..utils import (
     ExtractorError,
     js_to_json,
     int_or_none,
+    parse_iso8601,
 )
 
 
 class ABCIE(InfoExtractor):
     IE_NAME = 'abc.net.au'
-    _VALID_URL = r'https?://www\.abc\.net\.au/news/(?:[^/]+/){1,2}(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?abc\.net\.au/news/(?:[^/]+/){1,2}(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',
@@ -93,3 +94,59 @@ 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>[^/?#]+)'
+
+    # ABC iview programs are normally available for 14 days only.
+    _TESTS = [{
+        'url': 'http://iview.abc.net.au/programs/diaries-of-a-broken-mind/ZX9735A001S00',
+        'md5': 'cde42d728b3b7c2b32b1b94b4a548afc',
+        'info_dict': {
+            'id': 'ZX9735A001S00',
+            'ext': 'mp4',
+            'title': 'Diaries Of A Broken Mind',
+            'description': 'md5:7de3903874b7a1be279fe6b68718fc9e',
+            'upload_date': '20161010',
+            'uploader_id': 'abc2',
+            'timestamp': 1476064920,
+        },
+        'skip': 'Video gone',
+    }]
+
+    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.get('title') or video_params['seriesTitle']
+        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, default=None)),
+            'episode': self._html_search_meta('episode_title', webpage, default=None),
+            'uploader_id': video_params.get('channel'),
+            'formats': formats,
+            'subtitles': subtitles,
+        }

youtube_dl/extractor/abcnews.py

@@ -12,7 +12,7 @@ from ..compat import compat_urlparse
 
 class AbcNewsVideoIE(AMPIE):
     IE_NAME = 'abcnews:video'
-    _VALID_URL = 'http://abcnews.go.com/[^/]+/video/(?P<display_id>[0-9a-z-]+)-(?P<id>\d+)'
+    _VALID_URL = r'https?://abcnews\.go\.com/[^/]+/video/(?P<display_id>[0-9a-z-]+)-(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://abcnews.go.com/ThisWeek/video/week-exclusive-irans-foreign-minister-zarif-20411932',
@@ -49,7 +49,7 @@ class AbcNewsVideoIE(AMPIE):
 
 class AbcNewsIE(InfoExtractor):
     IE_NAME = 'abcnews'
-    _VALID_URL = 'https?://abcnews\.go\.com/(?:[^/]+/)+(?P<display_id>[0-9a-z-]+)/story\?id=(?P<id>\d+)'
+    _VALID_URL = r'https?://abcnews\.go\.com/(?:[^/]+/)+(?P<display_id>[0-9a-z-]+)/story\?id=(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://abcnews.go.com/Blotter/News/dramatic-video-rare-death-job-america/story?id=10498713#.UIhwosWHLjY',

youtube_dl/extractor/abcotvs.py

@@ -1,13 +1,19 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
 
 from .common import InfoExtractor
-from ..utils import parse_iso8601
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+)
 
 
-class Abc7NewsIE(InfoExtractor):
-    _VALID_URL = r'https?://abc7news\.com(?:/[^/]+/(?P<display_id>[^/]+))?/(?P<id>\d+)'
+class ABCOTVSIE(InfoExtractor):
+    IE_NAME = 'abcotvs'
+    IE_DESC = 'ABC Owned Television Stations'
+    _VALID_URL = r'https?://(?:abc(?:7(?:news|ny|chicago)?|11|13|30)|6abc)\.com(?:/[^/]+/(?P<display_id>[^/]+))?/(?P<id>\d+)'
     _TESTS = [
         {
             'url': 'http://abc7news.com/entertainment/east-bay-museum-celebrates-vintage-synthesizers/472581/',
@@ -15,7 +21,7 @@ class Abc7NewsIE(InfoExtractor):
                 'id': '472581',
                 'display_id': 'east-bay-museum-celebrates-vintage-synthesizers',
                 'ext': 'mp4',
-                'title': 'East Bay museum celebrates history of synthesized music',
+                'title': 'East Bay museum celebrates vintage synthesizers',
                 'description': 'md5:a4f10fb2f2a02565c1749d4adbab4b10',
                 'thumbnail': 're:^https?://.*\.jpg$',
                 'timestamp': 1421123075,
@@ -41,7 +47,7 @@ class Abc7NewsIE(InfoExtractor):
         webpage = self._download_webpage(url, display_id)
 
         m3u8 = self._html_search_meta(
-            'contentURL', webpage, 'm3u8 url', fatal=True)
+            'contentURL', webpage, 'm3u8 url', fatal=True).split('?')[0]
 
         formats = self._extract_m3u8_formats(m3u8, display_id, 'mp4')
         self._sort_formats(formats)
@@ -66,3 +72,41 @@ class Abc7NewsIE(InfoExtractor):
             'uploader': uploader,
             'formats': formats,
         }
+
+
+class ABCOTVSClipsIE(InfoExtractor):
+    IE_NAME = 'abcotvs:clips'
+    _VALID_URL = r'https?://clips\.abcotvs\.com/(?:[^/]+/)*video/(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://clips.abcotvs.com/kabc/video/214814',
+        'info_dict': {
+            'id': '214814',
+            'ext': 'mp4',
+            'title': 'SpaceX launch pad explosion destroys rocket, satellite',
+            'description': 'md5:9f186e5ad8f490f65409965ee9c7be1b',
+            'upload_date': '20160901',
+            'timestamp': 1472756695,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        video_data = self._download_json('https://clips.abcotvs.com/vogo/video/getByIds?ids=' + video_id, video_id)['results'][0]
+        title = video_data['title']
+        formats = self._extract_m3u8_formats(
+            video_data['videoURL'].split('?')[0], video_id, 'mp4')
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': video_data.get('description'),
+            'thumbnail': video_data.get('thumbnailURL'),
+            'duration': int_or_none(video_data.get('duration')),
+            'timestamp': int_or_none(video_data.get('pubDate')),
+            'formats': formats,
+        }

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 = [{
@@ -83,6 +81,42 @@ class AdultSwimIE(InfoExtractor):
             # m3u8 download
             'skip_download': True,
         }
+    }, {
+        # heroMetadata.trailer
+        'url': 'http://www.adultswim.com/videos/decker/inside-decker-a-new-hero/',
+        'info_dict': {
+            'id': 'I0LQFQkaSUaFp8PnAWHhoQ',
+            'ext': 'mp4',
+            'title': 'Decker - Inside Decker: A New Hero',
+            'description': 'md5:c916df071d425d62d70c86d4399d3ee0',
+            'duration': 249.008,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+        'expected_warnings': ['Unable to download f4m manifest'],
+    }, {
+        'url': 'http://www.adultswim.com/videos/toonami/friday-october-14th-2016/',
+        'info_dict': {
+            'id': 'eYiLsKVgQ6qTC6agD67Sig',
+            'title': 'Toonami - Friday, October 14th, 2016',
+            'description': 'md5:99892c96ffc85e159a428de85c30acde',
+        },
+        'playlist': [{
+            'md5': '',
+            'info_dict': {
+                'id': 'eYiLsKVgQ6qTC6agD67Sig',
+                'ext': 'mp4',
+                'title': 'Toonami - Friday, October 14th, 2016',
+                'description': 'md5:99892c96ffc85e159a428de85c30acde',
+            },
+        }],
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+        'expected_warnings': ['Unable to download f4m manifest'],
     }]
 
     @staticmethod
@@ -133,79 +167,58 @@ class AdultSwimIE(InfoExtractor):
             if video_info is None:
                 if bootstrapped_data.get('slugged_video', {}).get('slug') == episode_path:
                     video_info = bootstrapped_data['slugged_video']
-                else:
-                    raise ExtractorError('Unable to find video info')
+            if not video_info:
+                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')
 
             show = bootstrapped_data['show']
             show_title = show['title']
             stream = video_info.get('stream')
-            clips = [stream] if stream else video_info.get('clips')
-            if not clips:
-                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)
-            segment_ids = [clip['videoPlaybackID'] for clip in clips]
+            if stream and stream.get('videoPlaybackID'):
+                segment_ids = [stream['videoPlaybackID']]
+            elif video_info.get('clips'):
+                segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']]
+            elif video_info.get('videoPlaybackID'):
+                segment_ids = [video_info['videoPlaybackID']]
+            elif video_info.get('id'):
+                segment_ids = [video_info['id']]
+            else:
+                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',
@@ -214,5 +227,6 @@ 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/aftonbladet.py

@@ -1,64 +0,0 @@
-# encoding: utf-8
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-from ..utils import int_or_none
-
-
-class AftonbladetIE(InfoExtractor):
-    _VALID_URL = r'https?://tv\.aftonbladet\.se/abtv/articles/(?P<id>[0-9]+)'
-    _TEST = {
-        'url': 'http://tv.aftonbladet.se/abtv/articles/36015',
-        'info_dict': {
-            'id': '36015',
-            'ext': 'mp4',
-            'title': 'Vulkanutbrott i rymden - nu släpper NASA bilderna',
-            'description': 'Jupiters måne mest aktiv av alla himlakroppar',
-            'timestamp': 1394142732,
-            'upload_date': '20140306',
-        },
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-
-        # find internal video meta data
-        meta_url = 'http://aftonbladet-play-metadata.cdn.drvideo.aptoma.no/video/%s.json'
-        player_config = self._parse_json(self._html_search_regex(
-            r'data-player-config="([^"]+)"', webpage, 'player config'), video_id)
-        internal_meta_id = player_config['aptomaVideoId']
-        internal_meta_url = meta_url % internal_meta_id
-        internal_meta_json = self._download_json(
-            internal_meta_url, video_id, 'Downloading video meta data')
-
-        # find internal video formats
-        format_url = 'http://aftonbladet-play.videodata.drvideo.aptoma.no/actions/video/?id=%s'
-        internal_video_id = internal_meta_json['videoId']
-        internal_formats_url = format_url % internal_video_id
-        internal_formats_json = self._download_json(
-            internal_formats_url, video_id, 'Downloading video formats')
-
-        formats = []
-        for fmt in internal_formats_json['formats']['http']['pseudostreaming']['mp4']:
-            p = fmt['paths'][0]
-            formats.append({
-                'url': 'http://%s:%d/%s/%s' % (p['address'], p['port'], p['path'], p['filename']),
-                'ext': 'mp4',
-                'width': int_or_none(fmt.get('width')),
-                'height': int_or_none(fmt.get('height')),
-                'tbr': int_or_none(fmt.get('bitrate')),
-                'protocol': 'http',
-            })
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'title': internal_meta_json['title'],
-            'formats': formats,
-            'thumbnail': internal_meta_json.get('imageUrl'),
-            'description': internal_meta_json.get('shortPreamble'),
-            'timestamp': int_or_none(internal_meta_json.get('timePublished')),
-            'duration': int_or_none(internal_meta_json.get('duration')),
-            'view_count': int_or_none(internal_meta_json.get('views')),
-        }

youtube_dl/extractor/aljazeera.py

@@ -4,7 +4,7 @@ from .common import InfoExtractor
 
 
 class AlJazeeraIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.aljazeera\.com/programmes/.*?/(?P<id>[^/]+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?aljazeera\.com/programmes/.*?/(?P<id>[^/]+)\.html'
 
     _TEST = {
         'url': 'http://www.aljazeera.com/programmes/the-slum/2014/08/deliverance-201482883754237240.html',

youtube_dl/extractor/allocine.py

@@ -1,29 +1,26 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 from __future__ import unicode_literals
 
-import re
-import json
-
 from .common import InfoExtractor
-from ..compat import compat_str
 from ..utils import (
+    remove_end,
     qualities,
-    unescapeHTML,
-    xpath_element,
+    url_basename,
 )
 
 
 class AllocineIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?P<typ>article|video|film)/(fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=|video-)(?P<id>[0-9]+)(?:\.html)?'
+    _VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?:article|video|film)/(?:fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=|video-)(?P<id>[0-9]+)(?:\.html)?'
 
     _TESTS = [{
         'url': 'http://www.allocine.fr/article/fichearticle_gen_carticle=18635087.html',
         'md5': '0c9fcf59a841f65635fa300ac43d8269',
         'info_dict': {
             'id': '19546517',
+            'display_id': '18635087',
             'ext': 'mp4',
             'title': 'Astérix - Le Domaine des Dieux Teaser VF',
-            'description': 'md5:abcd09ce503c6560512c14ebfdb720d2',
+            'description': 'md5:4a754271d9c6f16c72629a8a993ee884',
             'thumbnail': 're:http://.*\.jpg',
         },
     }, {
@@ -31,64 +28,82 @@ class AllocineIE(InfoExtractor):
         'md5': 'd0cdce5d2b9522ce279fdfec07ff16e0',
         'info_dict': {
             'id': '19540403',
+            'display_id': '19540403',
             'ext': 'mp4',
             'title': 'Planes 2 Bande-annonce VF',
             'description': 'Regardez la bande annonce du film Planes 2 (Planes 2 Bande-annonce VF). Planes 2, un film de Roberts Gannaway',
             'thumbnail': 're:http://.*\.jpg',
         },
     }, {
-        'url': 'http://www.allocine.fr/film/fichefilm_gen_cfilm=181290.html',
+        'url': 'http://www.allocine.fr/video/player_gen_cmedia=19544709&cfilm=181290.html',
         'md5': '101250fb127ef9ca3d73186ff22a47ce',
         'info_dict': {
             'id': '19544709',
+            'display_id': '19544709',
             'ext': 'mp4',
             'title': 'Dragons 2 - Bande annonce finale VF',
-            'description': 'md5:601d15393ac40f249648ef000720e7e3',
+            'description': 'md5:6cdd2d7c2687d4c6aafe80a35e17267a',
             'thumbnail': 're:http://.*\.jpg',
         },
     }, {
         'url': 'http://www.allocine.fr/video/video-19550147/',
-        'only_matching': True,
+        'md5': '3566c0668c0235e2d224fd8edb389f67',
+        'info_dict': {
+            'id': '19550147',
+            'ext': 'mp4',
+            'title': 'Faux Raccord N°123 - Les gaffes de Cliffhanger',
+            'description': 'md5:bc734b83ffa2d8a12188d9eb48bb6354',
+            'thumbnail': 're:http://.*\.jpg',
+        },
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        typ = mobj.group('typ')
-        display_id = mobj.group('id')
+        display_id = self._match_id(url)
 
         webpage = self._download_webpage(url, display_id)
 
-        if typ == 'film':
-            video_id = self._search_regex(r'href="/video/player_gen_cmedia=([0-9]+).+"', webpage, 'video id')
-        else:
-            player = self._search_regex(r'data-player=\'([^\']+)\'>', webpage, 'data player', default=None)
-            if player:
-                player_data = json.loads(player)
-                video_id = compat_str(player_data['refMedia'])
-            else:
-                model = self._search_regex(r'data-model="([^"]+)">', webpage, 'data model')
-                model_data = self._parse_json(unescapeHTML(model), display_id)
-                video_id = compat_str(model_data['id'])
-
-        xml = self._download_xml('http://www.allocine.fr/ws/AcVisiondataV4.ashx?media=%s' % video_id, display_id)
-
-        video = xpath_element(xml, './/AcVisionVideo').attrib
+        formats = []
         quality = qualities(['ld', 'md', 'hd'])
 
-        formats = []
-        for k, v in video.items():
-            if re.match(r'.+_path', k):
-                format_id = k.split('_')[0]
+        model = self._html_search_regex(
+            r'data-model="([^"]+)"', webpage, 'data model', default=None)
+        if model:
+            model_data = self._parse_json(model, display_id)
+
+            for video_url in model_data['sources'].values():
+                video_id, format_id = url_basename(video_url).split('_')[:2]
                 formats.append({
                     'format_id': format_id,
                     'quality': quality(format_id),
-                    'url': v,
+                    'url': video_url,
                 })
+
+            title = model_data['title']
+        else:
+            video_id = display_id
+            media_data = self._download_json(
+                'http://www.allocine.fr/ws/AcVisiondataV5.ashx?media=%s' % video_id, display_id)
+            for key, value in media_data['video'].items():
+                if not key.endswith('Path'):
+                    continue
+
+                format_id = key[:-len('Path')]
+                formats.append({
+                    'format_id': format_id,
+                    'quality': quality(format_id),
+                    'url': value,
+                })
+
+            title = remove_end(self._html_search_regex(
+                r'(?s)<title>(.+?)</title>', webpage, 'title'
+            ).strip(), ' - AlloCiné')
+
         self._sort_formats(formats)
 
         return {
             'id': video_id,
-            'title': video['videoTitle'],
+            'display_id': display_id,
+            'title': title,
             'thumbnail': self._og_search_thumbnail(webpage),
             'formats': formats,
             'description': self._og_search_description(webpage),

youtube_dl/extractor/amcnetworks.py

@@ -0,0 +1,92 @@
+# 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,
+        },
+        'skip': 'Requires TV provider accounts',
+    }, {
+        '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/archiveorg.py

@@ -1,67 +1,65 @@
 from __future__ import unicode_literals
 
-from .common import InfoExtractor
-from ..utils import unified_strdate
+from .jwplatform import JWPlatformBaseIE
+from ..utils import (
+    unified_strdate,
+    clean_html,
+)
 
 
-class ArchiveOrgIE(InfoExtractor):
+class ArchiveOrgIE(JWPlatformBaseIE):
     IE_NAME = 'archive.org'
     IE_DESC = 'archive.org videos'
-    _VALID_URL = r'https?://(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$'
+    _VALID_URL = r'https?://(?:www\.)?archive\.org/(?:details|embed)/(?P<id>[^/?#]+)(?:[?].*)?$'
     _TESTS = [{
         'url': 'http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
         'md5': '8af1d4cf447933ed3c7f4871162602db',
         'info_dict': {
             'id': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect',
-            'ext': 'ogv',
+            'ext': 'ogg',
             'title': '1968 Demo - FJCC Conference Presentation Reel #1',
-            'description': 'md5:1780b464abaca9991d8968c877bb53ed',
+            'description': 'md5:da45c349df039f1cc8075268eb1b5c25',
             'upload_date': '19681210',
             'uploader': 'SRI International'
         }
     }, {
         'url': 'https://archive.org/details/Cops1922',
-        'md5': '18f2a19e6d89af8425671da1cf3d4e04',
+        'md5': 'bc73c8ab3838b5a8fc6c6651fa7b58ba',
         'info_dict': {
             'id': 'Cops1922',
-            'ext': 'ogv',
+            'ext': 'mp4',
             'title': 'Buster Keaton\'s "Cops" (1922)',
-            'description': 'md5:70f72ee70882f713d4578725461ffcc3',
+            'description': 'md5:b4544662605877edd99df22f9620d858',
         }
+    }, {
+        'url': 'http://archive.org/embed/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
+        webpage = self._download_webpage(
+            'http://archive.org/embed/' + video_id, video_id)
+        jwplayer_playlist = self._parse_json(self._search_regex(
+            r"(?s)Play\('[^']+'\s*,\s*(\[.+\])\s*,\s*{.*?}\);",
+            webpage, 'jwplayer playlist'), video_id)
+        info = self._parse_jwplayer_data(
+            {'playlist': jwplayer_playlist}, video_id, base_url=url)
 
-        json_url = url + ('&' if '?' in url else '?') + 'output=json'
-        data = self._download_json(json_url, video_id)
+        def get_optional(metadata, field):
+            return metadata.get(field, [None])[0]
 
-        def get_optional(data_dict, field):
-            return data_dict['metadata'].get(field, [None])[0]
-
-        title = get_optional(data, 'title')
-        description = get_optional(data, 'description')
-        uploader = get_optional(data, 'creator')
-        upload_date = unified_strdate(get_optional(data, 'date'))
-
-        formats = [
-            {
-                'format': fdata['format'],
-                'url': 'http://' + data['server'] + data['dir'] + fn,
-                'file_size': int(fdata['size']),
-            }
-            for fn, fdata in data['files'].items()
-            if 'Video' in fdata['format']]
-
-        self._sort_formats(formats)
-
-        return {
-            '_type': 'video',
-            'id': video_id,
-            'title': title,
-            'formats': formats,
-            'description': description,
-            'uploader': uploader,
-            'upload_date': upload_date,
-            'thumbnail': data.get('misc', {}).get('image'),
-        }
+        metadata = self._download_json(
+            'http://archive.org/details/' + video_id, video_id, query={
+                'output': 'json',
+            })['metadata']
+        info.update({
+            'title': get_optional(metadata, 'title') or info.get('title'),
+            'description': clean_html(get_optional(metadata, 'description')),
+        })
+        if info.get('_type') != 'playlist':
+            info.update({
+                'uploader': get_optional(metadata, 'creator'),
+                'upload_date': unified_strdate(get_optional(metadata, 'date')),
+            })
+        return info

youtube_dl/extractor/ard.py

@@ -174,11 +174,17 @@ class ARDMediathekIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
-        if '>Der gewünschte Beitrag ist nicht mehr verfügbar.<' in webpage:
-            raise ExtractorError('Video %s is no longer available' % video_id, expected=True)
+        ERRORS = (
+            ('>Leider liegt eine Störung vor.', 'Video %s is unavailable'),
+            ('>Der gewünschte Beitrag ist nicht mehr verfügbar.<',
+             'Video %s is no longer available'),
+            ('Diese Sendung ist für Jugendliche unter 12 Jahren nicht geeignet. Der Clip ist deshalb nur von 20 bis 6 Uhr verfügbar.',
+             'This program is only suitable for those aged 12 and older. Video %s is therefore only available between 8 pm and 6 am.'),
+        )
 
-        if 'Diese Sendung ist für Jugendliche unter 12 Jahren nicht geeignet. Der Clip ist deshalb nur von 20 bis 6 Uhr verfügbar.' in webpage:
-            raise ExtractorError('This program is only suitable for those aged 12 and older. Video %s is therefore only available between 20 pm and 6 am.' % video_id, expected=True)
+        for pattern, message in ERRORS:
+            if pattern in webpage:
+                raise ExtractorError(message % video_id, expected=True)
 
         if re.search(r'[\?&]rss($|[=&])', url):
             doc = compat_etree_fromstring(webpage.encode('utf-8'))
@@ -238,7 +244,7 @@ class ARDMediathekIE(InfoExtractor):
 
 
 class ARDIE(InfoExtractor):
-    _VALID_URL = '(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html'
+    _VALID_URL = r'(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html'
     _TEST = {
         'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html',
         'md5': 'd216c3a86493f9322545e045ddc3eb35',

youtube_dl/extractor/arte.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
@@ -410,6 +410,22 @@ class ArteTVEmbedIE(ArteTVPlus7IE):
         return self._extract_from_json_url(json_url, video_id, lang)
 
 
+class TheOperaPlatformIE(ArteTVPlus7IE):
+    IE_NAME = 'theoperaplatform'
+    _VALID_URL = r'https?://(?:www\.)?theoperaplatform\.eu/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
+
+    _TESTS = [{
+        'url': 'http://www.theoperaplatform.eu/de/opera/verdi-otello',
+        'md5': '970655901fa2e82e04c00b955e9afe7b',
+        'info_dict': {
+            'id': '060338-009-A',
+            'ext': 'mp4',
+            'title': 'Verdi - OTELLO',
+            'upload_date': '20160927',
+        },
+    }]
+
+
 class ArteTVPlaylistIE(ArteTVBaseIE):
     IE_NAME = 'arte.tv:playlist'
     _VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de|en|es)/[^#]*#collection/(?P<id>PL-\d+)'

youtube_dl/extractor/awaan.py

@@ -12,74 +12,51 @@ 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,
         }
 
-    def _extract_video_formats(self, webpage, video_id, m3u8_entry_protocol):
-        formats = []
-        format_url_base = 'http' + self._html_search_regex(
-            [
-                r'file\s*:\s*"https?(://[^"]+)/playlist.m3u8',
-                r'<a[^>]+href="rtsp(://[^"]+)"'
-            ], webpage, 'format url')
-        formats.extend(self._extract_mpd_formats(
-            format_url_base + '/manifest.mpd',
-            video_id, mpd_id='dash', fatal=False))
-        formats.extend(self._extract_m3u8_formats(
-            format_url_base + '/playlist.m3u8', video_id, 'mp4',
-            m3u8_entry_protocol, m3u8_id='hls', fatal=False))
-        formats.extend(self._extract_f4m_formats(
-            format_url_base + '/manifest.f4m',
-            video_id, f4m_id='hds', fatal=False))
-        self._sort_formats(formats)
-        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',
@@ -89,10 +66,7 @@ class DCNVideoIE(DCNBaseIE):
             'duration': 2041,
             'timestamp': 1227504126,
             'upload_date': '20081124',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
+            'uploader_id': '71',
         },
     }, {
         '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',
@@ -102,54 +76,69 @@ 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?' +
-            compat_urllib_parse_urlencode({
-                'id': video_data['id'],
-                'user_id': video_data['user_id'],
-                'signature': video_data['signature'],
-                'countries': 'Q0M=',
-                'filter': 'DENY',
-            }), video_id)
-        info['formats'] = self._extract_video_formats(webpage, video_id, 'm3u8_native')
+        embed_url = 'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' + compat_urllib_parse_urlencode({
+            'id': video_data['id'],
+            'user_id': video_data['user_id'],
+            'signature': video_data['signature'],
+            'countries': 'Q0M=',
+            'filter': 'DENY',
+        })
+        info.update({
+            '_type': 'url_transparent',
+            'url': embed_url,
+            'ie_key': 'MangomoloVideo',
+        })
         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_id, headers={'Origin': 'http://awaan.ae'})
+        info = self._parse_video_data(channel_data, channel_id, True)
 
-        channel_data = self._download_json(request, channel_id)
-        info = self._extract_video_info(channel_data, channel_id, True)
-
-        webpage = self._download_webpage(
-            'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' +
-            compat_urllib_parse_urlencode({
-                'id': base64.b64encode(channel_data['user_id'].encode()).decode(),
-                'channelid': base64.b64encode(channel_data['id'].encode()).decode(),
-                'signature': channel_data['signature'],
-                'countries': 'Q0M=',
-                'filter': 'DENY',
-            }), channel_id)
-        info['formats'] = self._extract_video_formats(webpage, channel_id, 'm3u8')
+        embed_url = 'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' + compat_urllib_parse_urlencode({
+            'id': base64.b64encode(channel_data['user_id'].encode()).decode(),
+            'channelid': base64.b64encode(channel_data['id'].encode()).decode(),
+            'signature': channel_data['signature'],
+            'countries': 'Q0M=',
+            'filter': 'DENY',
+        })
+        info.update({
+            '_type': 'url_transparent',
+            'url': embed_url,
+            'ie_key': 'MangomoloLive',
+        })
         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 +159,17 @@ 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 +180,6 @@ 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/azubu.py

@@ -103,7 +103,7 @@ class AzubuIE(InfoExtractor):
 
 
 class AzubuLiveIE(InfoExtractor):
-    _VALID_URL = r'https?://www.azubu.tv/(?P<id>[^/]+)$'
+    _VALID_URL = r'https?://(?:www\.)?azubu\.tv/(?P<id>[^/]+)$'
 
     _TEST = {
         'url': 'http://www.azubu.tv/MarsTVMDLen',

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

@@ -2,19 +2,23 @@
 from __future__ import unicode_literals
 
 import re
+import itertools
 
 from .common import InfoExtractor
 from ..utils import (
+    dict_get,
     ExtractorError,
     float_or_none,
     int_or_none,
     parse_duration,
     parse_iso8601,
+    try_get,
     unescapeHTML,
 )
 from ..compat import (
     compat_etree_fromstring,
     compat_HTTPError,
+    compat_urlparse,
 )
 
 
@@ -229,51 +233,6 @@ class BBCCoUkIE(InfoExtractor):
         asx = self._download_xml(connection.get('href'), programme_id, 'Downloading ASX playlist')
         return [ref.get('href') for ref in asx.findall('./Entry/ref')]
 
-    def _extract_connection(self, connection, programme_id):
-        formats = []
-        kind = connection.get('kind')
-        protocol = connection.get('protocol')
-        supplier = connection.get('supplier')
-        if protocol == 'http':
-            href = connection.get('href')
-            transfer_format = connection.get('transferFormat')
-            # ASX playlist
-            if supplier == 'asx':
-                for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)):
-                    formats.append({
-                        'url': ref,
-                        'format_id': 'ref%s_%s' % (i, supplier),
-                    })
-            # Skip DASH until supported
-            elif transfer_format == 'dash':
-                pass
-            elif transfer_format == 'hls':
-                formats.extend(self._extract_m3u8_formats(
-                    href, programme_id, ext='mp4', entry_protocol='m3u8_native',
-                    m3u8_id=supplier, fatal=False))
-            # Direct link
-            else:
-                formats.append({
-                    'url': href,
-                    'format_id': supplier or kind or protocol,
-                })
-        elif protocol == 'rtmp':
-            application = connection.get('application', 'ondemand')
-            auth_string = connection.get('authString')
-            identifier = connection.get('identifier')
-            server = connection.get('server')
-            formats.append({
-                'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string),
-                'play_path': identifier,
-                'app': '%s?%s' % (application, auth_string),
-                'page_url': 'http://www.bbc.co.uk',
-                'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf',
-                'rtmp_live': False,
-                'ext': 'flv',
-                'format_id': supplier,
-            })
-        return formats
-
     def _extract_items(self, playlist):
         return playlist.findall('./{%s}item' % self._EMP_PLAYLIST_NS)
 
@@ -294,46 +253,6 @@ class BBCCoUkIE(InfoExtractor):
     def _extract_connections(self, media):
         return self._findall_ns(media, './{%s}connection')
 
-    def _extract_video(self, media, programme_id):
-        formats = []
-        vbr = int_or_none(media.get('bitrate'))
-        vcodec = media.get('encoding')
-        service = media.get('service')
-        width = int_or_none(media.get('width'))
-        height = int_or_none(media.get('height'))
-        file_size = int_or_none(media.get('media_file_size'))
-        for connection in self._extract_connections(media):
-            conn_formats = self._extract_connection(connection, programme_id)
-            for format in conn_formats:
-                format.update({
-                    'width': width,
-                    'height': height,
-                    'vbr': vbr,
-                    'vcodec': vcodec,
-                    'filesize': file_size,
-                })
-                if service:
-                    format['format_id'] = '%s_%s' % (service, format['format_id'])
-            formats.extend(conn_formats)
-        return formats
-
-    def _extract_audio(self, media, programme_id):
-        formats = []
-        abr = int_or_none(media.get('bitrate'))
-        acodec = media.get('encoding')
-        service = media.get('service')
-        for connection in self._extract_connections(media):
-            conn_formats = self._extract_connection(connection, programme_id)
-            for format in conn_formats:
-                format.update({
-                    'format_id': '%s_%s' % (service, format['format_id']),
-                    'abr': abr,
-                    'acodec': acodec,
-                    'vcodec': 'none',
-                })
-            formats.extend(conn_formats)
-        return formats
-
     def _get_subtitles(self, media, programme_id):
         subtitles = {}
         for connection in self._extract_connections(media):
@@ -379,13 +298,87 @@ class BBCCoUkIE(InfoExtractor):
     def _process_media_selector(self, media_selection, programme_id):
         formats = []
         subtitles = None
+        urls = []
 
         for media in self._extract_medias(media_selection):
             kind = media.get('kind')
-            if kind == 'audio':
-                formats.extend(self._extract_audio(media, programme_id))
-            elif kind == 'video':
-                formats.extend(self._extract_video(media, programme_id))
+            if kind in ('video', 'audio'):
+                bitrate = int_or_none(media.get('bitrate'))
+                encoding = media.get('encoding')
+                service = media.get('service')
+                width = int_or_none(media.get('width'))
+                height = int_or_none(media.get('height'))
+                file_size = int_or_none(media.get('media_file_size'))
+                for connection in self._extract_connections(media):
+                    href = connection.get('href')
+                    if href in urls:
+                        continue
+                    if href:
+                        urls.append(href)
+                    conn_kind = connection.get('kind')
+                    protocol = connection.get('protocol')
+                    supplier = connection.get('supplier')
+                    transfer_format = connection.get('transferFormat')
+                    format_id = supplier or conn_kind or protocol
+                    if service:
+                        format_id = '%s_%s' % (service, format_id)
+                    # ASX playlist
+                    if supplier == 'asx':
+                        for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)):
+                            formats.append({
+                                'url': ref,
+                                'format_id': 'ref%s_%s' % (i, format_id),
+                            })
+                    elif transfer_format == 'dash':
+                        formats.extend(self._extract_mpd_formats(
+                            href, programme_id, mpd_id=format_id, fatal=False))
+                    elif transfer_format == 'hls':
+                        formats.extend(self._extract_m3u8_formats(
+                            href, programme_id, ext='mp4', entry_protocol='m3u8_native',
+                            m3u8_id=format_id, fatal=False))
+                    elif transfer_format == 'hds':
+                        formats.extend(self._extract_f4m_formats(
+                            href, programme_id, f4m_id=format_id, fatal=False))
+                    else:
+                        if not service and not supplier and bitrate:
+                            format_id += '-%d' % bitrate
+                        fmt = {
+                            'format_id': format_id,
+                            'filesize': file_size,
+                        }
+                        if kind == 'video':
+                            fmt.update({
+                                'width': width,
+                                'height': height,
+                                'vbr': bitrate,
+                                'vcodec': encoding,
+                            })
+                        else:
+                            fmt.update({
+                                'abr': bitrate,
+                                'acodec': encoding,
+                                'vcodec': 'none',
+                            })
+                        if protocol == 'http':
+                            # Direct link
+                            fmt.update({
+                                'url': href,
+                            })
+                        elif protocol == 'rtmp':
+                            application = connection.get('application', 'ondemand')
+                            auth_string = connection.get('authString')
+                            identifier = connection.get('identifier')
+                            server = connection.get('server')
+                            fmt.update({
+                                'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string),
+                                'play_path': identifier,
+                                'app': '%s?%s' % (application, auth_string),
+                                'page_url': 'http://www.bbc.co.uk',
+                                'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf',
+                                'rtmp_live': False,
+                                'ext': 'flv',
+                            })
+                        formats.append(fmt)
             elif kind == 'captions':
                 subtitles = self.extract_subtitles(media, programme_id)
         return formats, subtitles
@@ -589,7 +582,7 @@ class BBCIE(BBCCoUkIE):
         'info_dict': {
             'id': '150615_telabyad_kentin_cogu',
             'ext': 'mp4',
-            'title': "Tel Abyad'da IŞİD bayrağı indirildi YPG bayrağı çekildi",
+            'title': "YPG: Tel Abyad'ın tamamı kontrolümüzde",
             'description': 'md5:33a4805a855c9baf7115fcbde57e7025',
             'timestamp': 1434397334,
             'upload_date': '20150615',
@@ -654,6 +647,23 @@ class BBCIE(BBCCoUkIE):
             # rtmp download
             'skip_download': True,
         }
+    }, {
+        # single video embedded with Morph
+        'url': 'http://www.bbc.co.uk/sport/live/olympics/36895975',
+        'info_dict': {
+            'id': 'p041vhd0',
+            'ext': 'mp4',
+            'title': "Nigeria v Japan - Men's First Round",
+            'description': 'Live coverage of the first round from Group B at the Amazonia Arena.',
+            'duration': 7980,
+            'uploader': 'BBC Sport',
+            'uploader_id': 'bbc_sport',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+        'skip': 'Georestricted to UK',
     }, {
         # single video with playlist.sxml URL in playlist param
         'url': 'http://www.bbc.com/sport/0/football/33653409',
@@ -751,7 +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')
@@ -820,13 +830,19 @@ class BBCIE(BBCCoUkIE):
                         # http://www.bbc.com/turkce/multimedya/2015/10/151010_vid_ankara_patlama_ani)
                         playlist = data_playable.get('otherSettings', {}).get('playlist', {})
                         if playlist:
-                            for key in ('progressiveDownload', 'streaming'):
+                            entry = None
+                            for key in ('streaming', 'progressiveDownload'):
                                 playlist_url = playlist.get('%sUrl' % key)
                                 if not playlist_url:
                                     continue
                                 try:
-                                    entries.append(self._extract_from_playlist_sxml(
-                                        playlist_url, playlist_id, timestamp))
+                                    info = self._extract_from_playlist_sxml(
+                                        playlist_url, playlist_id, timestamp)
+                                    if not entry:
+                                        entry = info
+                                    else:
+                                        entry['title'] = info['title']
+                                        entry['formats'].extend(info['formats'])
                                 except Exception as e:
                                     # Some playlist URL may fail with 500, at the same time
                                     # the other one may work fine (e.g.
@@ -834,6 +850,9 @@ class BBCIE(BBCCoUkIE):
                                     if isinstance(e.cause, compat_HTTPError) and e.cause.code == 500:
                                         continue
                                     raise
+                            if entry:
+                                self._sort_formats(entry['formats'])
+                                entries.append(entry)
 
         if entries:
             return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
@@ -866,6 +885,50 @@ class BBCIE(BBCCoUkIE):
                 'subtitles': subtitles,
             }
 
+        # Morph based embed (e.g. http://www.bbc.co.uk/sport/live/olympics/36895975)
+        # There are several setPayload calls may be present but the video
+        # seems to be always related to the first one
+        morph_payload = self._parse_json(
+            self._search_regex(
+                r'Morph\.setPayload\([^,]+,\s*({.+?})\);',
+                webpage, 'morph payload', default='{}'),
+            playlist_id, fatal=False)
+        if morph_payload:
+            components = try_get(morph_payload, lambda x: x['body']['components'], list) or []
+            for component in components:
+                if not isinstance(component, dict):
+                    continue
+                lead_media = try_get(component, lambda x: x['props']['leadMedia'], dict)
+                if not lead_media:
+                    continue
+                identifiers = lead_media.get('identifiers')
+                if not identifiers or not isinstance(identifiers, dict):
+                    continue
+                programme_id = identifiers.get('vpid') or identifiers.get('playablePid')
+                if not programme_id:
+                    continue
+                title = lead_media.get('title') or self._og_search_title(webpage)
+                formats, subtitles = self._download_media_selector(programme_id)
+                self._sort_formats(formats)
+                description = lead_media.get('summary')
+                uploader = lead_media.get('masterBrand')
+                uploader_id = lead_media.get('mid')
+                duration = None
+                duration_d = lead_media.get('duration')
+                if isinstance(duration_d, dict):
+                    duration = parse_duration(dict_get(
+                        duration_d, ('rawDuration', 'formattedDuration', 'spokenDuration')))
+                return {
+                    'id': programme_id,
+                    'title': title,
+                    'description': description,
+                    'duration': duration,
+                    'uploader': uploader,
+                    'uploader_id': uploader_id,
+                    'formats': formats,
+                    'subtitles': subtitles,
+                }
+
         def extract_all(pattern):
             return list(filter(None, map(
                 lambda s: self._parse_json(s, playlist_id, fatal=False),
@@ -883,7 +946,7 @@ class BBCIE(BBCCoUkIE):
             r'setPlaylist\("(%s)"\)' % EMBED_URL, webpage))
         if entries:
             return self.playlist_result(
-                [self.url_result(entry, 'BBCCoUk') for entry in entries],
+                [self.url_result(entry_, 'BBCCoUk') for entry_ in entries],
                 playlist_id, playlist_title, playlist_description)
 
         # Multiple video article (e.g. http://www.bbc.com/news/world-europe-32668511)
@@ -965,7 +1028,7 @@ class BBCIE(BBCCoUkIE):
 
 
 class BBCCoUkArticleIE(InfoExtractor):
-    _VALID_URL = r'https?://www.bbc.co.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
     IE_NAME = 'bbc.co.uk:article'
     IE_DESC = 'BBC articles'
 
@@ -995,19 +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):
@@ -1056,6 +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/beatport.py

@@ -8,10 +8,10 @@ from ..compat import compat_str
 from ..utils import int_or_none
 
 
-class BeatportProIE(InfoExtractor):
-    _VALID_URL = r'https?://pro\.beatport\.com/track/(?P<display_id>[^/]+)/(?P<id>[0-9]+)'
+class BeatportIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.|pro\.)?beatport\.com/track/(?P<display_id>[^/]+)/(?P<id>[0-9]+)'
     _TESTS = [{
-        'url': 'https://pro.beatport.com/track/synesthesia-original-mix/5379371',
+        'url': 'https://beatport.com/track/synesthesia-original-mix/5379371',
         'md5': 'b3c34d8639a2f6a7f734382358478887',
         'info_dict': {
             'id': '5379371',
@@ -20,7 +20,7 @@ class BeatportProIE(InfoExtractor):
             'title': 'Froxic - Synesthesia (Original Mix)',
         },
     }, {
-        'url': 'https://pro.beatport.com/track/love-and-war-original-mix/3756896',
+        'url': 'https://beatport.com/track/love-and-war-original-mix/3756896',
         'md5': 'e44c3025dfa38c6577fbaeb43da43514',
         'info_dict': {
             'id': '3756896',
@@ -29,7 +29,7 @@ class BeatportProIE(InfoExtractor):
             'title': 'Wolfgang Gartner - Love & War (Original Mix)',
         },
     }, {
-        'url': 'https://pro.beatport.com/track/birds-original-mix/4991738',
+        'url': 'https://beatport.com/track/birds-original-mix/4991738',
         'md5': 'a1fd8e8046de3950fd039304c186c05f',
         'info_dict': {
             'id': '4991738',

youtube_dl/extractor/beeg.py

@@ -46,19 +46,19 @@ class BeegIE(InfoExtractor):
                 self._proto_relative_url(cpl_url), video_id,
                 'Downloading cpl JS', fatal=False)
             if cpl:
-                beeg_version = self._search_regex(
-                    r'beeg_version\s*=\s*(\d+)', cpl,
-                    'beeg version', default=None) or self._search_regex(
+                beeg_version = int_or_none(self._search_regex(
+                    r'beeg_version\s*=\s*([^\b]+)', cpl,
+                    'beeg version', default=None)) or self._search_regex(
                     r'/(\d+)\.js', cpl_url, 'beeg version', default=None)
                 beeg_salt = self._search_regex(
-                    r'beeg_salt\s*=\s*(["\'])(?P<beeg_salt>.+?)\1', cpl, 'beeg beeg_salt',
+                    r'beeg_salt\s*=\s*(["\'])(?P<beeg_salt>.+?)\1', cpl, 'beeg salt',
                     default=None, group='beeg_salt')
 
-        beeg_version = beeg_version or '1750'
-        beeg_salt = beeg_salt or 'MIDtGaw96f0N1kMMAM1DE46EC9pmFr'
+        beeg_version = beeg_version or '2000'
+        beeg_salt = beeg_salt or 'pmweAkq8lAYKdfWcFCUj0yoVgoPlinamH5UE1CB3H'
 
         video = self._download_json(
-            'http://api.beeg.com/api/v6/%s/video/%s' % (beeg_version, video_id),
+            'https://api.beeg.com/api/v6/%s/video/%s' % (beeg_version, video_id),
             video_id)
 
         def split(o, e):

youtube_dl/extractor/bellmedia.py

@@ -0,0 +1,75 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class BellMediaIE(InfoExtractor):
+    _VALID_URL = r'''(?x)https?://(?:www\.)?
+        (?P<domain>
+            (?:
+                ctv|
+                tsn|
+                bnn|
+                thecomedynetwork|
+                discovery|
+                discoveryvelocity|
+                sciencechannel|
+                investigationdiscovery|
+                animalplanet|
+                bravo|
+                mtv|
+                space
+            )\.ca|
+            much\.com
+        )/.*?(?:\bvid=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6})'''
+    _TESTS = [{
+        'url': 'http://www.ctv.ca/video/player?vid=706966',
+        'md5': 'ff2ebbeae0aa2dcc32a830c3fd69b7b0',
+        'info_dict': {
+            'id': '706966',
+            'ext': 'mp4',
+            'title': 'Larry Day and Richard Jutras on the TIFF red carpet of \'Stonewall\'',
+            'description': 'etalk catches up with Larry Day and Richard Jutras on the TIFF red carpet of "Stonewall”.',
+            'upload_date': '20150919',
+            '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,
+    }, {
+        'url': 'http://www.much.com/shows/atmidnight/episode948007/tuesday-september-13-2016',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.much.com/shows/the-almost-impossible-gameshow/928979/episode-6',
+        'only_matching': True,
+    }]
+    _DOMAINS = {
+        'thecomedynetwork': 'comedy',
+        'discoveryvelocity': 'discvel',
+        'sciencechannel': 'discsci',
+        'investigationdiscovery': 'invdisc',
+        'animalplanet': 'aniplan',
+    }
+
+    def _real_extract(self, url):
+        domain, video_id = re.match(self._VALID_URL, url).groups()
+        domain = domain.split('.')[0]
+        return {
+            '_type': 'url_transparent',
+            'id': video_id,
+            'url': '9c9media:%s_web:%s' % (self._DOMAINS.get(domain, domain), video_id),
+            'ie_key': 'NineCNineMedia',
+        }

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

@@ -1,205 +1,101 @@
 # 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,
+    urlencode_postdata,
 )
 
 
 class BiliBiliIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.bilibili\.(?:tv|com)/video/av(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.|bangumi\.|)bilibili\.(?:tv|com)/(?:video/av|anime/v/)(?P<id>\d+)'
 
-    _TESTS = [{
+    _TEST = {
         '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',
             'uploader': '菊子桑',
             'uploader_id': '156160',
         },
-    }, {
-        'url': 'http://www.bilibili.com/video/av1041170/',
-        'info_dict': {
-            'id': '1041170',
-            '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！~',
-        },
-        'playlist_count': 9,
-    }, {
-        'url': 'http://www.bilibili.com/video/av4808130/',
-        'info_dict': {
-            'id': '4808130',
-            'title': '【长篇】哆啦A梦443【钉铛】',
-            'description': '(2016.05.27)来组合客人的脸吧&amp;amp;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&amp;amp;illust_id=56912929',
-        },
-        '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&amp;amp;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&amp;amp;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&amp;amp;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&amp;amp;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&amp;amp;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&amp;amp;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&amp;amp;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&amp;amp;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',
-            '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】',
-            'uploader': '黑夜为猫',
-            'uploader_id': '610729',
-        },
-        'params': {
-            # Just to test metadata extraction
-            'skip_download': True,
-        },
-        '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(
-            [r'EmbedPlayer\([^)]+,\s*"([^"]+)"\)',
-             r'<iframe[^>]+src="https://secure\.bilibili\.com/secure,([^"]+)"'],
-            webpage, 'player parameters'))
-        cid = params['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')
-
-        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')
+        if 'anime/v' not in url:
+            cid = compat_parse_qs(self._search_regex(
+                [r'EmbedPlayer\([^)]+,\s*"([^"]+)"\)',
+                 r'<iframe[^>]+src="https://secure\.bilibili\.com/secure,([^"]+)"'],
+                webpage, 'player parameters'))['cid'][0]
         else:
-            err_msg = xpath_text(info_xml, './message')
+            js = self._download_json(
+                'http://bangumi.bilibili.com/web_api/get_source', video_id,
+                data=urlencode_postdata({'episode_id': video_id}),
+                headers={'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8'})
+            cid = js['result']['cid']
 
-        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!')
+        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()
+
+        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.get('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))
+        thumbnail = self._html_search_meta(['og:image', 'thumbnailUrl'], webpage)
 
         # 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),
+            'thumbnail': thumbnail,
+            '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/bpb.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 class BpbIE(InfoExtractor):
     IE_DESC = 'Bundeszentrale für politische Bildung'
-    _VALID_URL = r'https?://www\.bpb\.de/mediathek/(?P<id>[0-9]+)/'
+    _VALID_URL = r'https?://(?:www\.)?bpb\.de/mediathek/(?P<id>[0-9]+)/'
 
     _TEST = {
         'url': 'http://www.bpb.de/mediathek/297/joachim-gauck-zu-1989-und-die-erinnerung-an-die-ddr',

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/brightcove.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
@@ -621,15 +621,21 @@ class BrightcoveNewIE(InfoExtractor):
                     'url': text_track['src'],
                 })
 
+        is_live = False
+        duration = float_or_none(json_data.get('duration'), 1000)
+        if duration and duration < 0:
+            is_live = True
+
         return {
             'id': video_id,
-            'title': title,
+            'title': self._live_title(title) if is_live else title,
             'description': clean_html(json_data.get('description')),
             'thumbnail': json_data.get('thumbnail') or json_data.get('poster'),
-            'duration': float_or_none(json_data.get('duration'), 1000),
+            'duration': duration,
             'timestamp': parse_iso8601(json_data.get('published_at')),
             'uploader_id': account_id,
             'formats': formats,
             'subtitles': subtitles,
             'tags': json_data.get('tags', []),
+            'is_live': is_live,
         }

youtube_dl/extractor/byutv.py

@@ -1,6 +1,5 @@
 from __future__ import unicode_literals
 
-import json
 import re
 
 from .common import InfoExtractor
@@ -8,15 +7,15 @@ from ..utils import ExtractorError
 
 
 class BYUtvIE(InfoExtractor):
-    _VALID_URL = r'^https?://(?:www\.)?byutv.org/watch/[0-9a-f-]+/(?P<video_id>[^/?#]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?byutv\.org/watch/(?!event/)(?P<id>[0-9a-f-]+)(?:/(?P<display_id>[^/?#&]+))?'
+    _TESTS = [{
         'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d/studio-c-season-5-episode-5',
-        'md5': '05850eb8c749e2ee05ad5a1c34668493',
         'info_dict': {
-            'id': 'studio-c-season-5-episode-5',
+            'id': '6587b9a3-89d2-42a6-a7f7-fd2f81840a7d',
+            'display_id': 'studio-c-season-5-episode-5',
             'ext': 'mp4',
-            'description': 'md5:e07269172baff037f8e8bf9956bc9747',
             'title': 'Season 5 Episode 5',
+            'description': 'md5:e07269172baff037f8e8bf9956bc9747',
             'thumbnail': 're:^https?://.*\.jpg$',
             'duration': 1486.486,
         },
@@ -24,28 +23,71 @@ class BYUtvIE(InfoExtractor):
             'skip_download': True,
         },
         'add_ie': ['Ooyala'],
+    }, {
+        'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id') or video_id
+
+        webpage = self._download_webpage(url, display_id)
+        episode_code = self._search_regex(
+            r'(?s)episode:(.*?\}),\s*\n', webpage, 'episode information')
+
+        ep = self._parse_json(
+            episode_code, display_id, transform_source=lambda s:
+            re.sub(r'(\n\s+)([a-zA-Z]+):\s+\'(.*?)\'', r'\1"\2": "\3"', s))
+
+        if ep['providerType'] != 'Ooyala':
+            raise ExtractorError('Unsupported provider %s' % ep['provider'])
+
+        return {
+            '_type': 'url_transparent',
+            'ie_key': 'Ooyala',
+            'url': 'ooyala:%s' % ep['providerId'],
+            'id': video_id,
+            'display_id': display_id,
+            'title': ep['title'],
+            'description': ep.get('description'),
+            'thumbnail': ep.get('imageThumbnail'),
+        }
+
+
+class BYUtvEventIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?byutv\.org/watch/event/(?P<id>[0-9a-f-]+)'
+    _TEST = {
+        'url': 'http://www.byutv.org/watch/event/29941b9b-8bf6-48d2-aebf-7a87add9e34b',
+        'info_dict': {
+            'id': '29941b9b-8bf6-48d2-aebf-7a87add9e34b',
+            'ext': 'mp4',
+            'title': 'Toledo vs. BYU (9/30/16)',
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'add_ie': ['Ooyala'],
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('video_id')
+        video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
-        episode_code = self._search_regex(
-            r'(?s)episode:(.*?\}),\s*\n', webpage, 'episode information')
-        episode_json = re.sub(
-            r'(\n\s+)([a-zA-Z]+):\s+\'(.*?)\'', r'\1"\2": "\3"', episode_code)
-        ep = json.loads(episode_json)
 
-        if ep['providerType'] == 'Ooyala':
-            return {
-                '_type': 'url_transparent',
-                'ie_key': 'Ooyala',
-                'url': 'ooyala:%s' % ep['providerId'],
-                'id': video_id,
-                'title': ep['title'],
-                'description': ep.get('description'),
-                'thumbnail': ep.get('imageThumbnail'),
-            }
-        else:
-            raise ExtractorError('Unsupported provider %s' % ep['provider'])
+        ooyala_id = self._search_regex(
+            r'providerId\s*:\s*(["\'])(?P<id>(?:(?!\1).)+)\1',
+            webpage, 'ooyala id', group='id')
+
+        title = self._search_regex(
+            r'class=["\']description["\'][^>]*>\s*<h1>([^<]+)</h1>', webpage,
+            'title').strip()
+
+        return {
+            '_type': 'url_transparent',
+            'ie_key': 'Ooyala',
+            'url': 'ooyala:%s' % ooyala_id,
+            'id': video_id,
+            'title': title,
+        }

youtube_dl/extractor/camdemy.py

@@ -112,7 +112,7 @@ class CamdemyIE(InfoExtractor):
 
 
 class CamdemyFolderIE(InfoExtractor):
-    _VALID_URL = r'https?://www.camdemy.com/folder/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?camdemy\.com/folder/(?P<id>\d+)'
     _TESTS = [{
         # links with trailing slash
         'url': 'http://www.camdemy.com/folder/450',

youtube_dl/extractor/canalplus.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
@@ -6,11 +6,13 @@ import re
 from .common import InfoExtractor
 from ..compat import compat_urllib_parse_urlparse
 from ..utils import (
+    dict_get,
     ExtractorError,
     HEADRequest,
-    unified_strdate,
-    qualities,
     int_or_none,
+    qualities,
+    remove_end,
+    unified_strdate,
 )
 
 
@@ -23,6 +25,7 @@ class CanalplusIE(InfoExtractor):
                                     (?:(?:www|m)\.)?canalplus\.fr|
                                     (?:www\.)?piwiplus\.fr|
                                     (?:www\.)?d8\.tv|
+                                    (?:www\.)?c8\.fr|
                                     (?:www\.)?d17\.tv|
                                     (?:www\.)?itele\.fr
                                 )/(?:(?:[^/]+/)*(?P<display_id>[^/?#&]+))?(?:\?.*\bvid=(?P<vid>\d+))?|
@@ -35,53 +38,53 @@ class CanalplusIE(InfoExtractor):
         'canalplus': 'cplus',
         'piwiplus': 'teletoon',
         'd8': 'd8',
+        'c8': 'd8',
         'd17': 'd17',
         'itele': 'itele',
     }
 
     _TESTS = [{
         'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1192814',
-        'md5': '41f438a4904f7664b91b4ed0dec969dc',
         'info_dict': {
-            'id': '1192814',
+            'id': '1405510',
+            'display_id': 'pid1830-c-zapping',
             'ext': 'mp4',
-            'title': "L'Année du Zapping 2014 - L'Année du Zapping 2014",
-            'description': "Toute l'année 2014 dans un Zapping exceptionnel !",
-            'upload_date': '20150105',
+            'title': 'Zapping - 02/07/2016',
+            'description': 'Le meilleur de toutes les chaînes, tous les jours',
+            'upload_date': '20160702',
         },
     }, {
         'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190',
         'info_dict': {
             'id': '1108190',
-            'ext': 'flv',
-            'title': 'Le labyrinthe - Boing super ranger',
+            'display_id': 'pid1405-le-labyrinthe-boing-super-ranger',
+            'ext': 'mp4',
+            'title': 'BOING SUPER RANGER - Ep : Le labyrinthe',
             'description': 'md5:4cea7a37153be42c1ba2c1d3064376ff',
             'upload_date': '20140724',
         },
         'skip': 'Only works from France',
     }, {
-        'url': 'http://www.d8.tv/d8-docs-mags/pid5198-d8-en-quete-d-actualite.html?vid=1390231',
+        'url': 'http://www.c8.fr/c8-divertissement/ms-touche-pas-a-mon-poste/pid6318-videos-integrales.html',
+        'md5': '4b47b12b4ee43002626b97fad8fb1de5',
         'info_dict': {
-            'id': '1390231',
+            'id': '1420213',
+            'display_id': 'pid6318-videos-integrales',
             'ext': 'mp4',
-            'title': "Vacances pas chères : prix discount ou grosses dépenses ? - En quête d'actualité",
-            'description': 'md5:edb6cf1cb4a1e807b5dd089e1ac8bfc6',
-            'upload_date': '20160512',
-        },
-        'params': {
-            'skip_download': True,
+            'title': 'TPMP ! Même le matin - Les 35H de Baba - 14/10/2016',
+            'description': 'md5:f96736c1b0ffaa96fd5b9e60ad871799',
+            'upload_date': '20161014',
         },
+        'skip': 'Only works from France',
     }, {
-        'url': 'http://www.itele.fr/chroniques/invite-bruce-toussaint/thierry-solere-nicolas-sarkozy-officialisera-sa-candidature-a-la-primaire-quand-il-le-voudra-167224',
+        'url': 'http://www.itele.fr/chroniques/invite-michael-darmon/rachida-dati-nicolas-sarkozy-est-le-plus-en-phase-avec-les-inquietudes-des-francais-171510',
         'info_dict': {
-            'id': '1398334',
+            'id': '1420176',
+            'display_id': 'rachida-dati-nicolas-sarkozy-est-le-plus-en-phase-avec-les-inquietudes-des-francais-171510',
             'ext': 'mp4',
-            'title': "L'invité de Bruce Toussaint du 07/06/2016 - ",
-            'description': 'md5:40ac7c9ad0feaeb6f605bad986f61324',
-            'upload_date': '20160607',
-        },
-        'params': {
-            'skip_download': True,
+            'title': 'L\'invité de Michaël Darmon du 14/10/2016 - ',
+            'description': 'Chaque matin du lundi au vendredi, Michaël Darmon reçoit un invité politique à 8h25.',
+            'upload_date': '20161014',
         },
     }, {
         'url': 'http://m.canalplus.fr/?vid=1398231',
@@ -93,18 +96,17 @@ class CanalplusIE(InfoExtractor):
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.groupdict().get('id') or mobj.groupdict().get('vid')
 
         site_id = self._SITE_ID_MAP[compat_urllib_parse_urlparse(url).netloc.rsplit('.', 2)[-2]]
 
         # Beware, some subclasses do not define an id group
-        display_id = mobj.group('display_id') or video_id
+        display_id = remove_end(dict_get(mobj.groupdict(), ('display_id', 'id', 'vid')), '.html')
 
-        if video_id is None:
-            webpage = self._download_webpage(url, display_id)
-            video_id = self._search_regex(
-                [r'<canal:player[^>]+?videoId=(["\'])(?P<id>\d+)', r'id=["\']canal_video_player(?P<id>\d+)'],
-                webpage, 'video id', group='id')
+        webpage = self._download_webpage(url, display_id)
+        video_id = self._search_regex(
+            [r'<canal:player[^>]+?videoId=(["\'])(?P<id>\d+)',
+             r'id=["\']canal_video_player(?P<id>\d+)'],
+            webpage, 'video id', group='id')
 
         info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
         video_data = self._download_json(info_url, video_id, 'Downloading video JSON')

youtube_dl/extractor/canvas.py

@@ -1,11 +1,13 @@
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import float_or_none
 
 
 class CanvasIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?canvas\.be/video/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?P<site_id>canvas|een)\.be/(?:[^/]+/)*(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'http://www.canvas.be/video/de-afspraak/najaar-2015/de-afspraak-veilt-voor-de-warmste-week',
         'md5': 'ea838375a547ac787d4064d8c7860a6c',
@@ -38,22 +40,42 @@ class CanvasIE(InfoExtractor):
         'params': {
             'skip_download': True,
         }
+    }, {
+        'url': 'https://www.een.be/sorry-voor-alles/herbekijk-sorry-voor-alles',
+        'info_dict': {
+            'id': 'mz-ast-11a587f8-b921-4266-82e2-0bce3e80d07f',
+            'display_id': 'herbekijk-sorry-voor-alles',
+            'ext': 'mp4',
+            'title': 'Herbekijk Sorry voor alles',
+            'description': 'md5:8bb2805df8164e5eb95d6a7a29dc0dd3',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 3788.06,
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        'url': 'https://www.canvas.be/check-point/najaar-2016/de-politie-uw-vriend',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        display_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        site_id, display_id = mobj.group('site_id'), mobj.group('id')
 
         webpage = self._download_webpage(url, display_id)
 
-        title = self._search_regex(
+        title = (self._search_regex(
             r'<h1[^>]+class="video__body__header__title"[^>]*>(.+?)</h1>',
-            webpage, 'title', default=None) or self._og_search_title(webpage)
+            webpage, 'title', default=None) or self._og_search_title(
+            webpage)).strip()
 
         video_id = self._html_search_regex(
-            r'data-video=(["\'])(?P<id>.+?)\1', webpage, 'video id', group='id')
+            r'data-video=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video id', group='id')
 
         data = self._download_json(
-            'https://mediazone.vrt.be/api/v1/canvas/assets/%s' % video_id, display_id)
+            'https://mediazone.vrt.be/api/v1/%s/assets/%s'
+            % (site_id, video_id), display_id)
 
         formats = []
         for target in data['targetUrls']:

youtube_dl/extractor/carambatv.py

@@ -9,6 +9,8 @@ from ..utils import (
     try_get,
 )
 
+from .videomore import VideomoreIE
+
 
 class CarambaTVIE(InfoExtractor):
     _VALID_URL = r'(?:carambatv:|https?://video1\.carambatv\.ru/v/)(?P<id>\d+)'
@@ -62,14 +64,16 @@ class CarambaTVPageIE(InfoExtractor):
     _VALID_URL = r'https?://carambatv\.ru/(?:[^/]+/)+(?P<id>[^/?#&]+)'
     _TEST = {
         'url': 'http://carambatv.ru/movie/bad-comedian/razborka-v-manile/',
-        'md5': '',
+        'md5': 'a49fb0ec2ad66503eeb46aac237d3c86',
         'info_dict': {
-            'id': '191910501',
-            'ext': 'mp4',
+            'id': '475222',
+            'ext': 'flv',
             'title': '[BadComedian] - Разборка в Маниле (Абсолютный обзор)',
-            'thumbnail': 're:^https?://.*\.jpg$',
-            'duration': 2678.31,
+            'thumbnail': 're:^https?://.*\.jpg',
+            # duration reported by videomore is incorrect
+            'duration': int,
         },
+        'add_ie': [VideomoreIE.ie_key()],
     }
 
     def _real_extract(self, url):
@@ -77,6 +81,16 @@ class CarambaTVPageIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
+        videomore_url = VideomoreIE._extract_url(webpage)
+        if videomore_url:
+            title = self._og_search_title(webpage)
+            return {
+                '_type': 'url_transparent',
+                'url': videomore_url,
+                'ie_key': VideomoreIE.ie_key(),
+                'title': title,
+            }
+
         video_url = self._og_search_property('video:iframe', webpage, default=None)
 
         if not video_url:

youtube_dl/extractor/cartoonnetwork.py

@@ -0,0 +1,42 @@
+# 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://androidhls-secure.cdn.turner.com/toon/big',
+                    'tokenizer_src': 'http://www.cartoonnetwork.com/cntv/mvpd/processors/services/token_ipadAdobe.do',
+                },
+            }, {
+                'url': url,
+                'site_name': 'CartoonNetwork',
+                'auth_required': self._search_regex(
+                    r'_cnglobal\.cvpFullOrPreviewAuth\s*=\s*(true|false);',
+                    webpage, 'auth required', default='false') == 'true',
+            })

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 +4,9 @@ from .theplatform import ThePlatformFeedIE
 from ..utils import (
     int_or_none,
     find_xpath_attr,
+    xpath_element,
+    xpath_text,
+    update_url_query,
 )
 
 
@@ -17,19 +20,6 @@ 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 +28,6 @@ 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 +36,10 @@ 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 +48,53 @@ 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, content_id):
+        items_data = self._download_xml(
+            'http://can.cbs.com/thunder/player/videoPlayerService.php',
+            content_id, query={'partner': 'cbs', 'contentId': content_id})
+        video_data = xpath_element(items_data, './/item')
+        title = xpath_text(video_data, 'videoTitle', 'title', True)
+        tp_path = 'dJ5BDC/media/guid/2198311517/%s' % content_id
+        tp_release_url = 'http://link.theplatform.com/s/' + tp_path
+
+        asset_types = []
+        subtitles = {}
+        formats = []
+        for item in items_data.findall('.//item'):
+            asset_type = xpath_text(item, 'assetType')
+            if not asset_type or asset_type in asset_types:
+                continue
+            asset_types.append(asset_type)
+            query = {
+                'mbr': 'true',
+                'assetTypes': asset_type,
+            }
+            if asset_type.startswith('HLS') or asset_type in ('OnceURL', 'StreamPack'):
+                query['formats'] = 'MPEG4,M3U'
+            elif asset_type in ('RTMP', 'WIFI', '3G'):
+                query['formats'] = 'MPEG4,FLV'
+            tp_formats, tp_subtitles = self._extract_theplatform_smil(
+                update_url_query(tp_release_url, query), content_id,
+                'Downloading %s SMIL data' % asset_type)
+            formats.extend(tp_formats)
+            subtitles = self._merge_subtitles(subtitles, tp_subtitles)
+        self._sort_formats(formats)
+
+        info = self._extract_theplatform_metadata(tp_path, content_id)
+        info.update({
+            'id': content_id,
+            'title': title,
+            'series': xpath_text(video_data, 'seriesTitle'),
+            'season_number': int_or_none(xpath_text(video_data, 'seasonNumber')),
+            'episode_number': int_or_none(xpath_text(video_data, 'episodeNumber')),
+            'duration': int_or_none(xpath_text(video_data, 'videoLength'), 1000),
+            'thumbnail': xpath_text(video_data, 'previewImageURL'),
+            'formats': formats,
+            'subtitles': subtitles,
+        })
+        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/cbsinteractive.py

@@ -63,7 +63,7 @@ class CBSInteractiveIE(ThePlatformIE):
         webpage = self._download_webpage(url, display_id)
 
         data_json = self._html_search_regex(
-            r"data-(?:cnet|zdnet)-video(?:-uvp)?-options='([^']+)'",
+            r"data-(?:cnet|zdnet)-video(?:-uvp(?:js)?)?-options='([^']+)'",
             webpage, 'data json')
         data = self._parse_json(data_json, display_id)
         vdata = data.get('video') or data['videos'][0]

youtube_dl/extractor/cbslocal.py

@@ -1,12 +1,10 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import calendar
-import datetime
-
 from .anvato import AnvatoIE
 from .sendtonews import SendtoNewsIE
 from ..compat import compat_urlparse
+from ..utils import unified_timestamp
 
 
 class CBSLocalIE(AnvatoIE):
@@ -43,13 +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,
@@ -62,19 +55,15 @@ 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)
-        timestamp = None
-        if time_str:
-            timestamp = calendar.timegm(datetime.datetime.strptime(
-                time_str, '%b %d, %Y %I:%M %p').timetuple())
+        timestamp = unified_timestamp(time_str)
 
         info_dict.update({
             'display_id': display_id,

youtube_dl/extractor/cbsnews.py

@@ -1,14 +1,15 @@
-# encoding: utf-8
+# coding: utf-8
 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_NAME = 'cbsnews'
     IE_DESC = 'CBS News'
     _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P<id>[\da-z_-]+)'
 
@@ -35,7 +36,8 @@ 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,
@@ -63,51 +65,43 @@ 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_NAME = 'cbsnews:livevideo'
     IE_DESC = 'CBS News Live Videos'
-    _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/video/(?P<id>[\da-z_-]+)'
+    _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/video/(?P<id>[^/?#]+)'
 
-    _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',
-            'ext': 'flv',
+            'ext': 'mp4',
             '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)
+        display_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
+        video_info = self._download_json(
+            'http://feeds.cbsn.cbsnews.com/rundown/story', display_id, query={
+                'device': 'desktop',
+                'dvr_slug': display_id,
+            })
 
-        video_info = self._parse_json(self._html_search_regex(
-            r'data-story-obj=\'({.+?})\'', webpage, 'video JSON info'), video_id)['story']
-
-        hdcore_sign = 'hdcore=3.3.1'
-        f4m_formats = self._extract_f4m_formats(video_info['url'] + '&' + hdcore_sign, video_id)
-        if f4m_formats:
-            for entry in f4m_formats:
-                # URLs without the extra param induce an 404 error
-                entry.update({'extra_param_to_segment_url': hdcore_sign})
-        self._sort_formats(f4m_formats)
+        formats = self._extract_akamai_formats(video_info['url'], display_id)
+        self._sort_formats(formats)
 
         return {
-            'id': video_id,
+            'id': display_id,
+            'display_id': display_id,
             'title': video_info['headline'],
             'thumbnail': video_info.get('thumbnail_url_hd') or video_info.get('thumbnail_url_sd'),
             'duration': parse_duration(video_info.get('segmentDur')),
-            'formats': f4m_formats,
+            'formats': formats,
         }

youtube_dl/extractor/cbssports.py

@@ -4,7 +4,7 @@ from .cbs import CBSBaseIE
 
 
 class CBSSportsIE(CBSBaseIE):
-    _VALID_URL = r'https?://www\.cbssports\.com/video/player/[^/]+/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?cbssports\.com/video/player/[^/]+/(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.cbssports.com/video/player/videos/708337219968/0/ben-simmons-the-next-lebron?-not-so-fast',
@@ -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/cctv.py

@@ -0,0 +1,53 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import float_or_none
+
+
+class CCTVIE(InfoExtractor):
+    _VALID_URL = r'''(?x)https?://(?:.+?\.)?
+        (?:
+            cctv\.(?:com|cn)|
+            cntv\.cn
+        )/
+        (?:
+            video/[^/]+/(?P<id>[0-9a-f]{32})|
+            \d{4}/\d{2}/\d{2}/(?P<display_id>VID[0-9A-Za-z]+)
+        )'''
+    _TESTS = [{
+        'url': 'http://english.cntv.cn/2016/09/03/VIDEhnkB5y9AgHyIEVphCEz1160903.shtml',
+        'md5': '819c7b49fc3927d529fb4cd555621823',
+        'info_dict': {
+            'id': '454368eb19ad44a1925bf1eb96140a61',
+            'ext': 'mp4',
+            'title': 'Portrait of Real Current Life 09/03/2016 Modern Inventors Part 1',
+        }
+    }, {
+        'url': 'http://tv.cctv.com/2016/09/07/VIDE5C1FnlX5bUywlrjhxXOV160907.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'http://tv.cntv.cn/video/C39296/95cfac44cabd3ddc4a9438780a4e5c44',
+        'only_matching': True
+    }]
+
+    def _real_extract(self, url):
+        video_id, display_id = re.match(self._VALID_URL, url).groups()
+        if not video_id:
+            webpage = self._download_webpage(url, display_id)
+            video_id = self._search_regex(
+                r'(?:fo\.addVariable\("videoCenterId",\s*|guid\s*=\s*)"([0-9a-f]{32})',
+                webpage, 'video_id')
+        api_data = self._download_json(
+            'http://vdn.apps.cntv.cn/api/getHttpVideoInfo.do?pid=' + video_id, video_id)
+        m3u8_url = re.sub(r'maxbr=\d+&?', '', api_data['hls_url'])
+
+        return {
+            'id': video_id,
+            'title': api_data['title'],
+            'formats': self._extract_m3u8_formats(
+                m3u8_url, video_id, 'mp4', 'm3u8_native', fatal=False),
+            'duration': float_or_none(api_data.get('video', {}).get('totalLength')),
+        }

youtube_dl/extractor/ceskatelevize.py

@@ -1,4 +1,4 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
@@ -17,7 +17,7 @@ from ..utils import (
 
 
 class CeskaTelevizeIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(?:[^/]+/)*(?P<id>[^/#?]+)/*(?:[#?].*)?$'
+    _VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/(porady|ivysilani)/(?:[^/]+/)*(?P<id>[^/#?]+)/*(?:[#?].*)?$'
     _TESTS = [{
         'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220',
         'info_dict': {

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 +1,34 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import base64
+import re
+
 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):
@@ -33,38 +37,40 @@ 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,
         }
 
 
 class ChirbitProfileIE(InfoExtractor):
     IE_NAME = 'chirbit:profile'
-    _VALID_URL = r'https?://(?:www\.)?chirbit.com/(?:rss/)?(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?chirbit\.com/(?:rss/)?(?P<id>[^/]+)'
     _TEST = {
         'url': 'http://chirbit.com/ScarletBeauty',
         'info_dict': {
             'id': 'ScarletBeauty',
-            'title': 'Chirbits by ScarletBeauty',
         },
         'playlist_mincount': 3,
     }
@@ -72,13 +78,10 @@ class ChirbitProfileIE(InfoExtractor):
     def _real_extract(self, url):
         profile_id = self._match_id(url)
 
-        rss = self._download_xml(
-            'http://chirbit.com/rss/%s' % profile_id, profile_id)
+        webpage = self._download_webpage(url, profile_id)
 
         entries = [
-            self.url_result(audio_url.text, 'Chirbit')
-            for audio_url in rss.findall('./channel/item/link')]
+            self.url_result(self._proto_relative_url('//chirb.it/' + video_id))
+            for _, video_id in re.findall(r'<input[^>]+id=([\'"])copy-btn-(?P<id>[0-9a-zA-Z]+)\1', webpage)]
 
-        title = rss.find('./channel/title').text
-
-        return self.playlist_result(entries, profile_id, title)
+        return self.playlist_result(entries, profile_id)

youtube_dl/extractor/clipfish.py

@@ -1,3 +1,4 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
@@ -10,15 +11,15 @@ from ..utils import (
 class ClipfishIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?clipfish\.de/(?:[^/]+/)+video/(?P<id>[0-9]+)'
     _TEST = {
-        'url': 'http://www.clipfish.de/special/game-trailer/video/3966754/fifa-14-e3-2013-trailer/',
-        'md5': '79bc922f3e8a9097b3d68a93780fd475',
+        'url': 'http://www.clipfish.de/special/ugly-americans/video/4343170/s01-e01-ugly-americans-date-in-der-hoelle/',
+        'md5': '720563e467b86374c194bdead08d207d',
         'info_dict': {
-            'id': '3966754',
+            'id': '4343170',
             'ext': 'mp4',
-            'title': 'FIFA 14 - E3 2013 Trailer',
-            'description': 'Video zu FIFA 14: E3 2013 Trailer',
-            'upload_date': '20130611',
-            'duration': 82,
+            'title': 'S01 E01 - Ugly Americans - Date in der Hölle',
+            'description': 'Mark Lilly arbeitet im Sozialdienst der Stadt New York und soll Immigranten bei ihrer Einbürgerung in die USA zur Seite stehen.',
+            'upload_date': '20161005',
+            'duration': 1291,
             'view_count': int,
         }
     }
@@ -50,10 +51,14 @@ class ClipfishIE(InfoExtractor):
                 'tbr': int_or_none(video_info.get('bitrate')),
             })
 
+        descr = video_info.get('descr')
+        if descr:
+            descr = descr.strip()
+
         return {
             'id': video_id,
             'title': video_info['title'],
-            'description': video_info.get('descr'),
+            'description': descr,
             'formats': formats,
             'thumbnail': video_info.get('media_content_thumbnail_large') or video_info.get('media_thumbnail'),
             'duration': int_or_none(video_info.get('media_length')),

youtube_dl/extractor/clubic.py

@@ -1,9 +1,6 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import json
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     clean_html,
@@ -30,16 +27,14 @@ class ClubicIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         player_url = 'http://player.m6web.fr/v1/player/clubic/%s.html' % video_id
         player_page = self._download_webpage(player_url, video_id)
 
-        config_json = self._search_regex(
+        config = self._parse_json(self._search_regex(
             r'(?m)M6\.Player\.config\s*=\s*(\{.+?\});$', player_page,
-            'configuration')
-        config = json.loads(config_json)
+            'configuration'), video_id)
 
         video_info = config['videoInfo']
         sources = config['sources']

youtube_dl/extractor/cmt.py

@@ -6,7 +6,7 @@ from ..utils import ExtractorError
 
 class CMTIE(MTVIE):
     IE_NAME = 'cmt.com'
-    _VALID_URL = r'https?://www\.cmt\.com/(?:videos|shows)/(?:[^/]+/)*(?P<videoid>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?cmt\.com/(?:videos|shows)/(?:[^/]+/)*(?P<videoid>\d+)'
     _FEED_URL = 'http://www.cmt.com/sitewide/apps/player/embed/rss/'
 
     _TESTS = [{
@@ -26,7 +26,7 @@ class CMTIE(MTVIE):
             'id': '1504699',
             'ext': 'mp4',
             'title': 'Still The King Ep. 109 in 3 Minutes',
-            'description': 'Relive or catch up with Still The King by watching this recap of season 1, episode 9. New episodes Sundays 9/8c.',
+            'description': 'Relive or catch up with Still The King by watching this recap of season 1, episode 9.',
             'timestamp': 1469421000.0,
             'upload_date': '20160725',
         },
@@ -42,3 +42,8 @@ class CMTIE(MTVIE):
                 '%s said: video is not available' % cls.IE_NAME, expected=True)
 
         return super(CMTIE, cls)._transform_rtmp_url(rtmp_video_url)
+
+    def _extract_mgid(self, webpage):
+        return self._search_regex(
+            r'MTVN\.VIDEO\.contentUri\s*=\s*([\'"])(?P<mgid>.+?)\1',
+            webpage, 'mgid', group='mgid')

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/comcarcoff.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

youtube_dl/extractor/comedycentral.py

@@ -1,6 +1,7 @@
 from __future__ import unicode_literals
 
 from .mtv import MTVServicesInfoExtractor
+from .common import InfoExtractor
 
 
 class ComedyCentralIE(MTVServicesInfoExtractor):
@@ -96,3 +97,22 @@ class ComedyCentralTVIE(MTVServicesInfoExtractor):
             webpage, 'mrss url', group='url')
 
         return self._get_videos_info_from_url(mrss_url, video_id)
+
+
+class ComedyCentralShortnameIE(InfoExtractor):
+    _VALID_URL = r'^:(?P<id>tds|thedailyshow)$'
+    _TESTS = [{
+        'url': ':tds',
+        'only_matching': True,
+    }, {
+        'url': ':thedailyshow',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        shortcut_map = {
+            'tds': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
+            'thedailyshow': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
+        }
+        return self.url_result(shortcut_map[video_id])

youtube_dl/extractor/common.py

@@ -21,6 +21,7 @@ from ..compat import (
     compat_os_name,
     compat_str,
     compat_urllib_error,
+    compat_urllib_parse_unquote,
     compat_urllib_parse_urlencode,
     compat_urllib_request,
     compat_urlparse,
@@ -29,6 +30,7 @@ from ..downloader.f4m import remove_encrypted_media
 from ..utils import (
     NO_DEFAULT,
     age_restricted,
+    base_url,
     bug_reports_message,
     clean_html,
     compiled_regex_type,
@@ -87,6 +89,9 @@ class InfoExtractor(object):
 
                     Potential fields:
                     * url        Mandatory. The URL of the video file
+                    * manifest_url
+                                 The URL of the manifest file in case of
+                                 fragmented media (DASH, hls, hds)
                     * ext        Will be calculated from URL if missing
                     * format     A human-readable description of the format
                                  ("mp4 container with h264/opus").
@@ -115,6 +120,11 @@ class InfoExtractor(object):
                                  download, lower-case.
                                  "http", "https", "rtsp", "rtmp", "rtmpe",
                                  "m3u8", "m3u8_native" or "http_dash_segments".
+                    * fragments  A list of fragments of the fragmented media,
+                                 with the following entries:
+                                 * "url" (mandatory) - fragment's URL
+                                 * "duration" (optional, int or float)
+                                 * "filesize" (optional, int)
                     * preference Order number of this format. If this field is
                                  present and not None, the formats get sorted
                                  by this field, regardless of all other values.
@@ -226,7 +236,7 @@ class InfoExtractor(object):
     chapter_id:     Id of the chapter the video belongs to, as a unicode string.
 
     The following fields should only be used when the video is an episode of some
-    series or programme:
+    series, programme or podcast:
 
     series:         Title of the series or programme the video episode belongs to.
     season:         Title of the season the video episode belongs to.
@@ -662,35 +672,48 @@ class InfoExtractor(object):
         else:
             return res
 
-    def _get_login_info(self):
+    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, username_option='username', password_option='password', netrc_machine=None):
         """
         Get the login info as (username, password)
-        It will look in the netrc file using the _NETRC_MACHINE value
+        First look for the manually specified credentials using username_option
+        and password_option as keys in params dictionary. If no such credentials
+        available look in the netrc file using the netrc_machine or _NETRC_MACHINE
+        value.
         If there's no info available, return (None, None)
         """
         if self._downloader is None:
             return (None, None)
 
-        username = None
-        password = None
         downloader_params = self._downloader.params
 
         # Attempt to use provided username and password or .netrc data
-        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))
+        if downloader_params.get(username_option) is not None:
+            username = downloader_params[username_option]
+            password = downloader_params[password_option]
+        else:
+            username, password = self._get_netrc_login_info(netrc_machine)
 
-        return (username, password)
+        return username, password
 
     def _get_tfa_info(self, note='two-factor verification code'):
         """
@@ -727,9 +750,14 @@ class InfoExtractor(object):
                     [^>]+?content=(["\'])(?P<content>.*?)\2''' % re.escape(prop)
 
     def _og_search_property(self, prop, html, name=None, **kargs):
+        if not isinstance(prop, (list, tuple)):
+            prop = [prop]
         if name is None:
-            name = 'OpenGraph %s' % prop
-        escaped = self._search_regex(self._og_regexes(prop), html, name, flags=re.DOTALL, **kargs)
+            name = 'OpenGraph %s' % prop[0]
+        og_regexes = []
+        for p in prop:
+            og_regexes.extend(self._og_regexes(p))
+        escaped = self._search_regex(og_regexes, html, name, flags=re.DOTALL, **kargs)
         if escaped is None:
             return None
         return unescapeHTML(escaped)
@@ -811,11 +839,14 @@ 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):
@@ -823,57 +854,63 @@ class InfoExtractor(object):
         if not json_ld:
             return {}
         info = {}
-        if json_ld.get('@context') == 'http://schema.org':
-            item_type = json_ld.get('@type')
-            if expected_type is not None and expected_type != item_type:
-                return info
-            if item_type == 'TVEpisode':
-                info.update({
-                    'episode': unescapeHTML(json_ld.get('name')),
-                    'episode_number': int_or_none(json_ld.get('episodeNumber')),
-                    'description': unescapeHTML(json_ld.get('description')),
-                })
-                part_of_season = json_ld.get('partOfSeason')
-                if isinstance(part_of_season, dict) and part_of_season.get('@type') == 'TVSeason':
-                    info['season_number'] = int_or_none(part_of_season.get('seasonNumber'))
-                part_of_series = json_ld.get('partOfSeries')
-                if isinstance(part_of_series, dict) and part_of_series.get('@type') == 'TVSeries':
-                    info['series'] = unescapeHTML(part_of_series.get('name'))
-            elif item_type == 'Article':
-                info.update({
-                    'timestamp': parse_iso8601(json_ld.get('datePublished')),
-                    'title': unescapeHTML(json_ld.get('headline')),
-                    'description': unescapeHTML(json_ld.get('articleBody')),
-                })
-            elif item_type == 'VideoObject':
-                info.update({
-                    'url': json_ld.get('contentUrl'),
-                    'title': unescapeHTML(json_ld.get('name')),
-                    'description': unescapeHTML(json_ld.get('description')),
-                    'thumbnail': json_ld.get('thumbnailUrl'),
-                    'duration': parse_duration(json_ld.get('duration')),
-                    'timestamp': unified_timestamp(json_ld.get('uploadDate')),
-                    'filesize': float_or_none(json_ld.get('contentSize')),
-                    'tbr': int_or_none(json_ld.get('bitrate')),
-                    'width': int_or_none(json_ld.get('width')),
-                    'height': int_or_none(json_ld.get('height')),
-                })
+        if not isinstance(json_ld, (list, tuple, dict)):
+            return info
+        if isinstance(json_ld, dict):
+            json_ld = [json_ld]
+        for e in json_ld:
+            if e.get('@context') == 'http://schema.org':
+                item_type = e.get('@type')
+                if expected_type is not None and expected_type != item_type:
+                    return info
+                if item_type == 'TVEpisode':
+                    info.update({
+                        'episode': unescapeHTML(e.get('name')),
+                        'episode_number': int_or_none(e.get('episodeNumber')),
+                        'description': unescapeHTML(e.get('description')),
+                    })
+                    part_of_season = e.get('partOfSeason')
+                    if isinstance(part_of_season, dict) and part_of_season.get('@type') == 'TVSeason':
+                        info['season_number'] = int_or_none(part_of_season.get('seasonNumber'))
+                    part_of_series = e.get('partOfSeries') or e.get('partOfTVSeries')
+                    if isinstance(part_of_series, dict) and part_of_series.get('@type') == 'TVSeries':
+                        info['series'] = unescapeHTML(part_of_series.get('name'))
+                elif item_type == 'Article':
+                    info.update({
+                        'timestamp': parse_iso8601(e.get('datePublished')),
+                        'title': unescapeHTML(e.get('headline')),
+                        'description': unescapeHTML(e.get('articleBody')),
+                    })
+                elif item_type == 'VideoObject':
+                    info.update({
+                        'url': e.get('contentUrl'),
+                        'title': unescapeHTML(e.get('name')),
+                        'description': unescapeHTML(e.get('description')),
+                        'thumbnail': e.get('thumbnailUrl'),
+                        'duration': parse_duration(e.get('duration')),
+                        'timestamp': unified_timestamp(e.get('uploadDate')),
+                        'filesize': float_or_none(e.get('contentSize')),
+                        'tbr': int_or_none(e.get('bitrate')),
+                        'width': int_or_none(e.get('width')),
+                        'height': int_or_none(e.get('height')),
+                    })
+                break
         return dict((k, v) for k, v in info.items() if v is not None)
 
     @staticmethod
     def _hidden_inputs(html):
         html = re.sub(r'<!--(?:(?!<!--).)*-->', '', html)
         hidden_inputs = {}
-        for input in re.findall(r'(?i)<input([^>]+)>', html):
-            if not re.search(r'type=(["\'])(?:hidden|submit)\1', input):
+        for input in re.findall(r'(?i)(<input[^>]+>)', html):
+            attrs = extract_attributes(input)
+            if not input:
                 continue
-            name = re.search(r'(?:name|id)=(["\'])(?P<value>.+?)\1', input)
-            if not name:
+            if attrs.get('type') not in ('hidden', 'submit'):
                 continue
-            value = re.search(r'value=(["\'])(?P<value>.*?)\1', input)
-            if not value:
-                continue
-            hidden_inputs[name.group('value')] = value.group('value')
+            name = attrs.get('name') or attrs.get('id')
+            value = attrs.get('value')
+            if name and value is not None:
+                hidden_inputs[name] = value
         return hidden_inputs
 
     def _form_hidden_inputs(self, form_id, html):
@@ -911,7 +948,8 @@ class InfoExtractor(object):
                 if f.get('ext') in ['f4f', 'f4m']:  # Not yet supported
                     preference -= 0.5
 
-            proto_preference = 0 if determine_protocol(f) in ['http', 'https'] else -0.1
+            protocol = f.get('protocol') or determine_protocol(f)
+            proto_preference = 0 if protocol in ['http', 'https'] else (-0.5 if protocol == 'rtsp' else -0.1)
 
             if f.get('vcodec') == 'none':  # audio only
                 preference -= 50
@@ -1063,6 +1101,13 @@ class InfoExtractor(object):
             manifest, ['{http://ns.adobe.com/f4m/1.0}bootstrapInfo', '{http://ns.adobe.com/f4m/2.0}bootstrapInfo'],
             'bootstrap info', default=None)
 
+        vcodec = None
+        mime_type = xpath_text(
+            manifest, ['{http://ns.adobe.com/f4m/1.0}mimeType', '{http://ns.adobe.com/f4m/2.0}mimeType'],
+            'base URL', default=None)
+        if mime_type and mime_type.startswith('audio/'):
+            vcodec = 'none'
+
         for i, media_el in enumerate(media_nodes):
             tbr = int_or_none(media_el.attrib.get('bitrate'))
             width = int_or_none(media_el.attrib.get('width'))
@@ -1103,6 +1148,7 @@ class InfoExtractor(object):
                             'width': f.get('width') or width,
                             'height': f.get('height') or height,
                             'format_id': f.get('format_id') if not tbr else format_id,
+                            'vcodec': vcodec,
                         })
                     formats.extend(f4m_formats)
                     continue
@@ -1114,10 +1160,12 @@ class InfoExtractor(object):
             formats.append({
                 'format_id': format_id,
                 'url': manifest_url,
+                'manifest_url': manifest_url,
                 'ext': 'flv' if bootstrap_info is not None else None,
                 'tbr': tbr,
                 'width': width,
                 'height': height,
+                'vcodec': vcodec,
                 'preference': preference,
             })
         return formats
@@ -1128,7 +1176,7 @@ class InfoExtractor(object):
             'url': m3u8_url,
             'ext': ext,
             'protocol': 'm3u8',
-            'preference': preference - 1 if preference else -1,
+            'preference': preference - 100 if preference else -100,
             'resolution': 'multiple',
             'format_note': 'Quality selection URL',
         }
@@ -1138,13 +1186,6 @@ class InfoExtractor(object):
                               m3u8_id=None, note=None, errnote=None,
                               fatal=True, live=False):
 
-        formats = [self._m3u8_meta_format(m3u8_url, ext, preference, m3u8_id)]
-
-        format_url = lambda u: (
-            u
-            if re.match(r'^https?://', u)
-            else compat_urlparse.urljoin(m3u8_url, u))
-
         res = self._download_webpage_handle(
             m3u8_url, video_id,
             note=note or 'Downloading m3u8 information',
@@ -1155,6 +1196,13 @@ class InfoExtractor(object):
         m3u8_doc, urlh = res
         m3u8_url = urlh.geturl()
 
+        formats = [self._m3u8_meta_format(m3u8_url, ext, preference, m3u8_id)]
+
+        format_url = lambda u: (
+            u
+            if re.match(r'^https?://', u)
+            else compat_urlparse.urljoin(m3u8_url, u))
+
         # We should try extracting formats only from master playlists [1], i.e.
         # playlists that describe available qualities. On the other hand media
         # playlists [2] should be returned as is since they contain just the media
@@ -1176,35 +1224,54 @@ 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.
                 if not live:
                     format_id.append(stream_name if stream_name else '%d' % (tbr if tbr else len(formats)))
+                manifest_url = format_url(line.strip())
                 f = {
                     'format_id': '-'.join(format_id),
-                    'url': format_url(line.strip()),
+                    'url': manifest_url,
+                    'manifest_url': manifest_url,
                     'tbr': tbr,
                     'ext': ext,
                     'fps': float_or_none(last_info.get('FRAME-RATE')),
@@ -1227,11 +1294,9 @@ 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
@@ -1475,12 +1540,13 @@ class InfoExtractor(object):
         if res is False:
             return []
         mpd, urlh = res
-        mpd_base_url = re.match(r'https?://.+/', urlh.geturl()).group()
+        mpd_base_url = base_url(urlh.geturl())
 
         return self._parse_mpd_formats(
-            compat_etree_fromstring(mpd.encode('utf-8')), mpd_id, mpd_base_url, formats_dict=formats_dict)
+            compat_etree_fromstring(mpd.encode('utf-8')), mpd_id, mpd_base_url,
+            formats_dict=formats_dict, mpd_url=mpd_url)
 
-    def _parse_mpd_formats(self, mpd_doc, mpd_id=None, mpd_base_url='', formats_dict={}):
+    def _parse_mpd_formats(self, mpd_doc, mpd_id=None, mpd_base_url='', formats_dict={}, mpd_url=None):
         """
         Parse formats from MPD manifest.
         References:
@@ -1501,42 +1567,52 @@ class InfoExtractor(object):
 
         def extract_multisegment_info(element, ms_parent_info):
             ms_info = ms_parent_info.copy()
+
+            # As per [1, 5.3.9.2.2] SegmentList and SegmentTemplate share some
+            # common attributes and elements.  We will only extract relevant
+            # for us.
+            def extract_common(source):
+                segment_timeline = source.find(_add_ns('SegmentTimeline'))
+                if segment_timeline is not None:
+                    s_e = segment_timeline.findall(_add_ns('S'))
+                    if s_e:
+                        ms_info['total_number'] = 0
+                        ms_info['s'] = []
+                        for s in s_e:
+                            r = int(s.get('r', 0))
+                            ms_info['total_number'] += 1 + r
+                            ms_info['s'].append({
+                                't': int(s.get('t', 0)),
+                                # @d is mandatory (see [1, 5.3.9.6.2, Table 17, page 60])
+                                'd': int(s.attrib['d']),
+                                'r': r,
+                            })
+                start_number = source.get('startNumber')
+                if start_number:
+                    ms_info['start_number'] = int(start_number)
+                timescale = source.get('timescale')
+                if timescale:
+                    ms_info['timescale'] = int(timescale)
+                segment_duration = source.get('duration')
+                if segment_duration:
+                    ms_info['segment_duration'] = int(segment_duration)
+
+            def extract_Initialization(source):
+                initialization = source.find(_add_ns('Initialization'))
+                if initialization is not None:
+                    ms_info['initialization_url'] = initialization.attrib['sourceURL']
+
             segment_list = element.find(_add_ns('SegmentList'))
             if segment_list is not None:
+                extract_common(segment_list)
+                extract_Initialization(segment_list)
                 segment_urls_e = segment_list.findall(_add_ns('SegmentURL'))
                 if segment_urls_e:
                     ms_info['segment_urls'] = [segment.attrib['media'] for segment in segment_urls_e]
-                initialization = segment_list.find(_add_ns('Initialization'))
-                if initialization is not None:
-                    ms_info['initialization_url'] = initialization.attrib['sourceURL']
             else:
                 segment_template = element.find(_add_ns('SegmentTemplate'))
                 if segment_template is not None:
-                    start_number = segment_template.get('startNumber')
-                    if start_number:
-                        ms_info['start_number'] = int(start_number)
-                    segment_timeline = segment_template.find(_add_ns('SegmentTimeline'))
-                    if segment_timeline is not None:
-                        s_e = segment_timeline.findall(_add_ns('S'))
-                        if s_e:
-                            ms_info['total_number'] = 0
-                            ms_info['s'] = []
-                            for s in s_e:
-                                r = int(s.get('r', 0))
-                                ms_info['total_number'] += 1 + r
-                                ms_info['s'].append({
-                                    't': int(s.get('t', 0)),
-                                    # @d is mandatory (see [1, 5.3.9.6.2, Table 17, page 60])
-                                    'd': int(s.attrib['d']),
-                                    'r': r,
-                                })
-                    else:
-                        timescale = segment_template.get('timescale')
-                        if timescale:
-                            ms_info['timescale'] = int(timescale)
-                        segment_duration = segment_template.get('duration')
-                        if segment_duration:
-                            ms_info['segment_duration'] = int(segment_duration)
+                    extract_common(segment_template)
                     media_template = segment_template.get('media')
                     if media_template:
                         ms_info['media_template'] = media_template
@@ -1544,11 +1620,14 @@ class InfoExtractor(object):
                     if initialization:
                         ms_info['initialization_url'] = initialization
                     else:
-                        initialization = segment_template.find(_add_ns('Initialization'))
-                        if initialization is not None:
-                            ms_info['initialization_url'] = initialization.attrib['sourceURL']
+                        extract_Initialization(segment_template)
             return ms_info
 
+        def combine_url(base_url, target_url):
+            if re.match(r'^https?://', target_url):
+                return target_url
+            return '%s%s%s' % (base_url, '' if base_url.endswith('/') else '/', target_url)
+
         mpd_duration = parse_duration(mpd_doc.get('mediaPresentationDuration'))
         formats = []
         for period in mpd_doc.findall(_add_ns('Period')):
@@ -1591,6 +1670,7 @@ class InfoExtractor(object):
                         f = {
                             'format_id': '%s-%s' % (mpd_id, representation_id) if mpd_id else representation_id,
                             'url': base_url,
+                            'manifest_url': mpd_url,
                             'ext': mimetype2ext(mime_type),
                             'width': int_or_none(representation_attrib.get('width')),
                             'height': int_or_none(representation_attrib.get('height')),
@@ -1605,9 +1685,7 @@ class InfoExtractor(object):
                         }
                         representation_ms_info = extract_multisegment_info(representation, adaption_set_ms_info)
                         if 'segment_urls' not in representation_ms_info and 'media_template' in representation_ms_info:
-                            if 'total_number' not in representation_ms_info and 'segment_duration':
-                                segment_duration = float(representation_ms_info['segment_duration']) / float(representation_ms_info['timescale'])
-                                representation_ms_info['total_number'] = int(math.ceil(float(period_duration) / segment_duration))
+
                             media_template = representation_ms_info['media_template']
                             media_template = media_template.replace('$RepresentationID$', representation_id)
                             media_template = re.sub(r'\$(Number|Bandwidth|Time)\$', r'%(\1)d', media_template)
@@ -1616,46 +1694,79 @@ class InfoExtractor(object):
 
                             # As per [1, 5.3.9.4.4, Table 16, page 55] $Number$ and $Time$
                             # can't be used at the same time
-                            if '%(Number' in media_template:
-                                representation_ms_info['segment_urls'] = [
-                                    media_template % {
+                            if '%(Number' in media_template and 's' not in representation_ms_info:
+                                segment_duration = None
+                                if 'total_number' not in representation_ms_info and 'segment_duration':
+                                    segment_duration = float_or_none(representation_ms_info['segment_duration'], representation_ms_info['timescale'])
+                                    representation_ms_info['total_number'] = int(math.ceil(float(period_duration) / segment_duration))
+                                representation_ms_info['fragments'] = [{
+                                    'url': media_template % {
                                         'Number': segment_number,
                                         'Bandwidth': representation_attrib.get('bandwidth'),
-                                    }
-                                    for segment_number in range(
-                                        representation_ms_info['start_number'],
-                                        representation_ms_info['total_number'] + representation_ms_info['start_number'])]
+                                    },
+                                    'duration': segment_duration,
+                                } for segment_number in range(
+                                    representation_ms_info['start_number'],
+                                    representation_ms_info['total_number'] + representation_ms_info['start_number'])]
                             else:
-                                representation_ms_info['segment_urls'] = []
+                                # $Number*$ or $Time$ in media template with S list available
+                                # Example $Number*$: http://www.svtplay.se/klipp/9023742/stopptid-om-bjorn-borg
+                                # Example $Time$: https://play.arkena.com/embed/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411
+                                representation_ms_info['fragments'] = []
                                 segment_time = 0
+                                segment_d = None
+                                segment_number = representation_ms_info['start_number']
 
                                 def add_segment_url():
-                                    representation_ms_info['segment_urls'].append(
-                                        media_template % {
-                                            'Time': segment_time,
-                                            'Bandwidth': representation_attrib.get('bandwidth'),
-                                        }
-                                    )
+                                    segment_url = media_template % {
+                                        'Time': segment_time,
+                                        'Bandwidth': representation_attrib.get('bandwidth'),
+                                        'Number': segment_number,
+                                    }
+                                    representation_ms_info['fragments'].append({
+                                        'url': segment_url,
+                                        'duration': float_or_none(segment_d, representation_ms_info['timescale']),
+                                    })
 
                                 for num, s in enumerate(representation_ms_info['s']):
                                     segment_time = s.get('t') or segment_time
+                                    segment_d = s['d']
                                     add_segment_url()
+                                    segment_number += 1
                                     for r in range(s.get('r', 0)):
-                                        segment_time += s['d']
+                                        segment_time += segment_d
                                         add_segment_url()
-                                    segment_time += s['d']
-                        if 'segment_urls' in representation_ms_info:
+                                        segment_number += 1
+                                    segment_time += segment_d
+                        elif 'segment_urls' in representation_ms_info and 's' in representation_ms_info:
+                            # No media template
+                            # Example: https://www.youtube.com/watch?v=iXZV5uAYMJI
+                            # or any YouTube dashsegments video
+                            fragments = []
+                            s_num = 0
+                            for segment_url in representation_ms_info['segment_urls']:
+                                s = representation_ms_info['s'][s_num]
+                                for r in range(s.get('r', 0) + 1):
+                                    fragments.append({
+                                        'url': segment_url,
+                                        'duration': float_or_none(s['d'], representation_ms_info['timescale']),
+                                    })
+                            representation_ms_info['fragments'] = fragments
+                        # NB: MPD manifest may contain direct URLs to unfragmented media.
+                        # No fragments key is present in this case.
+                        if 'fragments' in representation_ms_info:
                             f.update({
-                                'segment_urls': representation_ms_info['segment_urls'],
+                                'fragments': [],
                                 'protocol': 'http_dash_segments',
                             })
                             if 'initialization_url' in representation_ms_info:
                                 initialization_url = representation_ms_info['initialization_url'].replace('$RepresentationID$', representation_id)
-                                f.update({
-                                    'initialization_url': initialization_url,
-                                })
                                 if not f.get('url'):
                                     f['url'] = initialization_url
+                                f['fragments'].append({'url': initialization_url})
+                            f['fragments'].extend(representation_ms_info['fragments'])
+                            for fragment in f['fragments']:
+                                fragment['url'] = combine_url(base_url, fragment['url'])
                         try:
                             existing_format = next(
                                 fo for fo in formats
@@ -1670,7 +1781,106 @@ 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 _extract_ism_formats(self, ism_url, video_id, ism_id=None, note=None, errnote=None, fatal=True):
+        res = self._download_webpage_handle(
+            ism_url, video_id,
+            note=note or 'Downloading ISM manifest',
+            errnote=errnote or 'Failed to download ISM manifest',
+            fatal=fatal)
+        if res is False:
+            return []
+        ism, urlh = res
+
+        return self._parse_ism_formats(
+            compat_etree_fromstring(ism.encode('utf-8')), urlh.geturl(), ism_id)
+
+    def _parse_ism_formats(self, ism_doc, ism_url, ism_id=None):
+        if ism_doc.get('IsLive') == 'TRUE' or ism_doc.find('Protection') is not None:
+            return []
+
+        duration = int(ism_doc.attrib['Duration'])
+        timescale = int_or_none(ism_doc.get('TimeScale')) or 10000000
+
+        formats = []
+        for stream in ism_doc.findall('StreamIndex'):
+            stream_type = stream.get('Type')
+            if stream_type not in ('video', 'audio'):
+                continue
+            url_pattern = stream.attrib['Url']
+            stream_timescale = int_or_none(stream.get('TimeScale')) or timescale
+            stream_name = stream.get('Name')
+            for track in stream.findall('QualityLevel'):
+                fourcc = track.get('FourCC')
+                # TODO: add support for WVC1 and WMAP
+                if fourcc not in ('H264', 'AVC1', 'AACL'):
+                    self.report_warning('%s is not a supported codec' % fourcc)
+                    continue
+                tbr = int(track.attrib['Bitrate']) // 1000
+                width = int_or_none(track.get('MaxWidth'))
+                height = int_or_none(track.get('MaxHeight'))
+                sampling_rate = int_or_none(track.get('SamplingRate'))
+
+                track_url_pattern = re.sub(r'{[Bb]itrate}', track.attrib['Bitrate'], url_pattern)
+                track_url_pattern = compat_urlparse.urljoin(ism_url, track_url_pattern)
+
+                fragments = []
+                fragment_ctx = {
+                    'time': 0,
+                }
+                stream_fragments = stream.findall('c')
+                for stream_fragment_index, stream_fragment in enumerate(stream_fragments):
+                    fragment_ctx['time'] = int_or_none(stream_fragment.get('t')) or fragment_ctx['time']
+                    fragment_repeat = int_or_none(stream_fragment.get('r')) or 1
+                    fragment_ctx['duration'] = int_or_none(stream_fragment.get('d'))
+                    if not fragment_ctx['duration']:
+                        try:
+                            next_fragment_time = int(stream_fragment[stream_fragment_index + 1].attrib['t'])
+                        except IndexError:
+                            next_fragment_time = duration
+                        fragment_ctx['duration'] = (next_fragment_time - fragment_ctx['time']) / fragment_repeat
+                    for _ in range(fragment_repeat):
+                        fragments.append({
+                            'url': re.sub(r'{start[ _]time}', compat_str(fragment_ctx['time']), track_url_pattern),
+                            'duration': fragment_ctx['duration'] / stream_timescale,
+                        })
+                        fragment_ctx['time'] += fragment_ctx['duration']
+
+                format_id = []
+                if ism_id:
+                    format_id.append(ism_id)
+                if stream_name:
+                    format_id.append(stream_name)
+                format_id.append(compat_str(tbr))
+
+                formats.append({
+                    'format_id': '-'.join(format_id),
+                    'url': ism_url,
+                    'manifest_url': ism_url,
+                    'ext': 'ismv' if stream_type == 'video' else 'isma',
+                    'width': width,
+                    'height': height,
+                    'tbr': tbr,
+                    'asr': sampling_rate,
+                    'vcodec': 'none' if stream_type == 'audio' else fourcc,
+                    'acodec': 'none' if stream_type == 'video' else fourcc,
+                    'protocol': 'ism',
+                    'fragments': fragments,
+                    '_download_params': {
+                        'duration': duration,
+                        'timescale': stream_timescale,
+                        'width': width or 0,
+                        'height': height or 0,
+                        'fourcc': fourcc,
+                        'codec_private_data': track.get('CodecPrivateData'),
+                        'sampling_rate': sampling_rate,
+                        'channels': int_or_none(track.get('Channels', 2)),
+                        'bits_per_sample': int_or_none(track.get('BitsPerSample', 16)),
+                        'nal_unit_length_field': int_or_none(track.get('NALUnitLengthField', 4)),
+                    },
+                })
+        return formats
+
+    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)
 
@@ -1685,8 +1895,27 @@ 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_tags = [(media_tag, media_type, '')
+                      for media_tag, media_type
+                      in re.findall(r'(?s)(<(video|audio)[^>]*/>)', webpage)]
+        media_tags.extend(re.findall(r'(?s)(<(?P<tag>video|audio)[^>]*>)(.*?)</(?P=tag)>', webpage))
+        for media_tag, media_type, media_content in media_tags:
             media_info = {
                 'formats': [],
                 'subtitles': {},
@@ -1694,10 +1923,8 @@ 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_type)
+                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):
@@ -1705,16 +1932,17 @@ 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')
-                    if not kind or kind == 'subtitles':
+                    if not kind or kind in ('subtitles', 'captions'):
                         src = track_attributes.get('src')
                         if not src:
                             continue
@@ -1722,10 +1950,70 @@ class InfoExtractor(object):
                         media_info['subtitles'].setdefault(lang, []).append({
                             'url': absolute_url(src),
                         })
-            if media_info['formats']:
+            if media_info['formats'] or media_info['subtitles']:
                 entries.append(media_info)
         return entries
 
+    def _extract_akamai_formats(self, manifest_url, video_id):
+        formats = []
+        hdcore_sign = 'hdcore=3.7.0'
+        f4m_url = re.sub(r'(https?://.+?)/i/', r'\1/z/', manifest_url).replace('/master.m3u8', '/manifest.f4m')
+        if 'hdcore=' not in f4m_url:
+            f4m_url += ('&' if '?' in f4m_url else '?') + hdcore_sign
+        f4m_formats = self._extract_f4m_formats(
+            f4m_url, video_id, f4m_id='hds', fatal=False)
+        for entry in f4m_formats:
+            entry.update({'extra_param_to_segment_url': hdcore_sign})
+        formats.extend(f4m_formats)
+        m3u8_url = re.sub(r'(https?://.+?)/z/', r'\1/i/', manifest_url).replace('/manifest.f4m', '/master.m3u8')
+        formats.extend(self._extract_m3u8_formats(
+            m3u8_url, video_id, 'mp4', 'm3u8_native',
+            m3u8_id='hls', fatal=False))
+        return formats
+
+    def _extract_wowza_formats(self, url, video_id, m3u8_entry_protocol='m3u8_native', skip_protocols=[]):
+        url = re.sub(r'/(?:manifest|playlist|jwplayer)\.(?:m3u8|f4m|mpd|smil)', '', url)
+        url_base = self._search_regex(r'(?:https?|rtmp|rtsp)(://[^?]+)', url, 'format url')
+        http_base_url = 'http' + url_base
+        formats = []
+        if 'm3u8' not in skip_protocols:
+            formats.extend(self._extract_m3u8_formats(
+                http_base_url + '/playlist.m3u8', video_id, 'mp4',
+                m3u8_entry_protocol, m3u8_id='hls', fatal=False))
+        if 'f4m' not in skip_protocols:
+            formats.extend(self._extract_f4m_formats(
+                http_base_url + '/manifest.f4m',
+                video_id, f4m_id='hds', fatal=False))
+        if 'dash' not in skip_protocols:
+            formats.extend(self._extract_mpd_formats(
+                http_base_url + '/manifest.mpd',
+                video_id, mpd_id='dash', fatal=False))
+        if re.search(r'(?:/smil:|\.smil)', url_base):
+            if 'smil' not in skip_protocols:
+                rtmp_formats = self._extract_smil_formats(
+                    http_base_url + '/jwplayer.smil',
+                    video_id, fatal=False)
+                for rtmp_format in rtmp_formats:
+                    rtsp_format = rtmp_format.copy()
+                    rtsp_format['url'] = '%s/%s' % (rtmp_format['url'], rtmp_format['play_path'])
+                    del rtsp_format['play_path']
+                    del rtsp_format['ext']
+                    rtsp_format.update({
+                        'url': rtsp_format['url'].replace('rtmp://', 'rtsp://'),
+                        'format_id': rtmp_format['format_id'].replace('rtmp', 'rtsp'),
+                        'protocol': 'rtsp',
+                    })
+                    formats.extend([rtmp_format, rtsp_format])
+        else:
+            for protocol in ('rtmp', 'rtsp'):
+                if protocol not in skip_protocols:
+                    formats.append({
+                        'url': protocol + url_base,
+                        'format_id': protocol,
+                        'protocol': protocol,
+                    })
+        return formats
+
     def _live_title(self, name):
         """ Generate the title for a live video """
         now = datetime.datetime.now()
@@ -1846,6 +2134,12 @@ class InfoExtractor(object):
             headers['Ytdl-request-proxy'] = geo_verification_proxy
         return headers
 
+    def _generic_id(self, url):
+        return compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
+
+    def _generic_title(self, url):
+        return compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0])
+
 
 class SearchInfoExtractor(InfoExtractor):
     """

youtube_dl/extractor/commonprotocols.py

@@ -1,13 +1,9 @@
 from __future__ import unicode_literals
 
-import os
-
 from .common import InfoExtractor
 from ..compat import (
-    compat_urllib_parse_unquote,
     compat_urlparse,
 )
-from ..utils import url_basename
 
 
 class RtmpIE(InfoExtractor):
@@ -23,8 +19,8 @@ class RtmpIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
-        title = compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0])
+        video_id = self._generic_id(url)
+        title = self._generic_title(url)
         return {
             'id': video_id,
             'title': title,
@@ -34,3 +30,31 @@ class RtmpIE(InfoExtractor):
                 'format_id': compat_urlparse.urlparse(url).scheme,
             }],
         }
+
+
+class MmsIE(InfoExtractor):
+    IE_DESC = False  # Do not list
+    _VALID_URL = r'(?i)mms://.+'
+
+    _TEST = {
+        # Direct MMS link
+        'url': 'mms://kentro.kaist.ac.kr/200907/MilesReid(0709).wmv',
+        'info_dict': {
+            'id': 'MilesReid(0709)',
+            'ext': 'wmv',
+            'title': 'MilesReid(0709)',
+        },
+        'params': {
+            'skip_download': True,  # rtsp downloads, requiring mplayer or mpv
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._generic_id(url)
+        title = self._generic_title(url)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': url,
+        }

youtube_dl/extractor/condenast.py

@@ -5,13 +5,17 @@ import re
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_urllib_parse_urlencode,
     compat_urllib_parse_urlparse,
     compat_urlparse,
 )
 from ..utils import (
     orderedSet,
     remove_end,
+    extract_attributes,
+    mimetype2ext,
+    determine_ext,
+    int_or_none,
+    parse_iso8601,
 )
 
 
@@ -58,6 +62,9 @@ class CondeNastIE(InfoExtractor):
             'ext': 'mp4',
             'title': '3D Printed Speakers Lit With LED',
             'description': 'Check out these beautiful 3D printed LED speakers.  You can\'t actually buy them, but LumiGeek is working on a board that will let you make you\'re own.',
+            'uploader': 'wired',
+            'upload_date': '20130314',
+            'timestamp': 1363219200,
         }
     }, {
         # JS embed
@@ -67,70 +74,93 @@ class CondeNastIE(InfoExtractor):
             'id': '55f9cf8b61646d1acf00000c',
             'ext': 'mp4',
             'title': '3D printed TSA Travel Sentry keys really do open TSA locks',
+            'uploader': 'arstechnica',
+            'upload_date': '20150916',
+            'timestamp': 1442434955,
         }
     }]
 
     def _extract_series(self, url, webpage):
-        title = self._html_search_regex(r'<div class="cne-series-info">.*?<h1>(.+?)</h1>',
-                                        webpage, 'series title', flags=re.DOTALL)
+        title = self._html_search_regex(
+            r'(?s)<div class="cne-series-info">.*?<h1>(.+?)</h1>',
+            webpage, 'series title')
         url_object = compat_urllib_parse_urlparse(url)
         base_url = '%s://%s' % (url_object.scheme, url_object.netloc)
-        m_paths = re.finditer(r'<p class="cne-thumb-title">.*?<a href="(/watch/.+?)["\?]',
-                              webpage, flags=re.DOTALL)
+        m_paths = re.finditer(
+            r'(?s)<p class="cne-thumb-title">.*?<a href="(/watch/.+?)["\?]', webpage)
         paths = orderedSet(m.group(1) for m in m_paths)
         build_url = lambda path: compat_urlparse.urljoin(base_url, path)
         entries = [self.url_result(build_url(path), 'CondeNast') for path in paths]
         return self.playlist_result(entries, playlist_title=title)
 
     def _extract_video(self, webpage, url_type):
-        if url_type != 'embed':
-            description = self._html_search_regex(
-                [
-                    r'<div class="cne-video-description">(.+?)</div>',
-                    r'<div class="video-post-content">(.+?)</div>',
-                ],
-                webpage, 'description', fatal=False, flags=re.DOTALL)
+        query = {}
+        params = self._search_regex(
+            r'(?s)var params = {(.+?)}[;,]', webpage, 'player params', default=None)
+        if params:
+            query.update({
+                'videoId': self._search_regex(r'videoId: [\'"](.+?)[\'"]', params, 'video id'),
+                'playerId': self._search_regex(r'playerId: [\'"](.+?)[\'"]', params, 'player id'),
+                'target': self._search_regex(r'target: [\'"](.+?)[\'"]', params, 'target'),
+            })
         else:
-            description = None
-        params = self._search_regex(r'var params = {(.+?)}[;,]', webpage,
-                                    'player params', flags=re.DOTALL)
-        video_id = self._search_regex(r'videoId: [\'"](.+?)[\'"]', params, 'video id')
-        player_id = self._search_regex(r'playerId: [\'"](.+?)[\'"]', params, 'player id')
-        target = self._search_regex(r'target: [\'"](.+?)[\'"]', params, 'target')
-        data = compat_urllib_parse_urlencode({'videoId': video_id,
-                                              'playerId': player_id,
-                                              'target': target,
-                                              })
-        base_info_url = self._search_regex(r'url = [\'"](.+?)[\'"][,;]',
-                                           webpage, 'base info url',
-                                           default='http://player.cnevids.com/player/loader.js?')
-        info_url = base_info_url + data
-        info_page = self._download_webpage(info_url, video_id,
-                                           'Downloading video info')
-        video_info = self._search_regex(r'var\s+video\s*=\s*({.+?});', info_page, 'video info')
-        video_info = self._parse_json(video_info, video_id)
+            params = extract_attributes(self._search_regex(
+                r'(<[^>]+data-js="video-player"[^>]+>)',
+                webpage, 'player params element'))
+            query.update({
+                'videoId': params['data-video'],
+                'playerId': params['data-player'],
+                'target': params['id'],
+            })
+        video_id = query['videoId']
+        video_info = None
+        info_page = self._download_webpage(
+            'http://player.cnevids.com/player/video.js',
+            video_id, 'Downloading video info', query=query, fatal=False)
+        if info_page:
+            video_info = self._parse_json(self._search_regex(
+                r'loadCallback\(({.+})\)', info_page, 'video info'), video_id)['video']
+        else:
+            info_page = self._download_webpage(
+                'http://player.cnevids.com/player/loader.js',
+                video_id, 'Downloading loader info', query=query)
+            video_info = self._parse_json(self._search_regex(
+                r'var\s+video\s*=\s*({.+?});', info_page, 'video info'), video_id)
+        title = video_info['title']
 
-        formats = [{
-            'format_id': '%s-%s' % (fdata['type'].split('/')[-1], fdata['quality']),
-            'url': fdata['src'],
-            'ext': fdata['type'].split('/')[-1],
-            'quality': 1 if fdata['quality'] == 'high' else 0,
-        } for fdata in video_info['sources'][0]]
+        formats = []
+        for fdata in video_info.get('sources', [{}])[0]:
+            src = fdata.get('src')
+            if not src:
+                continue
+            ext = mimetype2ext(fdata.get('type')) or determine_ext(src)
+            quality = fdata.get('quality')
+            formats.append({
+                'format_id': ext + ('-%s' % quality if quality else ''),
+                'url': src,
+                'ext': ext,
+                'quality': 1 if quality == 'high' else 0,
+            })
         self._sort_formats(formats)
 
-        return {
+        info = self._search_json_ld(
+            webpage, video_id, fatal=False) if url_type != 'embed' else {}
+        info.update({
             'id': video_id,
             'formats': formats,
-            'title': video_info['title'],
-            'thumbnail': video_info['poster_frame'],
-            'description': description,
-        }
+            'title': title,
+            'thumbnail': video_info.get('poster_frame'),
+            'uploader': video_info.get('brand'),
+            'duration': int_or_none(video_info.get('duration')),
+            'tags': video_info.get('tags'),
+            'series': video_info.get('series_title'),
+            'season': video_info.get('season_title'),
+            'timestamp': parse_iso8601(video_info.get('premiere_date')),
+        })
+        return info
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        site = mobj.group('site')
-        url_type = mobj.group('type')
-        item_id = mobj.group('id')
+        site, url_type, item_id = re.match(self._VALID_URL, url).groups()
 
         # Convert JS embed to regular embed
         if url_type == 'embedjs':

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/criterion.py

@@ -1,13 +1,11 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 
 class CriterionIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.criterion\.com/films/(?P<id>[0-9]+)-.+'
+    _VALID_URL = r'https?://(?:www\.)?criterion\.com/films/(?P<id>[0-9]+)-.+'
     _TEST = {
         'url': 'http://www.criterion.com/films/184-le-samourai',
         'md5': 'bc51beba55685509883a9a7830919ec3',
@@ -16,20 +14,20 @@ class CriterionIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Le Samouraï',
             'description': 'md5:a2b4b116326558149bef81f76dcbb93f',
+            'thumbnail': 're:^https?://.*\.jpg$',
         }
     }
 
     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)
 
         final_url = self._search_regex(
-            r'so.addVariable\("videoURL", "(.+?)"\)\;', webpage, 'video url')
+            r'so\.addVariable\("videoURL", "(.+?)"\)\;', webpage, 'video url')
         title = self._og_search_title(webpage)
         description = self._html_search_meta('description', webpage)
         thumbnail = self._search_regex(
-            r'so.addVariable\("thumbnailURL", "(.+?)"\)\;',
+            r'so\.addVariable\("thumbnailURL", "(.+?)"\)\;',
             webpage, 'thumbnail url')
 
         return {

youtube_dl/extractor/crunchyroll.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
@@ -34,22 +34,58 @@ from ..aes import (
 
 
 class CrunchyrollBaseIE(InfoExtractor):
+    _LOGIN_URL = 'https://www.crunchyroll.com/login'
+    _LOGIN_FORM = 'login_form'
     _NETRC_MACHINE = 'crunchyroll'
 
     def _login(self):
         (username, password) = self._get_login_info()
         if username is None:
             return
-        self.report_login()
-        login_url = 'https://www.crunchyroll.com/?a=formhandler'
-        data = urlencode_postdata({
-            'formname': 'RpcApiUser_Login',
-            'name': username,
-            'password': password,
+
+        login_page = self._download_webpage(
+            self._LOGIN_URL, None, 'Downloading login page')
+
+        def is_logged(webpage):
+            return '<title>Redirecting' in webpage
+
+        # Already logged in
+        if is_logged(login_page):
+            return
+
+        login_form_str = self._search_regex(
+            r'(?P<form><form[^>]+?id=(["\'])%s\2[^>]*>)' % self._LOGIN_FORM,
+            login_page, 'login form', group='form')
+
+        post_url = extract_attributes(login_form_str).get('action')
+        if not post_url:
+            post_url = self._LOGIN_URL
+        elif not post_url.startswith('http'):
+            post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
+
+        login_form = self._form_hidden_inputs(self._LOGIN_FORM, login_page)
+
+        login_form.update({
+            'login_form[name]': username,
+            'login_form[password]': password,
         })
-        login_request = sanitized_Request(login_url, data)
-        login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
-        self._download_webpage(login_request, None, False, 'Wrong login info')
+
+        response = self._download_webpage(
+            post_url, None, 'Logging in', 'Wrong login info',
+            data=urlencode_postdata(login_form),
+            headers={'Content-Type': 'application/x-www-form-urlencoded'})
+
+        # Successful login
+        if is_logged(response):
+            return
+
+        error = self._html_search_regex(
+            '(?s)<ul[^>]+class=["\']messages["\'][^>]*>(.+?)</ul>',
+            response, 'error message', default=None)
+        if error:
+            raise ExtractorError('Unable to login: %s' % error, expected=True)
+
+        raise ExtractorError('Unable to log in')
 
     def _real_initialize(self):
         self._login()
@@ -114,6 +150,22 @@ class CrunchyrollIE(CrunchyrollBaseIE):
             # rtmp
             'skip_download': True,
         },
+        'skip': 'Video gone',
+    }, {
+        '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 +388,18 @@ 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 +414,7 @@ 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 +424,7 @@ 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

@@ -1,30 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-
-
-class CTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?ctv\.ca/video/player\?vid=(?P<id>[0-9.]+)'
-    _TESTS = [{
-        'url': 'http://www.ctv.ca/video/player?vid=706966',
-        'md5': 'ff2ebbeae0aa2dcc32a830c3fd69b7b0',
-        'info_dict': {
-            'id': '706966',
-            'ext': 'mp4',
-            'title': 'Larry Day and Richard Jutras on the TIFF red carpet of \'Stonewall\'',
-            'description': 'etalk catches up with Larry Day and Richard Jutras on the TIFF red carpet of "Stonewall”.',
-            'upload_date': '20150919',
-            'timestamp': 1442624700,
-        },
-        'expected_warnings': ['HTTP Error 404'],
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        return {
-            '_type': 'url_transparent',
-            'id': video_id,
-            'url': '9c9media:ctv_web:%s' % 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/dailymotion.py

@@ -94,7 +94,8 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
                 'title': 'Leanna Decker - Cyber Girl Of The Year Desires Nude [Playboy Plus]',
                 'uploader': 'HotWaves1012',
                 'age_limit': 18,
-            }
+            },
+            'skip': 'video gone',
         },
         # geo-restricted, player v5
         {
@@ -144,7 +145,8 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
         player_v5 = self._search_regex(
             [r'buildPlayer\(({.+?})\);\n',  # See https://github.com/rg3/youtube-dl/issues/7826
              r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);',
-             r'buildPlayer\(({.+?})\);'],
+             r'buildPlayer\(({.+?})\);',
+             r'var\s+config\s*=\s*({.+?});'],
             webpage, 'player v5', default=None)
         if player_v5:
             player = self._parse_json(player_v5, video_id)
@@ -394,7 +396,7 @@ class DailymotionUserIE(DailymotionPlaylistIE):
 
 
 class DailymotionCloudIE(DailymotionBaseInfoExtractor):
-    _VALID_URL_PREFIX = r'http://api\.dmcloud\.net/(?:player/)?embed/'
+    _VALID_URL_PREFIX = r'https?://api\.dmcloud\.net/(?:player/)?embed/'
     _VALID_URL = r'%s[^/]+/(?P<id>[^/?]+)' % _VALID_URL_PREFIX
     _VALID_EMBED_URL = r'%s[^/]+/[^\'"]+' % _VALID_URL_PREFIX
 

youtube_dl/extractor/daum.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 
 from __future__ import unicode_literals
 

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/dctp.py

@@ -1,61 +1,54 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import compat_str
+from ..utils import unified_strdate
 
 
 class DctpTvIE(InfoExtractor):
-    _VALID_URL = r'https?://www.dctp.tv/(#/)?filme/(?P<id>.+?)/$'
+    _VALID_URL = r'https?://(?:www\.)?dctp\.tv/(#/)?filme/(?P<id>.+?)/$'
     _TEST = {
         'url': 'http://www.dctp.tv/filme/videoinstallation-fuer-eine-kaufhausfassade/',
+        'md5': '174dd4a8a6225cf5655952f969cfbe24',
         'info_dict': {
-            'id': '1324',
+            'id': '95eaa4f33dad413aa17b4ee613cccc6c',
             'display_id': 'videoinstallation-fuer-eine-kaufhausfassade',
-            'ext': 'flv',
-            'title': 'Videoinstallation für eine Kaufhausfassade'
+            'ext': 'mp4',
+            'title': 'Videoinstallation für eine Kaufhausfassade',
+            'description': 'Kurzfilm',
+            'upload_date': '20110407',
+            'thumbnail': 're:^https?://.*\.jpg$',
         },
-        'params': {
-            # rtmp download
-            'skip_download': True,
-        }
     }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        base_url = 'http://dctp-ivms2-restapi.s3.amazonaws.com/'
-        version_json = self._download_json(
-            base_url + 'version.json',
-            video_id, note='Determining file version')
-        version = version_json['version_name']
-        info_json = self._download_json(
-            '{0}{1}/restapi/slugs/{2}.json'.format(base_url, version, video_id),
-            video_id, note='Fetching object ID')
-        object_id = compat_str(info_json['object_id'])
-        meta_json = self._download_json(
-            '{0}{1}/restapi/media/{2}.json'.format(base_url, version, object_id),
-            video_id, note='Downloading metadata')
-        uuid = meta_json['uuid']
-        title = meta_json['title']
-        wide = meta_json['is_wide']
-        if wide:
-            ratio = '16x9'
-        else:
-            ratio = '4x3'
-        play_path = 'mp4:{0}_dctp_0500_{1}.m4v'.format(uuid, ratio)
+        webpage = self._download_webpage(url, video_id)
+
+        object_id = self._html_search_meta('DC.identifier', webpage)
 
         servers_json = self._download_json(
-            'http://www.dctp.tv/streaming_servers/',
+            'http://www.dctp.tv/elastic_streaming_client/get_streaming_server/',
             video_id, note='Downloading server list')
-        url = servers_json[0]['endpoint']
+        server = servers_json[0]['server']
+        m3u8_path = self._search_regex(
+            r'\'([^\'"]+/playlist\.m3u8)"', webpage, 'm3u8 path')
+        formats = self._extract_m3u8_formats(
+            'http://%s%s' % (server, m3u8_path), video_id, ext='mp4',
+            entry_protocol='m3u8_native')
+
+        title = self._og_search_title(webpage)
+        description = self._html_search_meta('DC.description', webpage)
+        upload_date = unified_strdate(
+            self._html_search_meta('DC.date.created', webpage))
+        thumbnail = self._og_search_thumbnail(webpage)
 
         return {
             'id': object_id,
             'title': title,
-            'format': 'rtmp',
-            'url': url,
-            'play_path': play_path,
-            'rtmp_real_time': True,
-            'ext': 'flv',
-            'display_id': video_id
+            'formats': formats,
+            'display_id': video_id,
+            'description': description,
+            'upload_date': upload_date,
+            'thumbnail': thumbnail,
         }

youtube_dl/extractor/democracynow.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 
 class DemocracynowIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?democracynow.org/(?P<id>[^\?]*)'
+    _VALID_URL = r'https?://(?:www\.)?democracynow\.org/(?P<id>[^\?]*)'
     IE_NAME = 'democracynow'
     _TESTS = [{
         'url': 'http://www.democracynow.org/shows/2015/7/3',

youtube_dl/extractor/discoverygo.py

@@ -0,0 +1,116 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    extract_attributes,
+    int_or_none,
+    parse_age_limit,
+    unescapeHTML,
+    ExtractorError,
+)
+
+
+class DiscoveryGoIE(InfoExtractor):
+    _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': {
+            'id': '57a33c536b66d1cd0345eeb1',
+            'ext': 'mp4',
+            'title': 'Kiss First, Ask Questions Later!',
+            'description': 'md5:fe923ba34050eae468bffae10831cb22',
+            'duration': 2579,
+            'series': 'Love at First Kiss',
+            'season_number': 1,
+            'episode_number': 1,
+            'age_limit': 14,
+        },
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        container = extract_attributes(
+            self._search_regex(
+                r'(<div[^>]+class=["\']video-player-container[^>]+>)',
+                webpage, 'video container'))
+
+        video = self._parse_json(
+            unescapeHTML(container.get('data-video') or container.get('data-json')),
+            display_id)
+
+        title = video['name']
+
+        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'):
+            suffix = STREAM_URL_SUFFIX.capitalize() if stream_kind else STREAM_URL_SUFFIX
+            stream_url = stream.get('%s%s' % (stream_kind, suffix))
+            if not stream_url:
+                continue
+            if stream_kind == '':
+                formats.extend(self._extract_m3u8_formats(
+                    stream_url, display_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False))
+            elif stream_kind == 'hds':
+                formats.extend(self._extract_f4m_formats(
+                    stream_url, display_id, f4m_id=stream_kind, fatal=False))
+        self._sort_formats(formats)
+
+        video_id = video.get('id') or display_id
+        description = video.get('description', {}).get('detailed')
+        duration = int_or_none(video.get('duration'))
+
+        series = video.get('show', {}).get('name')
+        season_number = int_or_none(video.get('season', {}).get('number'))
+        episode_number = int_or_none(video.get('episodeNumber'))
+
+        tags = video.get('tags')
+        age_limit = parse_age_limit(video.get('parental', {}).get('rating'))
+
+        subtitles = {}
+        captions = stream.get('captions')
+        if isinstance(captions, list):
+            for caption in captions:
+                subtitle_url = caption.get('fileUrl')
+                if (not subtitle_url or not isinstance(subtitle_url, compat_str) or
+                        not subtitle_url.startswith('http')):
+                    continue
+                lang = caption.get('fileLang', 'en')
+                subtitles.setdefault(lang, []).append({'url': subtitle_url})
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'series': series,
+            'season_number': season_number,
+            'episode_number': episode_number,
+            'tags': tags,
+            'age_limit': age_limit,
+            'formats': formats,
+            'subtitles': subtitles,
+        }

youtube_dl/extractor/dotsub.py

@@ -9,22 +9,39 @@ 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',
+    _TESTS = [{
+        '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,
         }
-    }
+    }, {
+        'url': 'https://dotsub.com/view/747bcf58-bd59-45b7-8c8c-ac312d084ee6',
+        'md5': '2bb4a83896434d5c26be868c609429a3',
+        'info_dict': {
+            'id': '168006778',
+            'ext': 'mp4',
+            'title': 'Apartments and flats in Raipur the white symphony',
+            'description': 'md5:784d0639e6b7d1bc29530878508e38fe',
+            'thumbnail': 're:^https?://dotsub.com/media/747bcf58-bd59-45b7-8c8c-ac312d084ee6/p',
+            'duration': 290,
+            'timestamp': 1476767794.2809999,
+            'upload_date': '20160525',
+            'uploader': 'parthivi001',
+            'uploader_id': 'user52596202',
+            'view_count': int,
+        },
+        'add_ie': ['Vimeo'],
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -37,12 +54,23 @@ class DotsubIE(InfoExtractor):
             webpage = self._download_webpage(url, video_id)
             video_url = self._search_regex(
                 [r'<source[^>]+src="([^"]+)"', r'"file"\s*:\s*\'([^\']+)'],
-                webpage, 'video url')
+                webpage, 'video url', default=None)
+            info_dict = {
+                'id': video_id,
+                'url': video_url,
+                'ext': 'flv',
+            }
 
-        return {
-            'id': video_id,
-            'url': video_url,
-            'ext': 'flv',
+        if not video_url:
+            setup_data = self._parse_json(self._html_search_regex(
+                r'(?s)data-setup=([\'"])(?P<content>(?!\1).+?)\1',
+                webpage, 'setup data', group='content'), video_id)
+            info_dict = {
+                '_type': 'url_transparent',
+                'url': setup_data['src'],
+            }
+
+        info_dict.update({
             'title': info['title'],
             'description': info.get('description'),
             'thumbnail': info.get('screenshotURI'),
@@ -50,4 +78,6 @@ class DotsubIE(InfoExtractor):
             'uploader': info.get('user'),
             'timestamp': float_or_none(info.get('dateCreated'), 1000),
             'view_count': int_or_none(info.get('numberOfViews')),
-        }
+        })
+
+        return info_dict