release 2016.12.18

1. ProxyError now inherits from socket.error instead of IOError

The only functions socks.py overrides are connect and connect_ex. In
Python 2.x and Python <= 3.2, socket functions raises socket.error. In
newer Python versions, those functions raises OSError instead. The name
socket.error is preserved as an alias of OSError for backward
compability. To keep socks.py compatible with Python's standard library,
it should raise the same exception as raw sockets.

See PEP 3151 (https://www.python.org/dev/peps/pep-3151/) for more
information about the change in Python 3.3.

2. Raise EOFError instead of IOError when the socket receives less data
than it expects

There's no common convention, but both ftplib and telnetlib raises
EOFError for similar situations. socks.py follows them.

Closes #11355

In #11355, only Python 2 is affected. In Python 3, both socket.error and
IOError are alias of OSError, so AbstractHTTPHandler.do_open correctly
catches the error and thus InfoExtractor._is_valid_url works fine.

.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 *2016.11.02*. 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 Issues with outdated version will be rejected.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**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.12.18*. 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 Issues with outdated version will be rejected.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 **2016.12.18**
 
 ### 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 2016.11.02
+[debug] youtube-dl version 2016.12.18
 [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: {}

.gitignore

@@ -30,6 +30,10 @@ updates_key.pem
 *.m4v
 *.mp3
 *.3gp
+*.wav
+*.ape
+*.mkv
+*.swf
 *.part
 *.swp
 test/testdata

AUTHORS

@@ -190,3 +190,4 @@ John Hawkinson
 Rich Leeper
 Zhong Jianxin
 Thor77
+Philip Xu

CONTRIBUTING.md

@@ -92,7 +92,7 @@ If you want to create a build of youtube-dl yourself, you'll need
 
 ### Adding support for a new site
 
-If you want to add support for a new site, first of all **make sure** this site is **not dedicated to [copyright infringement](#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. youtube-dl does **not support** such sites thus pull requests adding support for them **will be rejected**.
+If you want to add support for a new site, first of all **make sure** this site is **not dedicated to [copyright infringement](README.md#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. youtube-dl does **not support** such sites thus pull requests adding support for them **will be rejected**.
 
 After you have ensured this site is distributing it's content legally, you can follow this quick list (assuming your service is called `yourextractor`):
 

ChangeLog

@@ -1,3 +1,179 @@
+version 2016.12.18
+
+Core
++ [extractor/common] Recognize DASH formats in html5 media entries
+
+Extractors
++ [ccma] Add support for ccma.cat (#11359)
+* [laola1tv] Improve extraction
++ [laola1tv] Add support embed URLs (#11460)
+* [nbc] Fix extraction for MSNBC videos (#11466)
+* [twitch] Adapt to new videos pages URL schema (#11469)
++ [meipai] Add support for meipai.com (#10718)
+* [jwplatform] Improve subtitles and duration extraction
++ [ondemandkorea] Add support for ondemandkorea.com (#10772)
++ [vvvvid] Add support for vvvvid.it (#5915)
+
+
+version 2016.12.15
+
+Core
++ [utils] Add convenience urljoin
+
+Extractors
++ [openload] Recognize oload.tv URLs (#10408)
++ [facebook] Recognize .onion URLs (#11443)
+* [vlive] Fix extraction (#11375, #11383)
++ [canvas] Extract DASH formats
++ [melonvod] Add support for vod.melon.com (#11419)
+
+
+version 2016.12.12
+
+Core
++ [utils] Add common user agents map
++ [common] Recognize HLS manifests that contain video only formats (#11394)
+
+Extractors
++ [dplay] Use Safari user agent for HLS (#11418)
++ [facebook] Detect login required error message
+* [facebook] Improve video selection (#11390)
++ [canalplus] Add another video id pattern (#11399)
+* [mixcloud] Relax URL regular expression (#11406)
+* [ctvnews] Relax URL regular expression (#11394)
++ [rte] Capture and output error message (#7746, #10498)
++ [prosiebensat1] Add support for DASH formats
+* [srgssr] Improve extraction for geo restricted videos (#11089)
+* [rts] Improve extraction for geo restricted videos (#4989)
+
+
+version 2016.12.09
+
+Core
+* [socks] Fix error reporting (#11355)
+
+Extractors
+* [openload] Fix extraction (#10408)
+* [pandoratv] Fix extraction (#11023)
++ [telebruxelles] Add support for emission URLs
+* [telebruxelles] Extract all formats
++ [bloomberg] Add another video id regular expression (#11371)
+* [fusion] Update ooyala id regular expression (#11364)
++ [1tv] Add support for playlists (#11335)
+* [1tv] Improve extraction (#11335)
++ [aenetworks] Extract more formats (#11321)
++ [thisoldhouse] Recognize /tv-episode/ URLs (#11271)
+
+
+version 2016.12.01
+
+Extractors
+* [soundcloud] Update client id (#11327)
+* [ruutu] Detect DRM protected videos
++ [liveleak] Add support for youtube embeds (#10688)
+* [spike] Fix full episodes support (#11312)
+* [comedycentral] Fix full episodes support
+* [normalboots] Rewrite in terms of JWPlatform (#11184)
+* [teamfourstar] Rewrite in terms of JWPlatform (#11184)
+- [screenwavemedia] Remove extractor (#11184)
+
+
+version 2016.11.27
+
+Extractors
++ [webcaster] Add support for webcaster.pro
++ [azubu] Add support for azubu.uol.com.br (#11305)
+* [viki] Prefer hls formats
+* [viki] Fix rtmp formats extraction (#11255)
+* [puls4] Relax URL regular expression (#11267)
+* [vevo] Improve artist extraction (#10911)
+* [mitele] Relax URL regular expression and extract more metadata (#11244)
++ [cbslocal] Recognize New York site (#11285)
++ [youtube:playlist] Pass disable_polymer in URL query (#11193)
+
+
+version 2016.11.22
+
+Extractors
+* [hellporno] Fix video extension extraction (#11247)
++ [hellporno] Add support for hellporno.net (#11247)
++ [amcnetworks] Recognize more BBC America URLs (#11263)
+* [funnyordie] Improve extraction (#11208)
+* [extractor/generic] Improve limelight embeds support
+- [crunchyroll] Remove ScaledBorderAndShadow from ASS subtitles (#8207, #9028)
+* [bandcamp] Fix free downloads extraction and extract all formats (#11067)
+* [twitter:card] Relax URL regular expression (#11225)
++ [tvanouvelles] Add support for tvanouvelles.ca (#10616)
+
+
+version 2016.11.18
+
+Extractors
+* [youtube:live] Relax URL regular expression (#11164)
+* [openload] Fix extraction (#10408, #11122)
+* [vlive] Prefer locale over language for subtitles id (#11203)
+
+
+version 2016.11.14.1
+
+Core
++ [downoader/fragment,f4m,hls] Respect HTTP headers from info dict
+* [extractor/common] Fix media templates with Bandwidth substitution pattern in
+  MPD manifests (#11175)
+* [extractor/common] Improve thumbnail extraction from JSON-LD
+
+Extractors
++ [nrk] Workaround geo restriction
++ [nrk] Improve error detection and messages
++ [afreecatv] Add support for vod.afreecatv.com (#11174)
+* [cda] Fix and improve extraction (#10929, #10936)
+* [plays] Fix extraction (#11165)
+* [eagleplatform] Fix extraction (#11160)
++ [audioboom] Recognize /posts/ URLs (#11149)
+
+
+version 2016.11.08.1
+
+Extractors
+* [espn:article] Fix support for espn.com articles
+* [franceculture] Fix extraction (#11140)
+
+
+version 2016.11.08
+
+Extractors
+* [tmz:article] Fix extraction (#11052)
+* [espn] Fix extraction (#11041)
+* [mitele] Fix extraction after website redesign (#10824)
+- [ard] Remove age restriction check (#11129)
+* [generic] Improve support for pornhub.com embeds (#11100)
++ [generic] Add support for redtube.com embeds (#11099)
++ [generic] Add support for drtuber.com embeds (#11098)
++ [redtube] Add support for embed URLs
++ [drtuber] Add support for embed URLs
++ [yahoo] Improve content id extraction (#11088)
+* [toutv] Relax URL regular expression (#11121)
+
+
+version 2016.11.04
+
+Core
+* [extractor/common] Tolerate malformed RESOLUTION attribute in m3u8
+  manifests (#11113)
+* [downloader/ism] Fix AVC Decoder Configuration Record
+
+Extractors
++ [fox9] Add support for fox9.com (#11110)
++ [anvato] Extract more metadata and improve formats extraction
+* [vodlocker] Improve removed videos detection (#11106)
++ [vzaar] Add support for vzaar.com (#11093)
++ [vice] Add support for uplynk preplay videos (#11101)
+* [tubitv] Fix extraction (#11061)
++ [shahid] Add support for authentication (#11091)
++ [radiocanada] Add subtitles support (#11096)
++ [generic] Add support for ISM manifests
+
+
 version 2016.11.02
 
 Core

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 *.3gp *.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 *.wav *.ape *.swf *.jpg *.png CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe
 	find . -name "*.pyc" -delete
 	find . -name "*.class" -delete
 

README.md

@@ -664,7 +664,7 @@ $ youtube-dl -f 'bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best'
 # Download best format available but not better that 480p
 $ youtube-dl -f 'bestvideo[height<=480]+bestaudio/best[height<=480]'
 
-# Download best video only format but no bigger that 50 MB
+# Download best video only format but no bigger than 50 MB
 $ youtube-dl -f 'best[filesize<50M]'
 
 # Download best format available via direct link over HTTP/HTTPS protocol
@@ -758,7 +758,7 @@ Once the video is fully downloaded, use any video player, such as [mpv](https://
 
 ### I extracted a video URL with `-g`, but it does not play on another machine / in my webbrowser.
 
-It depends a lot on the service. In many cases, requests for the video (to download/play it) must come from the same IP address and with the same cookies.  Use the `--cookies` option to write the required cookies into a file, and advise your downloader to read cookies from that file. Some sites also require a common user agent to be used, use `--dump-user-agent` to see the one in use by youtube-dl.
+It depends a lot on the service. In many cases, requests for the video (to download/play it) must come from the same IP address and with the same cookies and/or HTTP headers. Use the `--cookies` option to write the required cookies into a file, and advise your downloader to read cookies from that file. Some sites also require a common user agent to be used, use `--dump-user-agent` to see the one in use by youtube-dl. You can also get necessary cookies and HTTP headers from JSON output obtained with `--dump-json`.
 
 It may be beneficial to use IPv6; in some cases, the restrictions are only applied to IPv4. Some services (sometimes only for a subset of videos) do not restrict the video URL by IP address, cookie, or user-agent, but these are the exception rather than the rule.
 
@@ -930,7 +930,7 @@ If you want to create a build of youtube-dl yourself, you'll need
 
 ### Adding support for a new site
 
-If you want to add support for a new site, first of all **make sure** this site is **not dedicated to [copyright infringement](#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. youtube-dl does **not support** such sites thus pull requests adding support for them **will be rejected**.
+If you want to add support for a new site, first of all **make sure** this site is **not dedicated to [copyright infringement](README.md#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. youtube-dl does **not support** such sites thus pull requests adding support for them **will be rejected**.
 
 After you have ensured this site is distributing it's content legally, you can follow this quick list (assuming your service is called `yourextractor`):
 

devscripts/bash-completion.py

@@ -25,5 +25,6 @@ def build_completion(opt_parser):
         filled_template = template.replace("{{flags}}", " ".join(opts_flag))
         f.write(filled_template)
 
+
 parser = youtube_dl.parseOpts()[0]
 build_completion(parser)

devscripts/create-github-release.py

@@ -2,11 +2,13 @@
 from __future__ import unicode_literals
 
 import base64
+import io
 import json
 import mimetypes
 import netrc
 import optparse
 import os
+import re
 import sys
 
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
@@ -90,16 +92,23 @@ class GitHubReleaser(object):
 
 
 def main():
-    parser = optparse.OptionParser(usage='%prog VERSION BUILDPATH')
+    parser = optparse.OptionParser(usage='%prog CHANGELOG VERSION BUILDPATH')
     options, args = parser.parse_args()
-    if len(args) != 2:
+    if len(args) != 3:
         parser.error('Expected a version and a build directory')
 
-    version, build_path = args
+    changelog_file, version, build_path = args
+
+    with io.open(changelog_file, encoding='utf-8') as inf:
+        changelog = inf.read()
+
+    mobj = re.search(r'(?s)version %s\n{2}(.+?)\n{3}' % version, changelog)
+    body = mobj.group(1) if mobj else ''
 
     releaser = GitHubReleaser()
 
-    new_release = releaser.create_release(version, name='youtube-dl %s' % version)
+    new_release = releaser.create_release(
+        version, name='youtube-dl %s' % version, body=body)
     release_id = new_release['id']
 
     for asset in os.listdir(build_path):

devscripts/fish-completion.py

@@ -44,5 +44,6 @@ def build_completion(opt_parser):
     with open(FISH_COMPLETION_FILE, 'w') as f:
         f.write(filled_template)
 
+
 parser = youtube_dl.parseOpts()[0]
 build_completion(parser)

devscripts/generate_aes_testdata.py

@@ -23,6 +23,7 @@ def openssl_encode(algo, key, iv):
     out, _ = prog.communicate(secret_msg)
     return out
 
+
 iv = key = [0x20, 0x15] + 14 * [0]
 
 r = openssl_encode('aes-128-cbc', key, iv)

devscripts/gh-pages/update-sites.py

@@ -32,5 +32,6 @@ def main():
     with open('supportedsites.html', 'w', encoding='utf-8') as sitesf:
         sitesf.write(template)
 
+
 if __name__ == '__main__':
     main()

devscripts/make_contributing.py

@@ -28,5 +28,6 @@ def main():
     with io.open(outfile, 'w', encoding='utf-8') as outf:
         outf.write(out)
 
+
 if __name__ == '__main__':
     main()

devscripts/make_lazy_extractors.py

@@ -59,6 +59,7 @@ def build_lazy_ie(ie, name):
         s += make_valid_template.format(valid_url=ie._make_valid_url())
     return s
 
+
 # find the correct sorting and add the required base classes so that sublcasses
 # can be correctly created
 classes = _ALL_CLASSES[:-1]

devscripts/make_supportedsites.py

@@ -41,5 +41,6 @@ def main():
     with io.open(outfile, 'w', encoding='utf-8') as outf:
         outf.write(out)
 
+
 if __name__ == '__main__':
     main()

devscripts/prepare_manpage.py

@@ -74,5 +74,6 @@ def filter_options(readme):
 
     return ret
 
+
 if __name__ == '__main__':
     main()

devscripts/release.sh

@@ -110,7 +110,7 @@ RELEASE_FILES="youtube-dl youtube-dl.exe youtube-dl-$version.tar.gz"
 for f in $RELEASE_FILES; do gpg --passphrase-repeat 5 --detach-sig "build/$version/$f"; done
 
 ROOT=$(pwd)
-python devscripts/create-github-release.py $version "$ROOT/build/$version"
+python devscripts/create-github-release.py ChangeLog $version "$ROOT/build/$version"
 
 ssh ytdl@yt-dl.org "sh html/update_latest.sh $version"
 

devscripts/zsh-completion.py

@@ -44,5 +44,6 @@ def build_completion(opt_parser):
     with open(ZSH_COMPLETION_FILE, "w") as f:
         f.write(template)
 
+
 parser = youtube_dl.parseOpts()[0]
 build_completion(parser)

docs/supportedsites.md

@@ -131,6 +131,7 @@
  - **cbsnews**: CBS News
  - **cbsnews:livevideo**: CBS News Live Videos
  - **CBSSports**
+ - **CCMA**
  - **CCTV**
  - **CDA**
  - **CeskaTelevize**
@@ -158,6 +159,7 @@
  - **CollegeRama**
  - **ComCarCoff**
  - **ComedyCentral**
+ - **ComedyCentralFullEpisodes**
  - **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
@@ -225,6 +227,7 @@
  - **EroProfile**
  - **Escapist**
  - **ESPN**
+ - **ESPNArticle**
  - **EsriVideo**
  - **Europa**
  - **EveryonesMixtape**
@@ -247,6 +250,7 @@
  - **FootyRoom**
  - **Formula1**
  - **FOX**
+ - **FOX9**
  - **Foxgay**
  - **foxnews**: Fox News and Fox Business Video
  - **foxnews:article**
@@ -362,6 +366,7 @@
  - **kuwo:song**: 酷我音乐
  - **la7.it**
  - **Laola1Tv**
+ - **Laola1TvEmbed**
  - **LCI**
  - **Lcp**
  - **LcpPlay**
@@ -399,6 +404,8 @@
  - **MatchTV**
  - **MDR**: MDR.DE and KiKA
  - **media.ccc.de**
+ - **Meipai**: 美拍
+ - **MelonVOD**
  - **META**
  - **metacafe**
  - **Metacritic**
@@ -520,6 +527,7 @@
  - **Odnoklassniki**
  - **OktoberfestTV**
  - **on.aol.com**
+ - **OnDemandKorea**
  - **onet.tv**
  - **onet.tv:channel**
  - **OnionStudios**
@@ -641,7 +649,6 @@
  - **Screencast**
  - **ScreencastOMatic**
  - **ScreenJunkies**
- - **ScreenwaveMedia**
  - **Seeker**
  - **SenateISVP**
  - **SendtoNews**
@@ -713,7 +720,7 @@
  - **teachertube:user:collection**: teachertube.com user and collection videos
  - **TeachingChannel**
  - **Teamcoco**
- - **TeamFour**
+ - **TeamFourStar**
  - **TechTalks**
  - **techtv.mit.edu**
  - **ted**
@@ -769,6 +776,8 @@
  - **TV2Article**
  - **TV3**
  - **TV4**: tv4.se and tv4play.se
+ - **TVANouvelles**
+ - **TVANouvellesArticle**
  - **TVC**
  - **TVCArticle**
  - **tvigle**: Интернет-телевидение Tvigle.ru
@@ -780,10 +789,13 @@
  - **Tweakers**
  - **twitch:chapter**
  - **twitch:clips**
- - **twitch:past_broadcasts**
  - **twitch:profile**
  - **twitch:stream**
  - **twitch:video**
+ - **twitch:videos:all**
+ - **twitch:videos:highlights**
+ - **twitch:videos:past-broadcasts**
+ - **twitch:videos:uploads**
  - **twitch:vod**
  - **twitter**
  - **twitter:amplify**
@@ -869,7 +881,9 @@
  - **VRT**
  - **vube**: Vube.com
  - **VuClip**
+ - **VVVVID**
  - **VyboryMos**
+ - **Vzaar**
  - **Walla**
  - **washingtonpost**
  - **washingtonpost:article**
@@ -877,6 +891,8 @@
  - **WatchIndianPorn**: Watch Indian Porn
  - **WDR**
  - **wdr:mobile**
+ - **Webcaster**
+ - **WebcasterFeed**
  - **WebOfStories**
  - **WebOfStoriesPlaylist**
  - **WeiqiTV**: WQTV

test/test_InfoExtractor.py

@@ -84,5 +84,6 @@ class TestInfoExtractor(unittest.TestCase):
         self.assertRaises(ExtractorError, self.ie._download_json, uri, None)
         self.assertEqual(self.ie._download_json(uri, None, fatal=False), None)
 
+
 if __name__ == '__main__':
     unittest.main()

test/test_aes.py

@@ -51,5 +51,6 @@ class TestAES(unittest.TestCase):
         decrypted = (aes_decrypt_text(encrypted, password, 32))
         self.assertEqual(decrypted, self.secret_msg)
 
+
 if __name__ == '__main__':
     unittest.main()

test/test_download.py

@@ -60,6 +60,7 @@ def _file_md5(fn):
     with open(fn, 'rb') as f:
         return hashlib.md5(f.read()).hexdigest()
 
+
 defs = gettestcases()
 
 
@@ -217,6 +218,7 @@ def generator(test_case):
 
     return test_template
 
+
 # And add them to TestDownload
 for n, test_case in enumerate(defs):
     test_method = generator(test_case)

test/test_execution.py

@@ -39,5 +39,6 @@ class TestExecution(unittest.TestCase):
         _, stderr = p.communicate()
         self.assertFalse(stderr)
 
+
 if __name__ == '__main__':
     unittest.main()

test/test_http.py

@@ -169,5 +169,6 @@ class TestProxy(unittest.TestCase):
         # b'xn--fiq228c' is '中文'.encode('idna')
         self.assertEqual(response, 'normal: http://xn--fiq228c.tw/')
 
+
 if __name__ == '__main__':
     unittest.main()

test/test_iqiyi_sdk_interpreter.py

@@ -43,5 +43,6 @@ class TestIqiyiSDKInterpreter(unittest.TestCase):
         ie._login()
         self.assertTrue('unable to log in:' in logger.messages[0])
 
+
 if __name__ == '__main__':
     unittest.main()

test/test_jsinterp.py

@@ -104,6 +104,14 @@ class TestJSInterpreter(unittest.TestCase):
         }''')
         self.assertEqual(jsi.call_function('x'), [20, 20, 30, 40, 50])
 
+    def test_call(self):
+        jsi = JSInterpreter('''
+        function x() { return 2; }
+        function y(a) { return x() + a; }
+        function z() { return y(3); }
+        ''')
+        self.assertEqual(jsi.call_function('z'), 5)
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_utils.py

@@ -70,6 +70,7 @@ from youtube_dl.utils import (
     lowercase_escape,
     url_basename,
     base_url,
+    urljoin,
     urlencode_postdata,
     urshift,
     update_url_query,
@@ -445,6 +446,22 @@ class TestUtil(unittest.TestCase):
         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_urljoin(self):
+        self.assertEqual(urljoin('http://foo.de/', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+        self.assertEqual(urljoin('//foo.de/', '/a/b/c.txt'), '//foo.de/a/b/c.txt')
+        self.assertEqual(urljoin('http://foo.de/', 'a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+        self.assertEqual(urljoin('http://foo.de', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+        self.assertEqual(urljoin('http://foo.de', 'a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+        self.assertEqual(urljoin('http://foo.de/', 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+        self.assertEqual(urljoin('http://foo.de/', '//foo.de/a/b/c.txt'), '//foo.de/a/b/c.txt')
+        self.assertEqual(urljoin(None, 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+        self.assertEqual(urljoin(None, '//foo.de/a/b/c.txt'), '//foo.de/a/b/c.txt')
+        self.assertEqual(urljoin('', 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+        self.assertEqual(urljoin(['foobar'], 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+        self.assertEqual(urljoin('http://foo.de/', None), None)
+        self.assertEqual(urljoin('http://foo.de/', ''), None)
+        self.assertEqual(urljoin('http://foo.de/', ['foobar']), None)
+
     def test_parse_age_limit(self):
         self.assertEqual(parse_age_limit(None), None)
         self.assertEqual(parse_age_limit(False), None)
@@ -1075,5 +1092,6 @@ The first line
         self.assertEqual(get_element_by_class('foo', html), 'nice')
         self.assertEqual(get_element_by_class('no-such-class', html), None)
 
+
 if __name__ == '__main__':
     unittest.main()

test/test_verbose_output.py

@@ -66,5 +66,6 @@ class TestVerboseOutput(unittest.TestCase):
         self.assertTrue(b'-p' in serr)
         self.assertTrue(b'secret' not in serr)
 
+
 if __name__ == '__main__':
     unittest.main()

test/test_write_annotations.py

@@ -24,6 +24,7 @@ class YoutubeDL(youtube_dl.YoutubeDL):
         super(YoutubeDL, self).__init__(*args, **kwargs)
         self.to_stderr = self.to_screen
 
+
 params = get_params({
     'writeannotations': True,
     'skip_download': True,
@@ -74,5 +75,6 @@ class TestAnnotations(unittest.TestCase):
     def tearDown(self):
         try_rm(ANNOTATIONS_FILE)
 
+
 if __name__ == '__main__':
     unittest.main()

test/test_youtube_lists.py

@@ -66,5 +66,6 @@ class TestYoutubeLists(unittest.TestCase):
         for entry in result['entries']:
             self.assertTrue(entry.get('title'))
 
+
 if __name__ == '__main__':
     unittest.main()

test/test_youtube_signature.py

@@ -114,6 +114,7 @@ def make_tfunc(url, stype, sig_input, expected_sig):
     test_func.__name__ = str('test_signature_' + stype + '_' + test_id)
     setattr(TestSignature, test_func.__name__, test_func)
 
+
 for test_spec in _TESTS:
     make_tfunc(*test_spec)
 

youtube_dl/__init__.py

@@ -95,8 +95,7 @@ def _real_main(argv=None):
                 write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
         except IOError:
             sys.exit('ERROR: batch file could not be read')
-    all_urls = batch_urls + args
-    all_urls = [url.strip() for url in all_urls]
+    all_urls = batch_urls + [url.strip() for url in args]  # batch_urls are already striped in read_batch_urls
     _enc = preferredencoding()
     all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
 
@@ -450,4 +449,5 @@ def main(argv=None):
     except KeyboardInterrupt:
         sys.exit('\nERROR: Interrupted by user')
 
+
 __all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']

youtube_dl/aes.py

@@ -174,6 +174,7 @@ def aes_decrypt_text(data, password, key_size_bytes):
 
     return plaintext
 
+
 RCON = (0x8d, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36)
 SBOX = (0x63, 0x7C, 0x77, 0x7B, 0xF2, 0x6B, 0x6F, 0xC5, 0x30, 0x01, 0x67, 0x2B, 0xFE, 0xD7, 0xAB, 0x76,
         0xCA, 0x82, 0xC9, 0x7D, 0xFA, 0x59, 0x47, 0xF0, 0xAD, 0xD4, 0xA2, 0xAF, 0x9C, 0xA4, 0x72, 0xC0,
@@ -328,4 +329,5 @@ def inc(data):
             break
     return data
 
+
 __all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_cbc_decrypt', 'aes_decrypt_text']

youtube_dl/compat.py

@@ -2491,6 +2491,7 @@ class _TreeBuilder(etree.TreeBuilder):
     def doctype(self, name, pubid, system):
         pass
 
+
 if sys.version_info[0] >= 3:
     def compat_etree_fromstring(text):
         return etree.XML(text, parser=etree.XMLParser(target=_TreeBuilder()))
@@ -2787,6 +2788,7 @@ def workaround_optparse_bug9161():
             return real_add_option(self, *bargs, **bkwargs)
         optparse.OptionGroup.add_option = _compat_add_option
 
+
 if hasattr(shutil, 'get_terminal_size'):  # Python >= 3.3
     compat_get_terminal_size = shutil.get_terminal_size
 else:

youtube_dl/downloader/external.py

@@ -293,6 +293,7 @@ class FFmpegFD(ExternalFD):
 class AVconvFD(FFmpegFD):
     pass
 
+
 _BY_NAME = dict(
     (klass.get_basename(), klass)
     for name, klass in globals().items()

youtube_dl/downloader/f4m.py

@@ -314,7 +314,8 @@ class F4mFD(FragmentFD):
         man_url = info_dict['url']
         requested_bitrate = info_dict.get('tbr')
         self.to_screen('[%s] Downloading f4m manifest' % self.FD_NAME)
-        urlh = self.ydl.urlopen(man_url)
+
+        urlh = self.ydl.urlopen(self._prepare_url(info_dict, man_url))
         man_url = urlh.geturl()
         # Some manifests may be malformed, e.g. prosiebensat1 generated manifests
         # (see https://github.com/rg3/youtube-dl/issues/6215#issuecomment-121704244
@@ -387,7 +388,10 @@ class F4mFD(FragmentFD):
             url_parsed = base_url_parsed._replace(path=base_url_parsed.path + name, query='&'.join(query))
             frag_filename = '%s-%s' % (ctx['tmpfilename'], name)
             try:
-                success = ctx['dl'].download(frag_filename, {'url': url_parsed.geturl()})
+                success = ctx['dl'].download(frag_filename, {
+                    'url': url_parsed.geturl(),
+                    'http_headers': info_dict.get('http_headers'),
+                })
                 if not success:
                     return False
                 (down, frag_sanitized) = sanitize_open(frag_filename, 'rb')

youtube_dl/downloader/fragment.py

@@ -9,6 +9,7 @@ from ..utils import (
     error_to_compat_str,
     encodeFilename,
     sanitize_open,
+    sanitized_Request,
 )
 
 
@@ -37,6 +38,10 @@ class FragmentFD(FileDownloader):
     def report_skip_fragment(self, fragment_name):
         self.to_screen('[download] Skipping fragment %s...' % fragment_name)
 
+    def _prepare_url(self, info_dict, url):
+        headers = info_dict.get('http_headers')
+        return sanitized_Request(url, None, headers) if headers else url
+
     def _prepare_and_start_frag_download(self, ctx):
         self._prepare_frag_download(ctx)
         self._start_frag_download(ctx)

youtube_dl/downloader/hls.py

@@ -59,7 +59,8 @@ class HlsFD(FragmentFD):
     def real_download(self, filename, info_dict):
         man_url = info_dict['url']
         self.to_screen('[%s] Downloading m3u8 manifest' % self.FD_NAME)
-        manifest = self.ydl.urlopen(man_url).read()
+
+        manifest = self.ydl.urlopen(self._prepare_url(info_dict, man_url)).read()
 
         s = manifest.decode('utf-8', 'ignore')
 
@@ -112,7 +113,10 @@ class HlsFD(FragmentFD):
                     count = 0
                     while count <= fragment_retries:
                         try:
-                            success = ctx['dl'].download(frag_filename, {'url': frag_url})
+                            success = ctx['dl'].download(frag_filename, {
+                                'url': frag_url,
+                                'http_headers': info_dict.get('http_headers'),
+                            })
                             if not success:
                                 return False
                             down, frag_sanitized = sanitize_open(frag_filename, 'rb')

youtube_dl/downloader/ism.py

@@ -129,7 +129,7 @@ def write_piff_header(stream, params):
         sample_entry_payload += u1616.pack(params['sampling_rate'])
 
         if fourcc == 'AACL':
-            smaple_entry_box = box(b'mp4a', sample_entry_payload)
+            sample_entry_box = box(b'mp4a', sample_entry_payload)
     else:
         sample_entry_payload = sample_entry_payload
         sample_entry_payload += u16.pack(0)  # pre defined
@@ -149,9 +149,7 @@ def write_piff_header(stream, params):
         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 += sps[1:4]  # avc profile indication + profile compatibility + 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))
@@ -160,8 +158,8 @@ def write_piff_header(stream, params):
             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
+            sample_entry_box = box(b'avc1', sample_entry_payload)  # AVC Simple Entry
+    stsd_payload += sample_entry_box
 
     stbl_payload = full_box(b'stsd', 0, 0, stsd_payload)  # Sample Description Box
 

youtube_dl/extractor/aenetworks.py

@@ -26,7 +26,7 @@ class AENetworksIE(AENetworksBaseIE):
     _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:history|aetv|mylifetime)\.com|fyi\.tv)/(?:shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|movies/(?P<movie_display_id>[^/]+)/full-movie)'
     _TESTS = [{
         'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
-        'md5': '8ff93eb073449f151d6b90c0ae1ef0c7',
+        'md5': 'a97a65f7e823ae10e9244bc5433d5fe6',
         'info_dict': {
             'id': '22253814',
             'ext': 'mp4',
@@ -99,7 +99,7 @@ class AENetworksIE(AENetworksBaseIE):
 
         query = {
             'mbr': 'true',
-            'assetTypes': 'medium_video_s3'
+            'assetTypes': 'high_video_s3'
         }
         video_id = self._html_search_meta('aetn:VideoID', webpage)
         media_url = self._search_regex(
@@ -155,7 +155,7 @@ class HistoryTopicIE(AENetworksBaseIE):
             'id': 'world-war-i-history',
             'title': 'World War I History',
         },
-        'playlist_mincount': 24,
+        'playlist_mincount': 23,
     }, {
         'url': 'http://www.history.com/topics/world-war-i-history/videos',
         'only_matching': True,
@@ -193,7 +193,8 @@ class HistoryTopicIE(AENetworksBaseIE):
             return self.theplatform_url_result(
                 release_url, video_id, {
                     'mbr': 'true',
-                    'switch': 'hls'
+                    'switch': 'hls',
+                    'assetTypes': 'high_video_ak',
                 })
         else:
             webpage = self._download_webpage(url, topic_id)
@@ -203,6 +204,7 @@ class HistoryTopicIE(AENetworksBaseIE):
                 entries.append(self.theplatform_url_result(
                     video_attributes['data-release-url'], video_attributes['data-id'], {
                         'mbr': 'true',
-                        'switch': 'hls'
+                        'switch': 'hls',
+                        'assetTypes': 'high_video_ak',
                     }))
             return self.playlist_result(entries, topic_id, get_element_by_attribute('class', 'show-title', webpage))

youtube_dl/extractor/afreecatv.py

@@ -11,6 +11,7 @@ from ..compat import (
 from ..utils import (
     ExtractorError,
     int_or_none,
+    update_url_query,
     xpath_element,
     xpath_text,
 )
@@ -18,12 +19,18 @@ from ..utils import (
 
 class AfreecaTVIE(InfoExtractor):
     IE_DESC = 'afreecatv.com'
-    _VALID_URL = r'''(?x)^
-        https?://(?:(live|afbbs|www)\.)?afreeca(?:tv)?\.com(?::\d+)?
-        (?:
-            /app/(?:index|read_ucc_bbs)\.cgi|
-            /player/[Pp]layer\.(?:swf|html))
-        \?.*?\bnTitleNo=(?P<id>\d+)'''
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:
+                            (?:(?:live|afbbs|www)\.)?afreeca(?:tv)?\.com(?::\d+)?
+                            (?:
+                                /app/(?:index|read_ucc_bbs)\.cgi|
+                                /player/[Pp]layer\.(?:swf|html)
+                            )\?.*?\bnTitleNo=|
+                            vod\.afreecatv\.com/PLAYER/STATION/
+                        )
+                        (?P<id>\d+)
+                    '''
     _TESTS = [{
         'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=',
         'md5': 'f72c89fe7ecc14c1b5ce506c4996046e',
@@ -66,6 +73,9 @@ class AfreecaTVIE(InfoExtractor):
     }, {
         'url': 'http://www.afreecatv.com/player/Player.swf?szType=szBjId=djleegoon&nStationNo=11273158&nBbsNo=13161095&nTitleNo=36327652',
         'only_matching': True,
+    }, {
+        'url': 'http://vod.afreecatv.com/PLAYER/STATION/15055030',
+        'only_matching': True,
     }]
 
     @staticmethod
@@ -83,7 +93,9 @@ class AfreecaTVIE(InfoExtractor):
         info_url = compat_urlparse.urlunparse(parsed_url._replace(
             netloc='afbbs.afreecatv.com:8080',
             path='/api/video/get_video_info.php'))
-        video_xml = self._download_xml(info_url, video_id)
+
+        video_xml = self._download_xml(
+            update_url_query(info_url, {'nTitleNo': video_id}), video_id)
 
         if xpath_element(video_xml, './track/video/file') is None:
             raise ExtractorError('Specified AfreecaTV video does not exist',

youtube_dl/extractor/amcnetworks.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 
 class AMCNetworksIE(ThePlatformIE):
-    _VALID_URL = r'https?://(?:www\.)?(?:amc|bbcamerica|ifc|wetv)\.com/(?:movies/|shows/[^/]+/(?:full-episodes/)?season-\d+/episode-\d+(?:-(?:[^/]+/)?|/))(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:amc|bbcamerica|ifc|wetv)\.com/(?:movies/|shows/[^/]+/(?:full-episodes/)?[^/]+/episode-\d+(?:-(?:[^/]+/)?|/))(?P<id>[^/?#]+)'
     _TESTS = [{
         'url': 'http://www.ifc.com/shows/maron/season-04/episode-01/step-1',
         'md5': '',
@@ -41,6 +41,9 @@ class AMCNetworksIE(ThePlatformIE):
     }, {
         'url': 'http://www.ifc.com/movies/chaos',
         'only_matching': True,
+    }, {
+        'url': 'http://www.bbcamerica.com/shows/doctor-who/full-episodes/the-power-of-the-daleks/episode-01-episode-1-color-version',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/anvato.py

@@ -157,22 +157,16 @@ class AnvatoIE(InfoExtractor):
             video_data_url, video_id, transform_source=strip_jsonp,
             data=json.dumps(payload).encode('utf-8'))
 
-    def _extract_anvato_videos(self, webpage, video_id):
-        anvplayer_data = self._parse_json(self._html_search_regex(
-            r'<script[^>]+data-anvp=\'([^\']+)\'', webpage,
-            'Anvato player data'), video_id)
-
-        video_id = anvplayer_data['video']
-        access_key = anvplayer_data['accessKey']
-
+    def _get_anvato_videos(self, access_key, video_id):
         video_data = self._get_video_json(access_key, video_id)
 
         formats = []
         for published_url in video_data['published_urls']:
             video_url = published_url['embed_url']
+            media_format = published_url.get('format')
             ext = determine_ext(video_url)
 
-            if ext == 'smil':
+            if ext == 'smil' or media_format == 'smil':
                 formats.extend(self._extract_smil_formats(video_url, video_id))
                 continue
 
@@ -183,7 +177,7 @@ class AnvatoIE(InfoExtractor):
                 'tbr': tbr if tbr != 0 else None,
             }
 
-            if ext == 'm3u8':
+            if ext == 'm3u8' or media_format in ('m3u8', 'm3u8-variant'):
                 # Not using _extract_m3u8_formats here as individual media
                 # playlists are also included in published_urls.
                 if tbr is None:
@@ -194,7 +188,7 @@ class AnvatoIE(InfoExtractor):
                         'format_id': '-'.join(filter(None, ['hls', compat_str(tbr)])),
                         'ext': 'mp4',
                     })
-            elif ext == 'mp3':
+            elif ext == 'mp3' or media_format == 'mp3':
                 a_format['vcodec'] = 'none'
             else:
                 a_format.update({
@@ -218,7 +212,19 @@ class AnvatoIE(InfoExtractor):
             'formats': formats,
             'title': video_data.get('def_title'),
             'description': video_data.get('def_description'),
+            'tags': video_data.get('def_tags', '').split(','),
             'categories': video_data.get('categories'),
             'thumbnail': video_data.get('thumbnail'),
+            'timestamp': int_or_none(video_data.get(
+                'ts_published') or video_data.get('ts_added')),
+            'uploader': video_data.get('mcp_id'),
+            'duration': int_or_none(video_data.get('duration')),
             'subtitles': subtitles,
         }
+
+    def _extract_anvato_videos(self, webpage, video_id):
+        anvplayer_data = self._parse_json(self._html_search_regex(
+            r'<script[^>]+data-anvp=\'([^\']+)\'', webpage,
+            'Anvato player data'), video_id)
+        return self._get_anvato_videos(
+            anvplayer_data['accessKey'], anvplayer_data['video'])

youtube_dl/extractor/ard.py

@@ -178,8 +178,6 @@ class ARDMediathekIE(InfoExtractor):
             ('>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.'),
         )
 
         for pattern, message in ERRORS:

youtube_dl/extractor/audioboom.py

@@ -6,8 +6,8 @@ from ..utils import float_or_none
 
 
 class AudioBoomIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?audioboom\.com/boos/(?P<id>[0-9]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?audioboom\.com/(?:boos|posts)/(?P<id>[0-9]+)'
+    _TESTS = [{
         'url': 'https://audioboom.com/boos/4279833-3-09-2016-czaban-hour-3?t=0',
         'md5': '63a8d73a055c6ed0f1e51921a10a5a76',
         'info_dict': {
@@ -19,7 +19,10 @@ class AudioBoomIE(InfoExtractor):
             'uploader': 'Steve Czaban',
             'uploader_url': 're:https?://(?:www\.)?audioboom\.com/channel/steveczabanyahoosportsradio',
         }
-    }
+    }, {
+        'url': 'https://audioboom.com/posts/4279833-3-09-2016-czaban-hour-3?t=0',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

youtube_dl/extractor/azubu.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 
 class AzubuIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?azubu\.tv/[^/]+#!/play/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?azubu\.(?:tv|uol.com.br)/[^/]+#!/play/(?P<id>\d+)'
     _TESTS = [
         {
             'url': 'http://www.azubu.tv/GSL#!/play/15575/2014-hot6-cup-last-big-match-ro8-day-1',
@@ -103,12 +103,15 @@ class AzubuIE(InfoExtractor):
 
 
 class AzubuLiveIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?azubu\.tv/(?P<id>[^/]+)$'
+    _VALID_URL = r'https?://(?:www\.)?azubu\.(?:tv|uol.com.br)/(?P<id>[^/]+)$'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.azubu.tv/MarsTVMDLen',
         'only_matching': True,
-    }
+    }, {
+        'url': 'http://azubu.uol.com.br/adolfz',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         user = self._match_id(url)

youtube_dl/extractor/bandcamp.py

@@ -1,7 +1,9 @@
 from __future__ import unicode_literals
 
 import json
+import random
 import re
+import time
 
 from .common import InfoExtractor
 from ..compat import (
@@ -12,6 +14,9 @@ from ..utils import (
     ExtractorError,
     float_or_none,
     int_or_none,
+    parse_filesize,
+    unescapeHTML,
+    update_url_query,
 )
 
 
@@ -81,35 +86,68 @@ class BandcampIE(InfoExtractor):
             r'(?ms)var TralbumData = .*?[{,]\s*id: (?P<id>\d+),?$',
             webpage, 'video id')
 
-        download_webpage = self._download_webpage(download_link, video_id, 'Downloading free downloads page')
-        # We get the dictionary of the track from some javascript code
-        all_info = self._parse_json(self._search_regex(
-            r'(?sm)items: (.*?),$', download_webpage, 'items'), video_id)
-        info = all_info[0]
-        # We pick mp3-320 for now, until format selection can be easily implemented.
-        mp3_info = info['downloads']['mp3-320']
-        # If we try to use this url it says the link has expired
-        initial_url = mp3_info['url']
-        m_url = re.match(
-            r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$',
-            initial_url)
-        # We build the url we will use to get the final track url
-        # This url is build in Bandcamp in the script download_bunde_*.js
-        request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), video_id, m_url.group('ts'))
-        final_url_webpage = self._download_webpage(request_url, video_id, 'Requesting download url')
-        # If we could correctly generate the .rand field the url would be
-        # in the "download_url" key
-        final_url = self._proto_relative_url(self._search_regex(
-            r'"retry_url":"(.+?)"', final_url_webpage, 'final video URL'), 'http:')
+        download_webpage = self._download_webpage(
+            download_link, video_id, 'Downloading free downloads page')
+
+        blob = self._parse_json(
+            self._search_regex(
+                r'data-blob=(["\'])(?P<blob>{.+?})\1', download_webpage,
+                'blob', group='blob'),
+            video_id, transform_source=unescapeHTML)
+
+        info = blob['digital_items'][0]
+
+        downloads = info['downloads']
+        track = info['title']
+
+        artist = info.get('artist')
+        title = '%s - %s' % (artist, track) if artist else track
+
+        download_formats = {}
+        for f in blob['download_formats']:
+            name, ext = f.get('name'), f.get('file_extension')
+            if all(isinstance(x, compat_str) for x in (name, ext)):
+                download_formats[name] = ext.strip('.')
+
+        formats = []
+        for format_id, f in downloads.items():
+            format_url = f.get('url')
+            if not format_url:
+                continue
+            # Stat URL generation algorithm is reverse engineered from
+            # download_*_bundle_*.js
+            stat_url = update_url_query(
+                format_url.replace('/download/', '/statdownload/'), {
+                    '.rand': int(time.time() * 1000 * random.random()),
+                })
+            format_id = f.get('encoding_name') or format_id
+            stat = self._download_json(
+                stat_url, video_id, 'Downloading %s JSON' % format_id,
+                transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1],
+                fatal=False)
+            if not stat:
+                continue
+            retry_url = stat.get('retry_url')
+            if not isinstance(retry_url, compat_str):
+                continue
+            formats.append({
+                'url': self._proto_relative_url(retry_url, 'http:'),
+                'ext': download_formats.get(format_id),
+                'format_id': format_id,
+                'format_note': f.get('description'),
+                'filesize': parse_filesize(f.get('size_mb')),
+                'vcodec': 'none',
+            })
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
-            'title': info['title'],
-            'ext': 'mp3',
-            'vcodec': 'none',
-            'url': final_url,
+            'title': title,
             'thumbnail': info.get('thumb_url'),
             'uploader': info.get('artist'),
+            'artist': artist,
+            'track': track,
+            'formats': formats,
         }
 
 

youtube_dl/extractor/bloomberg.py

@@ -45,7 +45,8 @@ class BloombergIE(InfoExtractor):
         name = self._match_id(url)
         webpage = self._download_webpage(url, name)
         video_id = self._search_regex(
-            r'["\']bmmrId["\']\s*:\s*(["\'])(?P<url>.+?)\1',
+            (r'["\']bmmrId["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1',
+             r'videoId\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1'),
             webpage, 'id', group='url', default=None)
         if not video_id:
             bplayer_data = self._parse_json(self._search_regex(

youtube_dl/extractor/canalplus.py

@@ -105,7 +105,8 @@ class CanalplusIE(InfoExtractor):
         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+)'],
+             r'id=["\']canal_video_player(?P<id>\d+)',
+             r'data-video=["\'](?P<id>\d+)'],
             webpage, 'video id', group='id')
 
         info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)

youtube_dl/extractor/canvas.py

@@ -89,6 +89,9 @@ class CanvasIE(InfoExtractor):
             elif format_type == 'HDS':
                 formats.extend(self._extract_f4m_formats(
                     format_url, display_id, f4m_id=format_type, fatal=False))
+            elif format_type == 'MPEG_DASH':
+                formats.extend(self._extract_mpd_formats(
+                    format_url, display_id, mpd_id=format_type, fatal=False))
             else:
                 formats.append({
                     'format_id': format_type,

youtube_dl/extractor/cbc.py

@@ -283,11 +283,6 @@ class CBCWatchVideoIE(CBCWatchBaseIE):
         formats = self._extract_m3u8_formats(re.sub(r'/([^/]+)/[^/?]+\.m3u8', r'/\1/\1.m3u8', m3u8_url), video_id, 'mp4', fatal=False)
         if len(formats) < 2:
             formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4')
-        # 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 = {

youtube_dl/extractor/cbslocal.py

@@ -4,11 +4,14 @@ from __future__ import unicode_literals
 from .anvato import AnvatoIE
 from .sendtonews import SendtoNewsIE
 from ..compat import compat_urlparse
-from ..utils import unified_timestamp
+from ..utils import (
+    parse_iso8601,
+    unified_timestamp,
+)
 
 
 class CBSLocalIE(AnvatoIE):
-    _VALID_URL = r'https?://[a-z]+\.cbslocal\.com/\d+/\d+/\d+/(?P<id>[0-9a-z-]+)'
+    _VALID_URL = r'https?://[a-z]+\.cbslocal\.com/(?:\d+/\d+/\d+|video)/(?P<id>[0-9a-z-]+)'
 
     _TESTS = [{
         # Anvato backend
@@ -22,6 +25,7 @@ class CBSLocalIE(AnvatoIE):
             'thumbnail': 're:^https?://.*',
             'timestamp': 1463440500,
             'upload_date': '20160516',
+            'uploader': 'CBS',
             'subtitles': {
                 'en': 'mincount:5',
             },
@@ -35,6 +39,7 @@ class CBSLocalIE(AnvatoIE):
                 'Syndication\\Curb.tv',
                 'Content\\News'
             ],
+            'tags': ['CBS 2 News Evening'],
         },
     }, {
         # SendtoNews embed
@@ -47,6 +52,31 @@ class CBSLocalIE(AnvatoIE):
             # m3u8 download
             'skip_download': True,
         },
+    }, {
+        'url': 'http://newyork.cbslocal.com/video/3580809-a-very-blue-anniversary/',
+        'info_dict': {
+            'id': '3580809',
+            'ext': 'mp4',
+            'title': 'A Very Blue Anniversary',
+            'description': 'CBS2’s Cindy Hsu has more.',
+            'thumbnail': 're:^https?://.*',
+            'timestamp': 1479962220,
+            'upload_date': '20161124',
+            'uploader': 'CBS',
+            'subtitles': {
+                'en': 'mincount:5',
+            },
+            'categories': [
+                'Stations\\Spoken Word\\WCBSTV',
+                'Syndication\\AOL',
+                'Syndication\\MSN',
+                'Syndication\\NDN',
+                'Syndication\\Yahoo',
+                'Content\\News',
+                'Content\\News\\Local News',
+            ],
+            'tags': ['CBS 2 News Weekends', 'Cindy Hsu', 'Blue Man Group'],
+        },
     }]
 
     def _real_extract(self, url):
@@ -62,8 +92,11 @@ class CBSLocalIE(AnvatoIE):
         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 = unified_timestamp(time_str)
+            r'class="entry-date">([^<]+)<', webpage, 'released date', default=None)
+        if time_str:
+            timestamp = unified_timestamp(time_str)
+        else:
+            timestamp = parse_iso8601(self._html_search_meta('uploadDate', webpage))
 
         info_dict.update({
             'display_id': display_id,

youtube_dl/extractor/ccma.py

@@ -0,0 +1,99 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_duration,
+    parse_iso8601,
+    clean_html,
+)
+
+
+class CCMAIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?ccma\.cat/(?:[^/]+/)*?(?P<type>video|audio)/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://www.ccma.cat/tv3/alacarta/lespot-de-la-marato-de-tv3/lespot-de-la-marato-de-tv3/video/5630208/',
+        'md5': '7296ca43977c8ea4469e719c609b0871',
+        'info_dict': {
+            'id': '5630208',
+            'ext': 'mp4',
+            'title': 'L\'espot de La Marató de TV3',
+            'description': 'md5:f12987f320e2f6e988e9908e4fe97765',
+            'timestamp': 1470918540,
+            'upload_date': '20160811',
+        }
+    }, {
+        'url': 'http://www.ccma.cat/catradio/alacarta/programa/el-consell-de-savis-analitza-el-derbi/audio/943685/',
+        'md5': 'fa3e38f269329a278271276330261425',
+        'info_dict': {
+            'id': '943685',
+            'ext': 'mp3',
+            'title': 'El Consell de Savis analitza el derbi',
+            'description': 'md5:e2a3648145f3241cb9c6b4b624033e53',
+            'upload_date': '20171205',
+            'timestamp': 1512507300,
+        }
+    }]
+
+    def _real_extract(self, url):
+        media_type, media_id = re.match(self._VALID_URL, url).groups()
+        media_data = {}
+        formats = []
+        profiles = ['pc'] if media_type == 'audio' else ['mobil', 'pc']
+        for i, profile in enumerate(profiles):
+            md = self._download_json('http://dinamics.ccma.cat/pvideo/media.jsp', media_id, query={
+                'media': media_type,
+                'idint': media_id,
+                'profile': profile,
+            }, fatal=False)
+            if md:
+                media_data = md
+                media_url = media_data.get('media', {}).get('url')
+                if media_url:
+                    formats.append({
+                        'format_id': profile,
+                        'url': media_url,
+                        'quality': i,
+                    })
+        self._sort_formats(formats)
+
+        informacio = media_data['informacio']
+        title = informacio['titol']
+        durada = informacio.get('durada', {})
+        duration = int_or_none(durada.get('milisegons'), 1000) or parse_duration(durada.get('text'))
+        timestamp = parse_iso8601(informacio.get('data_emissio', {}).get('utc'))
+
+        subtitles = {}
+        subtitols = media_data.get('subtitols', {})
+        if subtitols:
+            sub_url = subtitols.get('url')
+            if sub_url:
+                subtitles.setdefault(
+                    subtitols.get('iso') or subtitols.get('text') or 'ca', []).append({
+                        'url': sub_url,
+                    })
+
+        thumbnails = []
+        imatges = media_data.get('imatges', {})
+        if imatges:
+            thumbnail_url = imatges.get('url')
+            if thumbnail_url:
+                thumbnails = [{
+                    'url': thumbnail_url,
+                    'width': int_or_none(imatges.get('amplada')),
+                    'height': int_or_none(imatges.get('alcada')),
+                }]
+
+        return {
+            'id': media_id,
+            'title': title,
+            'description': clean_html(informacio.get('descripcio')),
+            'duration': duration,
+            'timestamp': timestamp,
+            'thumnails': thumbnails,
+            'subtitles': subtitles,
+            'formats': formats,
+        }

youtube_dl/extractor/cda.py

@@ -5,14 +5,16 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
-    decode_packed_codes,
     ExtractorError,
-    parse_duration
+    float_or_none,
+    int_or_none,
+    parse_duration,
 )
 
 
 class CDAIE(InfoExtractor):
     _VALID_URL = r'https?://(?:(?:www\.)?cda\.pl/video|ebd\.cda\.pl/[0-9]+x[0-9]+)/(?P<id>[0-9a-z]+)'
+    _BASE_URL = 'http://www.cda.pl/'
     _TESTS = [{
         'url': 'http://www.cda.pl/video/5749950c',
         'md5': '6f844bf51b15f31fae165365707ae970',
@@ -21,6 +23,9 @@ class CDAIE(InfoExtractor):
             'ext': 'mp4',
             'height': 720,
             'title': 'Oto dlaczego przed zakrętem należy zwolnić.',
+            'description': 'md5:269ccd135d550da90d1662651fcb9772',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'average_rating': float,
             'duration': 39
         }
     }, {
@@ -30,6 +35,11 @@ class CDAIE(InfoExtractor):
             'id': '57413289',
             'ext': 'mp4',
             'title': 'Lądowanie na lotnisku na Maderze',
+            'description': 'md5:60d76b71186dcce4e0ba6d4bbdb13e1a',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': 'crash404',
+            'view_count': int,
+            'average_rating': float,
             'duration': 137
         }
     }, {
@@ -39,31 +49,55 @@ class CDAIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage('http://ebd.cda.pl/0x0/' + video_id, video_id)
+        self._set_cookie('cda.pl', 'cda.player', 'html5')
+        webpage = self._download_webpage(
+            self._BASE_URL + '/video/' + video_id, video_id)
 
         if 'Ten film jest dostępny dla użytkowników premium' in webpage:
             raise ExtractorError('This video is only available for premium users.', expected=True)
 
-        title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title')
-
         formats = []
 
+        uploader = self._search_regex(r'''(?x)
+            <(span|meta)[^>]+itemprop=(["\'])author\2[^>]*>
+            (?:<\1[^>]*>[^<]*</\1>|(?!</\1>)(?:.|\n))*?
+            <(span|meta)[^>]+itemprop=(["\'])name\4[^>]*>(?P<uploader>[^<]+)</\3>
+        ''', webpage, 'uploader', default=None, group='uploader')
+        view_count = self._search_regex(
+            r'Odsłony:(?:\s|&nbsp;)*([0-9]+)', webpage,
+            'view_count', default=None)
+        average_rating = self._search_regex(
+            r'<(?:span|meta)[^>]+itemprop=(["\'])ratingValue\1[^>]*>(?P<rating_value>[0-9.]+)',
+            webpage, 'rating', fatal=False, group='rating_value')
+
         info_dict = {
             'id': video_id,
-            'title': title,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'uploader': uploader,
+            'view_count': int_or_none(view_count),
+            'average_rating': float_or_none(average_rating),
+            'thumbnail': self._og_search_thumbnail(webpage),
             'formats': formats,
             'duration': None,
         }
 
         def extract_format(page, version):
-            unpacked = decode_packed_codes(page)
-            format_url = self._search_regex(
-                r"(?:file|url)\s*:\s*(\\?[\"'])(?P<url>http.+?)\1", unpacked,
-                '%s url' % version, fatal=False, group='url')
-            if not format_url:
+            json_str = self._search_regex(
+                r'player_data=(\\?["\'])(?P<player_data>.+?)\1', page,
+                '%s player_json' % version, fatal=False, group='player_data')
+            if not json_str:
+                return
+            player_data = self._parse_json(
+                json_str, '%s player_data' % version, fatal=False)
+            if not player_data:
+                return
+            video = player_data.get('video')
+            if not video or 'file' not in video:
+                self.report_warning('Unable to extract %s version information' % version)
                 return
             f = {
-                'url': format_url,
+                'url': video['file'],
             }
             m = re.search(
                 r'<a[^>]+data-quality="(?P<format_id>[^"]+)"[^>]+href="[^"]+"[^>]+class="[^"]*quality-btn-active[^"]*">(?P<height>[0-9]+)p',
@@ -75,9 +109,7 @@ class CDAIE(InfoExtractor):
                 })
             info_dict['formats'].append(f)
             if not info_dict['duration']:
-                info_dict['duration'] = parse_duration(self._search_regex(
-                    r"duration\s*:\s*(\\?[\"'])(?P<duration>.+?)\1",
-                    unpacked, 'duration', fatal=False, group='duration'))
+                info_dict['duration'] = parse_duration(video.get('duration'))
 
         extract_format(webpage, 'default')
 
@@ -85,7 +117,8 @@ class CDAIE(InfoExtractor):
                 r'<a[^>]+data-quality="[^"]+"[^>]+href="([^"]+)"[^>]+class="quality-btn"[^>]*>([0-9]+p)',
                 webpage):
             webpage = self._download_webpage(
-                href, video_id, 'Downloading %s version information' % resolution, fatal=False)
+                self._BASE_URL + href, video_id,
+                'Downloading %s version information' % resolution, fatal=False)
             if not webpage:
                 # Manually report warning because empty page is returned when
                 # invalid version is requested.

youtube_dl/extractor/comedycentral.py

@@ -6,7 +6,7 @@ from .common import InfoExtractor
 
 class ComedyCentralIE(MTVServicesInfoExtractor):
     _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
-        (video-clips|episodes|cc-studios|video-collections|full-episodes|shows)
+        (video-clips|episodes|cc-studios|video-collections|shows(?=/[^/]+/(?!full-episodes)))
         /(?P<title>.*)'''
     _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
 
@@ -27,6 +27,40 @@ class ComedyCentralIE(MTVServicesInfoExtractor):
     }]
 
 
+class ComedyCentralFullEpisodesIE(MTVServicesInfoExtractor):
+    _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
+        (?:full-episodes|shows(?=/[^/]+/full-episodes))
+        /(?P<id>[^?]+)'''
+    _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
+
+    _TESTS = [{
+        'url': 'http://www.cc.com/full-episodes/pv391a/the-daily-show-with-trevor-noah-november-28--2016---ryan-speedo-green-season-22-ep-22028',
+        'info_dict': {
+            'description': 'Donald Trump is accused of exploiting his president-elect status for personal gain, Cuban leader Fidel Castro dies, and Ryan Speedo Green discusses "Sing for Your Life."',
+            'title': 'November 28, 2016 - Ryan Speedo Green',
+        },
+        'playlist_count': 4,
+    }, {
+        'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+
+        feed_json = self._search_regex(r'var triforceManifestFeed\s*=\s*(\{.+?\});\n', webpage, 'triforce feeed')
+        feed = self._parse_json(feed_json, playlist_id)
+        zones = feed['manifest']['zones']
+
+        video_zone = zones['t2_lc_promo1']
+        feed = self._download_json(video_zone['feed'], playlist_id)
+        mgid = feed['result']['data']['id']
+
+        videos_info = self._get_videos_info(mgid)
+        return videos_info
+
+
 class ToshIE(MTVServicesInfoExtractor):
     IE_DESC = 'Tosh.0'
     _VALID_URL = r'^https?://tosh\.cc\.com/video-(?:clips|collections)/[^/]+/(?P<videotitle>[^/?#]+)'

youtube_dl/extractor/common.py

@@ -886,7 +886,7 @@ class InfoExtractor(object):
                         'url': e.get('contentUrl'),
                         'title': unescapeHTML(e.get('name')),
                         'description': unescapeHTML(e.get('description')),
-                        'thumbnail': e.get('thumbnailUrl'),
+                        'thumbnail': e.get('thumbnailUrl') or e.get('thumbnailURL'),
                         'duration': parse_duration(e.get('duration')),
                         'timestamp': unified_timestamp(e.get('uploadDate')),
                         'filesize': float_or_none(e.get('contentSize')),
@@ -1224,6 +1224,7 @@ class InfoExtractor(object):
                 'protocol': entry_protocol,
                 'preference': preference,
             }]
+        audio_groups = set()
         last_info = {}
         last_media = {}
         for line in m3u8_doc.splitlines():
@@ -1239,15 +1240,18 @@ class InfoExtractor(object):
                         for v in (media.get('GROUP-ID'), media.get('NAME')):
                             if v:
                                 format_id.append(v)
-                        formats.append({
+                        f = {
                             '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,
-                        })
+                        }
+                        if media_type == 'AUDIO':
+                            f['vcodec'] = 'none'
+                            audio_groups.add(media['GROUP-ID'])
+                        formats.append(f)
                     else:
                         # When there is no URI in EXT-X-MEDIA let this tag's
                         # data be used by regular URI lines below
@@ -1280,9 +1284,10 @@ class InfoExtractor(object):
                 }
                 resolution = last_info.get('RESOLUTION')
                 if resolution:
-                    width_str, height_str = resolution.split('x')
-                    f['width'] = int(width_str)
-                    f['height'] = int(height_str)
+                    mobj = re.search(r'(?P<width>\d+)[xX](?P<height>\d+)', resolution)
+                    if mobj:
+                        f['width'] = int(mobj.group('width'))
+                        f['height'] = int(mobj.group('height'))
                 # Unified Streaming Platform
                 mobj = re.search(
                     r'audio.*?(?:%3D|=)(\d+)(?:-video.*?(?:%3D|=)(\d+))?', f['url'])
@@ -1294,6 +1299,9 @@ class InfoExtractor(object):
                         'abr': abr,
                     })
                 f.update(parse_codecs(last_info.get('CODECS')))
+                if last_info.get('AUDIO') in audio_groups:
+                    # TODO: update acodec for for audio only formats with the same GROUP-ID
+                    f['acodec'] = 'none'
                 formats.append(f)
                 last_info = {}
                 last_media = {}
@@ -1702,7 +1710,7 @@ class InfoExtractor(object):
                                 representation_ms_info['fragments'] = [{
                                     'url': media_template % {
                                         'Number': segment_number,
-                                        'Bandwidth': representation_attrib.get('bandwidth'),
+                                        'Bandwidth': int_or_none(representation_attrib.get('bandwidth')),
                                     },
                                     'duration': segment_duration,
                                 } for segment_number in range(
@@ -1720,7 +1728,7 @@ class InfoExtractor(object):
                                 def add_segment_url():
                                     segment_url = media_template % {
                                         'Time': segment_time,
-                                        'Bandwidth': representation_attrib.get('bandwidth'),
+                                        'Bandwidth': int_or_none(representation_attrib.get('bandwidth')),
                                         'Number': segment_number,
                                     }
                                     representation_ms_info['fragments'].append({
@@ -1880,7 +1888,7 @@ class InfoExtractor(object):
                 })
         return formats
 
-    def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8'):
+    def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8', mpd_id=None):
         def absolute_url(video_url):
             return compat_urlparse.urljoin(base_url, video_url)
 
@@ -1897,11 +1905,16 @@ class InfoExtractor(object):
 
         def _media_formats(src, cur_media_type):
             full_url = absolute_url(src)
-            if determine_ext(full_url) == 'm3u8':
+            ext = determine_ext(full_url)
+            if ext == '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)
+            elif ext == 'mpd':
+                is_plain_url = False
+                formats = self._extract_mpd_formats(
+                    full_url, video_id, mpd_id=mpd_id)
             else:
                 is_plain_url = True
                 formats = [{

youtube_dl/extractor/crunchyroll.py

@@ -236,7 +236,7 @@ class CrunchyrollIE(CrunchyrollBaseIE):
         output += 'WrapStyle: %s\n' % sub_root.attrib['wrap_style']
         output += 'PlayResX: %s\n' % sub_root.attrib['play_res_x']
         output += 'PlayResY: %s\n' % sub_root.attrib['play_res_y']
-        output += """ScaledBorderAndShadow: yes
+        output += """ScaledBorderAndShadow: no
 
 [V4+ Styles]
 Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding

youtube_dl/extractor/ctvnews.py

@@ -8,7 +8,7 @@ from ..utils import orderedSet
 
 
 class CTVNewsIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?ctvnews\.ca/(?:video\?(?:clip|playlist|bin)Id=|.*?)(?P<id>[0-9.]+)'
+    _VALID_URL = r'https?://(?:.+?\.)?ctvnews\.ca/(?:video\?(?:clip|playlist|bin)Id=|.*?)(?P<id>[0-9.]+)'
     _TESTS = [{
         'url': 'http://www.ctvnews.ca/video?clipId=901995',
         'md5': '10deb320dc0ccb8d01d34d12fc2ea672',
@@ -40,6 +40,9 @@ class CTVNewsIE(InfoExtractor):
     }, {
         'url': 'http://www.ctvnews.ca/canadiens-send-p-k-subban-to-nashville-in-blockbuster-trade-1.2967231',
         'only_matching': True,
+    }, {
+        'url': 'http://vancouverisland.ctvnews.ca/video?clipId=761241',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/dplay.py

@@ -8,6 +8,7 @@ import time
 from .common import InfoExtractor
 from ..compat import compat_urlparse
 from ..utils import (
+    USER_AGENTS,
     int_or_none,
     update_url_query,
 )
@@ -102,10 +103,16 @@ class DPlayIE(InfoExtractor):
                     manifest_url, video_id, ext='mp4',
                     entry_protocol='m3u8_native', m3u8_id=protocol, fatal=False)
                 # Sometimes final URLs inside m3u8 are unsigned, let's fix this
-                # ourselves
+                # ourselves. Also fragments' URLs are only served signed for
+                # Safari user agent.
                 query = compat_urlparse.parse_qs(compat_urlparse.urlparse(manifest_url).query)
                 for m3u8_format in m3u8_formats:
-                    m3u8_format['url'] = update_url_query(m3u8_format['url'], query)
+                    m3u8_format.update({
+                        'url': update_url_query(m3u8_format['url'], query),
+                        'http_headers': {
+                            'User-Agent': USER_AGENTS['Safari'],
+                        },
+                    })
                 formats.extend(m3u8_formats)
             elif protocol == 'hds':
                 formats.extend(self._extract_f4m_formats(

youtube_dl/extractor/drtuber.py

@@ -10,8 +10,8 @@ from ..utils import (
 
 
 class DrTuberIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<display_id>[\w-]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?drtuber\.com/(?:video|embed)/(?P<id>\d+)(?:/(?P<display_id>[\w-]+))?'
+    _TESTS = [{
         'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
         'md5': '93e680cf2536ad0dfb7e74d94a89facd',
         'info_dict': {
@@ -25,20 +25,30 @@ class DrTuberIE(InfoExtractor):
             'thumbnail': 're:https?://.*\.jpg$',
             'age_limit': 18,
         }
-    }
+    }, {
+        'url': 'http://www.drtuber.com/embed/489939',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_urls(webpage):
+        return re.findall(
+            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?drtuber\.com/embed/\d+)',
+            webpage)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        display_id = mobj.group('display_id')
+        display_id = mobj.group('display_id') or video_id
 
-        webpage = self._download_webpage(url, display_id)
+        webpage = self._download_webpage(
+            'http://www.drtuber.com/video/%s' % video_id, display_id)
 
         video_url = self._html_search_regex(
             r'<source src="([^"]+)"', webpage, 'video URL')
 
         title = self._html_search_regex(
-            (r'class="title_watch"[^>]*><p>([^<]+)<',
+            (r'class="title_watch"[^>]*><(?:p|h\d+)[^>]*>([^<]+)<',
              r'<p[^>]+class="title_substrate">([^<]+)</p>',
              r'<title>([^<]+) - \d+'),
             webpage, 'title')

youtube_dl/extractor/eagleplatform.py

@@ -4,11 +4,13 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_HTTPError
+from ..compat import (
+    compat_HTTPError,
+    compat_str,
+)
 from ..utils import (
     ExtractorError,
     int_or_none,
-    url_basename,
 )
 
 
@@ -77,7 +79,7 @@ class EaglePlatformIE(InfoExtractor):
         if status != 200:
             raise ExtractorError(' '.join(response['errors']), expected=True)
 
-    def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata'):
+    def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata', *args, **kwargs):
         try:
             response = super(EaglePlatformIE, self)._download_json(url_or_request, video_id, note)
         except ExtractorError as ee:
@@ -116,29 +118,38 @@ class EaglePlatformIE(InfoExtractor):
 
         m3u8_url = self._get_video_url(secure_m3u8, video_id, 'Downloading m3u8 JSON')
         m3u8_formats = self._extract_m3u8_formats(
-            m3u8_url, video_id,
-            'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
+            m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
+            m3u8_id='hls', fatal=False)
         formats.extend(m3u8_formats)
 
-        mp4_url = self._get_video_url(
+        m3u8_formats_dict = {}
+        for f in m3u8_formats:
+            if f.get('height') is not None:
+                m3u8_formats_dict[f['height']] = f
+
+        mp4_data = self._download_json(
             # Secure mp4 URL is constructed according to Player.prototype.mp4 from
             # http://lentaru.media.eagleplatform.com/player/player.js
-            re.sub(r'm3u8|hlsvod|hls|f4m', 'mp4', secure_m3u8),
-            video_id, 'Downloading mp4 JSON')
-        mp4_url_basename = url_basename(mp4_url)
-        for m3u8_format in m3u8_formats:
-            mobj = re.search('/([^/]+)/index\.m3u8', m3u8_format['url'])
-            if mobj:
-                http_format = m3u8_format.copy()
-                video_url = mp4_url.replace(mp4_url_basename, mobj.group(1))
-                if not self._is_valid_url(video_url, video_id):
+            re.sub(r'm3u8|hlsvod|hls|f4m', 'mp4s', secure_m3u8),
+            video_id, 'Downloading mp4 JSON', fatal=False)
+        if mp4_data:
+            for format_id, format_url in mp4_data.get('data', {}).items():
+                if not isinstance(format_url, compat_str):
                     continue
-                http_format.update({
-                    'url': video_url,
-                    'format_id': m3u8_format['format_id'].replace('hls', 'http'),
-                    'protocol': 'http',
-                })
-                formats.append(http_format)
+                height = int_or_none(format_id)
+                if height is not None and m3u8_formats_dict.get(height):
+                    f = m3u8_formats_dict[height].copy()
+                    f.update({
+                        'format_id': f['format_id'].replace('hls', 'http'),
+                        'protocol': 'http',
+                    })
+                else:
+                    f = {
+                        'format_id': 'http-%s' % format_id,
+                        'height': int_or_none(format_id),
+                    }
+                f['url'] = format_url
+                formats.append(f)
 
         self._sort_formats(formats)
 

youtube_dl/extractor/espn.py

@@ -1,38 +1,117 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import remove_end
+from ..compat import compat_str
+from ..utils import (
+    determine_ext,
+    int_or_none,
+    unified_timestamp,
+)
 
 
 class ESPNIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:espn\.go|(?:www\.)?espn)\.com/(?:[^/]+/)*(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:espn\.go|(?:www\.)?espn)\.com/video/clip(?:\?.*?\bid=|/_/id/)(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://espn.go.com/video/clip?id=10365079',
-        'md5': '60e5d097a523e767d06479335d1bdc58',
         'info_dict': {
-            'id': 'FkYWtmazr6Ed8xmvILvKLWjd4QvYZpzG',
+            'id': '10365079',
             'ext': 'mp4',
             'title': '30 for 30 Shorts: Judging Jewell',
-            'description': None,
+            'description': 'md5:39370c2e016cb4ecf498ffe75bef7f0f',
+            'timestamp': 1390936111,
+            'upload_date': '20140128',
         },
         'params': {
             'skip_download': True,
         },
-        'add_ie': ['OoyalaExternal'],
     }, {
         # intl video, from http://www.espnfc.us/video/mls-highlights/150/video/2743663/must-see-moments-best-of-the-mls-season
         'url': 'http://espn.go.com/video/clip?id=2743663',
-        'md5': 'f4ac89b59afc7e2d7dbb049523df6768',
         'info_dict': {
-            'id': '50NDFkeTqRHB0nXBOK-RGdSG5YQPuxHg',
+            'id': '2743663',
             'ext': 'mp4',
             'title': 'Must-See Moments: Best of the MLS season',
+            'description': 'md5:4c2d7232beaea572632bec41004f0aeb',
+            'timestamp': 1449446454,
+            'upload_date': '20151207',
         },
         'params': {
             'skip_download': True,
         },
-        'add_ie': ['OoyalaExternal'],
+        'expected_warnings': ['Unable to download f4m manifest'],
     }, {
+        'url': 'http://www.espn.com/video/clip?id=10365079',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.espn.com/video/clip/_/id/17989860',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        clip = self._download_json(
+            'http://api-app.espn.com/v1/video/clips/%s' % video_id,
+            video_id)['videos'][0]
+
+        title = clip['headline']
+
+        format_urls = set()
+        formats = []
+
+        def traverse_source(source, base_source_id=None):
+            for source_id, source in source.items():
+                if isinstance(source, compat_str):
+                    extract_source(source, base_source_id)
+                elif isinstance(source, dict):
+                    traverse_source(
+                        source,
+                        '%s-%s' % (base_source_id, source_id)
+                        if base_source_id else source_id)
+
+        def extract_source(source_url, source_id=None):
+            if source_url in format_urls:
+                return
+            format_urls.add(source_url)
+            ext = determine_ext(source_url)
+            if ext == 'smil':
+                formats.extend(self._extract_smil_formats(
+                    source_url, video_id, fatal=False))
+            elif ext == 'f4m':
+                formats.extend(self._extract_f4m_formats(
+                    source_url, video_id, f4m_id=source_id, fatal=False))
+            elif ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    source_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id=source_id, fatal=False))
+            else:
+                formats.append({
+                    'url': source_url,
+                    'format_id': source_id,
+                })
+
+        traverse_source(clip['links']['source'])
+        self._sort_formats(formats)
+
+        description = clip.get('caption') or clip.get('description')
+        thumbnail = clip.get('thumbnail')
+        duration = int_or_none(clip.get('duration'))
+        timestamp = unified_timestamp(clip.get('originalPublishDate'))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+            'duration': duration,
+            'formats': formats,
+        }
+
+
+class ESPNArticleIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:espn\.go|(?:www\.)?espn)\.com/(?:[^/]+/)*(?P<id>[^/]+)'
+    _TESTS = [{
         'url': 'https://espn.go.com/video/iframe/twitter/?cms=espn&id=10365079',
         'only_matching': True,
     }, {
@@ -47,11 +126,12 @@ class ESPNIE(InfoExtractor):
     }, {
         'url': 'http://espn.go.com/nba/playoffs/2015/story/_/id/12887571/john-wall-washington-wizards-no-swelling-left-hand-wrist-game-5-return',
         'only_matching': True,
-    }, {
-        'url': 'http://www.espn.com/video/clip?id=10365079',
-        'only_matching': True,
     }]
 
+    @classmethod
+    def suitable(cls, url):
+        return False if ESPNIE.suitable(url) else super(ESPNArticleIE, cls).suitable(url)
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
@@ -61,23 +141,5 @@ class ESPNIE(InfoExtractor):
             r'class=(["\']).*?video-play-button.*?\1[^>]+data-id=["\'](?P<id>\d+)',
             webpage, 'video id', group='id')
 
-        cms = 'espn'
-        if 'data-source="intl"' in webpage:
-            cms = 'intl'
-        player_url = 'https://espn.go.com/video/iframe/twitter/?id=%s&cms=%s' % (video_id, cms)
-        player = self._download_webpage(
-            player_url, video_id)
-
-        pcode = self._search_regex(
-            r'["\']pcode=([^"\']+)["\']', player, 'pcode')
-
-        title = remove_end(
-            self._og_search_title(webpage),
-            '- ESPN Video').strip()
-
-        return {
-            '_type': 'url_transparent',
-            'url': 'ooyalaexternal:%s:%s:%s' % (cms, video_id, pcode),
-            'ie_key': 'OoyalaExternal',
-            'title': title,
-        }
+        return self.url_result(
+            'http://espn.go.com/video/clip?id=%s' % video_id, ESPNIE.ie_key())

youtube_dl/extractor/extractors.py

@@ -150,6 +150,7 @@ from .cbsnews import (
 )
 from .cbssports import CBSSportsIE
 from .ccc import CCCIE
+from .ccma import CCMAIE
 from .cctv import CCTVIE
 from .cda import CDAIE
 from .ceskatelevize import CeskaTelevizeIE
@@ -180,6 +181,7 @@ from .cnn import (
 from .coub import CoubIE
 from .collegerama import CollegeRamaIE
 from .comedycentral import (
+    ComedyCentralFullEpisodesIE,
     ComedyCentralIE,
     ComedyCentralShortnameIE,
     ComedyCentralTVIE,
@@ -267,7 +269,10 @@ from .engadget import EngadgetIE
 from .eporner import EpornerIE
 from .eroprofile import EroProfileIE
 from .escapist import EscapistIE
-from .espn import ESPNIE
+from .espn import (
+    ESPNIE,
+    ESPNArticleIE,
+)
 from .esri import EsriVideoIE
 from .europa import EuropaIE
 from .everyonesmixtape import EveryonesMixtapeIE
@@ -296,6 +301,7 @@ from .footyroom import FootyRoomIE
 from .formula1 import Formula1IE
 from .fourtube import FourTubeIE
 from .fox import FOXIE
+from .fox9 import FOX9IE
 from .foxgay import FoxgayIE
 from .foxnews import (
     FoxNewsIE,
@@ -441,7 +447,10 @@ from .kuwo import (
     KuwoMvIE,
 )
 from .la7 import LA7IE
-from .laola1tv import Laola1TvIE
+from .laola1tv import (
+    Laola1TvEmbedIE,
+    Laola1TvIE,
+)
 from .lci import LCIIE
 from .lcp import (
     LcpPlayIE,
@@ -493,6 +502,8 @@ from .mangomolo import (
 )
 from .matchtv import MatchTVIE
 from .mdr import MDRIE
+from .meipai import MeipaiIE
+from .melonvod import MelonVODIE
 from .meta import METAIE
 from .metacafe import MetacafeIE
 from .metacritic import MetacriticIE
@@ -656,6 +667,7 @@ from .nzz import NZZIE
 from .odatv import OdaTVIE
 from .odnoklassniki import OdnoklassnikiIE
 from .oktoberfesttv import OktoberfestTVIE
+from .ondemandkorea import OnDemandKoreaIE
 from .onet import (
     OnetIE,
     OnetChannelIE,
@@ -800,7 +812,6 @@ from .scivee import SciVeeIE
 from .screencast import ScreencastIE
 from .screencastomatic import ScreencastOMaticIE
 from .screenjunkies import ScreenJunkiesIE
-from .screenwavemedia import ScreenwaveMediaIE, TeamFourIE
 from .seeker import SeekerIE
 from .senateisvp import SenateISVPIE
 from .sendtonews import SendtoNewsIE
@@ -893,6 +904,7 @@ from .teachertube import (
 )
 from .teachingchannel import TeachingChannelIE
 from .teamcoco import TeamcocoIE
+from .teamfourstar import TeamFourStarIE
 from .techtalks import TechTalksIE
 from .ted import TEDIE
 from .tele13 import Tele13IE
@@ -961,6 +973,10 @@ from .tv2 import (
 )
 from .tv3 import TV3IE
 from .tv4 import TV4IE
+from .tvanouvelles import (
+    TVANouvellesIE,
+    TVANouvellesArticleIE,
+)
 from .tvc import (
     TVCIE,
     TVCArticleIE,
@@ -989,7 +1005,10 @@ from .twitch import (
     TwitchChapterIE,
     TwitchVodIE,
     TwitchProfileIE,
+    TwitchAllVideosIE,
+    TwitchUploadsIE,
     TwitchPastBroadcastsIE,
+    TwitchHighlightsIE,
     TwitchStreamIE,
     TwitchClipsIE,
 )
@@ -1100,7 +1119,9 @@ from .vporn import VpornIE
 from .vrt import VRTIE
 from .vube import VubeIE
 from .vuclip import VuClipIE
+from .vvvvid import VVVVIDIE
 from .vyborymos import VyboryMosIE
+from .vzaar import VzaarIE
 from .walla import WallaIE
 from .washingtonpost import (
     WashingtonPostIE,
@@ -1112,6 +1133,10 @@ from .wdr import (
     WDRIE,
     WDRMobileIE,
 )
+from .webcaster import (
+    WebcasterIE,
+    WebcasterFeedIE,
+)
 from .webofstories import (
     WebOfStoriesIE,
     WebOfStoriesPlaylistIE,

youtube_dl/extractor/facebook.py

@@ -27,7 +27,7 @@ class FacebookIE(InfoExtractor):
     _VALID_URL = r'''(?x)
                 (?:
                     https?://
-                        (?:[\w-]+\.)?facebook\.com/
+                        (?:[\w-]+\.)?(?:facebook\.com|facebookcorewwwi\.onion)/
                         (?:[^#]*?\#!/)?
                         (?:
                             (?:
@@ -150,6 +150,9 @@ class FacebookIE(InfoExtractor):
     }, {
         'url': 'https://zh-hk.facebook.com/peoplespower/videos/1135894589806027/',
         'only_matching': True,
+    }, {
+        'url': 'https://www.facebookcorewwwi.onion/video.php?v=274175099429670',
+        'only_matching': True,
     }]
 
     @staticmethod
@@ -244,8 +247,10 @@ class FacebookIE(InfoExtractor):
             r'handleServerJS\(({.+})(?:\);|,")', webpage, 'server js data', default='{}'), video_id)
         for item in server_js_data.get('instances', []):
             if item[1][0] == 'VideoConfig':
-                video_data = item[2][0]['videoData']
-                break
+                video_item = item[2][0]
+                if video_item.get('video_id') == video_id:
+                    video_data = video_item['videoData']
+                    break
 
         if not video_data:
             if not fatal_if_no_video:
@@ -255,6 +260,8 @@ class FacebookIE(InfoExtractor):
                 raise ExtractorError(
                     'The video is not available, Facebook said: "%s"' % m_msg.group(1),
                     expected=True)
+            elif '>You must log in to continue' in webpage:
+                self.raise_login_required()
             else:
                 raise ExtractorError('Cannot parse data')
 

youtube_dl/extractor/firsttv.py

@@ -2,7 +2,10 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import compat_urlparse
+from ..compat import (
+    compat_str,
+    compat_urlparse,
+)
 from ..utils import (
     int_or_none,
     qualities,
@@ -22,8 +25,7 @@ class FirstTVIE(InfoExtractor):
         'info_dict': {
             'id': '40049',
             'ext': 'mp4',
-            'title': 'Гость Людмила Сенчина. Наедине со всеми. Выпуск от 12.02.2015',
-            'description': 'md5:36a39c1d19618fec57d12efe212a8370',
+            'title': 'Гость Людмила Сенчина. Наедине со всеми. Выпуск от 12.02.2015',
             'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
             'upload_date': '20150212',
             'duration': 2694,
@@ -34,8 +36,7 @@ class FirstTVIE(InfoExtractor):
         'info_dict': {
             'id': '364746',
             'ext': 'mp4',
-            'title': 'Весенняя аллергия. Доброе утро. Фрагмент выпуска от 07.04.2016',
-            'description': 'md5:a242eea0031fd180a4497d52640a9572',
+            'title': 'Весенняя аллергия. Доброе утро. Фрагмент выпуска от 07.04.2016',
             'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
             'upload_date': '20160407',
             'duration': 179,
@@ -44,6 +45,17 @@ class FirstTVIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+    }, {
+        'url': 'http://www.1tv.ru/news/issue/2016-12-01/14:00',
+        'info_dict': {
+            'id': '14:00',
+            'title': 'Выпуск новостей в 14:00   1 декабря 2016 года. Новости. Первый канал',
+            'description': 'md5:2e921b948f8c1ff93901da78ebdb1dfd',
+        },
+        'playlist_count': 13,
+    }, {
+        'url': 'http://www.1tv.ru/shows/tochvtoch-supersezon/vystupleniya/evgeniy-dyatlov-vladimir-vysockiy-koni-priveredlivye-toch-v-toch-supersezon-fragment-vypuska-ot-06-11-2016',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -51,43 +63,66 @@ class FirstTVIE(InfoExtractor):
 
         webpage = self._download_webpage(url, display_id)
         playlist_url = compat_urlparse.urljoin(url, self._search_regex(
-            r'data-playlist-url="([^"]+)', webpage, 'playlist url'))
+            r'data-playlist-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
+            webpage, 'playlist url', group='url'))
 
-        item = self._download_json(playlist_url, display_id)[0]
-        video_id = item['id']
-        quality = qualities(('ld', 'sd', 'hd', ))
-        formats = []
-        for f in item.get('mbr', []):
-            src = f.get('src')
-            if not src:
-                continue
-            fname = f.get('name')
-            formats.append({
-                'url': src,
-                'format_id': fname,
-                'quality': quality(fname),
+        parsed_url = compat_urlparse.urlparse(playlist_url)
+        qs = compat_urlparse.parse_qs(parsed_url.query)
+        item_ids = qs.get('videos_ids[]') or qs.get('news_ids[]')
+
+        items = self._download_json(playlist_url, display_id)
+
+        if item_ids:
+            items = [
+                item for item in items
+                if item.get('uid') and compat_str(item['uid']) in item_ids]
+        else:
+            items = [items[0]]
+
+        entries = []
+        QUALITIES = ('ld', 'sd', 'hd', )
+
+        for item in items:
+            title = item['title']
+            quality = qualities(QUALITIES)
+            formats = []
+            for f in item.get('mbr', []):
+                src = f.get('src')
+                if not src or not isinstance(src, compat_str):
+                    continue
+                tbr = int_or_none(self._search_regex(
+                    r'_(\d{3,})\.mp4', src, 'tbr', default=None))
+                formats.append({
+                    'url': src,
+                    'format_id': f.get('name'),
+                    'tbr': tbr,
+                    'quality': quality(f.get('name')),
+                })
+            self._sort_formats(formats)
+
+            thumbnail = item.get('poster') or self._og_search_thumbnail(webpage)
+            duration = int_or_none(item.get('duration') or self._html_search_meta(
+                'video:duration', webpage, 'video duration', fatal=False))
+            upload_date = unified_strdate(self._html_search_meta(
+                'ya:ovs:upload_date', webpage, 'upload date', default=None))
+
+            entries.append({
+                'id': compat_str(item.get('id') or item['uid']),
+                'thumbnail': thumbnail,
+                'title': title,
+                'upload_date': upload_date,
+                'duration': int_or_none(duration),
+                'formats': formats
             })
-        self._sort_formats(formats)
 
         title = self._html_search_regex(
             (r'<div class="tv_translation">\s*<h1><a href="[^"]+">([^<]*)</a>',
              r"'title'\s*:\s*'([^']+)'"),
-            webpage, 'title', default=None) or item['title']
+            webpage, 'title', default=None) or self._og_search_title(
+            webpage, default=None)
         description = self._html_search_regex(
             r'<div class="descr">\s*<div>&nbsp;</div>\s*<p>([^<]*)</p></div>',
             webpage, 'description', default=None) or self._html_search_meta(
-            'description', webpage, 'description')
-        duration = int_or_none(self._html_search_meta(
-            'video:duration', webpage, 'video duration', fatal=False))
-        upload_date = unified_strdate(self._html_search_meta(
-            'ya:ovs:upload_date', webpage, 'upload date', fatal=False))
+            'description', webpage, 'description', default=None)
 
-        return {
-            'id': video_id,
-            'thumbnail': item.get('poster') or self._og_search_thumbnail(webpage),
-            'title': title,
-            'description': description,
-            'upload_date': upload_date,
-            'duration': int_or_none(duration),
-            'formats': formats
-        }
+        return self.playlist_result(entries, display_id, title, description)

youtube_dl/extractor/fox9.py

@@ -0,0 +1,43 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .anvato import AnvatoIE
+from ..utils import js_to_json
+
+
+class FOX9IE(AnvatoIE):
+    _VALID_URL = r'https?://(?:www\.)?fox9\.com/(?:[^/]+/)+(?P<id>\d+)-story'
+    _TESTS = [{
+        'url': 'http://www.fox9.com/news/215123287-story',
+        'md5': 'd6e1b2572c3bab8a849c9103615dd243',
+        'info_dict': {
+            'id': '314473',
+            'ext': 'mp4',
+            'title': 'Bear climbs tree in downtown Duluth',
+            'description': 'md5:6a36bfb5073a411758a752455408ac90',
+            'duration': 51,
+            'timestamp': 1478123580,
+            'upload_date': '20161102',
+            'uploader': 'EPFOX',
+            'categories': ['News', 'Sports'],
+            'tags': ['news', 'video'],
+        },
+    }, {
+        'url': 'http://www.fox9.com/news/investigators/214070684-story',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_id = self._parse_json(
+            self._search_regex(
+                r'AnvatoPlaylist\s*\(\s*(\[.+?\])\s*\)\s*;',
+                webpage, 'anvato playlist'),
+            video_id, transform_source=js_to_json)[0]['video']
+
+        return self._get_anvato_videos(
+            'anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b',
+            video_id)

youtube_dl/extractor/franceculture.py

@@ -29,7 +29,7 @@ class FranceCultureIE(InfoExtractor):
         webpage = self._download_webpage(url, display_id)
 
         video_url = self._search_regex(
-            r'(?s)<div[^>]+class="[^"]*?title-zone-diffusion[^"]*?"[^>]*>.*?<a[^>]+href="([^"]+)"',
+            r'(?s)<div[^>]+class="[^"]*?title-zone-diffusion[^"]*?"[^>]*>.*?<button[^>]+data-asset-source="([^"]+)"',
             webpage, 'video path')
 
         title = self._og_search_title(webpage)
@@ -38,7 +38,7 @@ class FranceCultureIE(InfoExtractor):
             '(?s)<div[^>]+class="date"[^>]*>.*?<span[^>]+class="inner"[^>]*>([^<]+)<',
             webpage, 'upload date', fatal=False))
         thumbnail = self._search_regex(
-            r'(?s)<figure[^>]+itemtype="https://schema.org/ImageObject"[^>]*>.*?<img[^>]+data-pagespeed-(?:lazy|high-res)-src="([^"]+)"',
+            r'(?s)<figure[^>]+itemtype="https://schema.org/ImageObject"[^>]*>.*?<img[^>]+data-dejavu-src="([^"]+)"',
             webpage, 'thumbnail', fatal=False)
         uploader = self._html_search_regex(
             r'(?s)<div id="emission".*?<span class="author">(.*?)</span>',

youtube_dl/extractor/funnyordie.py

@@ -28,6 +28,9 @@ class FunnyOrDieIE(InfoExtractor):
             'description': 'Please use this to sell something.  www.jonlajoie.com',
             'thumbnail': 're:^http:.*\.jpg$',
         },
+        'params': {
+            'skip_download': True,
+        },
     }, {
         'url': 'http://www.funnyordie.com/articles/ebf5e34fc8/10-hours-of-walking-in-nyc-as-a-man',
         'only_matching': True,
@@ -51,19 +54,45 @@ class FunnyOrDieIE(InfoExtractor):
 
         formats = []
 
-        formats.extend(self._extract_m3u8_formats(
-            m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
+        m3u8_formats = self._extract_m3u8_formats(
+            m3u8_url, video_id, 'mp4', 'm3u8_native',
+            m3u8_id='hls', fatal=False)
+        source_formats = list(filter(
+            lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple',
+            m3u8_formats))
 
-        bitrates = [int(bitrate) for bitrate in re.findall(r'[,/]v(\d+)[,/]', m3u8_url)]
+        bitrates = [int(bitrate) for bitrate in re.findall(r'[,/]v(\d+)(?=[,/])', m3u8_url)]
         bitrates.sort()
 
-        for bitrate in bitrates:
-            for link in links:
-                formats.append({
-                    'url': self._proto_relative_url('%s%d.%s' % (link[0], bitrate, link[1])),
-                    'format_id': '%s-%d' % (link[1], bitrate),
-                    'vbr': bitrate,
-                })
+        if source_formats:
+            self._sort_formats(source_formats)
+
+        for bitrate, f in zip(bitrates, source_formats or [{}] * len(bitrates)):
+            for path, ext in links:
+                ff = f.copy()
+                if ff:
+                    if ext != 'mp4':
+                        ff = dict(
+                            [(k, v) for k, v in ff.items()
+                             if k in ('height', 'width', 'format_id')])
+                    ff.update({
+                        'format_id': ff['format_id'].replace('hls', ext),
+                        'ext': ext,
+                        'protocol': 'http',
+                    })
+                else:
+                    ff.update({
+                        'format_id': '%s-%d' % (ext, bitrate),
+                        'vbr': bitrate,
+                    })
+                ff['url'] = self._proto_relative_url(
+                    '%s%d.%s' % (path, bitrate, ext))
+                formats.append(ff)
+        self._check_formats(formats, video_id)
+
+        formats.extend(m3u8_formats)
+        self._sort_formats(
+            formats, field_preference=('height', 'width', 'tbr', 'format_id'))
 
         subtitles = {}
         for src, src_lang in re.findall(r'<track kind="captions" src="([^"]+)" srclang="([^"]+)"', webpage):

youtube_dl/extractor/fusion.py

@@ -29,7 +29,7 @@ class FusionIE(InfoExtractor):
         webpage = self._download_webpage(url, display_id)
 
         ooyala_code = self._search_regex(
-            r'data-video-id=(["\'])(?P<code>.+?)\1',
+            r'data-ooyala-id=(["\'])(?P<code>(?:(?!\1).)+)\1',
             webpage, 'ooyala code', group='code')
 
         return OoyalaIE._build_url_result(ooyala_code)

youtube_dl/extractor/generic.py

@@ -47,6 +47,8 @@ from .svt import SVTIE
 from .pornhub import PornHubIE
 from .xhamster import XHamsterEmbedIE
 from .tnaflix import TNAFlixNetworkEmbedIE
+from .drtuber import DrTuberIE
+from .redtube import RedTubeIE
 from .vimeo import VimeoIE
 from .dailymotion import (
     DailymotionIE,
@@ -54,10 +56,10 @@ from .dailymotion import (
 )
 from .onionstudios import OnionStudiosIE
 from .viewlift import ViewLiftEmbedIE
-from .screenwavemedia import ScreenwaveMediaIE
 from .mtv import MTVServicesEmbeddedIE
 from .pladform import PladformIE
 from .videomore import VideomoreIE
+from .webcaster import WebcasterFeedIE
 from .googledrive import GoogleDriveIE
 from .jwplatform import JWPlatformIE
 from .digiteka import DigitekaIE
@@ -1187,16 +1189,6 @@ class GenericIE(InfoExtractor):
                 'duration': 248.667,
             },
         },
-        # ScreenwaveMedia embed
-        {
-            'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
-            'md5': '24ace5baba0d35d55c6810b51f34e9e0',
-            'info_dict': {
-                'id': 'cinemasnob-55d26273809dd',
-                'ext': 'mp4',
-                'title': 'cinemasnob',
-            },
-        },
         # BrightcoveInPageEmbed embed
         {
             'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
@@ -1634,6 +1626,10 @@ class GenericIE(InfoExtractor):
             doc = compat_etree_fromstring(webpage.encode('utf-8'))
             if doc.tag == 'rss':
                 return self._extract_rss(url, video_id, doc)
+            elif doc.tag == 'SmoothStreamingMedia':
+                info_dict['formats'] = self._parse_ism_formats(doc, url)
+                self._sort_formats(info_dict['formats'])
+                return info_dict
             elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
                 smil = self._parse_smil(doc, url, video_id)
                 self._sort_formats(smil['formats'])
@@ -1977,11 +1973,6 @@ class GenericIE(InfoExtractor):
         if sportbox_urls:
             return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
 
-        # Look for embedded PornHub player
-        pornhub_url = PornHubIE._extract_url(webpage)
-        if pornhub_url:
-            return self.url_result(pornhub_url, 'PornHub')
-
         # Look for embedded XHamster player
         xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
         if xhamster_urls:
@@ -1992,6 +1983,21 @@ class GenericIE(InfoExtractor):
         if tnaflix_urls:
             return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
 
+        # Look for embedded PornHub player
+        pornhub_urls = PornHubIE._extract_urls(webpage)
+        if pornhub_urls:
+            return _playlist_from_matches(pornhub_urls, ie=PornHubIE.ie_key())
+
+        # Look for embedded DrTuber player
+        drtuber_urls = DrTuberIE._extract_urls(webpage)
+        if drtuber_urls:
+            return _playlist_from_matches(drtuber_urls, ie=DrTuberIE.ie_key())
+
+        # Look for embedded RedTube player
+        redtube_urls = RedTubeIE._extract_urls(webpage)
+        if redtube_urls:
+            return _playlist_from_matches(redtube_urls, ie=RedTubeIE.ie_key())
+
         # Look for embedded Tvigle player
         mobj = re.search(
             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
@@ -2124,6 +2130,11 @@ class GenericIE(InfoExtractor):
         if videomore_url:
             return self.url_result(videomore_url)
 
+        # Look for Webcaster embeds
+        webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
+        if webcaster_url:
+            return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
+
         # Look for Playwire embeds
         mobj = re.search(
             r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
@@ -2190,11 +2201,6 @@ class GenericIE(InfoExtractor):
         if jwplatform_url:
             return self.url_result(jwplatform_url, 'JWPlatform')
 
-        # Look for ScreenwaveMedia embeds
-        mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
-        if mobj is not None:
-            return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
-
         # Look for Digiteka embeds
         digiteka_url = DigitekaIE._extract_url(webpage)
         if digiteka_url:
@@ -2216,6 +2222,16 @@ class GenericIE(InfoExtractor):
             return self.url_result('limelight:%s:%s' % (
                 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
 
+        mobj = re.search(
+            r'''(?sx)
+                <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
+                    <param[^>]+
+                        name=(["\'])flashVars\2[^>]+
+                        value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
+            ''', webpage)
+        if mobj:
+            return self.url_result('limelight:media:%s' % mobj.group('id'))
+
         # Look for AdobeTVVideo embeds
         mobj = re.search(
             r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
@@ -2449,6 +2465,21 @@ class GenericIE(InfoExtractor):
                 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
             elif ext == 'f4m':
                 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
+            elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
+                # Just matching .ism/manifest is not enough to be reliably sure
+                # whether it's actually an ISM manifest or some other streaming
+                # manifest since there are various streaming URL formats
+                # possible (see [1]) as well as some other shenanigans like
+                # .smil/manifest URLs that actually serve an ISM (see [2]) and
+                # so on.
+                # Thus the most reasonable way to solve this is to delegate
+                # to generic extractor in order to look into the contents of
+                # the manifest itself.
+                # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
+                # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
+                entry_info_dict = self.url_result(
+                    smuggle_url(video_url, {'to_generic': True}),
+                    GenericIE.ie_key())
             else:
                 entry_info_dict['url'] = video_url
 

youtube_dl/extractor/hellporno.py

@@ -6,12 +6,13 @@ from .common import InfoExtractor
 from ..utils import (
     js_to_json,
     remove_end,
+    determine_ext,
 )
 
 
 class HellPornoIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?hellporno\.com/videos/(?P<id>[^/]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?hellporno\.(?:com/videos|net/v)/(?P<id>[^/]+)'
+    _TESTS = [{
         'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/',
         'md5': '1fee339c610d2049699ef2aa699439f1',
         'info_dict': {
@@ -22,7 +23,10 @@ class HellPornoIE(InfoExtractor):
             'thumbnail': 're:https?://.*\.jpg$',
             'age_limit': 18,
         }
-    }
+    }, {
+        'url': 'http://hellporno.net/v/186271/',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
@@ -38,7 +42,7 @@ class HellPornoIE(InfoExtractor):
 
         video_id = flashvars.get('video_id')
         thumbnail = flashvars.get('preview_url')
-        ext = flashvars.get('postfix', '.mp4')[1:]
+        ext = determine_ext(flashvars.get('postfix'), 'mp4')
 
         formats = []
         for video_url_key in ['video_url', 'video_alt_url']:

youtube_dl/extractor/jwplatform.py

@@ -11,6 +11,7 @@ from ..utils import (
     int_or_none,
     js_to_json,
     mimetype2ext,
+    urljoin,
 )
 
 
@@ -110,10 +111,14 @@ class JWPlatformBaseIE(InfoExtractor):
             tracks = video_data.get('tracks')
             if tracks and isinstance(tracks, list):
                 for track in tracks:
-                    if track.get('file') and track.get('kind') == 'captions':
-                        subtitles.setdefault(track.get('label') or 'en', []).append({
-                            'url': self._proto_relative_url(track['file'])
-                        })
+                    if track.get('kind') != 'captions':
+                        continue
+                    track_url = urljoin(base_url, track.get('file'))
+                    if not track_url:
+                        continue
+                    subtitles.setdefault(track.get('label') or 'en', []).append({
+                        'url': self._proto_relative_url(track_url)
+                    })
 
             entries.append({
                 'id': this_video_id,
@@ -121,7 +126,7 @@ class JWPlatformBaseIE(InfoExtractor):
                 'description': video_data.get('description'),
                 'thumbnail': self._proto_relative_url(video_data.get('image')),
                 'timestamp': int_or_none(video_data.get('pubdate')),
-                'duration': float_or_none(jwplayer_data.get('duration')),
+                'duration': float_or_none(jwplayer_data.get('duration') or video_data.get('duration')),
                 'subtitles': subtitles,
                 'formats': formats,
             })

youtube_dl/extractor/laola1tv.py

@@ -1,25 +1,81 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse_urlencode,
-    compat_urlparse,
-)
 from ..utils import (
     ExtractorError,
-    sanitized_Request,
     unified_strdate,
     urlencode_postdata,
     xpath_element,
     xpath_text,
+    urljoin,
 )
 
 
+class Laola1TvEmbedIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?laola1\.tv/titanplayer\.php\?.*?\bvideoid=(?P<id>\d+)'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        flash_vars = self._search_regex(
+            r'(?s)flashvars\s*=\s*({.+?});', webpage, 'flash vars')
+        get_flashvar = lambda x: self._search_regex(r'%s\s*:\s*"([^"]+)"' % x, flash_vars, x)
+
+        hd_doc = self._download_xml(
+            'http://www.laola1.tv/server/hd_video.php', video_id, query={
+                'play': get_flashvar('streamid'),
+                'partner': get_flashvar('partnerid'),
+                'portal': get_flashvar('portalid'),
+                'lang': get_flashvar('sprache'),
+                'v5ident': '',
+            })
+
+        _v = lambda x, **k: xpath_text(hd_doc, './/video/' + x, **k)
+        title = _v('title', fatal=True)
+
+        data_abo = urlencode_postdata(
+            dict((i, v) for i, v in enumerate(_v('req_liga_abos').split(','))))
+        token_url = self._download_json(
+            'https://club.laola1.tv/sp/laola1/api/v3/user/session/premium/player/stream-access',
+            video_id, query={
+                'videoId': _v('id'),
+                'target': self._search_regex(r'vs_target = (\d+);', webpage, 'vs target'),
+                'label': _v('label'),
+                'area': _v('area'),
+            }, data=data_abo)['data']['stream-access'][0]
+        token_doc = self._download_xml(
+            token_url, video_id, 'Downloading token',
+            headers=self.geo_verification_headers())
+
+        token_attrib = xpath_element(token_doc, './/token').attrib
+
+        if token_attrib['status'] != '0':
+            raise ExtractorError(
+                'Token error: %s' % token_attrib['comment'], expected=True)
+
+        formats = self._extract_akamai_formats(
+            '%s?hdnea=%s' % (token_attrib['url'], token_attrib['auth']),
+            video_id)
+        self._sort_formats(formats)
+
+        categories_str = _v('meta_sports')
+        categories = categories_str.split(',') if categories_str else []
+        is_live = _v('islive') == 'true'
+
+        return {
+            'id': video_id,
+            'title': self._live_title(title) if is_live else title,
+            'upload_date': unified_strdate(_v('time_date')),
+            'uploader': _v('meta_organisation'),
+            'categories': categories,
+            'is_live': is_live,
+            'formats': formats,
+        }
+
+
 class Laola1TvIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?laola1\.tv/(?P<lang>[a-z]+)-(?P<portal>[a-z]+)/(?P<kind>[^/]+)/(?P<slug>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?laola1\.tv/[a-z]+-[a-z]+/[^/]+/(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie/227883.html',
         'info_dict': {
@@ -67,85 +123,20 @@ class Laola1TvIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        display_id = mobj.group('slug')
-        kind = mobj.group('kind')
-        lang = mobj.group('lang')
-        portal = mobj.group('portal')
+        display_id = self._match_id(url)
 
         webpage = self._download_webpage(url, display_id)
 
         if 'Dieser Livestream ist bereits beendet.' in webpage:
             raise ExtractorError('This live stream has already finished.', expected=True)
 
-        iframe_url = self._search_regex(
+        iframe_url = urljoin(url, self._search_regex(
             r'<iframe[^>]*?id="videoplayer"[^>]*?src="([^"]+)"',
-            webpage, 'iframe url')
-
-        video_id = self._search_regex(
-            r'videoid=(\d+)', iframe_url, 'video id')
-
-        iframe = self._download_webpage(compat_urlparse.urljoin(
-            url, iframe_url), display_id, 'Downloading iframe')
-
-        partner_id = self._search_regex(
-            r'partnerid\s*:\s*(["\'])(?P<partner_id>.+?)\1',
-            iframe, 'partner id', group='partner_id')
-
-        hd_doc = self._download_xml(
-            'http://www.laola1.tv/server/hd_video.php?%s'
-            % compat_urllib_parse_urlencode({
-                'play': video_id,
-                'partner': partner_id,
-                'portal': portal,
-                'lang': lang,
-                'v5ident': '',
-            }), display_id)
-
-        _v = lambda x, **k: xpath_text(hd_doc, './/video/' + x, **k)
-        title = _v('title', fatal=True)
-
-        VS_TARGETS = {
-            'video': '2',
-            'livestream': '17',
-        }
-
-        req = sanitized_Request(
-            'https://club.laola1.tv/sp/laola1/api/v3/user/session/premium/player/stream-access?%s' %
-            compat_urllib_parse_urlencode({
-                'videoId': video_id,
-                'target': VS_TARGETS.get(kind, '2'),
-                'label': _v('label'),
-                'area': _v('area'),
-            }),
-            urlencode_postdata(
-                dict((i, v) for i, v in enumerate(_v('req_liga_abos').split(',')))))
-
-        token_url = self._download_json(req, display_id)['data']['stream-access'][0]
-        token_doc = self._download_xml(token_url, display_id, 'Downloading token')
-
-        token_attrib = xpath_element(token_doc, './/token').attrib
-        token_auth = token_attrib['auth']
-
-        if token_auth in ('blocked', 'restricted', 'error'):
-            raise ExtractorError(
-                'Token error: %s' % token_attrib['comment'], expected=True)
-
-        formats = self._extract_f4m_formats(
-            '%s?hdnea=%s&hdcore=3.2.0' % (token_attrib['url'], token_auth),
-            video_id, f4m_id='hds')
-        self._sort_formats(formats)
-
-        categories_str = _v('meta_sports')
-        categories = categories_str.split(',') if categories_str else []
+            webpage, 'iframe url'))
 
         return {
-            'id': video_id,
+            '_type': 'url',
             'display_id': display_id,
-            'title': title,
-            'upload_date': unified_strdate(_v('time_date')),
-            'uploader': _v('meta_organisation'),
-            'categories': categories,
-            'is_live': _v('islive') == 'true',
-            'formats': formats,
+            'url': iframe_url,
+            'ie_key': 'Laola1TvEmbed',
         }

youtube_dl/extractor/liveleak.py

@@ -54,6 +54,22 @@ class LiveLeakIE(InfoExtractor):
             'title': 'Crazy Hungarian tourist films close call waterspout in Croatia',
             'thumbnail': 're:^https?://.*\.jpg$'
         }
+    }, {
+        # Covers https://github.com/rg3/youtube-dl/pull/10664#issuecomment-247439521
+        'url': 'http://m.liveleak.com/view?i=763_1473349649',
+        'add_ie': ['Youtube'],
+        'info_dict': {
+            'id': '763_1473349649',
+            'ext': 'mp4',
+            'title': 'Reporters and public officials ignore epidemic of black on asian violence in Sacramento | Colin Flaherty',
+            'description': 'Colin being the warrior he is and showing the injustice Asians in Sacramento are being subjected to.',
+            'uploader': 'Ziz',
+            'upload_date': '20160908',
+            'uploader_id': 'UCEbta5E_jqlZmEJsriTEtnw'
+        },
+        'params': {
+            'skip_download': True,
+        },
     }]
 
     @staticmethod
@@ -87,7 +103,7 @@ class LiveLeakIE(InfoExtractor):
             else:
                 # Maybe an embed?
                 embed_url = self._search_regex(
-                    r'<iframe[^>]+src="(http://www.prochan.com/embed\?[^"]+)"',
+                    r'<iframe[^>]+src="(https?://(?:www\.)?(?:prochan|youtube)\.com/embed[^"]+)"',
                     webpage, 'embed URL')
                 return {
                     '_type': 'url_transparent',
@@ -107,6 +123,7 @@ class LiveLeakIE(InfoExtractor):
             'format_note': s.get('label'),
             'url': s['file'],
         } for i, s in enumerate(sources)]
+
         for i, s in enumerate(sources):
             # Removing '.h264_*.mp4' gives the raw video, which is essentially
             # the same video without the LiveLeak logo at the top (see

youtube_dl/extractor/meipai.py

@@ -0,0 +1,104 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_duration,
+    unified_timestamp,
+)
+
+
+class MeipaiIE(InfoExtractor):
+    IE_DESC = '美拍'
+    _VALID_URL = r'https?://(?:www\.)?meipai.com/media/(?P<id>[0-9]+)'
+    _TESTS = [{
+        # regular uploaded video
+        'url': 'http://www.meipai.com/media/531697625',
+        'md5': 'e3e9600f9e55a302daecc90825854b4f',
+        'info_dict': {
+            'id': '531697625',
+            'ext': 'mp4',
+            'title': '#葉子##阿桑##余姿昀##超級女聲#',
+            'description': '#葉子##阿桑##余姿昀##超級女聲#',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 152,
+            'timestamp': 1465492420,
+            'upload_date': '20160609',
+            'view_count': 35511,
+            'creator': '她她-TATA',
+            'tags': ['葉子', '阿桑', '余姿昀', '超級女聲'],
+        }
+    }, {
+        # record of live streaming
+        'url': 'http://www.meipai.com/media/585526361',
+        'md5': 'ff7d6afdbc6143342408223d4f5fb99a',
+        'info_dict': {
+            'id': '585526361',
+            'ext': 'mp4',
+            'title': '姿昀和善願 練歌練琴啦😁😁😁',
+            'description': '姿昀和善願 練歌練琴啦😁😁😁',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 5975,
+            'timestamp': 1474311799,
+            'upload_date': '20160919',
+            'view_count': 1215,
+            'creator': '她她-TATA',
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._og_search_title(
+            webpage, default=None) or self._html_search_regex(
+            r'<title[^>]*>([^<]+)</title>', webpage, 'title')
+
+        formats = []
+
+        # recorded playback of live streaming
+        m3u8_url = self._html_search_regex(
+            r'file:\s*encodeURIComponent\((["\'])(?P<url>(?:(?!\1).)+)\1\)',
+            webpage, 'm3u8 url', group='url', default=None)
+        if m3u8_url:
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                m3u8_id='hls', fatal=False))
+
+        if not formats:
+            # regular uploaded video
+            video_url = self._search_regex(
+                r'data-video=(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, 'video url',
+                group='url', default=None)
+            if video_url:
+                formats.append({
+                    'url': video_url,
+                    'format_id': 'http',
+                })
+
+        timestamp = unified_timestamp(self._og_search_property(
+            'video:release_date', webpage, 'release date', fatal=False))
+
+        tags = self._og_search_property(
+            'video:tag', webpage, 'tags', default='').split(',')
+
+        view_count = int_or_none(self._html_search_meta(
+            'interactionCount', webpage, 'view count'))
+        duration = parse_duration(self._html_search_meta(
+            'duration', webpage, 'duration'))
+        creator = self._og_search_property(
+            'video:director', webpage, 'creator', fatal=False)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'duration': duration,
+            'timestamp': timestamp,
+            'view_count': view_count,
+            'creator': creator,
+            'tags': tags,
+            'formats': formats,
+        }

youtube_dl/extractor/melonvod.py

@@ -0,0 +1,72 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    urljoin,
+)
+
+
+class MelonVODIE(InfoExtractor):
+    _VALID_URL = r'https?://vod\.melon\.com/video/detail2\.html?\?.*?mvId=(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://vod.melon.com/video/detail2.htm?mvId=50158734',
+        'info_dict': {
+            'id': '50158734',
+            'ext': 'mp4',
+            'title': "Jessica 'Wonderland' MV Making Film",
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'artist': 'Jessica (제시카)',
+            'upload_date': '20161212',
+            'duration': 203,
+        },
+        'params': {
+            'skip_download': 'm3u8 download',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        play_info = self._download_json(
+            'http://vod.melon.com/video/playerInfo.json', video_id,
+            note='Downloading player info JSON', query={'mvId': video_id})
+
+        title = play_info['mvInfo']['MVTITLE']
+
+        info = self._download_json(
+            'http://vod.melon.com/delivery/streamingInfo.json', video_id,
+            note='Downloading streaming info JSON',
+            query={
+                'contsId': video_id,
+                'contsType': 'VIDEO',
+            })
+
+        stream_info = info['streamingInfo']
+
+        formats = self._extract_m3u8_formats(
+            stream_info['encUrl'], video_id, 'mp4', m3u8_id='hls')
+        self._sort_formats(formats)
+
+        artist_list = play_info.get('artistList')
+        artist = None
+        if isinstance(artist_list, list):
+            artist = ', '.join(
+                [a['ARTISTNAMEWEBLIST']
+                 for a in artist_list if a.get('ARTISTNAMEWEBLIST')])
+
+        thumbnail = urljoin(info.get('staticDomain'), stream_info.get('imgPath'))
+
+        duration = int_or_none(stream_info.get('playTime'))
+        upload_date = stream_info.get('mvSvcOpenDt', '')[:8] or None
+
+        return {
+            'id': video_id,
+            'title': title,
+            'artist': artist,
+            'thumbnail': thumbnail,
+            'upload_date': upload_date,
+            'duration': duration,
+            'formats': formats
+        }

youtube_dl/extractor/mitele.py

@@ -1,19 +1,20 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
+import uuid
 
 from .common import InfoExtractor
 from ..compat import (
+    compat_str,
     compat_urllib_parse_urlencode,
     compat_urlparse,
 )
 from ..utils import (
-    get_element_by_attribute,
     int_or_none,
-    remove_start,
     extract_attributes,
     determine_ext,
+    smuggle_url,
+    parse_duration,
 )
 
 
@@ -72,76 +73,133 @@ class MiTeleBaseIE(InfoExtractor):
         }
 
 
-class MiTeleIE(MiTeleBaseIE):
+class MiTeleIE(InfoExtractor):
     IE_DESC = 'mitele.es'
-    _VALID_URL = r'https?://(?:www\.)?mitele\.es/(?:[^/]+/){3}(?P<id>[^/]+)/'
+    _VALID_URL = r'https?://(?:www\.)?mitele\.es/(?:[^/]+/)+(?P<id>[^/]+)/player'
 
     _TESTS = [{
-        'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
-        # MD5 is unstable
+        'url': 'http://www.mitele.es/programas-tv/diario-de/57b0dfb9c715da65618b4afa/player',
         'info_dict': {
-            'id': '0NF1jJnxS1Wu3pHrmvFyw2',
-            'display_id': 'programa-144',
+            'id': '57b0dfb9c715da65618b4afa',
             'ext': 'mp4',
             'title': 'Tor, la web invisible',
             'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
             'series': 'Diario de',
             'season': 'La redacción',
+            'season_number': 14,
+            'season_id': 'diario_de_t14_11981',
             'episode': 'Programa 144',
+            'episode_number': 3,
             'thumbnail': 're:(?i)^https?://.*\.jpg$',
             'duration': 2913,
         },
+        'add_ie': ['Ooyala'],
     }, {
         # no explicit title
-        'url': 'http://www.mitele.es/programas-tv/cuarto-milenio/temporada-6/programa-226/',
+        'url': 'http://www.mitele.es/programas-tv/cuarto-milenio/57b0de3dc915da14058b4876/player',
         'info_dict': {
-            'id': 'eLZSwoEd1S3pVyUm8lc6F',
-            'display_id': 'programa-226',
+            'id': '57b0de3dc915da14058b4876',
             'ext': 'mp4',
-            'title': 'Cuarto Milenio - Temporada 6 - Programa 226',
-            'description': 'md5:50daf9fadefa4e62d9fc866d0c015701',
+            'title': 'Cuarto Milenio Temporada 6 Programa 226',
+            'description': 'md5:5ff132013f0cd968ffbf1f5f3538a65f',
             'series': 'Cuarto Milenio',
             'season': 'Temporada 6',
+            'season_number': 6,
+            'season_id': 'cuarto_milenio_t06_12715',
             'episode': 'Programa 226',
+            'episode_number': 24,
             'thumbnail': 're:(?i)^https?://.*\.jpg$',
-            'duration': 7312,
+            'duration': 7313,
         },
         'params': {
             'skip_download': True,
         },
+        'add_ie': ['Ooyala'],
+    }, {
+        'url': 'http://www.mitele.es/series-online/la-que-se-avecina/57aac5c1c915da951a8b45ed/player',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        display_id = self._match_id(url)
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
 
-        webpage = self._download_webpage(url, display_id)
+        gigya_url = self._search_regex(
+            r'<gigya-api>[^>]*</gigya-api>[^>]*<script\s+src="([^"]*)">[^>]*</script>',
+            webpage, 'gigya', default=None)
+        gigya_sc = self._download_webpage(
+            compat_urlparse.urljoin('http://www.mitele.es/', gigya_url),
+            video_id, 'Downloading gigya script')
 
-        info = self._get_player_info(url, webpage)
+        # Get a appKey/uuid for getting the session key
+        appKey_var = self._search_regex(
+            r'value\s*\(\s*["\']appGridApplicationKey["\']\s*,\s*([0-9a-f]+)',
+            gigya_sc, 'appKey variable')
+        appKey = self._search_regex(
+            r'var\s+%s\s*=\s*["\']([0-9a-f]+)' % appKey_var, gigya_sc, 'appKey')
 
-        title = self._search_regex(
-            r'class="Destacado-text"[^>]*>\s*<strong>([^<]+)</strong>',
-            webpage, 'title', default=None)
+        session_json = self._download_json(
+            'https://appgrid-api.cloud.accedo.tv/session',
+            video_id, 'Downloading session keys', query={
+                'appKey': appKey,
+                'uuid': compat_str(uuid.uuid4()),
+            })
 
-        mobj = re.search(r'''(?sx)
-                            class="Destacado-text"[^>]*>.*?<h1>\s*
-                            <span>(?P<series>[^<]+)</span>\s*
-                            <span>(?P<season>[^<]+)</span>\s*
-                            <span>(?P<episode>[^<]+)</span>''', webpage)
-        series, season, episode = mobj.groups() if mobj else [None] * 3
+        paths = self._download_json(
+            'https://appgrid-api.cloud.accedo.tv/metadata/general_configuration,%20web_configuration',
+            video_id, 'Downloading paths JSON',
+            query={'sessionKey': compat_str(session_json['sessionKey'])})
 
-        if not title:
-            if mobj:
-                title = '%s - %s - %s' % (series, season, episode)
-            else:
-                title = remove_start(self._search_regex(
-                    r'<title>([^<]+)</title>', webpage, 'title'), 'Ver online ')
+        ooyala_s = paths['general_configuration']['api_configuration']['ooyala_search']
+        source = self._download_json(
+            'http://%s%s%s/docs/%s' % (
+                ooyala_s['base_url'], ooyala_s['full_path'],
+                ooyala_s['provider_id'], video_id),
+            video_id, 'Downloading data JSON', query={
+                'include_titles': 'Series,Season',
+                'product_name': 'test',
+                'format': 'full',
+            })['hits']['hits'][0]['_source']
 
-        info.update({
-            'display_id': display_id,
+        embedCode = source['offers'][0]['embed_codes'][0]
+        titles = source['localizable_titles'][0]
+
+        title = titles.get('title_medium') or titles['title_long']
+
+        description = titles.get('summary_long') or titles.get('summary_medium')
+
+        def get(key1, key2):
+            value1 = source.get(key1)
+            if not value1 or not isinstance(value1, list):
+                return
+            if not isinstance(value1[0], dict):
+                return
+            return value1[0].get(key2)
+
+        series = get('localizable_titles_series', 'title_medium')
+
+        season = get('localizable_titles_season', 'title_medium')
+        season_number = int_or_none(source.get('season_number'))
+        season_id = source.get('season_id')
+
+        episode = titles.get('title_sort_name')
+        episode_number = int_or_none(source.get('episode_number'))
+
+        duration = parse_duration(get('videos', 'duration'))
+
+        return {
+            '_type': 'url_transparent',
+            # for some reason only HLS is supported
+            'url': smuggle_url('ooyala:' + embedCode, {'supportedformats': 'm3u8'}),
+            'id': video_id,
             'title': title,
-            'description': get_element_by_attribute('class', 'text', webpage),
+            'description': description,
             'series': series,
             'season': season,
+            'season_number': season_number,
+            'season_id': season_id,
             'episode': episode,
-        })
-        return info
+            'episode_number': episode_number,
+            'duration': duration,
+            'thumbnail': get('images', 'url'),
+        }

youtube_dl/extractor/mixcloud.py

@@ -22,7 +22,7 @@ from ..utils import (
 
 
 class MixcloudIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/(?!stream|uploads|favorites|listens|playlists)([^/]+)'
+    _VALID_URL = r'https?://(?:(?:www|beta|m)\.)?mixcloud\.com/([^/]+)/(?!stream|uploads|favorites|listens|playlists)([^/]+)'
     IE_NAME = 'mixcloud'
 
     _TESTS = [{
@@ -51,6 +51,9 @@ class MixcloudIE(InfoExtractor):
             'view_count': int,
             'like_count': int,
         },
+    }, {
+        'url': 'https://beta.mixcloud.com/RedLightRadio/nosedrip-15-red-light-radio-01-18-2016/',
+        'only_matching': True,
     }]
 
     # See https://www.mixcloud.com/media/js2/www_js_2.9e23256562c080482435196ca3975ab5.js

youtube_dl/extractor/msn.py

@@ -78,11 +78,6 @@ class MSNIE(InfoExtractor):
                 m3u8_formats = self._extract_m3u8_formats(
                     format_url, display_id, 'mp4',
                     m3u8_id='hls', fatal=False)
-                # Despite metadata in m3u8 all video+audio formats are
-                # actually video-only (no audio)
-                for f in m3u8_formats:
-                    if f.get('acodec') != 'none' and f.get('vcodec') != 'none':
-                        f['acodec'] = 'none'
                 formats.extend(m3u8_formats)
             else:
                 formats.append({

youtube_dl/extractor/mtv.py

@@ -13,6 +13,7 @@ from ..utils import (
     fix_xml_ampersands,
     float_or_none,
     HEADRequest,
+    NO_DEFAULT,
     RegexNotFoundError,
     sanitized_Request,
     strip_or_none,
@@ -201,7 +202,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
             [self._get_video_info(item) for item in idoc.findall('.//item')],
             playlist_title=title, playlist_description=description)
 
-    def _extract_mgid(self, webpage):
+    def _extract_mgid(self, webpage, default=NO_DEFAULT):
         try:
             # the url can be http://media.mtvnservices.com/fb/{mgid}.swf
             # or http://media.mtvnservices.com/{mgid}
@@ -221,7 +222,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
             sm4_embed = self._html_search_meta(
                 'sm4:video:embed', webpage, 'sm4 embed', default='')
             mgid = self._search_regex(
-                r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid')
+                r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid', default=default)
         return mgid
 
     def _real_extract(self, url):

youtube_dl/extractor/nbc.py

@@ -9,6 +9,7 @@ from ..utils import (
     lowercase_escape,
     smuggle_url,
     unescapeHTML,
+    update_url_query,
 )
 
 
@@ -208,7 +209,7 @@ class NBCNewsIE(ThePlatformIE):
             'url': 'http://www.nbcnews.com/watch/nbcnews-com/how-twitter-reacted-to-the-snowden-interview-269389891880',
             'md5': 'af1adfa51312291a017720403826bb64',
             'info_dict': {
-                'id': '269389891880',
+                'id': 'p_tweet_snow_140529',
                 'ext': 'mp4',
                 'title': 'How Twitter Reacted To The Snowden Interview',
                 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64',
@@ -232,7 +233,7 @@ class NBCNewsIE(ThePlatformIE):
             'url': 'http://www.nbcnews.com/nightly-news/video/nightly-news-with-brian-williams-full-broadcast-february-4-394064451844',
             'md5': '73135a2e0ef819107bbb55a5a9b2a802',
             'info_dict': {
-                'id': '394064451844',
+                'id': 'nn_netcast_150204',
                 'ext': 'mp4',
                 'title': 'Nightly News with Brian Williams Full Broadcast (February 4)',
                 'description': 'md5:1c10c1eccbe84a26e5debb4381e2d3c5',
@@ -245,7 +246,7 @@ class NBCNewsIE(ThePlatformIE):
             'url': 'http://www.nbcnews.com/business/autos/volkswagen-11-million-vehicles-could-have-suspect-software-emissions-scandal-n431456',
             'md5': 'a49e173825e5fcd15c13fc297fced39d',
             'info_dict': {
-                'id': '529953347624',
+                'id': 'x_lon_vwhorn_150922',
                 'ext': 'mp4',
                 'title': 'Volkswagen U.S. Chief:\xa0 We Have Totally Screwed Up',
                 'description': 'md5:c8be487b2d80ff0594c005add88d8351',
@@ -258,7 +259,7 @@ class NBCNewsIE(ThePlatformIE):
             'url': 'http://www.today.com/video/see-the-aurora-borealis-from-space-in-stunning-new-nasa-video-669831235788',
             'md5': '118d7ca3f0bea6534f119c68ef539f71',
             'info_dict': {
-                'id': '669831235788',
+                'id': 'tdy_al_space_160420',
                 'ext': 'mp4',
                 'title': 'See the aurora borealis from space in stunning new NASA video',
                 'description': 'md5:74752b7358afb99939c5f8bb2d1d04b1',
@@ -271,7 +272,7 @@ class NBCNewsIE(ThePlatformIE):
             'url': 'http://www.msnbc.com/all-in-with-chris-hayes/watch/the-chaotic-gop-immigration-vote-314487875924',
             'md5': '6d236bf4f3dddc226633ce6e2c3f814d',
             'info_dict': {
-                'id': '314487875924',
+                'id': 'n_hayes_Aimm_140801_272214',
                 'ext': 'mp4',
                 'title': 'The chaotic GOP immigration vote',
                 'description': 'The Republican House votes on a border bill that has no chance of getting through the Senate or signed by the President and is drawing criticism from all sides.',
@@ -279,7 +280,6 @@ class NBCNewsIE(ThePlatformIE):
                 'timestamp': 1406937606,
                 'upload_date': '20140802',
                 'uploader': 'NBCU-NEWS',
-                'categories': ['MSNBC/Topics/Franchise/Best of last night', 'MSNBC/Topics/General/Congress'],
             },
         },
         {
@@ -311,28 +311,41 @@ class NBCNewsIE(ThePlatformIE):
         else:
             # "feature" and "nightly-news" pages use theplatform.com
             video_id = mobj.group('mpx_id')
-            if not video_id.isdigit():
-                webpage = self._download_webpage(url, video_id)
-                info = None
-                bootstrap_json = self._search_regex(
-                    [r'(?m)(?:var\s+(?:bootstrapJson|playlistData)|NEWS\.videoObj)\s*=\s*({.+});?\s*$',
-                     r'videoObj\s*:\s*({.+})', r'data-video="([^"]+)"'],
-                    webpage, 'bootstrap json', default=None)
+            webpage = self._download_webpage(url, video_id)
+
+            filter_param = 'byId'
+            bootstrap_json = self._search_regex(
+                [r'(?m)(?:var\s+(?:bootstrapJson|playlistData)|NEWS\.videoObj)\s*=\s*({.+});?\s*$',
+                 r'videoObj\s*:\s*({.+})', r'data-video="([^"]+)"',
+                 r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);'],
+                webpage, 'bootstrap json', default=None)
+            if bootstrap_json:
                 bootstrap = self._parse_json(
                     bootstrap_json, video_id, transform_source=unescapeHTML)
+
+                info = None
                 if 'results' in bootstrap:
                     info = bootstrap['results'][0]['video']
                 elif 'video' in bootstrap:
                     info = bootstrap['video']
+                elif 'msnbcVideoInfo' in bootstrap:
+                    info = bootstrap['msnbcVideoInfo']['meta']
+                elif 'msnbcThePlatform' in bootstrap:
+                    info = bootstrap['msnbcThePlatform']['videoPlayer']['video']
                 else:
                     info = bootstrap
-                video_id = info['mpxId']
+
+                if 'guid' in info:
+                    video_id = info['guid']
+                    filter_param = 'byGuid'
+                elif 'mpxId' in info:
+                    video_id = info['mpxId']
 
             return {
                 '_type': 'url_transparent',
                 'id': video_id,
                 # http://feed.theplatform.com/f/2E2eJC/nbcnews also works
-                'url': 'http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews?byId=%s' % video_id,
+                'url': update_url_query('http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews', {filter_param: video_id}),
                 'ie_key': 'ThePlatformFeed',
             }
 

youtube_dl/extractor/normalboots.py

@@ -2,7 +2,7 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from .screenwavemedia import ScreenwaveMediaIE
+from .jwplatform import JWPlatformIE
 
 from ..utils import (
     unified_strdate,
@@ -25,7 +25,7 @@ class NormalbootsIE(InfoExtractor):
             # m3u8 download
             'skip_download': True,
         },
-        'add_ie': ['ScreenwaveMedia'],
+        'add_ie': ['JWPlatform'],
     }
 
     def _real_extract(self, url):
@@ -39,15 +39,13 @@ class NormalbootsIE(InfoExtractor):
             r'<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>',
             webpage, 'date', fatal=False))
 
-        screenwavemedia_url = self._html_search_regex(
-            ScreenwaveMediaIE.EMBED_PATTERN, webpage, 'screenwave URL',
-            group='url')
+        jwplatform_url = JWPlatformIE._extract_url(webpage)
 
         return {
             '_type': 'url_transparent',
             'id': video_id,
-            'url': screenwavemedia_url,
-            'ie_key': ScreenwaveMediaIE.ie_key(),
+            'url': jwplatform_url,
+            'ie_key': JWPlatformIE.ie_key(),
             'title': self._og_search_title(webpage),
             'description': self._og_search_description(webpage),
             'thumbnail': self._og_search_thumbnail(webpage),

youtube_dl/extractor/nrk.py

@@ -1,6 +1,7 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import random
 import re
 
 from .common import InfoExtractor
@@ -14,6 +15,25 @@ from ..utils import (
 
 
 class NRKBaseIE(InfoExtractor):
+    _faked_ip = None
+
+    def _download_webpage_handle(self, *args, **kwargs):
+        # NRK checks X-Forwarded-For HTTP header in order to figure out the
+        # origin of the client behind proxy. This allows to bypass geo
+        # restriction by faking this header's value to some Norway IP.
+        # We will do so once we encounter any geo restriction error.
+        if self._faked_ip:
+            # NB: str is intentional
+            kwargs.setdefault(str('headers'), {})['X-Forwarded-For'] = self._faked_ip
+        return super(NRKBaseIE, self)._download_webpage_handle(*args, **kwargs)
+
+    def _fake_ip(self):
+        # Use fake IP from 37.191.128.0/17 in order to workaround geo
+        # restriction
+        def octet(lb=0, ub=255):
+            return random.randint(lb, ub)
+        self._faked_ip = '37.191.%d.%d' % (octet(128), octet())
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
@@ -24,6 +44,8 @@ class NRKBaseIE(InfoExtractor):
         title = data.get('fullTitle') or data.get('mainTitle') or data['title']
         video_id = data.get('id') or video_id
 
+        http_headers = {'X-Forwarded-For': self._faked_ip} if self._faked_ip else {}
+
         entries = []
 
         media_assets = data.get('mediaAssets')
@@ -54,6 +76,7 @@ class NRKBaseIE(InfoExtractor):
                     'duration': duration,
                     'subtitles': subtitles,
                     'formats': formats,
+                    'http_headers': http_headers,
                 })
 
         if not entries:
@@ -70,10 +93,23 @@ class NRKBaseIE(InfoExtractor):
                 }]
 
         if not entries:
-            if data.get('usageRights', {}).get('isGeoBlocked'):
-                raise ExtractorError(
-                    'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
-                    expected=True)
+            message_type = data.get('messageType', '')
+            # Can be ProgramIsGeoBlocked or ChannelIsGeoBlocked*
+            if 'IsGeoBlocked' in message_type and not self._faked_ip:
+                self.report_warning(
+                    'Video is geo restricted, trying to fake IP')
+                self._fake_ip()
+                return self._real_extract(url)
+
+            MESSAGES = {
+                'ProgramRightsAreNotReady': 'Du kan dessverre ikke se eller høre programmet',
+                'ProgramRightsHasExpired': 'Programmet har gått ut',
+                'ProgramIsGeoBlocked': 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
+            }
+            raise ExtractorError(
+                '%s said: %s' % (self.IE_NAME, MESSAGES.get(
+                    message_type, message_type)),
+                expected=True)
 
         conviva = data.get('convivaStatistics') or {}
         series = conviva.get('seriesName') or data.get('seriesTitle')

youtube_dl/extractor/ondemandkorea.py

@@ -0,0 +1,60 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .jwplatform import JWPlatformBaseIE
+from ..utils import (
+    ExtractorError,
+    js_to_json,
+)
+
+
+class OnDemandKoreaIE(JWPlatformBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?ondemandkorea\.com/(?P<id>[^/]+)\.html'
+    _TEST = {
+        'url': 'http://www.ondemandkorea.com/ask-us-anything-e43.html',
+        'info_dict': {
+            'id': 'ask-us-anything-e43',
+            'ext': 'mp4',
+            'title': 'Ask Us Anything : E43',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+        'params': {
+            'skip_download': 'm3u8 download'
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id, fatal=False)
+
+        if not webpage:
+            # Page sometimes returns captcha page with HTTP 403
+            raise ExtractorError(
+                'Unable to access page. You may have been blocked.',
+                expected=True)
+
+        if 'msg_block_01.png' in webpage:
+            self.raise_geo_restricted(
+                'This content is not available in your region')
+
+        if 'This video is only available to ODK PLUS members.' in webpage:
+            raise ExtractorError(
+                'This video is only available to ODK PLUS members.',
+                expected=True)
+
+        title = self._og_search_title(webpage)
+
+        jw_config = self._parse_json(
+            self._search_regex(
+                r'(?s)jwplayer\(([\'"])(?:(?!\1).)+\1\)\.setup\s*\((?P<options>.+?)\);',
+                webpage, 'jw config', group='options'),
+            video_id, transform_source=js_to_json)
+        info = self._parse_jwplayer_data(
+            jw_config, video_id, require_title=False, m3u8_id='hls',
+            base_url=url)
+
+        info.update({
+            'title': title,
+            'thumbnail': self._og_search_thumbnail(webpage),
+        })
+        return info

youtube_dl/extractor/ooyala.py

@@ -18,7 +18,7 @@ class OoyalaBaseIE(InfoExtractor):
     _CONTENT_TREE_BASE = _PLAYER_BASE + 'player_api/v1/content_tree/'
     _AUTHORIZATION_URL_TEMPLATE = _PLAYER_BASE + 'sas/player_api/v2/authorization/embed_code/%s/%s?'
 
-    def _extract(self, content_tree_url, video_id, domain='example.org'):
+    def _extract(self, content_tree_url, video_id, domain='example.org', supportedformats=None):
         content_tree = self._download_json(content_tree_url, video_id)['content_tree']
         metadata = content_tree[list(content_tree)[0]]
         embed_code = metadata['embed_code']
@@ -29,7 +29,7 @@ class OoyalaBaseIE(InfoExtractor):
             self._AUTHORIZATION_URL_TEMPLATE % (pcode, embed_code) +
             compat_urllib_parse_urlencode({
                 'domain': domain,
-                'supportedFormats': 'mp4,rtmp,m3u8,hds',
+                'supportedFormats': supportedformats or 'mp4,rtmp,m3u8,hds',
             }), video_id)
 
         cur_auth_data = auth_data['authorization_data'][embed_code]
@@ -145,8 +145,9 @@ class OoyalaIE(OoyalaBaseIE):
         url, smuggled_data = unsmuggle_url(url, {})
         embed_code = self._match_id(url)
         domain = smuggled_data.get('domain')
+        supportedformats = smuggled_data.get('supportedformats')
         content_tree_url = self._CONTENT_TREE_BASE + 'embed_code/%s/%s' % (embed_code, embed_code)
-        return self._extract(content_tree_url, embed_code, domain)
+        return self._extract(content_tree_url, embed_code, domain, supportedformats)
 
 
 class OoyalaExternalIE(OoyalaBaseIE):

youtube_dl/extractor/openload.py

@@ -1,11 +1,8 @@
 # coding: utf-8
-from __future__ import unicode_literals, division
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_chr,
-    compat_ord,
-)
+from ..compat import compat_chr
 from ..utils import (
     determine_ext,
     ExtractorError,
@@ -13,7 +10,7 @@ from ..utils import (
 
 
 class OpenloadIE(InfoExtractor):
-    _VALID_URL = r'https?://openload\.(?:co|io)/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
+    _VALID_URL = r'https?://(?:openload\.(?:co|io)|oload\.tv)/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
 
     _TESTS = [{
         'url': 'https://openload.co/f/kUEfGclsU9o',
@@ -54,6 +51,9 @@ class OpenloadIE(InfoExtractor):
         # for title and ext
         'url': 'https://openload.co/embed/Sxz5sADo82g/',
         'only_matching': True,
+    }, {
+        'url': 'https://oload.tv/embed/KnG-kKZdcfY/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -63,29 +63,20 @@ class OpenloadIE(InfoExtractor):
         if 'File not found' in webpage or 'deleted by the owner' in webpage:
             raise ExtractorError('File not found', expected=True)
 
-        # The following decryption algorithm is written by @yokrysty and
-        # declared to be freely used in youtube-dl
-        # See https://github.com/rg3/youtube-dl/issues/10408
-        enc_data = self._html_search_regex(
-            r'<span[^>]*>([^<]+)</span>\s*<span[^>]*>[^<]+</span>\s*<span[^>]+id="streamurl"',
-            webpage, 'encrypted data')
+        ol_id = self._search_regex(
+            '<span[^>]+id="[a-zA-Z0-9]+x"[^>]*>([0-9]+)</span>',
+            webpage, 'openload ID')
 
-        magic = compat_ord(enc_data[-1])
-        video_url_chars = []
+        first_two_chars = int(float(ol_id[0:][:2]))
+        urlcode = ''
+        num = 2
 
-        for idx, c in enumerate(enc_data):
-            j = compat_ord(c)
-            if j == magic:
-                j -= 1
-            elif j == magic - 1:
-                j += 1
-            if j >= 33 and j <= 126:
-                j = ((j + 14) % 94) + 33
-            if idx == len(enc_data) - 1:
-                j += 3
-            video_url_chars += compat_chr(j)
+        while num < len(ol_id):
+            urlcode += compat_chr(int(float(ol_id[num:][:3])) -
+                                  first_two_chars * int(float(ol_id[num + 3:][:2])))
+            num += 5
 
-        video_url = 'https://openload.co/stream/%s?mime=true' % ''.join(video_url_chars)
+        video_url = 'https://openload.co/stream/' + urlcode
 
         title = self._og_search_title(webpage, default=None) or self._search_regex(
             r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,
@@ -104,5 +95,4 @@ class OpenloadIE(InfoExtractor):
             'ext': determine_ext(title),
             'subtitles': subtitles,
         }
-
         return info_dict

youtube_dl/extractor/pandoratv.py

@@ -11,6 +11,7 @@ from ..utils import (
     float_or_none,
     parse_duration,
     str_to_int,
+    urlencode_postdata,
 )
 
 
@@ -56,6 +57,22 @@ class PandoraTVIE(InfoExtractor):
                 r'^v(\d+)[Uu]rl$', format_id, 'height', default=None)
             if not height:
                 continue
+
+            play_url = self._download_json(
+                'http://m.pandora.tv/?c=api&m=play_url', video_id,
+                data=urlencode_postdata({
+                    'prgid': video_id,
+                    'runtime': info.get('runtime'),
+                    'vod_url': format_url,
+                }),
+                headers={
+                    'Origin': url,
+                    'Content-Type': 'application/x-www-form-urlencoded',
+                })
+            format_url = play_url.get('url')
+            if not format_url:
+                continue
+
             formats.append({
                 'format_id': '%sp' % height,
                 'url': format_url,

youtube_dl/extractor/plays.py

@@ -8,30 +8,31 @@ from ..utils import int_or_none
 
 
 class PlaysTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?plays\.tv/video/(?P<id>[0-9a-f]{18})'
-    _TEST = {
-        'url': 'http://plays.tv/video/56af17f56c95335490/when-you-outplay-the-azir-wall',
+    _VALID_URL = r'https?://(?:www\.)?plays\.tv/(?:video|embeds)/(?P<id>[0-9a-f]{18})'
+    _TESTS = [{
+        'url': 'https://plays.tv/video/56af17f56c95335490/when-you-outplay-the-azir-wall',
         'md5': 'dfeac1198506652b5257a62762cec7bc',
         'info_dict': {
             'id': '56af17f56c95335490',
             'ext': 'mp4',
-            'title': 'When you outplay the Azir wall',
+            'title': 'Bjergsen - When you outplay the Azir wall',
             'description': 'Posted by Bjergsen',
         }
-    }
+    }, {
+        'url': 'https://plays.tv/embeds/56af17f56c95335490',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(
+            'https://plays.tv/video/%s' % video_id, video_id)
+
+        info = self._search_json_ld(webpage, video_id,)
 
-        title = self._og_search_title(webpage)
-        content = self._parse_json(
-            self._search_regex(
-                r'R\.bindContent\(({.+?})\);', webpage,
-                'content'), video_id)['content']
         mpd_url, sources = re.search(
             r'(?s)<video[^>]+data-mpd="([^"]+)"[^>]*>(.+?)</video>',
-            content).groups()
+            webpage).groups()
         formats = self._extract_mpd_formats(
             self._proto_relative_url(mpd_url), video_id, mpd_id='DASH')
         for format_id, height, format_url in re.findall(r'<source\s+res="((\d+)h?)"\s+src="([^"]+)"', sources):
@@ -42,10 +43,11 @@ class PlaysTVIE(InfoExtractor):
             })
         self._sort_formats(formats)
 
-        return {
+        info.update({
             'id': video_id,
-            'title': title,
             'description': self._og_search_description(webpage),
-            'thumbnail': self._og_search_thumbnail(webpage),
+            'thumbnail': info.get('thumbnail') or self._og_search_thumbnail(webpage),
             'formats': formats,
-        }
+        })
+
+        return info

youtube_dl/extractor/pornhub.py

@@ -33,7 +33,7 @@ class PornHubIE(InfoExtractor):
                             (?:[a-z]+\.)?pornhub\.com/(?:view_video\.php\?viewkey=|embed/)|
                             (?:www\.)?thumbzilla\.com/video/
                         )
-                        (?P<id>[0-9a-z]+)
+                        (?P<id>[\da-z]+)
                     '''
     _TESTS = [{
         'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
@@ -96,12 +96,11 @@ class PornHubIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @classmethod
-    def _extract_url(cls, webpage):
-        mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/\d+)\1', webpage)
-        if mobj:
-            return mobj.group('url')
+    @staticmethod
+    def _extract_urls(webpage):
+        return re.findall(
+            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/[\da-z]+)',
+            webpage)
 
     def _extract_count(self, pattern, webpage, name):
         return str_to_int(self._search_regex(

youtube_dl/extractor/prosiebensat1.py

@@ -85,6 +85,9 @@ class ProSiebenSat1BaseIE(InfoExtractor):
                     formats.extend(self._extract_m3u8_formats(
                         source_url, clip_id, 'mp4', 'm3u8_native',
                         m3u8_id='hls', fatal=False))
+                elif mimetype == 'application/dash+xml':
+                    formats.extend(self._extract_mpd_formats(
+                        source_url, clip_id, mpd_id='dash', fatal=False))
                 else:
                     tbr = fix_bitrate(source['bitrate'])
                     if protocol in ('rtmp', 'rtmpe'):

youtube_dl/extractor/puls4.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 
 class Puls4IE(ProSiebenSat1BaseIE):
-    _VALID_URL = r'https?://(?:www\.)?puls4\.com/(?P<id>(?:[^/]+/)*?videos/[^?#]+)'
+    _VALID_URL = r'https?://(?:www\.)?puls4\.com/(?P<id>[^?#&]+)'
     _TESTS = [{
         'url': 'http://www.puls4.com/2-minuten-2-millionen/staffel-3/videos/2min2miotalk/Tobias-Homberger-von-myclubs-im-2min2miotalk-118118',
         'md5': 'fd3c6b0903ac72c9d004f04bc6bb3e03',
@@ -22,6 +22,12 @@ class Puls4IE(ProSiebenSat1BaseIE):
             'upload_date': '20160830',
             'uploader': 'PULS_4',
         },
+    }, {
+        'url': 'http://www.puls4.com/pro-und-contra/wer-wird-prasident/Ganze-Folgen/Wer-wird-Praesident.-Norbert-Hofer',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.puls4.com/pro-und-contra/wer-wird-prasident/Ganze-Folgen/Wer-wird-Praesident-Analyse-des-Interviews-mit-Norbert-Hofer-416598',
+        'only_matching': True,
     }]
     _TOKEN = 'puls4'
     _SALT = '01!kaNgaiNgah1Ie4AeSha'

youtube_dl/extractor/radiocanada.py

@@ -125,6 +125,14 @@ class RadioCanadaIE(InfoExtractor):
                                 f4m_id='hds', fatal=False))
         self._sort_formats(formats)
 
+        subtitles = {}
+        closed_caption_url = get_meta('closedCaption') or get_meta('closedCaptionHTML5')
+        if closed_caption_url:
+            subtitles['fr'] = [{
+                'url': closed_caption_url,
+                'ext': determine_ext(closed_caption_url, 'vtt'),
+            }]
+
         return {
             'id': video_id,
             'title': get_meta('Title'),
@@ -135,6 +143,7 @@ class RadioCanadaIE(InfoExtractor):
             'season_number': int_or_none('SrcSaison'),
             'episode_number': int_or_none('SrcEpisode'),
             'upload_date': unified_strdate(get_meta('Date')),
+            'subtitles': subtitles,
             'formats': formats,
         }
 

youtube_dl/extractor/redtube.py

@@ -1,5 +1,7 @@
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
@@ -10,8 +12,8 @@ from ..utils import (
 
 
 class RedTubeIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:(?:www\.)?redtube\.com/|embed\.redtube\.com/\?.*?\bid=)(?P<id>[0-9]+)'
+    _TESTS = [{
         'url': 'http://www.redtube.com/66418',
         'md5': '7b8c22b5e7098a3e1c09709df1126d2d',
         'info_dict': {
@@ -23,11 +25,21 @@ class RedTubeIE(InfoExtractor):
             'view_count': int,
             'age_limit': 18,
         }
-    }
+    }, {
+        'url': 'http://embed.redtube.com/?bgcolor=000000&id=1443286',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_urls(webpage):
+        return re.findall(
+            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//embed\.redtube\.com/\?.*?\bid=\d+)',
+            webpage)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(
+            'http://www.redtube.com/%s' % video_id, video_id)
 
         if any(s in webpage for s in ['video-deleted-info', '>This video has been removed']):
             raise ExtractorError('Video %s has been removed' % video_id, expected=True)

youtube_dl/extractor/rte.py

@@ -4,118 +4,31 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_HTTPError
 from ..utils import (
     float_or_none,
     parse_iso8601,
     unescapeHTML,
+    ExtractorError,
 )
 
 
-class RteIE(InfoExtractor):
-    IE_NAME = 'rte'
-    IE_DESC = 'Raidió Teilifís Éireann TV'
-    _VALID_URL = r'https?://(?:www\.)?rte\.ie/player/[^/]{2,3}/show/[^/]+/(?P<id>[0-9]+)'
-    _TEST = {
-        'url': 'http://www.rte.ie/player/ie/show/iwitness-862/10478715/',
-        'info_dict': {
-            'id': '10478715',
-            'ext': 'flv',
-            'title': 'Watch iWitness  online',
-            'thumbnail': 're:^https?://.*\.jpg$',
-            'description': 'iWitness : The spirit of Ireland, one voice and one minute at a time.',
-            'duration': 60.046,
-        },
-        'params': {
-            'skip_download': 'f4m fails with --test atm'
-        }
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-
-        title = self._og_search_title(webpage)
-        description = self._html_search_meta('description', webpage, 'description')
-        duration = float_or_none(self._html_search_meta(
-            'duration', webpage, 'duration', fatal=False), 1000)
-
-        thumbnail = None
-        thumbnail_meta = self._html_search_meta('thumbnail', webpage)
-        if thumbnail_meta:
-            thumbnail_id = self._search_regex(
-                r'uri:irus:(.+)', thumbnail_meta,
-                'thumbnail id', fatal=False)
-            if thumbnail_id:
-                thumbnail = 'http://img.rasset.ie/%s.jpg' % thumbnail_id
-
-        feeds_url = self._html_search_meta('feeds-prefix', webpage, 'feeds url') + video_id
-        json_string = self._download_json(feeds_url, video_id)
-
-        # f4m_url = server + relative_url
-        f4m_url = json_string['shows'][0]['media:group'][0]['rte:server'] + json_string['shows'][0]['media:group'][0]['url']
-        f4m_formats = self._extract_f4m_formats(f4m_url, video_id)
-        self._sort_formats(f4m_formats)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'formats': f4m_formats,
-            'description': description,
-            'thumbnail': thumbnail,
-            'duration': duration,
-        }
-
-
-class RteRadioIE(InfoExtractor):
-    IE_NAME = 'rte:radio'
-    IE_DESC = 'Raidió Teilifís Éireann radio'
-    # Radioplayer URLs have two distinct specifier formats,
-    # the old format #!rii=<channel_id>:<id>:<playable_item_id>:<date>:
-    # the new format #!rii=b<channel_id>_<id>_<playable_item_id>_<date>_
-    # where the IDs are int/empty, the date is DD-MM-YYYY, and the specifier may be truncated.
-    # An <id> uniquely defines an individual recording, and is the only part we require.
-    _VALID_URL = r'https?://(?:www\.)?rte\.ie/radio/utils/radioplayer/rteradioweb\.html#!rii=(?:b?[0-9]*)(?:%3A|:|%5F|_)(?P<id>[0-9]+)'
-
-    _TESTS = [{
-        # Old-style player URL; HLS and RTMPE formats
-        'url': 'http://www.rte.ie/radio/utils/radioplayer/rteradioweb.html#!rii=16:10507902:2414:27-12-2015:',
-        'info_dict': {
-            'id': '10507902',
-            'ext': 'mp4',
-            'title': 'Gloria',
-            'thumbnail': 're:^https?://.*\.jpg$',
-            'description': 'md5:9ce124a7fb41559ec68f06387cabddf0',
-            'timestamp': 1451203200,
-            'upload_date': '20151227',
-            'duration': 7230.0,
-        },
-        'params': {
-            'skip_download': 'f4m fails with --test atm'
-        }
-    }, {
-        # New-style player URL; RTMPE formats only
-        'url': 'http://rte.ie/radio/utils/radioplayer/rteradioweb.html#!rii=b16_3250678_8861_06-04-2012_',
-        'info_dict': {
-            'id': '3250678',
-            'ext': 'flv',
-            'title': 'The Lyric Concert with Paul Herriott',
-            'thumbnail': 're:^https?://.*\.jpg$',
-            'description': '',
-            'timestamp': 1333742400,
-            'upload_date': '20120406',
-            'duration': 7199.016,
-        },
-        'params': {
-            'skip_download': 'f4m fails with --test atm'
-        }
-    }]
-
+class RteBaseIE(InfoExtractor):
     def _real_extract(self, url):
         item_id = self._match_id(url)
 
-        json_string = self._download_json(
-            'http://www.rte.ie/rteavgen/getplaylist/?type=web&format=json&id=' + item_id,
-            item_id)
+        try:
+            json_string = self._download_json(
+                'http://www.rte.ie/rteavgen/getplaylist/?type=web&format=json&id=' + item_id,
+                item_id)
+        except ExtractorError as ee:
+            if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404:
+                error_info = self._parse_json(ee.cause.read().decode(), item_id, fatal=False)
+                if error_info:
+                    raise ExtractorError(
+                        '%s said: %s' % (self.IE_NAME, error_info['message']),
+                        expected=True)
+            raise
 
         # NB the string values in the JSON are stored using XML escaping(!)
         show = json_string['shows'][0]
@@ -163,3 +76,67 @@ class RteRadioIE(InfoExtractor):
             'duration': duration,
             'formats': formats,
         }
+
+
+class RteIE(RteBaseIE):
+    IE_NAME = 'rte'
+    IE_DESC = 'Raidió Teilifís Éireann TV'
+    _VALID_URL = r'https?://(?:www\.)?rte\.ie/player/[^/]{2,3}/show/[^/]+/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.rte.ie/player/ie/show/iwitness-862/10478715/',
+        'md5': '4a76eb3396d98f697e6e8110563d2604',
+        'info_dict': {
+            'id': '10478715',
+            'ext': 'mp4',
+            'title': 'iWitness',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'description': 'The spirit of Ireland, one voice and one minute at a time.',
+            'duration': 60.046,
+            'upload_date': '20151012',
+            'timestamp': 1444694160,
+        },
+    }
+
+
+class RteRadioIE(RteBaseIE):
+    IE_NAME = 'rte:radio'
+    IE_DESC = 'Raidió Teilifís Éireann radio'
+    # Radioplayer URLs have two distinct specifier formats,
+    # the old format #!rii=<channel_id>:<id>:<playable_item_id>:<date>:
+    # the new format #!rii=b<channel_id>_<id>_<playable_item_id>_<date>_
+    # where the IDs are int/empty, the date is DD-MM-YYYY, and the specifier may be truncated.
+    # An <id> uniquely defines an individual recording, and is the only part we require.
+    _VALID_URL = r'https?://(?:www\.)?rte\.ie/radio/utils/radioplayer/rteradioweb\.html#!rii=(?:b?[0-9]*)(?:%3A|:|%5F|_)(?P<id>[0-9]+)'
+
+    _TESTS = [{
+        # Old-style player URL; HLS and RTMPE formats
+        'url': 'http://www.rte.ie/radio/utils/radioplayer/rteradioweb.html#!rii=16:10507902:2414:27-12-2015:',
+        'md5': 'c79ccb2c195998440065456b69760411',
+        'info_dict': {
+            'id': '10507902',
+            'ext': 'mp4',
+            'title': 'Gloria',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'description': 'md5:9ce124a7fb41559ec68f06387cabddf0',
+            'timestamp': 1451203200,
+            'upload_date': '20151227',
+            'duration': 7230.0,
+        },
+    }, {
+        # New-style player URL; RTMPE formats only
+        'url': 'http://rte.ie/radio/utils/radioplayer/rteradioweb.html#!rii=b16_3250678_8861_06-04-2012_',
+        'info_dict': {
+            'id': '3250678',
+            'ext': 'flv',
+            'title': 'The Lyric Concert with Paul Herriott',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'description': '',
+            'timestamp': 1333742400,
+            'upload_date': '20120406',
+            'duration': 7199.016,
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+    }]

youtube_dl/extractor/rts.py

@@ -4,27 +4,24 @@ from __future__ import unicode_literals
 import re
 
 from .srgssr import SRGSSRIE
-from ..compat import (
-    compat_str,
-    compat_urllib_parse_urlparse,
-)
+from ..compat import compat_str
 from ..utils import (
     int_or_none,
     parse_duration,
     parse_iso8601,
     unescapeHTML,
-    xpath_text,
+    determine_ext,
 )
 
 
 class RTSIE(SRGSSRIE):
     IE_DESC = 'RTS.ch'
-    _VALID_URL = r'rts:(?P<rts_id>\d+)|https?://(?:www\.)?rts\.ch/(?:[^/]+/){2,}(?P<id>[0-9]+)-(?P<display_id>.+?)\.html'
+    _VALID_URL = r'rts:(?P<rts_id>\d+)|https?://(?:.+?\.)?rts\.ch/(?:[^/]+/){2,}(?P<id>[0-9]+)-(?P<display_id>.+?)\.html'
 
     _TESTS = [
         {
             'url': 'http://www.rts.ch/archives/tv/divers/3449373-les-enfants-terribles.html',
-            'md5': 'f254c4b26fb1d3c183793d52bc40d3e7',
+            'md5': 'ff7f8450a90cf58dacb64e29707b4a8e',
             'info_dict': {
                 'id': '3449373',
                 'display_id': 'les-enfants-terribles',
@@ -38,35 +35,17 @@ class RTSIE(SRGSSRIE):
                 'thumbnail': 're:^https?://.*\.image',
                 'view_count': int,
             },
-            'params': {
-                # m3u8 download
-                'skip_download': True,
-            }
         },
         {
             'url': 'http://www.rts.ch/emissions/passe-moi-les-jumelles/5624067-entre-ciel-et-mer.html',
-            'md5': 'f1077ac5af686c76528dc8d7c5df29ba',
             'info_dict': {
-                'id': '5742494',
-                'display_id': '5742494',
-                'ext': 'mp4',
-                'duration': 3720,
-                'title': 'Les yeux dans les cieux - Mon homard au Canada',
-                'description': 'md5:d22ee46f5cc5bac0912e5a0c6d44a9f7',
-                'uploader': 'Passe-moi les jumelles',
-                'upload_date': '20140404',
-                'timestamp': 1396635300,
-                'thumbnail': 're:^https?://.*\.image',
-                'view_count': int,
+                'id': '5624065',
+                'title': 'Passe-moi les jumelles',
             },
-            'params': {
-                # m3u8 download
-                'skip_download': True,
-            }
+            'playlist_mincount': 4,
         },
         {
             'url': 'http://www.rts.ch/video/sport/hockey/5745975-1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski.html',
-            'md5': 'b4326fecd3eb64a458ba73c73e91299d',
             'info_dict': {
                 'id': '5745975',
                 'display_id': '1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski',
@@ -80,11 +59,15 @@ class RTSIE(SRGSSRIE):
                 'thumbnail': 're:^https?://.*\.image',
                 'view_count': int,
             },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
             'skip': 'Blocked outside Switzerland',
         },
         {
             'url': 'http://www.rts.ch/video/info/journal-continu/5745356-londres-cachee-par-un-epais-smog.html',
-            'md5': '9f713382f15322181bb366cc8c3a4ff0',
+            'md5': '1bae984fe7b1f78e94abc74e802ed99f',
             'info_dict': {
                 'id': '5745356',
                 'display_id': 'londres-cachee-par-un-epais-smog',
@@ -92,16 +75,12 @@ class RTSIE(SRGSSRIE):
                 'duration': 33,
                 'title': 'Londres cachée par un épais smog',
                 'description': 'Un important voile de smog recouvre Londres depuis mercredi, provoqué par la pollution et du sable du Sahara.',
-                'uploader': 'Le Journal en continu',
+                'uploader': 'L\'actu en vidéo',
                 'upload_date': '20140403',
                 'timestamp': 1396537322,
                 'thumbnail': 're:^https?://.*\.image',
                 'view_count': int,
             },
-            'params': {
-                # m3u8 download
-                'skip_download': True,
-            }
         },
         {
             'url': 'http://www.rts.ch/audio/couleur3/programmes/la-belle-video-de-stephane-laurenceau/5706148-urban-hippie-de-damien-krisl-03-04-2014.html',
@@ -125,6 +104,10 @@ class RTSIE(SRGSSRIE):
                 'title': 'Hockey: Davos décroche son 31e titre de champion de Suisse',
             },
             'playlist_mincount': 5,
+        },
+        {
+            'url': 'http://pages.rts.ch/emissions/passe-moi-les-jumelles/5624065-entre-ciel-et-mer.html',
+            'only_matching': True,
         }
     ]
 
@@ -142,19 +125,32 @@ class RTSIE(SRGSSRIE):
 
         # media_id extracted out of URL is not always a real id
         if 'video' not in all_info and 'audio' not in all_info:
-            page = self._download_webpage(url, display_id)
+            entries = []
 
-            # article with videos on rhs
-            videos = re.findall(
-                r'<article[^>]+class="content-item"[^>]*>\s*<a[^>]+data-video-urn="urn:([^"]+)"',
-                page)
-            if not videos:
+            for item in all_info.get('items', []):
+                item_url = item.get('url')
+                if not item_url:
+                    continue
+                entries.append(self.url_result(item_url, 'RTS'))
+
+            if not entries:
+                page, urlh = self._download_webpage_handle(url, display_id)
+                if re.match(self._VALID_URL, urlh.geturl()).group('id') != media_id:
+                    return self.url_result(urlh.geturl(), 'RTS')
+
+                # article with videos on rhs
                 videos = re.findall(
-                    r'(?s)<iframe[^>]+class="srg-player"[^>]+src="[^"]+urn:([^"]+)"',
+                    r'<article[^>]+class="content-item"[^>]*>\s*<a[^>]+data-video-urn="urn:([^"]+)"',
                     page)
-            if videos:
-                entries = [self.url_result('srgssr:%s' % video_urn, 'SRGSSR') for video_urn in videos]
-                return self.playlist_result(entries, media_id, self._og_search_title(page))
+                if not videos:
+                    videos = re.findall(
+                        r'(?s)<iframe[^>]+class="srg-player"[^>]+src="[^"]+urn:([^"]+)"',
+                        page)
+                if videos:
+                    entries = [self.url_result('srgssr:%s' % video_urn, 'SRGSSR') for video_urn in videos]
+
+            if entries:
+                return self.playlist_result(entries, media_id, all_info.get('title'))
 
             internal_id = self._html_search_regex(
                 r'<(?:video|audio) data-id="([0-9]+)"', page,
@@ -168,36 +164,29 @@ class RTSIE(SRGSSRIE):
 
         info = all_info['video']['JSONinfo'] if 'video' in all_info else all_info['audio']
 
-        upload_timestamp = parse_iso8601(info.get('broadcast_date'))
-        duration = info.get('duration') or info.get('cutout') or info.get('cutduration')
-        if isinstance(duration, compat_str):
-            duration = parse_duration(duration)
-        view_count = info.get('plays')
-        thumbnail = unescapeHTML(info.get('preview_image_url'))
+        title = info['title']
 
         def extract_bitrate(url):
             return int_or_none(self._search_regex(
                 r'-([0-9]+)k\.', url, 'bitrate', default=None))
 
         formats = []
-        for format_id, format_url in info['streams'].items():
-            if format_id == 'hds_sd' and 'hds' in info['streams']:
+        streams = info.get('streams', {})
+        for format_id, format_url in streams.items():
+            if format_id == 'hds_sd' and 'hds' in streams:
                 continue
-            if format_id == 'hls_sd' and 'hls' in info['streams']:
+            if format_id == 'hls_sd' and 'hls' in streams:
                 continue
-            if format_url.endswith('.f4m'):
-                token = self._download_xml(
-                    'http://tp.srgssr.ch/token/akahd.xml?stream=%s/*' % compat_urllib_parse_urlparse(format_url).path,
-                    media_id, 'Downloading %s token' % format_id)
-                auth_params = xpath_text(token, './/authparams', 'auth params')
-                if not auth_params:
-                    continue
-                formats.extend(self._extract_f4m_formats(
-                    '%s?%s&hdcore=3.4.0&plugin=aasp-3.4.0.132.66' % (format_url, auth_params),
-                    media_id, f4m_id=format_id, fatal=False))
-            elif format_url.endswith('.m3u8'):
-                formats.extend(self._extract_m3u8_formats(
-                    format_url, media_id, 'mp4', 'm3u8_native', m3u8_id=format_id, fatal=False))
+            ext = determine_ext(format_url)
+            if ext in ('m3u8', 'f4m'):
+                format_url = self._get_tokenized_src(format_url, media_id, format_id)
+                if ext == 'f4m':
+                    formats.extend(self._extract_f4m_formats(
+                        format_url + ('?' if '?' not in format_url else '&') + 'hdcore=3.4.0',
+                        media_id, f4m_id=format_id, fatal=False))
+                else:
+                    formats.extend(self._extract_m3u8_formats(
+                        format_url, media_id, 'mp4', 'm3u8_native', m3u8_id=format_id, fatal=False))
             else:
                 formats.append({
                     'format_id': format_id,
@@ -205,25 +194,37 @@ class RTSIE(SRGSSRIE):
                     'tbr': extract_bitrate(format_url),
                 })
 
-        if 'media' in info:
-            formats.extend([{
-                'format_id': '%s-%sk' % (media['ext'], media['rate']),
-                'url': 'http://download-video.rts.ch/%s' % media['url'],
-                'tbr': media['rate'] or extract_bitrate(media['url']),
-            } for media in info['media'] if media.get('rate')])
+        for media in info.get('media', []):
+            media_url = media.get('url')
+            if not media_url or re.match(r'https?://', media_url):
+                continue
+            rate = media.get('rate')
+            ext = media.get('ext') or determine_ext(media_url, 'mp4')
+            format_id = ext
+            if rate:
+                format_id += '-%dk' % rate
+            formats.append({
+                'format_id': format_id,
+                'url': 'http://download-video.rts.ch/' + media_url,
+                'tbr': rate or extract_bitrate(media_url),
+            })
 
         self._check_formats(formats, media_id)
         self._sort_formats(formats)
 
+        duration = info.get('duration') or info.get('cutout') or info.get('cutduration')
+        if isinstance(duration, compat_str):
+            duration = parse_duration(duration)
+
         return {
             'id': media_id,
             'display_id': display_id,
             'formats': formats,
-            'title': info['title'],
+            'title': title,
             'description': info.get('intro'),
             'duration': duration,
-            'view_count': view_count,
+            'view_count': int_or_none(info.get('plays')),
             'uploader': info.get('programName'),
-            'timestamp': upload_timestamp,
-            'thumbnail': thumbnail,
+            'timestamp': parse_iso8601(info.get('broadcast_date')),
+            'thumbnail': unescapeHTML(info.get('preview_image_url')),
         }

youtube_dl/extractor/ruutu.py

@@ -5,6 +5,7 @@ from .common import InfoExtractor
 from ..compat import compat_urllib_parse_urlparse
 from ..utils import (
     determine_ext,
+    ExtractorError,
     int_or_none,
     xpath_attr,
     xpath_text,
@@ -101,6 +102,11 @@ class RuutuIE(InfoExtractor):
                         })
 
         extract_formats(video_xml.find('./Clip'))
+
+        drm = xpath_text(video_xml, './Clip/DRM', default=None)
+        if not formats and drm:
+            raise ExtractorError('This video is DRM protected.', expected=True)
+
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/screenwavemedia.py

@@ -1,146 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-    unified_strdate,
-    js_to_json,
-)
-
-
-class ScreenwaveMediaIE(InfoExtractor):
-    _VALID_URL = r'(?:https?:)?//player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?.*\bid=(?P<id>[A-Za-z0-9-]+)'
-    EMBED_PATTERN = r'src=(["\'])(?P<url>(?:https?:)?//player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?.*\bid=.+?)\1'
-    _TESTS = [{
-        'url': 'http://player.screenwavemedia.com/play/play.php?playerdiv=videoarea&companiondiv=squareAd&id=Cinemassacre-19911',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        playerdata = self._download_webpage(
-            'http://player.screenwavemedia.com/player.php?id=%s' % video_id,
-            video_id, 'Downloading player webpage')
-
-        vidtitle = self._search_regex(
-            r'\'vidtitle\'\s*:\s*"([^"]+)"', playerdata, 'vidtitle').replace('\\/', '/')
-
-        playerconfig = self._download_webpage(
-            'http://player.screenwavemedia.com/player.js',
-            video_id, 'Downloading playerconfig webpage')
-
-        videoserver = self._search_regex(r'SWMServer\s*=\s*"([\d\.]+)"', playerdata, 'videoserver')
-
-        sources = self._parse_json(
-            js_to_json(
-                re.sub(
-                    r'(?s)/\*.*?\*/', '',
-                    self._search_regex(
-                        r'sources\s*:\s*(\[[^\]]+?\])', playerconfig,
-                        'sources',
-                    ).replace(
-                        "' + thisObj.options.videoserver + '",
-                        videoserver
-                    ).replace(
-                        "' + playerVidId + '",
-                        video_id
-                    )
-                )
-            ),
-            video_id, fatal=False
-        )
-
-        # Fallback to hardcoded sources if JS changes again
-        if not sources:
-            self.report_warning('Falling back to a hardcoded list of streams')
-            sources = [{
-                'file': 'http://%s/vod/%s_%s.mp4' % (videoserver, video_id, format_id),
-                'type': 'mp4',
-                'label': format_label,
-            } for format_id, format_label in (
-                ('low', '144p Low'), ('med', '160p Med'), ('high', '360p High'), ('hd1', '720p HD1'))]
-            sources.append({
-                'file': 'http://%s/vod/smil:%s.smil/playlist.m3u8' % (videoserver, video_id),
-                'type': 'hls',
-            })
-
-        formats = []
-        for source in sources:
-            file_ = source.get('file')
-            if not file_:
-                continue
-            if source.get('type') == 'hls':
-                formats.extend(self._extract_m3u8_formats(file_, video_id, ext='mp4'))
-            else:
-                format_id = self._search_regex(
-                    r'_(.+?)\.[^.]+$', file_, 'format id', default=None)
-                if not self._is_valid_url(file_, video_id, format_id or 'video'):
-                    continue
-                format_label = source.get('label')
-                height = int_or_none(self._search_regex(
-                    r'^(\d+)[pP]', format_label, 'height', default=None))
-                formats.append({
-                    'url': file_,
-                    'format_id': format_id,
-                    'format': format_label,
-                    'ext': source.get('type'),
-                    'height': height,
-                })
-        self._sort_formats(formats, field_preference=('height', 'width', 'tbr', 'format_id'))
-
-        return {
-            'id': video_id,
-            'title': vidtitle,
-            'formats': formats,
-        }
-
-
-class TeamFourIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?teamfourstar\.com/video/(?P<id>[a-z0-9\-]+)/?'
-    _TEST = {
-        'url': 'http://teamfourstar.com/video/a-moment-with-tfs-episode-4/',
-        'info_dict': {
-            'id': 'TeamFourStar-5292a02f20bfa',
-            'ext': 'mp4',
-            'upload_date': '20130401',
-            'description': 'Check out this and more on our website: http://teamfourstar.com\nTFS Store: http://sharkrobot.com/team-four-star\nFollow on Twitter: http://twitter.com/teamfourstar\nLike on FB: http://facebook.com/teamfourstar',
-            'title': 'A Moment With TFS Episode 4',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-    }
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-
-        playerdata_url = self._search_regex(
-            r'src="(http://player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
-            webpage, 'player data URL')
-
-        video_title = self._html_search_regex(
-            r'<div class="heroheadingtitle">(?P<title>.+?)</div>',
-            webpage, 'title')
-        video_date = unified_strdate(self._html_search_regex(
-            r'<div class="heroheadingdate">(?P<date>.+?)</div>',
-            webpage, 'date', fatal=False))
-        video_description = self._html_search_regex(
-            r'(?s)<div class="postcontent">(?P<description>.+?)</div>',
-            webpage, 'description', fatal=False)
-        video_thumbnail = self._og_search_thumbnail(webpage)
-
-        return {
-            '_type': 'url_transparent',
-            'display_id': display_id,
-            'title': video_title,
-            'description': video_description,
-            'upload_date': video_date,
-            'thumbnail': video_thumbnail,
-            'url': playerdata_url,
-        }

youtube_dl/extractor/shahid.py

@@ -1,17 +1,24 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+import json
+
 from .common import InfoExtractor
+from ..compat import compat_HTTPError
 from ..utils import (
     ExtractorError,
     int_or_none,
     parse_iso8601,
     str_or_none,
+    urlencode_postdata,
+    clean_html,
 )
 
 
 class ShahidIE(InfoExtractor):
-    _VALID_URL = r'https?://shahid\.mbc\.net/ar/episode/(?P<id>\d+)/?'
+    _NETRC_MACHINE = 'shahid'
+    _VALID_URL = r'https?://shahid\.mbc\.net/ar/(?P<type>episode|movie)/(?P<id>\d+)'
     _TESTS = [{
         'url': 'https://shahid.mbc.net/ar/episode/90574/%D8%A7%D9%84%D9%85%D9%84%D9%83-%D8%B9%D8%A8%D8%AF%D8%A7%D9%84%D9%84%D9%87-%D8%A7%D9%84%D8%A5%D9%86%D8%B3%D8%A7%D9%86-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D9%83%D9%84%D9%8A%D8%A8-3.html',
         'info_dict': {
@@ -27,18 +34,54 @@ class ShahidIE(InfoExtractor):
             # m3u8 download
             'skip_download': True,
         }
+    }, {
+        'url': 'https://shahid.mbc.net/ar/movie/151746/%D8%A7%D9%84%D9%82%D9%86%D8%A7%D8%B5%D8%A9.html',
+        'only_matching': True
     }, {
         # shahid plus subscriber only
         'url': 'https://shahid.mbc.net/ar/episode/90511/%D9%85%D8%B1%D8%A7%D9%8A%D8%A7-2011-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1.html',
         'only_matching': True
     }]
 
-    def _call_api(self, path, video_id, note):
-        data = self._download_json(
-            'http://api.shahid.net/api/v1_1/' + path, video_id, note, query={
-                'apiKey': 'sh@hid0nlin3',
-                'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=',
-            }).get('data', {})
+    def _real_initialize(self):
+        email, password = self._get_login_info()
+        if email is None:
+            return
+
+        try:
+            user_data = self._download_json(
+                'https://shahid.mbc.net/wd/service/users/login',
+                None, 'Logging in', data=json.dumps({
+                    'email': email,
+                    'password': password,
+                    'basic': 'false',
+                }).encode('utf-8'), headers={
+                    'Content-Type': 'application/json; charset=UTF-8',
+                })['user']
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError):
+                fail_data = self._parse_json(
+                    e.cause.read().decode('utf-8'), None, fatal=False)
+                if fail_data:
+                    faults = fail_data.get('faults', [])
+                    faults_message = ', '.join([clean_html(fault['userMessage']) for fault in faults if fault.get('userMessage')])
+                    if faults_message:
+                        raise ExtractorError(faults_message, expected=True)
+            raise
+
+        self._download_webpage(
+            'https://shahid.mbc.net/populateContext',
+            None, 'Populate Context', data=urlencode_postdata({
+                'firstName': user_data['firstName'],
+                'lastName': user_data['lastName'],
+                'userName': user_data['email'],
+                'csg_user_name': user_data['email'],
+                'subscriberId': user_data['id'],
+                'sessionId': user_data['sessionId'],
+            }))
+
+    def _get_api_data(self, response):
+        data = response.get('data', {})
 
         error = data.get('error')
         if error:
@@ -49,11 +92,11 @@ class ShahidIE(InfoExtractor):
         return data
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        page_type, video_id = re.match(self._VALID_URL, url).groups()
 
-        player = self._call_api(
-            'Content/Episode/%s' % video_id,
-            video_id, 'Downloading player JSON')
+        player = self._get_api_data(self._download_json(
+            'https://shahid.mbc.net/arContent/getPlayerContent-param-.id-%s.type-player.html' % video_id,
+            video_id, 'Downloading player JSON'))
 
         if player.get('drm'):
             raise ExtractorError('This video is DRM protected.', expected=True)
@@ -61,9 +104,12 @@ class ShahidIE(InfoExtractor):
         formats = self._extract_m3u8_formats(player['url'], video_id, 'mp4')
         self._sort_formats(formats)
 
-        video = self._call_api(
-            'episode/%s' % video_id, video_id,
-            'Downloading video JSON')['episode']
+        video = self._get_api_data(self._download_json(
+            'http://api.shahid.net/api/v1_1/%s/%s' % (page_type, video_id),
+            video_id, 'Downloading video JSON', query={
+                'apiKey': 'sh@hid0nlin3',
+                'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=',
+            }))[page_type]
 
         title = video['title']
         categories = [

youtube_dl/extractor/soundcloud.py

@@ -121,7 +121,7 @@ class SoundcloudIE(InfoExtractor):
         },
     ]
 
-    _CLIENT_ID = '02gUJC0hH2ct1EGOcYXQIzRFU91c72Ea'
+    _CLIENT_ID = 'fDoItMDbsbZz8dY16ZzARCZmzgHBPotA'
     _IPHONE_CLIENT_ID = '376f225bf427445fc4bfb6b99b72e0bf'
 
     @staticmethod

youtube_dl/extractor/spike.py

@@ -1,5 +1,7 @@
 from __future__ import unicode_literals
 
+import re
+
 from .mtv import MTVServicesInfoExtractor
 
 
@@ -16,6 +18,15 @@ class SpikeIE(MTVServicesInfoExtractor):
             'timestamp': 1388120400,
             'upload_date': '20131227',
         },
+    }, {
+        'url': 'http://www.spike.com/full-episodes/j830qm/lip-sync-battle-joel-mchale-vs-jim-rash-season-2-ep-209',
+        'md5': 'b25c6f16418aefb9ad5a6cae2559321f',
+        'info_dict': {
+            'id': '37ace3a8-1df6-48be-85b8-38df8229e241',
+            'ext': 'mp4',
+            'title': 'Lip Sync Battle|April 28, 2016|2|209|Joel McHale Vs. Jim Rash|Act 1',
+            'description': 'md5:a739ca8f978a7802f67f8016d27ce114',
+        },
     }, {
         'url': 'http://www.spike.com/video-clips/lhtu8m/',
         'only_matching': True,
@@ -32,3 +43,12 @@ class SpikeIE(MTVServicesInfoExtractor):
 
     _FEED_URL = 'http://www.spike.com/feeds/mrss/'
     _MOBILE_TEMPLATE = 'http://m.spike.com/videos/video.rbml?id=%s'
+    _CUSTOM_URL_REGEX = re.compile(r'spikenetworkapp://([^/]+/[-a-fA-F0-9]+)')
+
+    def _extract_mgid(self, webpage):
+        mgid = super(SpikeIE, self)._extract_mgid(webpage, default=None)
+        if mgid is None:
+            url_parts = self._search_regex(self._CUSTOM_URL_REGEX, webpage, 'episode_id')
+            video_type, episode_id = url_parts.split('/', 1)
+            mgid = 'mgid:arc:{0}:spike.com:{1}'.format(video_type, episode_id)
+        return mgid