release 2016.01.14

In RFC6381, there's no rule stating that the first part of codecs should
be video and the second part should be audio, while it seems the case
for data reported by YouTube.

AUTHORS

@@ -149,3 +149,6 @@ Marco Ferragina
 reiv
 Muratcan Simsek
 Evan Lu
+flatgreen
+Brian Foley
+Vignesh Venkat

CONTRIBUTING.md

@@ -28,7 +28,7 @@ So please elaborate on what feature you are requesting, or what bug you want to
 - How it could be fixed
 - How your proposed solution would look like
 
-If your report is shorter than two lines, it is almost certainly missing some of these, which makes it hard for us to respond to it. We're often too polite to close the issue outright, but the missing info makes misinterpretation likely. As a commiter myself, I often get frustrated by these issues, since the only possible way for me to move forward on them is to ask for clarification over and over.
+If your report is shorter than two lines, it is almost certainly missing some of these, which makes it hard for us to respond to it. We're often too polite to close the issue outright, but the missing info makes misinterpretation likely. As a committer myself, I often get frustrated by these issues, since the only possible way for me to move forward on them is to ask for clarification over and over.
 
 For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the `-v` flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information.
 

README.md

@@ -400,7 +400,7 @@ which means you can modify it, redistribute it or use it however you like.
                                      downloading, similar to find's -exec
                                      syntax. Example: --exec 'adb push {}
                                      /sdcard/Music/ && rm {}'
-    --convert-subtitles FORMAT       Convert the subtitles to other format
+    --convert-subs FORMAT            Convert the subtitles to other format
                                      (currently supported: srt|ass|vtt)
 
 # CONFIGURATION
@@ -627,7 +627,7 @@ Either prepend `http://www.youtube.com/watch?v=` or separate the ID from the opt
 
 Use the `--cookies` option, for example `--cookies /path/to/cookies/file.txt`. Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows, `LF` (`\n`) for Linux and `CR` (`\r`) for Mac OS. `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format.
 
-Passing cookies to youtube-dl is a good way to workaround login when a particular extractor does not implement it explicitly.
+Passing cookies to youtube-dl is a good way to workaround login when a particular extractor does not implement it explicitly. Another use case is working around [CAPTCHA](https://en.wikipedia.org/wiki/CAPTCHA) some websites require you to solve in particular cases in order to get access (e.g. YouTube, CloudFlare).
 
 ### Can you add support for this anime video site, or site which shows current movies for free?
 
@@ -757,7 +757,7 @@ with youtube_dl.YoutubeDL(ydl_opts) as ydl:
     ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc'])
 ```
 
-Most likely, you'll want to use various options. For a list of what can be done, have a look at [youtube_dl/YoutubeDL.py](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L117-L265). For a start, if you want to intercept youtube-dl's output, set a `logger` object.
+Most likely, you'll want to use various options. For a list of what can be done, have a look at [`youtube_dl/YoutubeDL.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L121-L269). For a start, if you want to intercept youtube-dl's output, set a `logger` object.
 
 Here's a more complete example of a program that outputs only errors (and a short message after the download is finished), and downloads/converts the video to an mp3 file:
 
@@ -830,7 +830,7 @@ So please elaborate on what feature you are requesting, or what bug you want to
 - How it could be fixed
 - How your proposed solution would look like
 
-If your report is shorter than two lines, it is almost certainly missing some of these, which makes it hard for us to respond to it. We're often too polite to close the issue outright, but the missing info makes misinterpretation likely. As a commiter myself, I often get frustrated by these issues, since the only possible way for me to move forward on them is to ask for clarification over and over.
+If your report is shorter than two lines, it is almost certainly missing some of these, which makes it hard for us to respond to it. We're often too polite to close the issue outright, but the missing info makes misinterpretation likely. As a committer myself, I often get frustrated by these issues, since the only possible way for me to move forward on them is to ask for clarification over and over.
 
 For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the `-v` flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information.
 

devscripts/gh-pages/update-copyright.py

@@ -5,7 +5,7 @@ from __future__ import with_statement, unicode_literals
 
 import datetime
 import glob
-import io  # For Python 2 compatibilty
+import io  # For Python 2 compatibility
 import os
 import re
 

docs/supportedsites.md

@@ -1,6 +1,7 @@
 # Supported sites
  - **1tv**: Первый канал
  - **1up.com**
+ - **20min**
  - **220.ro**
  - **22tracks:genre**
  - **22tracks:track**
@@ -23,7 +24,6 @@
  - **AdobeTVShow**
  - **AdobeTVVideo**
  - **AdultSwim**
- - **Aftenposten**
  - **Aftonbladet**
  - **AirMozilla**
  - **AlJazeera**
@@ -34,9 +34,11 @@
  - **Aparat**
  - **AppleConnect**
  - **AppleDaily**: 臺灣蘋果日報
- - **AppleTrailers**
+ - **appletrailers**
+ - **appletrailers:section**
  - **archive.org**: archive.org videos
  - **ARD**
+ - **ARD:mediathek**: Saarländischer Rundfunk
  - **ARD:mediathek**
  - **arte.tv**
  - **arte.tv:+7**
@@ -63,11 +65,12 @@
  - **Beeg**
  - **BehindKink**
  - **Bet**
+ - **Bigflix**
  - **Bild**: Bild.de
  - **BiliBili**
+ - **BleacherReport**
+ - **BleacherReportCMS**
  - **blinkx**
- - **blip.tv:user**
- - **BlipTV**
  - **Bloomberg**
  - **Bpb**: Bundeszentrale für politische Bildung
  - **BR**: Bayerischer Rundfunk Mediathek
@@ -80,7 +83,6 @@
  - **BYUtv**
  - **Camdemy**
  - **CamdemyFolder**
- - **Canal13cl**
  - **canalc2.tv**
  - **Canalplus**: canalplus.fr, piwiplus.fr and d8.tv
  - **CBS**
@@ -125,8 +127,12 @@
  - **dailymotion:user**
  - **DailymotionCloud**
  - **daum.net**
+ - **daum.net:clip**
  - **DBTV**
  - **DCN**
+ - **dcn:live**
+ - **dcn:season**
+ - **dcn:video**
  - **DctpTv**
  - **DeezerPlaylist**
  - **defense.gouv.fr**
@@ -160,7 +166,7 @@
  - **Eporner**
  - **EroProfile**
  - **Escapist**
- - **ESPN** (Currently broken)
+ - **ESPN**
  - **EsriVideo**
  - **Europa**
  - **EveryonesMixtape**
@@ -177,11 +183,13 @@
  - **Flickr**
  - **Folketinget**: Folketinget (ft.dk; Danish parliament)
  - **FootyRoom**
+ - **FOX**
  - **Foxgay**
  - **FoxNews**: Fox News and Fox Business Video
  - **FoxSports**
  - **france2.fr:generation-quoi**
  - **FranceCulture**
+ - **FranceCultureEmission**
  - **FranceInter**
  - **francetv**: France 2, 3, 4, 5 and Ô
  - **francetvinfo.fr**
@@ -210,7 +218,9 @@
  - **GodTube**
  - **GoldenMoustache**
  - **Golem**
+ - **GoogleDrive**
  - **Goshgay**
+ - **GPUTechConf**
  - **Groupon**
  - **Hark**
  - **HearThisAt**
@@ -224,6 +234,7 @@
  - **hitbox:live**
  - **HornBunny**
  - **HotNewHipHop**
+ - **HotStar**
  - **Howcast**
  - **HowStuffWorks**
  - **HuffPost**: Huffington Post
@@ -241,17 +252,18 @@
  - **Instagram**
  - **instagram:user**: Instagram user profile
  - **InternetVideoArchive**
- - **IPrima**
+ - **IPrima** (Currently broken)
  - **iqiyi**: 爱奇艺
  - **Ir90Tv**
  - **ivi**: ivi.ru
  - **ivi:compilation**: ivi.ru compilations
+ - **ivideon**: Ivideon TV
  - **Izlesene**
  - **JadoreCettePub**
  - **JeuxVideo**
  - **Jove**
  - **jpopsuki.tv**
- - **Jukebox**
+ - **JWPlatform**
  - **Kaltura**
  - **KanalPlay**: Kanal 5/9/11 Play
  - **Kankan**
@@ -292,6 +304,7 @@
  - **m6**
  - **macgamestore**: MacGameStore trailers
  - **mailru**: Видео@Mail.Ru
+ - **MakerTV**
  - **Malemotion**
  - **MDR**: MDR.DE and KiKA
  - **media.ccc.de**
@@ -357,11 +370,13 @@
  - **Newstube**
  - **NextMedia**: 蘋果日報
  - **NextMediaActionNews**: 蘋果日報 - 動新聞
+ - **nextmovie.com**
  - **nfb**: National Film Board of Canada
  - **nfl.com**
  - **nhl.com**
  - **nhl.com:news**: NHL news
  - **nhl.com:videocenter**: NHL videocenter category
+ - **nick.com**
  - **niconico**: ニコニコ動画
  - **NiconicoPlaylist**
  - **njoy**: N-JOY
@@ -374,13 +389,14 @@
  - **nowness**
  - **nowness:playlist**
  - **nowness:series**
- - **NowTV**
+ - **NowTV** (Currently broken)
  - **NowTVList**
  - **nowvideo**: NowVideo
  - **npo**: npo.nl and ntr.nl
  - **npo.nl:live**
  - **npo.nl:radio**
  - **npo.nl:radio:fragment**
+ - **Npr**
  - **NRK**
  - **NRKPlaylist**
  - **NRKTV**: NRK TV and NRK Radio
@@ -395,16 +411,19 @@
  - **OnionStudios**
  - **Ooyala**
  - **OoyalaExternal**
+ - **OraTV**
  - **orf:fm4**: radio FM4
  - **orf:iptv**: iptv.ORF.at
  - **orf:oe1**: Radio Österreich 1
  - **orf:tvthek**: ORF TVthek
+ - **pandora.tv**: 판도라TV
  - **parliamentlive.tv**: UK parliament videos
  - **Patreon**
  - **pbs**: Public Broadcasting Service (PBS) and member stations: PBS: Public Broadcasting Service, APT - Alabama Public Television (WBIQ), GPB/Georgia Public Broadcasting (WGTV), Mississippi Public Broadcasting (WMPN), Nashville Public Television (WNPT), WFSU-TV (WFSU), WSRE (WSRE), WTCI (WTCI), WPBA/Channel 30 (WPBA), Alaska Public Media (KAKM), Arizona PBS (KAET), KNME-TV/Channel 5 (KNME), Vegas PBS (KLVX), AETN/ARKANSAS ETV NETWORK (KETS), KET (WKLE), WKNO/Channel 10 (WKNO), LPB/LOUISIANA PUBLIC BROADCASTING (WLPB), OETA (KETA), Ozarks Public Television (KOZK), WSIU Public Broadcasting (WSIU), KEET TV (KEET), KIXE/Channel 9 (KIXE), KPBS San Diego (KPBS), KQED (KQED), KVIE Public Television (KVIE), PBS SoCal/KOCE (KOCE), ValleyPBS (KVPT), CONNECTICUT PUBLIC TELEVISION (WEDH), KNPB Channel 5 (KNPB), SOPTV (KSYS), Rocky Mountain PBS (KRMA), KENW-TV3 (KENW), KUED Channel 7 (KUED), Wyoming PBS (KCWC), Colorado Public Television / KBDI 12 (KBDI), KBYU-TV (KBYU), Thirteen/WNET New York (WNET), WGBH/Channel 2 (WGBH), WGBY (WGBY), NJTV Public Media NJ (WNJT), WLIW21 (WLIW), mpt/Maryland Public Television (WMPB), WETA Television and Radio (WETA), WHYY (WHYY), PBS 39 (WLVT), WVPT - Your Source for PBS and More! (WVPT), Howard University Television (WHUT), WEDU PBS (WEDU), WGCU Public Media (WGCU), WPBT2 (WPBT), WUCF TV (WUCF), WUFT/Channel 5 (WUFT), WXEL/Channel 42 (WXEL), WLRN/Channel 17 (WLRN), WUSF Public Broadcasting (WUSF), ETV (WRLK), UNC-TV (WUNC), PBS Hawaii - Oceanic Cable Channel 10 (KHET), Idaho Public Television (KAID), KSPS (KSPS), OPB (KOPB), KWSU/Channel 10 & KTNW/Channel 31 (KWSU), WILL-TV (WILL), Network Knowledge - WSEC/Springfield (WSEC), WTTW11 (WTTW), Iowa Public Television/IPTV (KDIN), Nine Network (KETC), PBS39 Fort Wayne (WFWA), WFYI Indianapolis (WFYI), Milwaukee Public Television (WMVS), WNIN (WNIN), WNIT Public Television (WNIT), WPT (WPNE), WVUT/Channel 22 (WVUT), WEIU/Channel 51 (WEIU), WQPT-TV (WQPT), WYCC PBS Chicago (WYCC), WIPB-TV (WIPB), WTIU (WTIU), CET  (WCET), ThinkTVNetwork (WPTD), WBGU-TV (WBGU), WGVU TV (WGVU), NET1 (KUON), Pioneer Public Television (KWCM), SDPB Television (KUSD), TPT (KTCA), KSMQ (KSMQ), KPTS/Channel 8 (KPTS), KTWU/Channel 11 (KTWU), East Tennessee PBS (WSJK), WCTE-TV (WCTE), WLJT, Channel 11 (WLJT), WOSU TV (WOSU), WOUB/WOUC (WOUB), WVPB (WVPB), WKYU-PBS (WKYU), KERA 13 (KERA), MPBN (WCBB), Mountain Lake PBS (WCFE), NHPTV (WENH), Vermont PBS (WETK), witf (WITF), WQED Multimedia (WQED), WMHT Educational Telecommunications (WMHT), Q-TV (WDCQ), WTVS Detroit Public TV (WTVS), CMU Public Television (WCMU), WKAR-TV (WKAR), WNMU-TV Public TV 13 (WNMU), WDSE - WRPT (WDSE), WGTE TV (WGTE), Lakeland Public Television (KAWE), KMOS-TV - Channels 6.1, 6.2 and 6.3 (KMOS), MontanaPBS (KUSM), KRWG/Channel 22 (KRWG), KACV (KACV), KCOS/Channel 13 (KCOS), WCNY/Channel 24 (WCNY), WNED (WNED), WPBS (WPBS), WSKG Public TV (WSKG), WXXI (WXXI), WPSU (WPSU), WVIA Public Media Studios (WVIA), WTVI (WTVI), Western Reserve PBS (WNEO), WVIZ/PBS ideastream (WVIZ), KCTS 9 (KCTS), Basin PBS (KPBT), KUHT / Channel 8 (KUHT), KLRN (KLRN), KLRU (KLRU), WTJX Channel 12 (WTJX), WCVE PBS (WCVE), KBTC Public Television (KBTC)
+ - **pcmag**
  - **Periscope**: Periscope
  - **PhilharmonieDeParis**: Philharmonie de Paris
- - **Phoenix**
+ - **phoenix.de**
  - **Photobucket**
  - **Pinkbike**
  - **Pladform**
@@ -442,16 +461,20 @@
  - **radiofrance**
  - **RadioJavan**
  - **Rai**
+ - **RaiTV**
  - **RBMARadio**
  - **RDS**: RDS.ca
  - **RedTube**
+ - **RegioTV**
  - **Restudy**
  - **ReverbNation**
+ - **Revision3**
  - **RingTV**
  - **RottenTomatoes**
  - **Roxwel**
  - **RTBF**
- - **Rte**
+ - **rte**: Raidió Teilifís Éireann TV
+ - **rte:radio**: Raidió Teilifís Éireann radio
  - **rtl.nl**: rtl.nl and rtlxl.nl
  - **RTL2**
  - **RTP**
@@ -499,8 +522,6 @@
  - **SnagFilmsEmbed**
  - **Snotr**
  - **Sohu**
- - **soompi**
- - **soompi:show**
  - **soundcloud**
  - **soundcloud:playlist**
  - **soundcloud:search**: Soundcloud search
@@ -525,8 +546,8 @@
  - **SportBoxEmbed**
  - **SportDeutschland**
  - **Sportschau**
- - **Srf**
- - **SRMediathek**: Saarländischer Rundfunk
+ - **SRGSSR**
+ - **SRGSSRPlay**: srf.ch, rts.ch, rsi.ch, rtr.ch and swissinfo.ch play sites
  - **SSA**
  - **stanfordoc**: Stanford Open ClassRoom
  - **Steam**
@@ -551,14 +572,15 @@
  - **TechTalks**
  - **techtv.mit.edu**
  - **ted**
+ - **Tele13**
  - **TeleBruxelles**
  - **Telecinco**: telecinco.es, cuatro.com and mediaset.es
  - **Telegraaf**
  - **TeleMB**
  - **TeleTask**
  - **TenPlay**
- - **TestTube**
  - **TF1**
+ - **TheIntercept**
  - **TheOnion**
  - **ThePlatform**
  - **ThePlatformFeed**
@@ -568,11 +590,11 @@
  - **THVideo**
  - **THVideoPlaylist**
  - **tinypic**: tinypic.com videos
- - **tlc.com**
  - **tlc.de**
  - **TMZ**
  - **TMZArticle**
  - **TNAFlix**
+ - **toggle**
  - **tou.tv**
  - **Toypics**: Toypics user profile
  - **ToypicsUser**: Toypics user profile
@@ -581,9 +603,14 @@
  - **TruTube**
  - **Tube8**
  - **TubiTv**
- - **Tudou**
+ - **tudou**
+ - **tudou:album**
+ - **tudou:playlist**
  - **Tumblr**
- - **TuneIn**
+ - **tunein:clip**
+ - **tunein:program**
+ - **tunein:station**
+ - **tunein:topic**
  - **Turbo**
  - **Tutv**
  - **tv.dfb.de**
@@ -593,6 +620,7 @@
  - **TVC**
  - **TVCArticle**
  - **tvigle**: Интернет-телевидение Tvigle.ru
+ - **tvland.com**
  - **tvp.pl**
  - **tvp.pl:Series**
  - **TVPlay**: TV3Play and related services
@@ -622,7 +650,7 @@
  - **Vessel**
  - **Vesti**: Вести.Ru
  - **Vevo**
- - **VGTV**: VGTV and BTTV
+ - **VGTV**: VGTV, BTTV, FTV, Aftenposten and Aftonbladet
  - **vh1.com**
  - **Vice**
  - **Viddler**
@@ -630,9 +658,12 @@
  - **video.mit.edu**
  - **VideoDetective**
  - **videofy.me**
- - **VideoMega**
+ - **VideoMega** (Currently broken)
+ - **videomore**
+ - **videomore:season**
+ - **videomore:video**
  - **VideoPremium**
- - **VideoTt**: video.tt - Your True Tube
+ - **VideoTt**: video.tt - Your True Tube (Currently broken)
  - **videoweed**: VideoWeed
  - **Vidme**
  - **Vidzi**
@@ -711,6 +742,7 @@
  - **youtube:favorites**: YouTube.com favourite videos, ":ytfav" for short (requires authentication)
  - **youtube:history**: Youtube watch history, ":ythistory" for short (requires authentication)
  - **youtube:playlist**: YouTube.com playlists
+ - **youtube:playlists**: YouTube.com user/channel playlists
  - **youtube:recommended**: YouTube.com recommended videos, ":ytrec" for short (requires authentication)
  - **youtube:search**: YouTube.com searches
  - **youtube:search:date**: YouTube.com searches, newest videos first
@@ -718,7 +750,6 @@
  - **youtube:show**: YouTube.com (multi-season) shows
  - **youtube:subscriptions**: YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)
  - **youtube:user**: YouTube.com user videos (URL or "ytuser" keyword)
- - **youtube:user:playlists**: YouTube.com user playlists
  - **youtube:watchlater**: Youtube watch later list, ":ytwatchlater" for short (requires authentication)
  - **Zapiks**
  - **ZDF**

test/test_subtitles.py

@@ -11,7 +11,6 @@ from test.helper import FakeYDL, md5
 
 
 from youtube_dl.extractor import (
-    BlipTVIE,
     YoutubeIE,
     DailymotionIE,
     TEDIE,
@@ -145,18 +144,6 @@ class TestTedSubtitles(BaseTestSubtitles):
             self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang)
 
 
-class TestBlipTVSubtitles(BaseTestSubtitles):
-    url = 'http://blip.tv/a/a-6603250'
-    IE = BlipTVIE
-
-    def test_allsubtitles(self):
-        self.DL.params['writesubtitles'] = True
-        self.DL.params['allsubtitles'] = True
-        subtitles = self.getSubtitles()
-        self.assertEqual(set(subtitles.keys()), set(['en']))
-        self.assertEqual(md5(subtitles['en']), '5b75c300af65fe4476dff79478bb93e4')
-
-
 class TestVimeoSubtitles(BaseTestSubtitles):
     url = 'http://vimeo.com/76979871'
     IE = VimeoIE

test/test_utils.py

@@ -22,6 +22,7 @@ from youtube_dl.utils import (
     DateRange,
     detect_exe_version,
     determine_ext,
+    encode_compat_str,
     encodeFilename,
     escape_rfc3986,
     escape_url,
@@ -43,6 +44,7 @@ from youtube_dl.utils import (
     sanitize_path,
     prepend_extension,
     replace_extension,
+    remove_quotes,
     shell_quote,
     smuggle_url,
     str_to_int,
@@ -200,6 +202,15 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
         self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
 
+    def test_remove_quotes(self):
+        self.assertEqual(remove_quotes(None), None)
+        self.assertEqual(remove_quotes('"'), '"')
+        self.assertEqual(remove_quotes("'"), "'")
+        self.assertEqual(remove_quotes(';'), ';')
+        self.assertEqual(remove_quotes('";'), '";')
+        self.assertEqual(remove_quotes('""'), '')
+        self.assertEqual(remove_quotes('";"'), ';')
+
     def test_ordered_set(self):
         self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
         self.assertEqual(orderedSet([]), [])
@@ -439,6 +450,10 @@ class TestUtil(unittest.TestCase):
         data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
         self.assertTrue(isinstance(data, bytes))
 
+    def test_encode_compat_str(self):
+        self.assertEqual(encode_compat_str(b'\xd1\x82\xd0\xb5\xd1\x81\xd1\x82', 'utf-8'), 'тест')
+        self.assertEqual(encode_compat_str('тест', 'utf-8'), 'тест')
+
     def test_parse_iso8601(self):
         self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
         self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
@@ -651,12 +666,13 @@ ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
             {'like_count': 190, 'dislike_count': 10}))
 
     def test_parse_dfxp_time_expr(self):
-        self.assertEqual(parse_dfxp_time_expr(None), 0.0)
-        self.assertEqual(parse_dfxp_time_expr(''), 0.0)
+        self.assertEqual(parse_dfxp_time_expr(None), None)
+        self.assertEqual(parse_dfxp_time_expr(''), None)
         self.assertEqual(parse_dfxp_time_expr('0.1'), 0.1)
         self.assertEqual(parse_dfxp_time_expr('0.1s'), 0.1)
         self.assertEqual(parse_dfxp_time_expr('00:00:01'), 1.0)
         self.assertEqual(parse_dfxp_time_expr('00:00:01.100'), 1.1)
+        self.assertEqual(parse_dfxp_time_expr('00:00:01:100'), 1.1)
 
     def test_dfxp2srt(self):
         dfxp_data = '''<?xml version="1.0" encoding="UTF-8"?>
@@ -666,6 +682,9 @@ ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
                     <p begin="0" end="1">The following line contains Chinese characters and special symbols</p>
                     <p begin="1" end="2">第二行<br/>♪♪</p>
                     <p begin="2" dur="1"><span>Third<br/>Line</span></p>
+                    <p begin="3" end="-1">Lines with invalid timestamps are ignored</p>
+                    <p begin="-1" end="-1">Ignore, two</p>
+                    <p begin="3" dur="-1">Ignored, three</p>
                 </div>
             </body>
             </tt>'''

test/test_write_annotations.py

@@ -66,7 +66,7 @@ class TestAnnotations(unittest.TestCase):
                 textTag = a.find('TEXT')
                 text = textTag.text
                 self.assertTrue(text in expected)  # assertIn only added in python 2.7
-                # remove the first occurance, there could be more than one annotation with the same text
+                # remove the first occurrence, there could be more than one annotation with the same text
                 expected.remove(text)
         # We should have seen (and removed) all the expected annotation texts.
         self.assertEqual(len(expected), 0, 'Not all expected annotations were found.')

youtube_dl/YoutubeDL.py

@@ -47,7 +47,9 @@ from .utils import (
     DEFAULT_OUTTMPL,
     determine_ext,
     DownloadError,
+    encode_compat_str,
     encodeFilename,
+    error_to_compat_str,
     ExtractorError,
     format_bytes,
     formatSeconds,
@@ -495,7 +497,7 @@ class YoutubeDL(object):
                     tb = ''
                     if hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]:
                         tb += ''.join(traceback.format_exception(*sys.exc_info()[1].exc_info))
-                    tb += compat_str(traceback.format_exc())
+                    tb += encode_compat_str(traceback.format_exc())
                 else:
                     tb_data = traceback.format_list(traceback.extract_stack())
                     tb = ''.join(tb_data)
@@ -674,14 +676,14 @@ class YoutubeDL(object):
                     return self.process_ie_result(ie_result, download, extra_info)
                 else:
                     return ie_result
-            except ExtractorError as de:  # An error we somewhat expected
-                self.report_error(compat_str(de), de.format_traceback())
+            except ExtractorError as e:  # An error we somewhat expected
+                self.report_error(compat_str(e), e.format_traceback())
                 break
             except MaxDownloadsReached:
                 raise
             except Exception as e:
                 if self.params.get('ignoreerrors', False):
-                    self.report_error(compat_str(e), tb=compat_str(traceback.format_exc()))
+                    self.report_error(error_to_compat_str(e), tb=encode_compat_str(traceback.format_exc()))
                     break
                 else:
                     raise
@@ -1310,7 +1312,7 @@ class YoutubeDL(object):
             # only set the 'formats' fields if the original info_dict list them
             # otherwise we end up with a circular reference, the first (and unique)
             # element in the 'formats' field in info_dict is info_dict itself,
-            # wich can't be exported to json
+            # which can't be exported to json
             info_dict['formats'] = formats
         if self.params.get('listformats'):
             self.list_formats(info_dict)
@@ -1459,7 +1461,7 @@ class YoutubeDL(object):
             if dn and not os.path.exists(dn):
                 os.makedirs(dn)
         except (OSError, IOError) as err:
-            self.report_error('unable to create directory ' + compat_str(err))
+            self.report_error('unable to create directory ' + error_to_compat_str(err))
             return
 
         if self.params.get('writedescription', False):
@@ -1510,7 +1512,7 @@ class YoutubeDL(object):
                             sub_info['url'], info_dict['id'], note=False)
                     except ExtractorError as err:
                         self.report_warning('Unable to download subtitle for "%s": %s' %
-                                            (sub_lang, compat_str(err.cause)))
+                                            (sub_lang, error_to_compat_str(err.cause)))
                         continue
                 try:
                     sub_filename = subtitles_filename(filename, sub_lang, sub_format)
@@ -1789,6 +1791,10 @@ class YoutubeDL(object):
         res = ''
         if fdict.get('ext') in ['f4f', 'f4m']:
             res += '(unsupported) '
+        if fdict.get('language'):
+            if res:
+                res += ' '
+            res += '[%s]' % fdict['language']
         if fdict.get('format_note') is not None:
             res += fdict['format_note'] + ' '
         if fdict.get('tbr') is not None:
@@ -2039,4 +2045,4 @@ class YoutubeDL(object):
                                    (info_dict['extractor'], info_dict['id'], thumb_display_id, thumb_filename))
                 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
                     self.report_warning('Unable to download thumbnail "%s": %s' %
-                                        (t['url'], compat_str(err)))
+                                        (t['url'], error_to_compat_str(err)))

youtube_dl/downloader/common.py

@@ -5,9 +5,9 @@ import re
 import sys
 import time
 
-from ..compat import compat_str
 from ..utils import (
     encodeFilename,
+    error_to_compat_str,
     decodeArgument,
     format_bytes,
     timeconvert,
@@ -186,7 +186,7 @@ class FileDownloader(object):
                 return
             os.rename(encodeFilename(old_filename), encodeFilename(new_filename))
         except (IOError, OSError) as err:
-            self.report_error('unable to rename file: %s' % compat_str(err))
+            self.report_error('unable to rename file: %s' % error_to_compat_str(err))
 
     def try_utime(self, filename, last_modified_hdr):
         """Try to set the last-modified time of the given file."""

youtube_dl/downloader/fragment.py

@@ -59,37 +59,43 @@ class FragmentFD(FileDownloader):
             'filename': ctx['filename'],
             'tmpfilename': ctx['tmpfilename'],
         }
+
         start = time.time()
-        ctx['started'] = start
+        ctx.update({
+            'started': start,
+            # Total complete fragments downloaded so far in bytes
+            'complete_frags_downloaded_bytes': 0,
+            # Amount of fragment's bytes downloaded by the time of the previous
+            # frag progress hook invocation
+            'prev_frag_downloaded_bytes': 0,
+        })
 
         def frag_progress_hook(s):
             if s['status'] not in ('downloading', 'finished'):
                 return
 
-            frag_total_bytes = s.get('total_bytes', 0)
-            if s['status'] == 'finished':
-                state['downloaded_bytes'] += frag_total_bytes
-                state['frag_index'] += 1
+            frag_total_bytes = s.get('total_bytes') or 0
 
             estimated_size = (
-                (state['downloaded_bytes'] + frag_total_bytes) /
+                (ctx['complete_frags_downloaded_bytes'] + frag_total_bytes) /
                 (state['frag_index'] + 1) * total_frags)
             time_now = time.time()
             state['total_bytes_estimate'] = estimated_size
             state['elapsed'] = time_now - start
 
             if s['status'] == 'finished':
-                progress = self.calc_percent(state['frag_index'], total_frags)
+                state['frag_index'] += 1
+                state['downloaded_bytes'] += frag_total_bytes - ctx['prev_frag_downloaded_bytes']
+                ctx['complete_frags_downloaded_bytes'] = state['downloaded_bytes']
+                ctx['prev_frag_downloaded_bytes'] = 0
             else:
                 frag_downloaded_bytes = s['downloaded_bytes']
-                frag_progress = self.calc_percent(frag_downloaded_bytes,
-                                                  frag_total_bytes)
-                progress = self.calc_percent(state['frag_index'], total_frags)
-                progress += frag_progress / float(total_frags)
-
+                state['downloaded_bytes'] += frag_downloaded_bytes - ctx['prev_frag_downloaded_bytes']
                 state['eta'] = self.calc_eta(
-                    start, time_now, estimated_size, state['downloaded_bytes'] + frag_downloaded_bytes)
+                    start, time_now, estimated_size,
+                    state['downloaded_bytes'])
                 state['speed'] = s.get('speed')
+                ctx['prev_frag_downloaded_bytes'] = frag_downloaded_bytes
             self._hook_progress(state)
 
         ctx['dl'].add_progress_hook(frag_progress_hook)

youtube_dl/downloader/hls.py

@@ -46,7 +46,7 @@ class HlsFD(FileDownloader):
 
         self._debug_cmd(args)
 
-        retval = subprocess.call(args)
+        retval = subprocess.call(args, stdin=subprocess.PIPE)
         if retval == 0:
             fsize = os.path.getsize(encodeFilename(tmpfilename))
             self.to_screen('\r[%s] %s bytes' % (args[0], fsize))

youtube_dl/extractor/__init__.py

@@ -15,7 +15,6 @@ from .adobetv import (
     AdobeTVVideoIE,
 )
 from .adultswim import AdultSwimIE
-from .aftenposten import AftenpostenIE
 from .aftonbladet import AftonbladetIE
 from .airmozilla import AirMozillaIE
 from .aljazeera import AlJazeeraIE
@@ -26,7 +25,10 @@ from .aol import AolIE
 from .allocine import AllocineIE
 from .aparat import AparatIE
 from .appleconnect import AppleConnectIE
-from .appletrailers import AppleTrailersIE
+from .appletrailers import (
+    AppleTrailersIE,
+    AppleTrailersSectionIE,
+)
 from .archiveorg import ArchiveOrgIE
 from .ard import (
     ARDIE,
@@ -59,10 +61,14 @@ from .beeg import BeegIE
 from .behindkink import BehindKinkIE
 from .beatportpro import BeatportProIE
 from .bet import BetIE
+from .bigflix import BigflixIE
 from .bild import BildIE
 from .bilibili import BiliBiliIE
+from .bleacherreport import (
+    BleacherReportIE,
+    BleacherReportCMSIE,
+)
 from .blinkx import BlinkxIE
-from .bliptv import BlipTVIE, BlipTVUserIE
 from .bloomberg import BloombergIE
 from .bpb import BpbIE
 from .br import BRIE
@@ -78,7 +84,6 @@ from .camdemy import (
     CamdemyIE,
     CamdemyFolderIE
 )
-from .canal13cl import Canal13clIE
 from .canalplus import CanalplusIE
 from .canalc2 import Canalc2IE
 from .cbs import CBSIE
@@ -129,9 +134,17 @@ from .dailymotion import (
     DailymotionUserIE,
     DailymotionCloudIE,
 )
-from .daum import DaumIE
+from .daum import (
+    DaumIE,
+    DaumClipIE,
+)
 from .dbtv import DBTVIE
-from .dcn import DCNIE
+from .dcn import (
+    DCNIE,
+    DCNVideoIE,
+    DCNLiveIE,
+    DCNSeasonIE,
+)
 from .dctp import DctpTvIE
 from .deezer import DeezerPlaylistIE
 from .democracynow import DemocracynowIE
@@ -191,10 +204,14 @@ from .flickr import FlickrIE
 from .folketinget import FolketingetIE
 from .footyroom import FootyRoomIE
 from .fourtube import FourTubeIE
+from .fox import FOXIE
 from .foxgay import FoxgayIE
 from .foxnews import FoxNewsIE
 from .foxsports import FoxSportsIE
-from .franceculture import FranceCultureIE
+from .franceculture import (
+    FranceCultureIE,
+    FranceCultureEmissionIE,
+)
 from .franceinter import FranceInterIE
 from .francetv import (
     PluzzIE,
@@ -232,9 +249,11 @@ from .globo import (
 from .godtube import GodTubeIE
 from .goldenmoustache import GoldenMoustacheIE
 from .golem import GolemIE
+from .googledrive import GoogleDriveIE
 from .googleplus import GooglePlusIE
 from .googlesearch import GoogleSearchIE
 from .goshgay import GoshgayIE
+from .gputechconf import GPUTechConfIE
 from .groupon import GrouponIE
 from .hark import HarkIE
 from .hearthisat import HearThisAtIE
@@ -247,12 +266,17 @@ from .history import HistoryIE
 from .hitbox import HitboxIE, HitboxLiveIE
 from .hornbunny import HornBunnyIE
 from .hotnewhiphop import HotNewHipHopIE
+from .hotstar import HotStarIE
 from .howcast import HowcastIE
 from .howstuffworks import HowStuffWorksIE
 from .huffpost import HuffPostIE
 from .hypem import HypemIE
 from .iconosquare import IconosquareIE
-from .ign import IGNIE, OneUPIE
+from .ign import (
+    IGNIE,
+    OneUPIE,
+    PCMagIE,
+)
 from .imdb import (
     ImdbIE,
     ImdbListIE
@@ -276,11 +300,12 @@ from .ivi import (
     IviIE,
     IviCompilationIE
 )
+from .ivideon import IvideonIE
 from .izlesene import IzleseneIE
 from .jadorecettepub import JadoreCettePubIE
 from .jeuxvideo import JeuxVideoIE
 from .jove import JoveIE
-from .jukebox import JukeboxIE
+from .jwplatform import JWPlatformIE
 from .jpopsukitv import JpopsukiIE
 from .kaltura import KalturaIE
 from .kanalplay import KanalPlayIE
@@ -335,6 +360,7 @@ from .lynda import (
 from .m6 import M6IE
 from .macgamestore import MacGameStoreIE
 from .mailru import MailRuIE
+from .makertv import MakerTVIE
 from .malemotion import MalemotionIE
 from .mdr import MDRIE
 from .metacafe import MetacafeIE
@@ -410,6 +436,7 @@ from .nextmedia import (
     NextMediaActionNewsIE,
     AppleDailyIE,
 )
+from .nextmovie import NextMovieIE
 from .nfb import NFBIE
 from .nfl import NFLIE
 from .nhl import (
@@ -417,6 +444,7 @@ from .nhl import (
     NHLNewsIE,
     NHLVideocenterIE,
 )
+from .nick import NickIE
 from .niconico import NiconicoIE, NiconicoPlaylistIE
 from .ninegag import NineGagIE
 from .noco import NocoIE
@@ -447,6 +475,7 @@ from .npo import (
     VPROIE,
     WNLIE
 )
+from .npr import NprIE
 from .nrk import (
     NRKIE,
     NRKPlaylistIE,
@@ -466,12 +495,14 @@ from .ooyala import (
     OoyalaIE,
     OoyalaExternalIE,
 )
+from .ora import OraTVIE
 from .orf import (
     ORFTVthekIE,
     ORFOE1IE,
     ORFFM4IE,
     ORFIPTVIE,
 )
+from .pandoratv import PandoraTVIE
 from .parliamentliveuk import ParliamentLiveUKIE
 from .patreon import PatreonIE
 from .pbs import PBSIE
@@ -519,18 +550,23 @@ from .radiode import RadioDeIE
 from .radiojavan import RadioJavanIE
 from .radiobremen import RadioBremenIE
 from .radiofrance import RadioFranceIE
-from .rai import RaiIE
+from .rai import (
+    RaiTVIE,
+    RaiIE,
+)
 from .rbmaradio import RBMARadioIE
 from .rds import RDSIE
 from .redtube import RedTubeIE
+from .regiotv import RegioTVIE
 from .restudy import RestudyIE
 from .reverbnation import ReverbNationIE
+from .revision3 import Revision3IE
 from .ringtv import RingTVIE
 from .ro220 import Ro220IE
 from .rottentomatoes import RottenTomatoesIE
 from .roxwel import RoxwelIE
 from .rtbf import RTBFIE
-from .rte import RteIE
+from .rte import RteIE, RteRadioIE
 from .rtlnl import RtlNlIE
 from .rtl2 import RTL2IE
 from .rtp import RTPIE
@@ -585,10 +621,6 @@ from .snagfilms import (
 )
 from .snotr import SnotrIE
 from .sohu import SohuIE
-from .soompi import (
-    SoompiIE,
-    SoompiShowIE,
-)
 from .soundcloud import (
     SoundcloudIE,
     SoundcloudSetIE,
@@ -620,7 +652,10 @@ from .sportbox import (
     SportBoxEmbedIE,
 )
 from .sportdeutschland import SportDeutschlandIE
-from .srf import SrfIE
+from .srgssr import (
+    SRGSSRIE,
+    SRGSSRPlayIE,
+)
 from .srmediathek import SRMediathekIE
 from .ssa import SSAIE
 from .stanfordoc import StanfordOpenClassroomIE
@@ -647,6 +682,7 @@ from .teachingchannel import TeachingChannelIE
 from .teamcoco import TeamcocoIE
 from .techtalks import TechTalksIE
 from .ted import TEDIE
+from .tele13 import Tele13IE
 from .telebruxelles import TeleBruxellesIE
 from .telecinco import TelecincoIE
 from .telegraaf import TelegraafIE
@@ -654,8 +690,8 @@ from .telemb import TeleMBIE
 from .teletask import TeleTaskIE
 from .tenplay import TenPlayIE
 from .testurl import TestURLIE
-from .testtube import TestTubeIE
 from .tf1 import TF1IE
+from .theintercept import TheInterceptIE
 from .theonion import TheOnionIE
 from .theplatform import (
     ThePlatformIE,
@@ -665,7 +701,7 @@ from .thesixtyone import TheSixtyOneIE
 from .thisamericanlife import ThisAmericanLifeIE
 from .thisav import ThisAVIE
 from .tinypic import TinyPicIE
-from .tlc import TlcIE, TlcDeIE
+from .tlc import TlcDeIE
 from .tmz import (
     TMZIE,
     TMZArticleIE,
@@ -675,6 +711,7 @@ from .tnaflix import (
     EMPFlixIE,
     MovieFapIE,
 )
+from .toggle import ToggleIE
 from .thvideo import (
     THVideoIE,
     THVideoPlaylistIE
@@ -686,9 +723,19 @@ from .trilulilu import TriluliluIE
 from .trutube import TruTubeIE
 from .tube8 import Tube8IE
 from .tubitv import TubiTvIE
-from .tudou import TudouIE
+from .tudou import (
+    TudouIE,
+    TudouPlaylistIE,
+    TudouAlbumIE,
+)
 from .tumblr import TumblrIE
-from .tunein import TuneInIE
+from .tunein import (
+    TuneInClipIE,
+    TuneInStationIE,
+    TuneInProgramIE,
+    TuneInTopicIE,
+    TuneInShortenerIE,
+)
 from .turbo import TurboIE
 from .tutv import TutvIE
 from .tv2 import (
@@ -701,10 +748,12 @@ from .tvc import (
     TVCArticleIE,
 )
 from .tvigle import TvigleIE
+from .tvland import TVLandIE
 from .tvp import TvpIE, TvpSeriesIE
 from .tvplay import TVPlayIE
 from .tweakers import TweakersIE
 from .twentyfourvideo import TwentyFourVideoIE
+from .twentymin import TwentyMinutenIE
 from .twentytwotracks import (
     TwentyTwoTracksIE,
     TwentyTwoTracksGenreIE
@@ -747,6 +796,11 @@ from .viddler import ViddlerIE
 from .videodetective import VideoDetectiveIE
 from .videofyme import VideofyMeIE
 from .videomega import VideoMegaIE
+from .videomore import (
+    VideomoreIE,
+    VideomoreVideoIE,
+    VideomoreSeasonIE,
+)
 from .videopremium import VideoPremiumIE
 from .videott import VideoTtIE
 from .vidme import VidmeIE
@@ -850,7 +904,7 @@ from .youtube import (
     YoutubeTruncatedIDIE,
     YoutubeTruncatedURLIE,
     YoutubeUserIE,
-    YoutubeUserPlaylistsIE,
+    YoutubePlaylistsIE,
     YoutubeWatchLaterIE,
 )
 from .zapiks import ZapiksIE

youtube_dl/extractor/abc.py

@@ -23,6 +23,7 @@ class ABCIE(InfoExtractor):
             'title': 'Australia to help staff Ebola treatment centre in Sierra Leone',
             'description': 'md5:809ad29c67a05f54eb41f2a105693a67',
         },
+        'skip': 'this video has expired',
     }, {
         'url': 'http://www.abc.net.au/news/2015-08-17/warren-entsch-introduces-same-sex-marriage-bill/6702326',
         'md5': 'db2a5369238b51f9811ad815b69dc086',
@@ -36,6 +37,7 @@ class ABCIE(InfoExtractor):
             'title': 'Marriage Equality: Warren Entsch introduces same sex marriage bill',
         },
         'add_ie': ['Youtube'],
+        'skip': 'Not accessible from Travis CI server',
     }, {
         'url': 'http://www.abc.net.au/news/2015-10-23/nab-lifts-interest-rates-following-westpac-and-cba/6880080',
         'md5': 'b96eee7c9edf4fc5a358a0252881cc1f',
@@ -58,6 +60,9 @@ class ABCIE(InfoExtractor):
             r'inline(?P<type>Video|Audio|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
             webpage)
         if mobj is None:
+            expired = self._html_search_regex(r'(?s)class="expired-(?:video|audio)".+?<span>(.+?)</span>', webpage, 'expired', None)
+            if expired:
+                raise ExtractorError('%s said: %s' % (self.IE_NAME, expired), expected=True)
             raise ExtractorError('Unable to extract video urls')
 
         urls_info = self._parse_json(

youtube_dl/extractor/abc7news.py

@@ -44,7 +44,6 @@ class Abc7NewsIE(InfoExtractor):
             'contentURL', webpage, 'm3u8 url', fatal=True)
 
         formats = self._extract_m3u8_formats(m3u8, display_id, 'mp4')
-        self._sort_formats(formats)
 
         title = self._og_search_title(webpage).strip()
         description = self._og_search_description(webpage).strip()

youtube_dl/extractor/adultswim.py

@@ -68,7 +68,7 @@ class AdultSwimIE(InfoExtractor):
                 'md5': '3e346a2ab0087d687a05e1e7f3b3e529',
                 'info_dict': {
                     'id': 'sY3cMUR_TbuE4YmdjzbIcQ-0',
-                    'ext': 'flv',
+                    'ext': 'mp4',
                     'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
                     'description': 'Dr. Brule reports live from Wine Country with a special report on wines.  \r\nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.\r\n\r\n',
                 },
@@ -79,6 +79,10 @@ class AdultSwimIE(InfoExtractor):
             'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
             'description': 'Dr. Brule reports live from Wine Country with a special report on wines.  \r\nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.\r\n\r\n',
         },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
     }]
 
     @staticmethod
@@ -183,7 +187,8 @@ class AdultSwimIE(InfoExtractor):
                 media_url = file_el.text
                 if determine_ext(media_url) == 'm3u8':
                     formats.extend(self._extract_m3u8_formats(
-                        media_url, segment_title, 'mp4', preference=0, m3u8_id='hls'))
+                        media_url, segment_title, 'mp4', preference=0,
+                        m3u8_id='hls', fatal=False))
                 else:
                     formats.append({
                         'format_id': '%s_%s' % (bitrate, ftype),

youtube_dl/extractor/aftenposten.py

@@ -1,23 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-
-
-class AftenpostenIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?aftenposten\.no/webtv/(?:#!/)?video/(?P<id>\d+)'
-    _TEST = {
-        'url': 'http://www.aftenposten.no/webtv/#!/video/21039/trailer-sweatshop-i-can-t-take-any-more',
-        'md5': 'fd828cd29774a729bf4d4425fe192972',
-        'info_dict': {
-            'id': '21039',
-            'ext': 'mov',
-            'title': 'TRAILER: "Sweatshop" - I can´t take any more',
-            'description': 'md5:21891f2b0dd7ec2f78d84a50e54f8238',
-            'timestamp': 1416927969,
-            'upload_date': '20141125',
-        }
-    }
-
-    def _real_extract(self, url):
-        return self.url_result('xstream:ap:%s' % self._match_id(url), 'Xstream')

youtube_dl/extractor/amp.py

@@ -0,0 +1,81 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+)
+
+
+class AMPIE(InfoExtractor):
+    # parse Akamai Adaptive Media Player feed
+    def _extract_feed_info(self, url):
+        item = self._download_json(
+            url, None, 'Downloading Akamai AMP feed',
+            'Unable to download Akamai AMP feed')['channel']['item']
+
+        video_id = item['guid']
+
+        def get_media_node(name, default=None):
+            media_name = 'media-%s' % name
+            media_group = item.get('media-group') or item
+            return media_group.get(media_name) or item.get(media_name) or item.get(name, default)
+
+        thumbnails = []
+        media_thumbnail = get_media_node('thumbnail')
+        if media_thumbnail:
+            if isinstance(media_thumbnail, dict):
+                media_thumbnail = [media_thumbnail]
+            for thumbnail_data in media_thumbnail:
+                thumbnail = thumbnail_data['@attributes']
+                thumbnails.append({
+                    'url': self._proto_relative_url(thumbnail['url'], 'http:'),
+                    'width': int_or_none(thumbnail.get('width')),
+                    'height': int_or_none(thumbnail.get('height')),
+                })
+
+        subtitles = {}
+        media_subtitle = get_media_node('subTitle')
+        if media_subtitle:
+            if isinstance(media_subtitle, dict):
+                media_subtitle = [media_subtitle]
+            for subtitle_data in media_subtitle:
+                subtitle = subtitle_data['@attributes']
+                lang = subtitle.get('lang') or 'en'
+                subtitles[lang] = [{'url': subtitle['href']}]
+
+        formats = []
+        media_content = get_media_node('content')
+        if isinstance(media_content, dict):
+            media_content = [media_content]
+        for media_data in media_content:
+            media = media_data['@attributes']
+            media_type = media['type']
+            if media_type == 'video/f4m':
+                formats.extend(self._extract_f4m_formats(
+                    media['url'] + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124',
+                    video_id, f4m_id='hds', fatal=False))
+            elif media_type == 'application/x-mpegURL':
+                formats.extend(self._extract_m3u8_formats(
+                    media['url'], video_id, 'mp4', m3u8_id='hls', fatal=False))
+            else:
+                formats.append({
+                    'format_id': media_data['media-category']['@attributes']['label'],
+                    'url': media['url'],
+                    'tbr': int_or_none(media.get('bitrate')),
+                    'filesize': int_or_none(media.get('fileSize')),
+                })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': get_media_node('title'),
+            'description': get_media_node('description'),
+            'thumbnails': thumbnails,
+            'timestamp': parse_iso8601(item.get('pubDate'), ' '),
+            'duration': int_or_none(media_content[0].get('@attributes', {}).get('duration')),
+            'subtitles': subtitles,
+            'formats': formats,
+        }

youtube_dl/extractor/appletrailers.py

@@ -11,6 +11,7 @@ from ..utils import (
 
 
 class AppleTrailersIE(InfoExtractor):
+    IE_NAME = 'appletrailers'
     _VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/(?:trailers|ca)/(?P<company>[^/]+)/(?P<movie>[^/]+)'
     _TESTS = [{
         'url': 'http://trailers.apple.com/trailers/wb/manofsteel/',
@@ -63,6 +64,12 @@ class AppleTrailersIE(InfoExtractor):
                 },
             },
         ]
+    }, {
+        'url': 'http://trailers.apple.com/trailers/magnolia/blackthorn/',
+        'info_dict': {
+            'id': 'blackthorn',
+        },
+        'playlist_mincount': 2,
     }, {
         'url': 'http://trailers.apple.com/ca/metropole/autrui/',
         'only_matching': True,
@@ -79,7 +86,7 @@ class AppleTrailersIE(InfoExtractor):
 
         def fix_html(s):
             s = re.sub(r'(?s)<script[^<]*?>.*?</script>', '', s)
-            s = re.sub(r'<img ([^<]*?)>', r'<img \1/>', s)
+            s = re.sub(r'<img ([^<]*?)/?>', r'<img \1/>', s)
             # The ' in the onClick attributes are not escaped, it couldn't be parsed
             # like: http://trailers.apple.com/trailers/wb/gravity/
 
@@ -96,6 +103,9 @@ class AppleTrailersIE(InfoExtractor):
             trailer_info_json = self._search_regex(self._JSON_RE,
                                                    on_click, 'trailer info')
             trailer_info = json.loads(trailer_info_json)
+            first_url = trailer_info.get('url')
+            if not first_url:
+                continue
             title = trailer_info['title']
             video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower()
             thumbnail = li.find('.//img').attrib['src']
@@ -107,7 +117,6 @@ class AppleTrailersIE(InfoExtractor):
             if m:
                 duration = 60 * int(m.group('minutes')) + int(m.group('seconds'))
 
-            first_url = trailer_info['url']
             trailer_id = first_url.split('/')[-1].rpartition('_')[0].lower()
             settings_json_url = compat_urlparse.urljoin(url, 'includes/settings/%s.json' % trailer_id)
             settings = self._download_json(settings_json_url, trailer_id, 'Downloading settings json')
@@ -144,3 +153,76 @@ class AppleTrailersIE(InfoExtractor):
             'id': movie,
             'entries': playlist,
         }
+
+
+class AppleTrailersSectionIE(InfoExtractor):
+    IE_NAME = 'appletrailers:section'
+    _SECTIONS = {
+        'justadded': {
+            'feed_path': 'just_added',
+            'title': 'Just Added',
+        },
+        'exclusive': {
+            'feed_path': 'exclusive',
+            'title': 'Exclusive',
+        },
+        'justhd': {
+            'feed_path': 'just_hd',
+            'title': 'Just HD',
+        },
+        'mostpopular': {
+            'feed_path': 'most_pop',
+            'title': 'Most Popular',
+        },
+        'moviestudios': {
+            'feed_path': 'studios',
+            'title': 'Movie Studios',
+        },
+    }
+    _VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/#section=(?P<id>%s)' % '|'.join(_SECTIONS)
+    _TESTS = [{
+        'url': 'http://trailers.apple.com/#section=justadded',
+        'info_dict': {
+            'title': 'Just Added',
+            'id': 'justadded',
+        },
+        'playlist_mincount': 80,
+    }, {
+        'url': 'http://trailers.apple.com/#section=exclusive',
+        'info_dict': {
+            'title': 'Exclusive',
+            'id': 'exclusive',
+        },
+        'playlist_mincount': 80,
+    }, {
+        'url': 'http://trailers.apple.com/#section=justhd',
+        'info_dict': {
+            'title': 'Just HD',
+            'id': 'justhd',
+        },
+        'playlist_mincount': 80,
+    }, {
+        'url': 'http://trailers.apple.com/#section=mostpopular',
+        'info_dict': {
+            'title': 'Most Popular',
+            'id': 'mostpopular',
+        },
+        'playlist_mincount': 80,
+    }, {
+        'url': 'http://trailers.apple.com/#section=moviestudios',
+        'info_dict': {
+            'title': 'Movie Studios',
+            'id': 'moviestudios',
+        },
+        'playlist_mincount': 80,
+    }]
+
+    def _real_extract(self, url):
+        section = self._match_id(url)
+        section_data = self._download_json(
+            'http://trailers.apple.com/trailers/home/feeds/%s.json' % self._SECTIONS[section]['feed_path'],
+            section)
+        entries = [
+            self.url_result('http://trailers.apple.com' + e['location'])
+            for e in section_data]
+        return self.playlist_result(entries, section, self._SECTIONS[section]['title'])

youtube_dl/extractor/ard.py

@@ -110,13 +110,15 @@ class ARDMediathekIE(InfoExtractor):
                 server = stream.get('_server')
                 for stream_url in stream_urls:
                     ext = determine_ext(stream_url)
+                    if quality != 'auto' and ext in ('f4m', 'm3u8'):
+                        continue
                     if ext == 'f4m':
                         formats.extend(self._extract_f4m_formats(
                             stream_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124',
-                            video_id, preference=-1, f4m_id='hds'))
+                            video_id, preference=-1, f4m_id='hds', fatal=False))
                     elif ext == 'm3u8':
                         formats.extend(self._extract_m3u8_formats(
-                            stream_url, video_id, 'mp4', preference=1, m3u8_id='hls'))
+                            stream_url, video_id, 'mp4', preference=1, m3u8_id='hls', fatal=False))
                     else:
                         if server and server.startswith('rtmp'):
                             f = {

youtube_dl/extractor/arte.py

@@ -68,9 +68,13 @@ class ArteTVPlus7IE(InfoExtractor):
     def _extract_url_info(cls, url):
         mobj = re.match(cls._VALID_URL, url)
         lang = mobj.group('lang')
-        # This is not a real id, it can be for example AJT for the news
-        # http://www.arte.tv/guide/fr/emissions/AJT/arte-journal
-        video_id = mobj.group('id')
+        query = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
+        if 'vid' in query:
+            video_id = query['vid'][0]
+        else:
+            # This is not a real id, it can be for example AJT for the news
+            # http://www.arte.tv/guide/fr/emissions/AJT/arte-journal
+            video_id = mobj.group('id')
         return video_id, lang
 
     def _real_extract(self, url):
@@ -79,9 +83,15 @@ class ArteTVPlus7IE(InfoExtractor):
         return self._extract_from_webpage(webpage, video_id, lang)
 
     def _extract_from_webpage(self, webpage, video_id, lang):
+        patterns_templates = (r'arte_vp_url=["\'](.*?%s.*?)["\']', r'data-url=["\']([^"]+%s[^"]+)["\']')
+        ids = (video_id, '')
+        # some pages contain multiple videos (like
+        # http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D),
+        # so we first try to look for json URLs that contain the video id from
+        # the 'vid' parameter.
+        patterns = [t % re.escape(_id) for _id in ids for t in patterns_templates]
         json_url = self._html_search_regex(
-            [r'arte_vp_url=["\'](.*?)["\']', r'data-url=["\']([^"]+)["\']'],
-            webpage, 'json vp url', default=None)
+            patterns, webpage, 'json vp url', default=None)
         if not json_url:
             iframe_url = self._html_search_regex(
                 r'<iframe[^>]+src=(["\'])(?P<url>.+\bjson_url=.+?)\1',

youtube_dl/extractor/atresplayer.py

@@ -2,6 +2,8 @@ from __future__ import unicode_literals
 
 import time
 import hmac
+import hashlib
+import re
 
 from .common import InfoExtractor
 from ..compat import (
@@ -32,6 +34,19 @@ class AtresPlayerIE(InfoExtractor):
                 'duration': 5527.6,
                 'thumbnail': 're:^https?://.*\.jpg$',
             },
+            'skip': 'This video is only available for registered users'
+        },
+        {
+            'url': 'http://www.atresplayer.com/television/especial/videoencuentros/temporada-1/capitulo-112-david-bustamante_2014121600375.html',
+            'md5': '0d0e918533bbd4b263f2de4d197d4aac',
+            'info_dict': {
+                'id': 'capitulo-112-david-bustamante',
+                'ext': 'flv',
+                'title': 'David Bustamante',
+                'description': 'md5:f33f1c0a05be57f6708d4dd83a3b81c6',
+                'duration': 1439.0,
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
         },
         {
             'url': 'http://www.atresplayer.com/television/series/el-secreto-de-puente-viejo/el-chico-de-los-tres-lunares/capitulo-977-29-12-14_2014122400174.html',
@@ -50,6 +65,13 @@ class AtresPlayerIE(InfoExtractor):
 
     _LOGIN_URL = 'https://servicios.atresplayer.com/j_spring_security_check'
 
+    _ERRORS = {
+        'UNPUBLISHED': 'We\'re sorry, but this video is not yet available.',
+        'DELETED': 'This video has expired and is no longer available for online streaming.',
+        'GEOUNPUBLISHED': 'We\'re sorry, but this video is not available in your region due to right restrictions.',
+        # 'PREMIUM': 'PREMIUM',
+    }
+
     def _real_initialize(self):
         self._login()
 
@@ -83,58 +105,77 @@ class AtresPlayerIE(InfoExtractor):
         episode_id = self._search_regex(
             r'episode="([^"]+)"', webpage, 'episode id')
 
+        request = sanitized_Request(
+            self._PLAYER_URL_TEMPLATE % episode_id,
+            headers={'User-Agent': self._USER_AGENT})
+        player = self._download_json(request, episode_id, 'Downloading player JSON')
+
+        episode_type = player.get('typeOfEpisode')
+        error_message = self._ERRORS.get(episode_type)
+        if error_message:
+            raise ExtractorError(
+                '%s returned error: %s' % (self.IE_NAME, error_message), expected=True)
+
+        formats = []
+        video_url = player.get('urlVideo')
+        if video_url:
+            format_info = {
+                'url': video_url,
+                'format_id': 'http',
+            }
+            mobj = re.search(r'(?P<bitrate>\d+)K_(?P<width>\d+)x(?P<height>\d+)', video_url)
+            if mobj:
+                format_info.update({
+                    'width': int_or_none(mobj.group('width')),
+                    'height': int_or_none(mobj.group('height')),
+                    'tbr': int_or_none(mobj.group('bitrate')),
+                })
+            formats.append(format_info)
+
+        m3u8_url = player.get('urlVideoHls')
+        if m3u8_url:
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, episode_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
+
         timestamp = int_or_none(self._download_webpage(
             self._TIME_API_URL,
             video_id, 'Downloading timestamp', fatal=False), 1000, time.time())
         timestamp_shifted = compat_str(timestamp + self._TIMESTAMP_SHIFT)
         token = hmac.new(
             self._MAGIC.encode('ascii'),
-            (episode_id + timestamp_shifted).encode('utf-8')
+            (episode_id + timestamp_shifted).encode('utf-8'), hashlib.md5
         ).hexdigest()
 
-        formats = []
-        for fmt in ['windows', 'android_tablet']:
-            request = sanitized_Request(
-                self._URL_VIDEO_TEMPLATE.format(fmt, episode_id, timestamp_shifted, token))
-            request.add_header('User-Agent', self._USER_AGENT)
+        request = sanitized_Request(
+            self._URL_VIDEO_TEMPLATE.format('windows', episode_id, timestamp_shifted, token),
+            headers={'User-Agent': self._USER_AGENT})
 
-            fmt_json = self._download_json(
-                request, video_id, 'Downloading %s video JSON' % fmt)
+        fmt_json = self._download_json(
+            request, video_id, 'Downloading windows video JSON')
 
-            result = fmt_json.get('resultDes')
-            if result.lower() != 'ok':
-                raise ExtractorError(
-                    '%s returned error: %s' % (self.IE_NAME, result), expected=True)
+        result = fmt_json.get('resultDes')
+        if result.lower() != 'ok':
+            raise ExtractorError(
+                '%s returned error: %s' % (self.IE_NAME, result), expected=True)
 
-            for format_id, video_url in fmt_json['resultObject'].items():
-                if format_id == 'token' or not video_url.startswith('http'):
-                    continue
-                if video_url.endswith('/Manifest'):
-                    if 'geodeswowsmpra3player' in video_url:
-                        f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0]
-                        f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path)
-                        # this videos are protected by DRM, the f4m downloader doesn't support them
-                        continue
-                    else:
-                        f4m_url = video_url[:-9] + '/manifest.f4m'
-                    formats.extend(self._extract_f4m_formats(f4m_url, video_id))
-                else:
-                    formats.append({
-                        'url': video_url,
-                        'format_id': 'android-%s' % format_id,
-                        'preference': 1,
-                    })
+        for format_id, video_url in fmt_json['resultObject'].items():
+            if format_id == 'token' or not video_url.startswith('http'):
+                continue
+            if 'geodeswowsmpra3player' in video_url:
+                f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0]
+                f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path)
+                # this videos are protected by DRM, the f4m downloader doesn't support them
+                continue
+            else:
+                f4m_url = video_url[:-9] + '/manifest.f4m'
+            formats.extend(self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds', fatal=False))
         self._sort_formats(formats)
 
-        player = self._download_json(
-            self._PLAYER_URL_TEMPLATE % episode_id,
-            episode_id)
-
         path_data = player.get('pathData')
 
         episode = self._download_xml(
-            self._EPISODE_URL_TEMPLATE % path_data,
-            video_id, 'Downloading episode XML')
+            self._EPISODE_URL_TEMPLATE % path_data, video_id,
+            'Downloading episode XML')
 
         duration = float_or_none(xpath_text(
             episode, './media/asset/info/technical/contentDuration', 'duration'))

youtube_dl/extractor/audimedia.py

@@ -15,7 +15,7 @@ class AudiMediaIE(InfoExtractor):
         'url': 'https://audimedia.tv/en/vid/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test',
         'md5': '79a8b71c46d49042609795ab59779b66',
         'info_dict': {
-            'id': '1564',
+            'id': '1565',
             'ext': 'mp4',
             'title': '60 Seconds of Audi Sport 104/2015 - WEC Bahrain, Rookie Test',
             'description': 'md5:60e5d30a78ced725f7b8d34370762941',
@@ -45,15 +45,15 @@ class AudiMediaIE(InfoExtractor):
 
             stream_url_hls = json_data.get('stream_url_hls')
             if stream_url_hls:
-                m3u8_formats = self._extract_m3u8_formats(stream_url_hls, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
-                if m3u8_formats:
-                    formats.extend(m3u8_formats)
+                formats.extend(self._extract_m3u8_formats(
+                    stream_url_hls, video_id, 'mp4',
+                    entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
 
             stream_url_hds = json_data.get('stream_url_hds')
             if stream_url_hds:
-                f4m_formats = self._extract_f4m_formats(json_data.get('stream_url_hds') + '?hdcore=3.4.0', video_id, -1, f4m_id='hds', fatal=False)
-                if f4m_formats:
-                    formats.extend(f4m_formats)
+                formats.extend(self._extract_f4m_formats(
+                    stream_url_hds + '?hdcore=3.4.0',
+                    video_id, f4m_id='hds', fatal=False))
 
             for video_version in json_data.get('video_versions'):
                 video_version_url = video_version.get('download_url') or video_version.get('stream_url')

youtube_dl/extractor/audiomack.py

@@ -56,7 +56,7 @@ class AudiomackIE(InfoExtractor):
 
         # API is inconsistent with errors
         if 'url' not in api_response or not api_response['url'] or 'error' in api_response:
-            raise ExtractorError('Invalid url %s', url)
+            raise ExtractorError('Invalid url %s' % url)
 
         # Audiomack wraps a lot of soundcloud tracks in their branded wrapper
         # if so, pass the work off to the soundcloud extractor

youtube_dl/extractor/baidu.py

@@ -4,7 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urlparse
+from ..utils import unescapeHTML
 
 
 class BaiduVideoIE(InfoExtractor):
@@ -14,8 +14,8 @@ class BaiduVideoIE(InfoExtractor):
         'url': 'http://v.baidu.com/comic/1069.htm?frp=bdbrand&q=%E4%B8%AD%E5%8D%8E%E5%B0%8F%E5%BD%93%E5%AE%B6',
         'info_dict': {
             'id': '1069',
-            'title': '中华小当家 TV版 (全52集)',
-            'description': 'md5:395a419e41215e531c857bb037bbaf80',
+            'title': '中华小当家 TV版国语',
+            'description': 'md5:51be07afe461cf99fa61231421b5397c',
         },
         'playlist_count': 52,
     }, {
@@ -25,45 +25,32 @@ class BaiduVideoIE(InfoExtractor):
             'title': 're:^奔跑吧兄弟',
             'description': 'md5:1bf88bad6d850930f542d51547c089b8',
         },
-        'playlist_mincount': 3,
+        'playlist_mincount': 12,
     }]
 
+    def _call_api(self, path, category, playlist_id, note):
+        return self._download_json('http://app.video.baidu.com/%s/?worktype=adnative%s&id=%s' % (
+            path, category, playlist_id), playlist_id, note)
+
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        playlist_id = mobj.group('id')
-        category = category2 = mobj.group('type')
+        category, playlist_id = re.match(self._VALID_URL, url).groups()
         if category == 'show':
-            category2 = 'tvshow'
+            category = 'tvshow'
+        if category == 'tv':
+            category = 'tvplay'
 
-        webpage = self._download_webpage(url, playlist_id)
+        playlist_detail = self._call_api(
+            'xqinfo', category, playlist_id, 'Download playlist JSON metadata')
 
-        playlist_title = self._html_search_regex(
-            r'title\s*:\s*(["\'])(?P<title>[^\']+)\1', webpage,
-            'playlist title', group='title')
-        playlist_description = self._html_search_regex(
-            r'<input[^>]+class="j-data-intro"[^>]+value="([^"]+)"/>', webpage,
-            playlist_id, 'playlist description')
+        playlist_title = playlist_detail['title']
+        playlist_description = unescapeHTML(playlist_detail.get('intro'))
 
-        site = self._html_search_regex(
-            r'filterSite\s*:\s*["\']([^"]*)["\']', webpage,
-            'primary provider site')
-        api_result = self._download_json(
-            'http://v.baidu.com/%s_intro/?dtype=%sPlayUrl&id=%s&site=%s' % (
-                category, category2, playlist_id, site),
-            playlist_id, 'Get playlist links')
+        episodes_detail = self._call_api(
+            'xqsingle', category, playlist_id, 'Download episodes JSON metadata')
 
-        entries = []
-        for episode in api_result[0]['episodes']:
-            episode_id = '%s_%s' % (playlist_id, episode['episode'])
-
-            redirect_page = self._download_webpage(
-                compat_urlparse.urljoin(url, episode['url']), episode_id,
-                note='Download Baidu redirect page')
-            real_url = self._html_search_regex(
-                r'location\.replace\("([^"]+)"\)', redirect_page, 'real URL')
-
-            entries.append(self.url_result(
-                real_url, video_title=episode['single_title']))
+        entries = [self.url_result(
+            episode['url'], video_title=episode['title']
+        ) for episode in episodes_detail['videos']]
 
         return self.playlist_result(
             entries, playlist_id, playlist_title, playlist_description)

youtube_dl/extractor/bbc.py

@@ -23,7 +23,17 @@ class BBCCoUkIE(InfoExtractor):
     IE_NAME = 'bbc.co.uk'
     IE_DESC = 'BBC iPlayer'
     _ID_REGEX = r'[pb][\da-z]{7}'
-    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:programmes/(?!articles/)|iplayer(?:/[^/]+)?/(?:episode/|playlist/))|music/clips[/#])(?P<id>%s)' % _ID_REGEX
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?bbc\.co\.uk/
+                        (?:
+                            programmes/(?!articles/)|
+                            iplayer(?:/[^/]+)?/(?:episode/|playlist/)|
+                            music/clips[/#]|
+                            radio/player/
+                        )
+                        (?P<id>%s)
+                    ''' % _ID_REGEX
 
     _MEDIASELECTOR_URLS = [
         # Provides HQ HLS streams with even better quality that pc mediaset but fails
@@ -114,14 +124,14 @@ class BBCCoUkIE(InfoExtractor):
             },
             'skip': 'Episode is no longer available on BBC iPlayer Radio',
         }, {
-            'url': 'http://www.bbc.co.uk/music/clips/p02frcc3',
+            'url': 'http://www.bbc.co.uk/music/clips/p022h44b',
             'note': 'Audio',
             'info_dict': {
-                'id': 'p02frcch',
+                'id': 'p022h44j',
                 'ext': 'flv',
-                'title': 'Pete Tong, Past, Present and Future Special, Madeon - After Hours mix',
-                'description': 'French house superstar Madeon takes us out of the club and onto the after party.',
-                'duration': 3507,
+                'title': 'BBC Proms Music Guides, Rachmaninov: Symphonic Dances',
+                'description': "In this Proms Music Guide, Andrew McGregor looks at Rachmaninov's Symphonic Dances.",
+                'duration': 227,
             },
             'params': {
                 # rtmp download
@@ -172,13 +182,12 @@ class BBCCoUkIE(InfoExtractor):
         }, {
             # iptv-all mediaset fails with geolocation however there is no geo restriction
             # for this programme at all
-            'url': 'http://www.bbc.co.uk/programmes/b06bp7lf',
+            'url': 'http://www.bbc.co.uk/programmes/b06rkn85',
             'info_dict': {
-                'id': 'b06bp7kf',
+                'id': 'b06rkms3',
                 'ext': 'flv',
-                'title': "Annie Mac's Friday Night, B.Traits sits in for Annie",
-                'description': 'B.Traits sits in for Annie Mac with a Mini-Mix from Disclosure.',
-                'duration': 10800,
+                'title': "Best of the Mini-Mixes 2015: Part 3, Annie Mac's Friday Night - BBC Radio 1",
+                'description': "Annie has part three in the Best of the Mini-Mixes 2015, plus the year's Most Played!",
             },
             'params': {
                 # rtmp download
@@ -193,6 +202,9 @@ class BBCCoUkIE(InfoExtractor):
         }, {
             'url': 'http://www.bbc.co.uk/iplayer/cbeebies/episode/b0480276/bing-14-atchoo',
             'only_matching': True,
+        }, {
+            'url': 'http://www.bbc.co.uk/radio/player/p03cchwf',
+            'only_matching': True,
         }
     ]
 
@@ -223,11 +235,9 @@ class BBCCoUkIE(InfoExtractor):
             elif transfer_format == 'dash':
                 pass
             elif transfer_format == 'hls':
-                m3u8_formats = self._extract_m3u8_formats(
+                formats.extend(self._extract_m3u8_formats(
                     href, programme_id, ext='mp4', entry_protocol='m3u8_native',
-                    m3u8_id=supplier, fatal=False)
-                if m3u8_formats:
-                    formats.extend(m3u8_formats)
+                    m3u8_id=supplier, fatal=False))
             # Direct link
             else:
                 formats.append({
@@ -471,7 +481,8 @@ class BBCCoUkIE(InfoExtractor):
 
         if programme_id:
             formats, subtitles = self._download_media_selector(programme_id)
-            title = self._og_search_title(webpage)
+            title = self._og_search_title(webpage, default=None) or self._html_search_regex(
+                r'<h2[^>]+id="parent-title"[^>]*>(.+?)</h2>', webpage, 'title')
             description = self._search_regex(
                 r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>',
                 webpage, 'description', default=None)

youtube_dl/extractor/beeg.py

@@ -34,7 +34,7 @@ class BeegIE(InfoExtractor):
         video_id = self._match_id(url)
 
         video = self._download_json(
-            'http://beeg.com/api/v5/video/%s' % video_id, video_id)
+            'https://api.beeg.com/api/v5/video/%s' % video_id, video_id)
 
         def split(o, e):
             def cut(s, x):
@@ -60,7 +60,7 @@ class BeegIE(InfoExtractor):
 
         def decrypt_url(encrypted_url):
             encrypted_url = self._proto_relative_url(
-                encrypted_url.replace('{DATA_MARKERS}', ''), 'http:')
+                encrypted_url.replace('{DATA_MARKERS}', ''), 'https:')
             key = self._search_regex(
                 r'/key=(.*?)%2Cend=', encrypted_url, 'key', default=None)
             if not key:

youtube_dl/extractor/bigflix.py

@@ -0,0 +1,85 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import base64
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_parse_unquote
+
+
+class BigflixIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?bigflix\.com/.+/(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'http://www.bigflix.com/Hindi-movies/Action-movies/Singham-Returns/16537',
+        'md5': 'ec76aa9b1129e2e5b301a474e54fab74',
+        'info_dict': {
+            'id': '16537',
+            'ext': 'mp4',
+            'title': 'Singham Returns',
+            'description': 'md5:3d2ba5815f14911d5cc6a501ae0cf65d',
+        }
+    }, {
+        # 2 formats
+        'url': 'http://www.bigflix.com/Tamil-movies/Drama-movies/Madarasapatinam/16070',
+        'info_dict': {
+            'id': '16070',
+            'ext': 'mp4',
+            'title': 'Madarasapatinam',
+            'description': 'md5:63b9b8ed79189c6f0418c26d9a3452ca',
+            'formats': 'mincount:2',
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        # multiple formats
+        'url': 'http://www.bigflix.com/Malayalam-movies/Drama-movies/Indian-Rupee/15967',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(
+            r'<div[^>]+class=["\']pagetitle["\'][^>]*>(.+?)</div>',
+            webpage, 'title')
+
+        def decode_url(quoted_b64_url):
+            return base64.b64decode(compat_urllib_parse_unquote(
+                quoted_b64_url).encode('ascii')).decode('utf-8')
+
+        formats = []
+        for height, encoded_url in re.findall(
+                r'ContentURL_(\d{3,4})[pP][^=]+=([^&]+)', webpage):
+            video_url = decode_url(encoded_url)
+            f = {
+                'url': video_url,
+                'format_id': '%sp' % height,
+                'height': int(height),
+            }
+            if video_url.startswith('rtmp'):
+                f['ext'] = 'flv'
+            formats.append(f)
+
+        file_url = self._search_regex(
+            r'file=([^&]+)', webpage, 'video url', default=None)
+        if file_url:
+            video_url = decode_url(file_url)
+            if all(f['url'] != video_url for f in formats):
+                formats.append({
+                    'url': decode_url(file_url),
+                })
+
+        self._sort_formats(formats)
+
+        description = self._html_search_meta('description', webpage)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'formats': formats
+        }

youtube_dl/extractor/bleacherreport.py

@@ -0,0 +1,106 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from .amp import AMPIE
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    parse_iso8601,
+)
+
+
+class BleacherReportIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/articles/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://bleacherreport.com/articles/2496438-fsu-stat-projections-is-jalen-ramsey-best-defensive-player-in-college-football',
+        'md5': 'a3ffc3dc73afdbc2010f02d98f990f20',
+        'info_dict': {
+            'id': '2496438',
+            'ext': 'mp4',
+            'title': 'FSU Stat Projections: Is Jalen Ramsey Best Defensive Player in College Football?',
+            'uploader_id': 3992341,
+            'description': 'CFB, ACC, Florida State',
+            'timestamp': 1434380212,
+            'upload_date': '20150615',
+            'uploader': 'Team Stream Now ',
+        },
+        'add_ie': ['Ooyala'],
+    }, {
+        'url': 'http://bleacherreport.com/articles/2586817-aussie-golfers-get-fright-of-their-lives-after-being-chased-by-angry-kangaroo',
+        'md5': 'af5f90dc9c7ba1c19d0a3eac806bbf50',
+        'info_dict': {
+            'id': '2586817',
+            'ext': 'mp4',
+            'title': 'Aussie Golfers Get Fright of Their Lives After Being Chased by Angry Kangaroo',
+            'timestamp': 1446839961,
+            'uploader': 'Sean Fay',
+            'description': 'md5:825e94e0f3521df52fa83b2ed198fa20',
+            'uploader_id': 6466954,
+            'upload_date': '20151011',
+        },
+        'add_ie': ['Youtube'],
+    }]
+
+    def _real_extract(self, url):
+        article_id = self._match_id(url)
+
+        article_data = self._download_json('http://api.bleacherreport.com/api/v1/articles/%s' % article_id, article_id)['article']
+
+        thumbnails = []
+        primary_photo = article_data.get('primaryPhoto')
+        if primary_photo:
+            thumbnails = [{
+                'url': primary_photo['url'],
+                'width': primary_photo.get('width'),
+                'height': primary_photo.get('height'),
+            }]
+
+        info = {
+            '_type': 'url_transparent',
+            'id': article_id,
+            'title': article_data['title'],
+            'uploader': article_data.get('author', {}).get('name'),
+            'uploader_id': article_data.get('authorId'),
+            'timestamp': parse_iso8601(article_data.get('createdAt')),
+            'thumbnails': thumbnails,
+            'comment_count': int_or_none(article_data.get('commentsCount')),
+            'view_count': int_or_none(article_data.get('hitCount')),
+        }
+
+        video = article_data.get('video')
+        if video:
+            video_type = video['type']
+            if video_type == 'cms.bleacherreport.com':
+                info['url'] = 'http://bleacherreport.com/video_embed?id=%s' % video['id']
+            elif video_type == 'ooyala.com':
+                info['url'] = 'ooyala:%s' % video['id']
+            elif video_type == 'youtube.com':
+                info['url'] = video['id']
+            elif video_type == 'vine.co':
+                info['url'] = 'https://vine.co/v/%s' % video['id']
+            else:
+                info['url'] = video_type + video['id']
+            return info
+        else:
+            raise ExtractorError('no video in the article', expected=True)
+
+
+class BleacherReportCMSIE(AMPIE):
+    _VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/video_embed\?id=(?P<id>[0-9a-f-]{36})'
+    _TESTS = [{
+        'url': 'http://bleacherreport.com/video_embed?id=8fd44c2f-3dc5-4821-9118-2c825a98c0e1',
+        'md5': '8c2c12e3af7805152675446c905d159b',
+        'info_dict': {
+            'id': '8fd44c2f-3dc5-4821-9118-2c825a98c0e1',
+            'ext': 'flv',
+            'title': 'Cena vs. Rollins Would Expose the Heavyweight Division',
+            'description': 'md5:984afb4ade2f9c0db35f3267ed88b36e',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        info = self._extract_feed_info('http://cms.bleacherreport.com/media/items/%s/akamai.json' % video_id)
+        info['id'] = video_id
+        return info

youtube_dl/extractor/bliptv.py

@@ -1,290 +0,0 @@
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-
-from ..compat import compat_urlparse
-from ..utils import (
-    clean_html,
-    int_or_none,
-    parse_iso8601,
-    sanitized_Request,
-    unescapeHTML,
-    xpath_text,
-    xpath_with_ns,
-)
-
-
-class BlipTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:\w+\.)?blip\.tv/(?:(?:.+-|rss/flash/)(?P<id>\d+)|((?:play/|api\.swf#)(?P<lookup_id>[\da-zA-Z+_]+)))'
-
-    _TESTS = [
-        {
-            'url': 'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352',
-            'md5': '80baf1ec5c3d2019037c1c707d676b9f',
-            'info_dict': {
-                'id': '5779306',
-                'ext': 'm4v',
-                'title': 'CBR EXCLUSIVE: "Gotham City Imposters" Bats VS Jokerz Short 3',
-                'description': 'md5:9bc31f227219cde65e47eeec8d2dc596',
-                'timestamp': 1323138843,
-                'upload_date': '20111206',
-                'uploader': 'cbr',
-                'uploader_id': '679425',
-                'duration': 81,
-            }
-        },
-        {
-            # https://github.com/rg3/youtube-dl/pull/2274
-            'note': 'Video with subtitles',
-            'url': 'http://blip.tv/play/h6Uag5OEVgI.html',
-            'md5': '309f9d25b820b086ca163ffac8031806',
-            'info_dict': {
-                'id': '6586561',
-                'ext': 'mp4',
-                'title': 'Red vs. Blue Season 11 Episode 1',
-                'description': 'One-Zero-One',
-                'timestamp': 1371261608,
-                'upload_date': '20130615',
-                'uploader': 'redvsblue',
-                'uploader_id': '792887',
-                'duration': 279,
-            }
-        },
-        {
-            # https://bugzilla.redhat.com/show_bug.cgi?id=967465
-            'url': 'http://a.blip.tv/api.swf#h6Uag5KbVwI',
-            'md5': '314e87b1ebe7a48fcbfdd51b791ce5a6',
-            'info_dict': {
-                'id': '6573122',
-                'ext': 'mov',
-                'upload_date': '20130520',
-                'description': 'Two hapless space marines argue over what to do when they realize they have an astronomically huge problem on their hands.',
-                'title': 'Red vs. Blue Season 11 Trailer',
-                'timestamp': 1369029609,
-                'uploader': 'redvsblue',
-                'uploader_id': '792887',
-            }
-        },
-        {
-            'url': 'http://blip.tv/play/gbk766dkj4Yn',
-            'md5': 'fe0a33f022d49399a241e84a8ea8b8e3',
-            'info_dict': {
-                'id': '1749452',
-                'ext': 'mp4',
-                'upload_date': '20090208',
-                'description': 'Witness the first appearance of the Nostalgia Critic character, as Doug reviews the movie Transformers.',
-                'title': 'Nostalgia Critic: Transformers',
-                'timestamp': 1234068723,
-                'uploader': 'NostalgiaCritic',
-                'uploader_id': '246467',
-            }
-        },
-        {
-            # https://github.com/rg3/youtube-dl/pull/4404
-            'note': 'Audio only',
-            'url': 'http://blip.tv/hilarios-productions/weekly-manga-recap-kingdom-7119982',
-            'md5': '76c0a56f24e769ceaab21fbb6416a351',
-            'info_dict': {
-                'id': '7103299',
-                'ext': 'flv',
-                'title': 'Weekly Manga Recap: Kingdom',
-                'description': 'And then Shin breaks the enemy line, and he&apos;s all like HWAH! And then he slices a guy and it&apos;s all like FWASHING! And... it&apos;s really hard to describe the best parts of this series without breaking down into sound effects, okay?',
-                'timestamp': 1417660321,
-                'upload_date': '20141204',
-                'uploader': 'The Rollo T',
-                'uploader_id': '407429',
-                'duration': 7251,
-                'vcodec': 'none',
-            }
-        },
-        {
-            # missing duration
-            'url': 'http://blip.tv/rss/flash/6700880',
-            'info_dict': {
-                'id': '6684191',
-                'ext': 'm4v',
-                'title': 'Cowboy Bebop: Gateway Shuffle Review',
-                'description': 'md5:3acc480c0f9ae157f5fe88547ecaf3f8',
-                'timestamp': 1386639757,
-                'upload_date': '20131210',
-                'uploader': 'sfdebris',
-                'uploader_id': '706520',
-            }
-        }
-    ]
-
-    @staticmethod
-    def _extract_url(webpage):
-        mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage)
-        if mobj:
-            return 'http://blip.tv/a/a-' + mobj.group(1)
-        mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage)
-        if mobj:
-            return mobj.group(1)
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        lookup_id = mobj.group('lookup_id')
-
-        # See https://github.com/rg3/youtube-dl/issues/857 and
-        # https://github.com/rg3/youtube-dl/issues/4197
-        if lookup_id:
-            urlh = self._request_webpage(
-                'http://blip.tv/play/%s' % lookup_id, lookup_id, 'Resolving lookup id')
-            url = compat_urlparse.urlparse(urlh.geturl())
-            qs = compat_urlparse.parse_qs(url.query)
-            mobj = re.match(self._VALID_URL, qs['file'][0])
-
-        video_id = mobj.group('id')
-
-        rss = self._download_xml('http://blip.tv/rss/flash/%s' % video_id, video_id, 'Downloading video RSS')
-
-        def _x(p):
-            return xpath_with_ns(p, {
-                'blip': 'http://blip.tv/dtd/blip/1.0',
-                'media': 'http://search.yahoo.com/mrss/',
-                'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
-            })
-
-        item = rss.find('channel/item')
-
-        video_id = xpath_text(item, _x('blip:item_id'), 'video id') or lookup_id
-        title = xpath_text(item, 'title', 'title', fatal=True)
-        description = clean_html(xpath_text(item, _x('blip:puredescription'), 'description'))
-        timestamp = parse_iso8601(xpath_text(item, _x('blip:datestamp'), 'timestamp'))
-        uploader = xpath_text(item, _x('blip:user'), 'uploader')
-        uploader_id = xpath_text(item, _x('blip:userid'), 'uploader id')
-        duration = int_or_none(xpath_text(item, _x('blip:runtime'), 'duration'))
-        media_thumbnail = item.find(_x('media:thumbnail'))
-        thumbnail = (media_thumbnail.get('url') if media_thumbnail is not None
-                     else xpath_text(item, 'image', 'thumbnail'))
-        categories = [category.text for category in item.findall('category') if category is not None]
-
-        formats = []
-        subtitles_urls = {}
-
-        media_group = item.find(_x('media:group'))
-        for media_content in media_group.findall(_x('media:content')):
-            url = media_content.get('url')
-            role = media_content.get(_x('blip:role'))
-            msg = self._download_webpage(
-                url + '?showplayer=20140425131715&referrer=http://blip.tv&mask=7&skin=flashvars&view=url',
-                video_id, 'Resolving URL for %s' % role)
-            real_url = compat_urlparse.parse_qs(msg.strip())['message'][0]
-
-            media_type = media_content.get('type')
-            if media_type == 'text/srt' or url.endswith('.srt'):
-                LANGS = {
-                    'english': 'en',
-                }
-                lang = role.rpartition('-')[-1].strip().lower()
-                langcode = LANGS.get(lang, lang)
-                subtitles_urls[langcode] = url
-            elif media_type.startswith('video/'):
-                formats.append({
-                    'url': real_url,
-                    'format_id': role,
-                    'format_note': media_type,
-                    'vcodec': media_content.get(_x('blip:vcodec')) or 'none',
-                    'acodec': media_content.get(_x('blip:acodec')),
-                    'filesize': media_content.get('filesize'),
-                    'width': int_or_none(media_content.get('width')),
-                    'height': int_or_none(media_content.get('height')),
-                })
-        self._check_formats(formats, video_id)
-        self._sort_formats(formats)
-
-        subtitles = self.extract_subtitles(video_id, subtitles_urls)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'timestamp': timestamp,
-            'uploader': uploader,
-            'uploader_id': uploader_id,
-            'duration': duration,
-            'thumbnail': thumbnail,
-            'categories': categories,
-            'formats': formats,
-            'subtitles': subtitles,
-        }
-
-    def _get_subtitles(self, video_id, subtitles_urls):
-        subtitles = {}
-        for lang, url in subtitles_urls.items():
-            # For some weird reason, blip.tv serves a video instead of subtitles
-            # when we request with a common UA
-            req = sanitized_Request(url)
-            req.add_header('User-Agent', 'youtube-dl')
-            subtitles[lang] = [{
-                # The extension is 'srt' but it's actually an 'ass' file
-                'ext': 'ass',
-                'data': self._download_webpage(req, None, note=False),
-            }]
-        return subtitles
-
-
-class BlipTVUserIE(InfoExtractor):
-    _VALID_URL = r'(?:(?:https?://(?:\w+\.)?blip\.tv/)|bliptvuser:)(?!api\.swf)([^/]+)/*$'
-    _PAGE_SIZE = 12
-    IE_NAME = 'blip.tv:user'
-    _TEST = {
-        'url': 'http://blip.tv/actone',
-        'info_dict': {
-            'id': 'actone',
-            'title': 'Act One: The Series',
-        },
-        'playlist_count': 5,
-    }
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        username = mobj.group(1)
-
-        page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1'
-
-        page = self._download_webpage(url, username, 'Downloading user page')
-        mobj = re.search(r'data-users-id="([^"]+)"', page)
-        page_base = page_base % mobj.group(1)
-        title = self._og_search_title(page)
-
-        # Download video ids using BlipTV Ajax calls. Result size per
-        # query is limited (currently to 12 videos) so we need to query
-        # page by page until there are no video ids - it means we got
-        # all of them.
-
-        video_ids = []
-        pagenum = 1
-
-        while True:
-            url = page_base + "&page=" + str(pagenum)
-            page = self._download_webpage(
-                url, username, 'Downloading video ids from page %d' % pagenum)
-
-            # Extract video identifiers
-            ids_in_page = []
-
-            for mobj in re.finditer(r'href="/([^"]+)"', page):
-                if mobj.group(1) not in ids_in_page:
-                    ids_in_page.append(unescapeHTML(mobj.group(1)))
-
-            video_ids.extend(ids_in_page)
-
-            # A little optimization - if current page is not
-            # "full", ie. does not contain PAGE_SIZE video ids then
-            # we can assume that this page is the last one - there
-            # are no more ids on further pages - no need to query
-            # again.
-
-            if len(ids_in_page) < self._PAGE_SIZE:
-                break
-
-            pagenum += 1
-
-        urls = ['http://blip.tv/%s' % video_id for video_id in video_ids]
-        url_entries = [self.url_result(vurl, 'BlipTV') for vurl in urls]
-        return self.playlist_result(
-            url_entries, playlist_title=title, playlist_id=username)

youtube_dl/extractor/bloomberg.py

@@ -41,15 +41,11 @@ class BloombergIE(InfoExtractor):
             if not stream_url:
                 continue
             if stream['muxing_format'] == 'TS':
-                m3u8_formats = self._extract_m3u8_formats(
-                    stream_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
-                if m3u8_formats:
-                    formats.extend(m3u8_formats)
+                formats.extend(self._extract_m3u8_formats(
+                    stream_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
             else:
-                f4m_formats = self._extract_f4m_formats(
-                    stream_url, video_id, f4m_id='hds', fatal=False)
-                if f4m_formats:
-                    formats.extend(f4m_formats)
+                formats.extend(self._extract_f4m_formats(
+                    stream_url, video_id, f4m_id='hds', fatal=False))
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/br.py

@@ -1,18 +1,21 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     int_or_none,
     parse_duration,
+    xpath_element,
+    xpath_text,
 )
 
 
 class BRIE(InfoExtractor):
     IE_DESC = 'Bayerischer Rundfunk Mediathek'
-    _VALID_URL = r'https?://(?:www\.)?br\.de/(?:[a-z0-9\-_]+/)+(?P<id>[a-z0-9\-_]+)\.html'
-    _BASE_URL = 'http://www.br.de'
+    _VALID_URL = r'(?P<base_url>https?://(?:www\.)?br(?:-klassik)?\.de)/(?:[a-z0-9\-_]+/)+(?P<id>[a-z0-9\-_]+)\.html'
 
     _TESTS = [
         {
@@ -22,7 +25,7 @@ class BRIE(InfoExtractor):
                 'id': '48f656ef-287e-486f-be86-459122db22cc',
                 'ext': 'mp4',
                 'title': 'Die böse Überraschung',
-                'description': 'Betriebliche Altersvorsorge: Die böse Überraschung',
+                'description': 'md5:ce9ac81b466ce775b8018f6801b48ac9',
                 'duration': 180,
                 'uploader': 'Reinhard Weber',
                 'upload_date': '20150422',
@@ -30,23 +33,23 @@ class BRIE(InfoExtractor):
         },
         {
             'url': 'http://www.br.de/nachrichten/oberbayern/inhalt/muenchner-polizeipraesident-schreiber-gestorben-100.html',
-            'md5': 'a44396d73ab6a68a69a568fae10705bb',
+            'md5': 'af3a3a4aa43ff0ce6a89504c67f427ef',
             'info_dict': {
                 'id': 'a4b83e34-123d-4b81-9f4e-c0d3121a4e05',
-                'ext': 'mp4',
+                'ext': 'flv',
                 'title': 'Manfred Schreiber ist tot',
-                'description': 'Abendschau kompakt: Manfred Schreiber ist tot',
+                'description': 'md5:b454d867f2a9fc524ebe88c3f5092d97',
                 'duration': 26,
             }
         },
         {
-            'url': 'http://www.br.de/radio/br-klassik/sendungen/allegro/premiere-urauffuehrung-the-land-2015-dance-festival-muenchen-100.html',
+            'url': 'https://www.br-klassik.de/audio/peeping-tom-premierenkritik-dance-festival-muenchen-100.html',
             'md5': '8b5b27c0b090f3b35eac4ab3f7a73d3d',
             'info_dict': {
                 'id': '74c603c9-26d3-48bb-b85b-079aeed66e0b',
                 'ext': 'aac',
                 'title': 'Kurzweilig und sehr bewegend',
-                'description': '"The Land" von Peeping Tom: Kurzweilig und sehr bewegend',
+                'description': 'md5:0351996e3283d64adeb38ede91fac54e',
                 'duration': 296,
             }
         },
@@ -57,7 +60,7 @@ class BRIE(InfoExtractor):
                 'id': '6ba73750-d405-45d3-861d-1ce8c524e059',
                 'ext': 'mp4',
                 'title': 'Umweltbewusster Häuslebauer',
-                'description': 'Uwe Erdelt: Umweltbewusster Häuslebauer',
+                'description': 'md5:d52dae9792d00226348c1dbb13c9bae2',
                 'duration': 116,
             }
         },
@@ -68,7 +71,7 @@ class BRIE(InfoExtractor):
                 'id': 'd982c9ce-8648-4753-b358-98abb8aec43d',
                 'ext': 'mp4',
                 'title': 'Folge 1 - Metaphysik',
-                'description': 'Kant für Anfänger: Folge 1 - Metaphysik',
+                'description': 'md5:bb659990e9e59905c3d41e369db1fbe3',
                 'duration': 893,
                 'uploader': 'Eva Maria Steimle',
                 'upload_date': '20140117',
@@ -77,28 +80,31 @@ class BRIE(InfoExtractor):
     ]
 
     def _real_extract(self, url):
-        display_id = self._match_id(url)
+        base_url, display_id = re.search(self._VALID_URL, url).groups()
         page = self._download_webpage(url, display_id)
         xml_url = self._search_regex(
             r"return BRavFramework\.register\(BRavFramework\('avPlayer_(?:[a-f0-9-]{36})'\)\.setup\({dataURL:'(/(?:[a-z0-9\-]+/)+[a-z0-9/~_.-]+)'}\)\);", page, 'XMLURL')
-        xml = self._download_xml(self._BASE_URL + xml_url, None)
+        xml = self._download_xml(base_url + xml_url, display_id)
 
         medias = []
 
         for xml_media in xml.findall('video') + xml.findall('audio'):
+            media_id = xml_media.get('externalId')
             media = {
-                'id': xml_media.get('externalId'),
-                'title': xml_media.find('title').text,
-                'duration': parse_duration(xml_media.find('duration').text),
-                'formats': self._extract_formats(xml_media.find('assets')),
-                'thumbnails': self._extract_thumbnails(xml_media.find('teaserImage/variants')),
-                'description': ' '.join(xml_media.find('shareTitle').text.splitlines()),
-                'webpage_url': xml_media.find('permalink').text
+                'id': media_id,
+                'title': xpath_text(xml_media, 'title', 'title', True),
+                'duration': parse_duration(xpath_text(xml_media, 'duration')),
+                'formats': self._extract_formats(xpath_element(
+                    xml_media, 'assets'), media_id),
+                'thumbnails': self._extract_thumbnails(xpath_element(
+                    xml_media, 'teaserImage/variants'), base_url),
+                'description': xpath_text(xml_media, 'desc'),
+                'webpage_url': xpath_text(xml_media, 'permalink'),
+                'uploader': xpath_text(xml_media, 'author'),
             }
-            if xml_media.find('author').text:
-                media['uploader'] = xml_media.find('author').text
-            if xml_media.find('broadcastDate').text:
-                media['upload_date'] = ''.join(reversed(xml_media.find('broadcastDate').text.split('.')))
+            broadcast_date = xpath_text(xml_media, 'broadcastDate')
+            if broadcast_date:
+                media['upload_date'] = ''.join(reversed(broadcast_date.split('.')))
             medias.append(media)
 
         if len(medias) > 1:
@@ -109,35 +115,54 @@ class BRIE(InfoExtractor):
             raise ExtractorError('No media entries found')
         return medias[0]
 
-    def _extract_formats(self, assets):
-
-        def text_or_none(asset, tag):
-            elem = asset.find(tag)
-            return None if elem is None else elem.text
-
-        formats = [{
-            'url': text_or_none(asset, 'downloadUrl'),
-            'ext': text_or_none(asset, 'mediaType'),
-            'format_id': asset.get('type'),
-            'width': int_or_none(text_or_none(asset, 'frameWidth')),
-            'height': int_or_none(text_or_none(asset, 'frameHeight')),
-            'tbr': int_or_none(text_or_none(asset, 'bitrateVideo')),
-            'abr': int_or_none(text_or_none(asset, 'bitrateAudio')),
-            'vcodec': text_or_none(asset, 'codecVideo'),
-            'acodec': text_or_none(asset, 'codecAudio'),
-            'container': text_or_none(asset, 'mediaType'),
-            'filesize': int_or_none(text_or_none(asset, 'size')),
-        } for asset in assets.findall('asset')
-            if asset.find('downloadUrl') is not None]
-
+    def _extract_formats(self, assets, media_id):
+        formats = []
+        for asset in assets.findall('asset'):
+            format_url = xpath_text(asset, ['downloadUrl', 'url'])
+            asset_type = asset.get('type')
+            if asset_type == 'HDS':
+                formats.extend(self._extract_f4m_formats(
+                    format_url + '?hdcore=3.2.0', media_id, f4m_id='hds', fatal=False))
+            elif asset_type == 'HLS':
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, media_id, 'mp4', 'm3u8_native', m3u8_id='hds', fatal=False))
+            else:
+                format_info = {
+                    'ext': xpath_text(asset, 'mediaType'),
+                    'width': int_or_none(xpath_text(asset, 'frameWidth')),
+                    'height': int_or_none(xpath_text(asset, 'frameHeight')),
+                    'tbr': int_or_none(xpath_text(asset, 'bitrateVideo')),
+                    'abr': int_or_none(xpath_text(asset, 'bitrateAudio')),
+                    'vcodec': xpath_text(asset, 'codecVideo'),
+                    'acodec': xpath_text(asset, 'codecAudio'),
+                    'container': xpath_text(asset, 'mediaType'),
+                    'filesize': int_or_none(xpath_text(asset, 'size')),
+                }
+                format_url = self._proto_relative_url(format_url)
+                if format_url:
+                    http_format_info = format_info.copy()
+                    http_format_info.update({
+                        'url': format_url,
+                        'format_id': 'http-%s' % asset_type,
+                    })
+                    formats.append(http_format_info)
+                server_prefix = xpath_text(asset, 'serverPrefix')
+                if server_prefix:
+                    rtmp_format_info = format_info.copy()
+                    rtmp_format_info.update({
+                        'url': server_prefix,
+                        'play_path': xpath_text(asset, 'fileName'),
+                        'format_id': 'rtmp-%s' % asset_type,
+                    })
+                    formats.append(rtmp_format_info)
         self._sort_formats(formats)
         return formats
 
-    def _extract_thumbnails(self, variants):
+    def _extract_thumbnails(self, variants, base_url):
         thumbnails = [{
-            'url': self._BASE_URL + variant.find('url').text,
-            'width': int_or_none(variant.find('width').text),
-            'height': int_or_none(variant.find('height').text),
-        } for variant in variants.findall('variant')]
+            'url': base_url + xpath_text(variant, 'url'),
+            'width': int_or_none(xpath_text(variant, 'width')),
+            'height': int_or_none(xpath_text(variant, 'height')),
+        } for variant in variants.findall('variant') if xpath_text(variant, 'url')]
         thumbnails.sort(key=lambda x: x['width'] * x['height'], reverse=True)
         return thumbnails

youtube_dl/extractor/brightcove.py

@@ -355,7 +355,7 @@ class BrightcoveLegacyIE(InfoExtractor):
 
 class BrightcoveNewIE(InfoExtractor):
     IE_NAME = 'brightcove:new'
-    _VALID_URL = r'https?://players\.brightcove\.net/(?P<account_id>\d+)/(?P<player_id>[^/]+)_(?P<embed>[^/]+)/index\.html\?.*videoId=(?P<video_id>\d+)'
+    _VALID_URL = r'https?://players\.brightcove\.net/(?P<account_id>\d+)/(?P<player_id>[^/]+)_(?P<embed>[^/]+)/index\.html\?.*videoId=(?P<video_id>(?:ref:)?\d+)'
     _TESTS = [{
         'url': 'http://players.brightcove.net/929656772001/e41d32dc-ec74-459e-a845-6c69f7b724ea_default/index.html?videoId=4463358922001',
         'md5': 'c8100925723840d4b0d243f7025703be',
@@ -387,14 +387,24 @@ class BrightcoveNewIE(InfoExtractor):
         'params': {
             'skip_download': True,
         }
+    }, {
+        # ref: prefixed video id
+        'url': 'http://players.brightcove.net/3910869709001/21519b5c-4b3b-4363-accb-bdc8f358f823_default/index.html?videoId=ref:7069442',
+        'only_matching': True,
     }]
 
+    @staticmethod
+    def _extract_url(webpage):
+        urls = BrightcoveNewIE._extract_urls(webpage)
+        return urls[0] if urls else None
+
     @staticmethod
     def _extract_urls(webpage):
         # Reference:
         # 1. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/publish-video.html#setvideoiniframe
-        # 2. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/publish-video.html#setvideousingjavascript)
+        # 2. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/publish-video.html#setvideousingjavascript
         # 3. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/embed-in-page.html
+        # 4. https://support.brightcove.com/en/video-cloud/docs/dynamically-assigning-videos-player
 
         entries = []
 
@@ -407,9 +417,10 @@ class BrightcoveNewIE(InfoExtractor):
         for video_id, account_id, player_id, embed in re.findall(
                 # According to examples from [3] it's unclear whether video id
                 # may be optional and what to do when it is
+                # According to [4] data-video-id may be prefixed with ref:
                 r'''(?sx)
                     <video[^>]+
-                        data-video-id=["\'](\d+)["\'][^>]*>.*?
+                        data-video-id=["\']((?:ref:)?\d+)["\'][^>]*>.*?
                     </video>.*?
                     <script[^>]+
                         src=["\'](?:https?:)?//players\.brightcove\.net/
@@ -458,11 +469,9 @@ class BrightcoveNewIE(InfoExtractor):
             if source_type == 'application/x-mpegURL':
                 if not src:
                     continue
-                m3u8_formats = self._extract_m3u8_formats(
+                formats.extend(self._extract_m3u8_formats(
                     src, video_id, 'mp4', entry_protocol='m3u8_native',
-                    m3u8_id='hls', fatal=False)
-                if m3u8_formats:
-                    formats.extend(m3u8_formats)
+                    m3u8_id='hls', fatal=False))
             else:
                 streaming_src = source.get('streaming_src')
                 stream_name, app_name = source.get('stream_name'), source.get('app_name')

youtube_dl/extractor/canal13cl.py

@@ -1,48 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-
-
-class Canal13clIE(InfoExtractor):
-    _VALID_URL = r'^http://(?:www\.)?13\.cl/(?:[^/?#]+/)*(?P<id>[^/?#]+)'
-    _TEST = {
-        'url': 'http://www.13.cl/t13/nacional/el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda',
-        'md5': '4cb1fa38adcad8fea88487a078831755',
-        'info_dict': {
-            'id': '1403022125',
-            'display_id': 'el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda',
-            'ext': 'mp4',
-            'title': 'El "círculo de hierro" de Michelle Bachelet en su regreso a La Moneda',
-            'description': '(Foto: Agencia Uno) En nueve días más, Michelle Bachelet va a asumir por segunda vez como presidenta de la República. Entre aquellos que la acompañarán hay caras que se repiten y otras que se consolidan en su entorno de colaboradores más cercanos.',
-        }
-    }
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        display_id = mobj.group('id')
-
-        webpage = self._download_webpage(url, display_id)
-
-        title = self._html_search_meta(
-            'twitter:title', webpage, 'title', fatal=True)
-        description = self._html_search_meta(
-            'twitter:description', webpage, 'description')
-        url = self._html_search_regex(
-            r'articuloVideo = \"(.*?)\"', webpage, 'url')
-        real_id = self._search_regex(
-            r'[^0-9]([0-9]{7,})[^0-9]', url, 'id', default=display_id)
-        thumbnail = self._html_search_regex(
-            r'articuloImagen = \"(.*?)\"', webpage, 'thumbnail')
-
-        return {
-            'id': real_id,
-            'display_id': display_id,
-            'url': url,
-            'title': title,
-            'description': description,
-            'ext': 'mp4',
-            'thumbnail': thumbnail,
-        }

youtube_dl/extractor/canalc2.py

@@ -9,9 +9,9 @@ from ..utils import parse_duration
 
 class Canalc2IE(InfoExtractor):
     IE_NAME = 'canalc2.tv'
-    _VALID_URL = r'https?://(?:www\.)?canalc2\.tv/video/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:(?:www\.)?canalc2\.tv/video/|archives-canalc2\.u-strasbg\.fr/video\.asp\?.*\bidVideo=)(?P<id>\d+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.canalc2.tv/video/12163',
         'md5': '060158428b650f896c542dfbb3d6487f',
         'info_dict': {
@@ -23,24 +23,36 @@ class Canalc2IE(InfoExtractor):
         'params': {
             'skip_download': True,  # Requires rtmpdump
         }
-    }
+    }, {
+        'url': 'http://archives-canalc2.u-strasbg.fr/video.asp?idVideo=11427&voir=oui',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-        video_url = self._search_regex(
-            r'jwplayer\((["\'])Player\1\)\.setup\({[^}]*file\s*:\s*(["\'])(?P<file>.+?)\2',
-            webpage, 'video_url', group='file')
-        formats = [{'url': video_url}]
-        if video_url.startswith('rtmp://'):
-            rtmp = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+/))(?P<play_path>mp4:.+)$', video_url)
-            formats[0].update({
-                'url': rtmp.group('url'),
-                'ext': 'flv',
-                'app': rtmp.group('app'),
-                'play_path': rtmp.group('play_path'),
-                'page_url': url,
-            })
+
+        webpage = self._download_webpage(
+            'http://www.canalc2.tv/video/%s' % video_id, video_id)
+
+        formats = []
+        for _, video_url in re.findall(r'file\s*=\s*(["\'])(.+?)\1', webpage):
+            if video_url.startswith('rtmp://'):
+                rtmp = re.search(
+                    r'^(?P<url>rtmp://[^/]+/(?P<app>.+/))(?P<play_path>mp4:.+)$', video_url)
+                formats.append({
+                    'url': rtmp.group('url'),
+                    'format_id': 'rtmp',
+                    'ext': 'flv',
+                    'app': rtmp.group('app'),
+                    'play_path': rtmp.group('play_path'),
+                    'page_url': url,
+                })
+            else:
+                formats.append({
+                    'url': video_url,
+                    'format_id': 'http',
+                })
+        self._sort_formats(formats)
 
         title = self._html_search_regex(
             r'(?s)class="[^"]*col_description[^"]*">.*?<h3>(.*?)</h3>', webpage, 'title')

youtube_dl/extractor/canalplus.py

@@ -10,13 +10,14 @@ from ..utils import (
     unified_strdate,
     url_basename,
     qualities,
+    int_or_none,
 )
 
 
 class CanalplusIE(InfoExtractor):
     IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv'
     _VALID_URL = r'https?://(?:www\.(?P<site>canalplus\.fr|piwiplus\.fr|d8\.tv|itele\.fr)/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))'
-    _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s'
+    _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s?format=json'
     _SITE_ID_MAP = {
         'canalplus.fr': 'cplus',
         'piwiplus.fr': 'teletoon',
@@ -26,10 +27,10 @@ class CanalplusIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1263092',
-        'md5': 'b3481d7ca972f61e37420798d0a9d934',
+        'md5': '12164a6f14ff6df8bd628e8ba9b10b78',
         'info_dict': {
             'id': '1263092',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Le Zapping - 13/05/15',
             'description': 'md5:09738c0d06be4b5d06a0940edb0da73f',
             'upload_date': '20150513',
@@ -56,10 +57,10 @@ class CanalplusIE(InfoExtractor):
         'skip': 'videos get deleted after a while',
     }, {
         'url': 'http://www.itele.fr/france/video/aubervilliers-un-lycee-en-colere-111559',
-        'md5': 'f3a46edcdf28006598ffaf5b30e6a2d4',
+        'md5': '38b8f7934def74f0d6f3ba6c036a5f82',
         'info_dict': {
             'id': '1213714',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Aubervilliers : un lycée en colère - Le 11/02/2015 à 06h45',
             'description': 'md5:8216206ec53426ea6321321f3b3c16db',
             'upload_date': '20150211',
@@ -82,15 +83,16 @@ class CanalplusIE(InfoExtractor):
                 webpage, 'video id', group='id')
 
         info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
-        doc = self._download_xml(info_url, video_id, 'Downloading video XML')
+        video_data = self._download_json(info_url, video_id, 'Downloading video JSON')
 
-        video_info = [video for video in doc if video.find('ID').text == video_id][0]
-        media = video_info.find('MEDIA')
-        infos = video_info.find('INFOS')
+        if isinstance(video_data, list):
+            video_data = [video for video in video_data if video.get('ID') == video_id][0]
+        media = video_data['MEDIA']
+        infos = video_data['INFOS']
 
-        preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD', 'HLS', 'HDS'])
+        preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD'])
 
-        fmt_url = next(iter(media.find('VIDEOS'))).text
+        fmt_url = next(iter(media.get('VIDEOS')))
         if '/geo' in fmt_url.lower():
             response = self._request_webpage(
                 HEADRequest(fmt_url), video_id,
@@ -101,35 +103,42 @@ class CanalplusIE(InfoExtractor):
                     expected=True)
 
         formats = []
-        for fmt in media.find('VIDEOS'):
-            format_url = fmt.text
+        for format_id, format_url in media['VIDEOS'].items():
             if not format_url:
                 continue
-            format_id = fmt.tag
             if format_id == 'HLS':
                 formats.extend(self._extract_m3u8_formats(
-                    format_url, video_id, 'mp4', preference=preference(format_id)))
+                    format_url, video_id, 'mp4', 'm3u8_native', m3u8_id=format_id, fatal=False))
             elif format_id == 'HDS':
                 formats.extend(self._extract_f4m_formats(
-                    format_url + '?hdcore=2.11.3', video_id, preference=preference(format_id)))
+                    format_url + '?hdcore=2.11.3', video_id, f4m_id=format_id, fatal=False))
             else:
                 formats.append({
-                    'url': format_url,
+                    # the secret extracted ya function in http://player.canalplus.fr/common/js/canalPlayer.js
+                    'url': format_url + '?secret=pqzerjlsmdkjfoiuerhsdlfknaes',
                     'format_id': format_id,
                     'preference': preference(format_id),
                 })
         self._sort_formats(formats)
 
+        thumbnails = [{
+            'id': image_id,
+            'url': image_url,
+        } for image_id, image_url in media.get('images', {}).items()]
+
+        titrage = infos['TITRAGE']
+
         return {
             'id': video_id,
             'display_id': display_id,
-            'title': '%s - %s' % (infos.find('TITRAGE/TITRE').text,
-                                  infos.find('TITRAGE/SOUS_TITRE').text),
-            'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text),
-            'thumbnail': media.find('IMAGES/GRAND').text,
-            'description': infos.find('DESCRIPTION').text,
-            'view_count': int(infos.find('NB_VUES').text),
-            'like_count': int(infos.find('NB_LIKES').text),
-            'comment_count': int(infos.find('NB_COMMENTS').text),
+            'title': '%s - %s' % (titrage['TITRE'],
+                                  titrage['SOUS_TITRE']),
+            'upload_date': unified_strdate(infos.get('PUBLICATION', {}).get('DATE')),
+            'thumbnails': thumbnails,
+            'description': infos.get('DESCRIPTION'),
+            'duration': int_or_none(infos.get('DURATION')),
+            'view_count': int_or_none(infos.get('NB_VUES')),
+            'like_count': int_or_none(infos.get('NB_LIKES')),
+            'comment_count': int_or_none(infos.get('NB_COMMENTS')),
             'formats': formats,
         }

youtube_dl/extractor/cbsnews.py

@@ -5,6 +5,7 @@ import re
 import json
 
 from .common import InfoExtractor
+from ..utils import remove_start
 
 
 class CBSNewsIE(InfoExtractor):
@@ -62,6 +63,7 @@ class CBSNewsIE(InfoExtractor):
             uri = item.get('media' + format_id + 'URI')
             if not uri:
                 continue
+            uri = remove_start(uri, '{manifest:none}')
             fmt = {
                 'url': uri,
                 'format_id': format_id,
@@ -70,6 +72,8 @@ class CBSNewsIE(InfoExtractor):
                 play_path = re.sub(
                     r'{slistFilePath}', '',
                     uri.split('<break>')[-1].split('{break}')[-1])
+                play_path = re.sub(
+                    r'{manifest:.+}.*$', '', play_path)
                 fmt.update({
                     'app': 'ondemand?auth=cbs',
                     'play_path': 'mp4:' + play_path,

youtube_dl/extractor/ccc.py

@@ -5,6 +5,7 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
+    parse_duration,
     qualities,
     unified_strdate,
 )
@@ -12,21 +13,25 @@ from ..utils import (
 
 class CCCIE(InfoExtractor):
     IE_NAME = 'media.ccc.de'
-    _VALID_URL = r'https?://(?:www\.)?media\.ccc\.de/[^?#]+/[^?#/]*?_(?P<id>[0-9]{8,})._[^?#/]*\.html'
+    _VALID_URL = r'https?://(?:www\.)?media\.ccc\.de/v/(?P<id>[^/?#&]+)'
 
-    _TEST = {
-        'url': 'http://media.ccc.de/browse/congress/2013/30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor.html#video',
+    _TESTS = [{
+        'url': 'https://media.ccc.de/v/30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor#video',
         'md5': '3a1eda8f3a29515d27f5adb967d7e740',
         'info_dict': {
-            'id': '20131228183',
+            'id': '30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor',
             'ext': 'mp4',
             'title': 'Introduction to Processor Design',
-            'description': 'md5:5ddbf8c734800267f2cee4eab187bc1b',
+            'description': 'md5:80be298773966f66d56cb11260b879af',
             'thumbnail': 're:^https?://.*\.jpg$',
             'view_count': int,
-            'upload_date': '20131229',
+            'upload_date': '20131228',
+            'duration': 3660,
         }
-    }
+    }, {
+        'url': 'https://media.ccc.de/v/32c3-7368-shopshifting#download',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -40,21 +45,25 @@ class CCCIE(InfoExtractor):
         title = self._html_search_regex(
             r'(?s)<h1>(.*?)</h1>', webpage, 'title')
         description = self._html_search_regex(
-            r"(?s)<p class='description'>(.*?)</p>",
+            r"(?s)<h3>About</h3>(.+?)<h3>",
             webpage, 'description', fatal=False)
         upload_date = unified_strdate(self._html_search_regex(
-            r"(?s)<span class='[^']*fa-calendar-o'></span>(.*?)</li>",
+            r"(?s)<span[^>]+class='[^']*fa-calendar-o'[^>]*>(.+?)</span>",
             webpage, 'upload date', fatal=False))
         view_count = int_or_none(self._html_search_regex(
             r"(?s)<span class='[^']*fa-eye'></span>(.*?)</li>",
             webpage, 'view count', fatal=False))
+        duration = parse_duration(self._html_search_regex(
+            r'(?s)<span[^>]+class=(["\']).*?fa-clock-o.*?\1[^>]*></span>(?P<duration>.+?)</li',
+            webpage, 'duration', fatal=False, group='duration'))
 
         matches = re.finditer(r'''(?xs)
-            <(?:span|div)\s+class='label\s+filetype'>(?P<format>.*?)</(?:span|div)>\s*
+            <(?:span|div)\s+class='label\s+filetype'>(?P<format>[^<]*)</(?:span|div)>\s*
+            <(?:span|div)\s+class='label\s+filetype'>(?P<lang>[^<]*)</(?:span|div)>\s*
             <a\s+download\s+href='(?P<http_url>[^']+)'>\s*
             (?:
                 .*?
-                <a\s+href='(?P<torrent_url>[^']+\.torrent)'
+                <a\s+(?:download\s+)?href='(?P<torrent_url>[^']+\.torrent)'
             )?''', webpage)
         formats = []
         for m in matches:
@@ -62,12 +71,15 @@ class CCCIE(InfoExtractor):
             format_id = self._search_regex(
                 r'.*/([a-z0-9_-]+)/[^/]*$',
                 m.group('http_url'), 'format id', default=None)
+            if format_id:
+                format_id = m.group('lang') + '-' + format_id
             vcodec = 'h264' if 'h264' in format_id else (
                 'none' if format_id in ('mp3', 'opus') else None
             )
             formats.append({
                 'format_id': format_id,
                 'format': format,
+                'language': m.group('lang'),
                 'url': m.group('http_url'),
                 'vcodec': vcodec,
                 'preference': preference(format_id),
@@ -95,5 +107,6 @@ class CCCIE(InfoExtractor):
             'thumbnail': thumbnail,
             'view_count': view_count,
             'upload_date': upload_date,
+            'duration': duration,
             'formats': formats,
         }

youtube_dl/extractor/chaturbate.py

@@ -23,6 +23,8 @@ class ChaturbateIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    _ROOM_OFFLINE = 'Room is currently offline'
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
@@ -34,9 +36,16 @@ class ChaturbateIE(InfoExtractor):
 
         if not m3u8_url:
             error = self._search_regex(
-                r'<span[^>]+class=(["\'])desc_span\1[^>]*>(?P<error>[^<]+)</span>',
-                webpage, 'error', group='error')
-            raise ExtractorError(error, expected=True)
+                [r'<span[^>]+class=(["\'])desc_span\1[^>]*>(?P<error>[^<]+)</span>',
+                 r'<div[^>]+id=(["\'])defchat\1[^>]*>\s*<p><strong>(?P<error>[^<]+)<'],
+                webpage, 'error', group='error', default=None)
+            if not error:
+                if any(p not in webpage for p in (
+                        self._ROOM_OFFLINE, 'offline_tipping', 'tip_offline')):
+                    error = self._ROOM_OFFLINE
+            if error:
+                raise ExtractorError(error, expected=True)
+            raise ExtractorError('Unable to find stream URL')
 
         formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
 

youtube_dl/extractor/cinemassacre.py

@@ -5,7 +5,6 @@ import re
 
 from .common import InfoExtractor
 from ..utils import ExtractorError
-from .bliptv import BlipTVIE
 from .screenwavemedia import ScreenwaveMediaIE
 
 
@@ -34,18 +33,17 @@ class CinemassacreIE(InfoExtractor):
             },
         },
         {
-            # blip.tv embedded video
+            # Youtube embedded video
             'url': 'http://cinemassacre.com/2006/12/07/chronologically-confused-about-bad-movie-and-video-game-sequel-titles/',
-            'md5': 'ca9b3c8dd5a66f9375daeb5135f5a3de',
+            'md5': 'df4cf8a1dcedaec79a73d96d83b99023',
             'info_dict': {
-                'id': '4065369',
-                'ext': 'flv',
+                'id': 'OEVzPCY2T-g',
+                'ext': 'mp4',
                 'title': 'AVGN: Chronologically Confused about Bad Movie and Video Game Sequel Titles',
                 'upload_date': '20061207',
-                'uploader': 'cinemassacre',
-                'uploader_id': '250778',
-                'timestamp': 1283233867,
-                'description': 'md5:0a108c78d130676b207d0f6d029ecffd',
+                'uploader': 'Cinemassacre',
+                'uploader_id': 'JamesNintendoNerd',
+                'description': 'md5:784734696c2b8b7f4b8625cc799e07f6',
             }
         },
         {
@@ -88,8 +86,6 @@ class CinemassacreIE(InfoExtractor):
                 r'<iframe[^>]+src="(?P<url>(?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"',
             ],
             webpage, 'player data URL', default=None, group='url')
-        if not playerdata_url:
-            playerdata_url = BlipTVIE._extract_url(webpage)
         if not playerdata_url:
             raise ExtractorError('Unable to find player data')
 

youtube_dl/extractor/cnet.py

@@ -1,15 +1,11 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import json
-
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-)
+from .theplatform import ThePlatformIE
+from ..utils import int_or_none
 
 
-class CNETIE(InfoExtractor):
+class CNETIE(ThePlatformIE):
     _VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/'
     _TESTS = [{
         'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/',
@@ -18,25 +14,20 @@ class CNETIE(InfoExtractor):
             'ext': 'flv',
             'title': 'Hands-on with Microsoft Windows 8.1 Update',
             'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.',
-            'thumbnail': 're:^http://.*/flmswindows8.jpg$',
             'uploader_id': '6085384d-619e-11e3-b231-14feb5ca9861',
             'uploader': 'Sarah Mitroff',
+            'duration': 70,
         },
-        'params': {
-            'skip_download': 'requires rtmpdump',
-        }
     }, {
         'url': 'http://www.cnet.com/videos/whiny-pothole-tweets-at-local-government-when-hit-by-cars-tomorrow-daily-187/',
         'info_dict': {
             'id': '56527b93-d25d-44e3-b738-f989ce2e49ba',
             'ext': 'flv',
+            'title': 'Whiny potholes tweet at local government when hit by cars (Tomorrow Daily 187)',
             'description': 'Khail and Ashley wonder what other civic woes can be solved by self-tweeting objects, investigate a new kind of VR camera and watch an origami robot self-assemble, walk, climb, dig and dissolve. #TDPothole',
             'uploader_id': 'b163284d-6b73-44fc-b3e6-3da66c392d40',
             'uploader': 'Ashley Esqueda',
-            'title': 'Whiny potholes tweet at local government when hit by cars (Tomorrow Daily 187)',
-        },
-        'params': {
-            'skip_download': True,  # requires rtmpdump
+            'duration': 1482,
         },
     }]
 
@@ -45,26 +36,13 @@ class CNETIE(InfoExtractor):
         webpage = self._download_webpage(url, display_id)
 
         data_json = self._html_search_regex(
-            r"<div class=\"cnetVideoPlayer\"\s+.*?data-cnet-video-options='([^']+)'",
+            r"data-cnet-video(?:-uvp)?-options='([^']+)'",
             webpage, 'data json')
-        data = json.loads(data_json)
-        vdata = data['video']
-        if not vdata:
-            vdata = data['videos'][0]
-        if not vdata:
-            raise ExtractorError('Cannot find video data')
-
-        mpx_account = data['config']['players']['default']['mpx_account']
-        vid = vdata['files'].get('rtmp', vdata['files']['hds'])
-        tp_link = 'http://link.theplatform.com/s/%s/%s' % (mpx_account, vid)
+        data = self._parse_json(data_json, display_id)
+        vdata = data.get('video') or data['videos'][0]
 
         video_id = vdata['id']
-        title = vdata.get('headline')
-        if title is None:
-            title = vdata.get('title')
-        if title is None:
-            raise ExtractorError('Cannot find title!')
-        thumbnail = vdata.get('image', {}).get('path')
+        title = vdata['title']
         author = vdata.get('author')
         if author:
             uploader = '%s %s' % (author['firstName'], author['lastName'])
@@ -73,13 +51,34 @@ class CNETIE(InfoExtractor):
             uploader = None
             uploader_id = None
 
+        mpx_account = data['config']['uvpConfig']['default']['mpx_account']
+
+        metadata = self.get_metadata('%s/%s' % (mpx_account, list(vdata['files'].values())[0]), video_id)
+        description = vdata.get('description') or metadata.get('description')
+        duration = int_or_none(vdata.get('duration')) or metadata.get('duration')
+
+        formats = []
+        subtitles = {}
+        for (fkey, vid) in vdata['files'].items():
+            if fkey == 'hls_phone' and 'hls_tablet' in vdata['files']:
+                continue
+            release_url = 'http://link.theplatform.com/s/%s/%s?format=SMIL&mbr=true' % (mpx_account, vid)
+            if fkey == 'hds':
+                release_url += '&manifest=f4m'
+            tp_formats, tp_subtitles = self._extract_theplatform_smil(release_url, video_id, 'Downloading %s SMIL data' % fkey)
+            formats.extend(tp_formats)
+            subtitles = self._merge_subtitles(subtitles, tp_subtitles)
+        self._sort_formats(formats)
+
         return {
-            '_type': 'url_transparent',
-            'url': tp_link,
             'id': video_id,
             'display_id': display_id,
             'title': title,
+            'description': description,
+            'thumbnail': metadata.get('thumbnail'),
+            'duration': duration,
             'uploader': uploader,
             'uploader_id': uploader_id,
-            'thumbnail': thumbnail,
+            'subtitles': subtitles,
+            'formats': formats,
         }

youtube_dl/extractor/comcarcoff.py

@@ -1,10 +1,12 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
-import json
-
 from .common import InfoExtractor
-from ..utils import parse_iso8601
+from ..utils import (
+    int_or_none,
+    parse_duration,
+    parse_iso8601,
+)
 
 
 class ComCarCoffIE(InfoExtractor):
@@ -16,6 +18,7 @@ class ComCarCoffIE(InfoExtractor):
             'ext': 'mp4',
             'upload_date': '20141127',
             'timestamp': 1417107600,
+            'duration': 1232,
             'title': 'Happy Thanksgiving Miranda',
             'description': 'Jerry Seinfeld and his special guest Miranda Sings cruise around town in search of coffee, complaining and apologizing along the way.',
             'thumbnail': 'http://ccc.crackle.com/images/s5e4_thumb.jpg',
@@ -31,9 +34,10 @@ class ComCarCoffIE(InfoExtractor):
             display_id = 'comediansincarsgettingcoffee.com'
         webpage = self._download_webpage(url, display_id)
 
-        full_data = json.loads(self._search_regex(
-            r'<script type="application/json" id="videoData">(?P<json>.+?)</script>',
-            webpage, 'full data json'))
+        full_data = self._parse_json(
+            self._search_regex(
+                r'window\.app\s*=\s*({.+?});\n', webpage, 'full data json'),
+            display_id)['videoData']
 
         video_id = full_data['activeVideo']['video']
         video_data = full_data.get('videos', {}).get(video_id) or full_data['singleshots'][video_id]
@@ -45,12 +49,18 @@ class ComCarCoffIE(InfoExtractor):
         formats = self._extract_m3u8_formats(
             video_data['mediaUrl'], video_id, ext='mp4')
 
+        timestamp = int_or_none(video_data.get('pubDateTime')) or parse_iso8601(
+            video_data.get('pubDate'))
+        duration = int_or_none(video_data.get('durationSeconds')) or parse_duration(
+            video_data.get('duration'))
+
         return {
             'id': video_id,
             'display_id': display_id,
             'title': video_data['title'],
             'description': video_data.get('description'),
-            'timestamp': parse_iso8601(video_data.get('pubDate')),
+            'timestamp': timestamp,
+            'duration': duration,
             'thumbnails': thumbnails,
             'formats': formats,
             'webpage_url': 'http://comediansincarsgettingcoffee.com/%s' % (video_data.get('urlSlug', video_data.get('slug'))),

youtube_dl/extractor/common.py

@@ -18,7 +18,6 @@ from ..compat import (
     compat_http_client,
     compat_urllib_error,
     compat_urllib_parse,
-    compat_urllib_parse_urlparse,
     compat_urlparse,
     compat_str,
     compat_etree_fromstring,
@@ -30,6 +29,7 @@ from ..utils import (
     clean_html,
     compiled_regex_type,
     determine_ext,
+    error_to_compat_str,
     ExtractorError,
     fix_xml_ampersands,
     float_or_none,
@@ -42,6 +42,7 @@ from ..utils import (
     url_basename,
     xpath_text,
     xpath_with_ns,
+    determine_protocol,
 )
 
 
@@ -107,8 +108,9 @@ class InfoExtractor(object):
                                  -2 or smaller for less than default.
                                  < -1000 to hide the format (if there is
                                     another one which is strictly better)
-                    * language_preference  Is this in the correct requested
-                                 language?
+                    * language   Language code, e.g. "de" or "en-US".
+                    * language_preference  Is this in the language mentioned in
+                                 the URL?
                                  10 if it's what the URL is about,
                                  -1 for default (don't know),
                                  -10 otherwise, other values reserved for now.
@@ -199,6 +201,26 @@ class InfoExtractor(object):
     end_time:       Time in seconds where the reproduction should end, as
                     specified in the URL.
 
+    The following fields should only be used when the video belongs to some logical
+    chapter or section:
+
+    chapter:        Name or title of the chapter the video belongs to.
+    chapter_number: Number of the chapter the video belongs to, as an integer.
+    chapter_id:     Id of the chapter the video belongs to, as a unicode string.
+
+    The following fields should only be used when the video is an episode of some
+    series or programme:
+
+    series:         Title of the series or programme the video episode belongs to.
+    season:         Title of the season the video episode belongs to.
+    season_number:  Number of the season the video episode belongs to, as an integer.
+    season_id:      Id of the season the video episode belongs to, as a unicode string.
+    episode:        Title of the video episode. Unlike mandatory video title field,
+                    this field should denote the exact title of the video episode
+                    without any kind of decoration.
+    episode_number: Number of the video episode within a season, as an integer.
+    episode_id:     Id of the video episode, as a unicode string.
+
     Unless mentioned otherwise, the fields should be Unicode strings.
 
     Unless mentioned otherwise, None is equivalent to absence of information.
@@ -291,9 +313,9 @@ class InfoExtractor(object):
         except ExtractorError:
             raise
         except compat_http_client.IncompleteRead as e:
-            raise ExtractorError('A network error has occured.', cause=e, expected=True)
+            raise ExtractorError('A network error has occurred.', cause=e, expected=True)
         except (KeyError, StopIteration) as e:
-            raise ExtractorError('An extractor error has occured.', cause=e)
+            raise ExtractorError('An extractor error has occurred.', cause=e)
 
     def set_downloader(self, downloader):
         """Sets the downloader for this IE."""
@@ -332,7 +354,8 @@ class InfoExtractor(object):
                 return False
             if errnote is None:
                 errnote = 'Unable to download webpage'
-            errmsg = '%s: %s' % (errnote, compat_str(err))
+
+            errmsg = '%s: %s' % (errnote, error_to_compat_str(err))
             if fatal:
                 raise ExtractorError(errmsg, sys.exc_info()[2], cause=err)
             else:
@@ -622,7 +645,7 @@ class InfoExtractor(object):
                 else:
                     raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
             except (IOError, netrc.NetrcParseError) as err:
-                self._downloader.report_warning('parsing .netrc: %s' % compat_str(err))
+                self._downloader.report_warning('parsing .netrc: %s' % error_to_compat_str(err))
 
         return (username, password)
 
@@ -776,14 +799,12 @@ class InfoExtractor(object):
 
             preference = f.get('preference')
             if preference is None:
-                proto = f.get('protocol')
-                if proto is None:
-                    proto = compat_urllib_parse_urlparse(f.get('url', '')).scheme
-
-                preference = 0 if proto in ['http', 'https'] else -0.1
+                preference = 0
                 if f.get('ext') in ['f4f', 'f4m']:  # Not yet supported
                     preference -= 0.5
 
+            proto_preference = 0 if determine_protocol(f) in ['http', 'https'] else -0.1
+
             if f.get('vcodec') == 'none':  # audio only
                 if self._downloader.params.get('prefer_free_formats'):
                     ORDER = ['aac', 'mp3', 'm4a', 'webm', 'ogg', 'opus']
@@ -814,6 +835,7 @@ class InfoExtractor(object):
                 f.get('vbr') if f.get('vbr') is not None else -1,
                 f.get('height') if f.get('height') is not None else -1,
                 f.get('width') if f.get('width') is not None else -1,
+                proto_preference,
                 ext_preference,
                 f.get('abr') if f.get('abr') is not None else -1,
                 audio_ext_preference,
@@ -883,7 +905,7 @@ class InfoExtractor(object):
             fatal=fatal)
 
         if manifest is False:
-            return manifest
+            return []
 
         formats = []
         manifest_version = '1.0'
@@ -909,10 +931,8 @@ class InfoExtractor(object):
                 # may differ leading to inability to resolve the format by requested
                 # bitrate in f4m downloader
                 if determine_ext(manifest_url) == 'f4m':
-                    f4m_formats = self._extract_f4m_formats(
-                        manifest_url, video_id, preference, f4m_id, fatal=fatal)
-                    if f4m_formats:
-                        formats.extend(f4m_formats)
+                    formats.extend(self._extract_f4m_formats(
+                        manifest_url, video_id, preference, f4m_id, fatal=fatal))
                     continue
             tbr = int_or_none(media_el.attrib.get('bitrate'))
             formats.append({
@@ -954,7 +974,7 @@ class InfoExtractor(object):
             errnote=errnote or 'Failed to download m3u8 information',
             fatal=fatal)
         if res is False:
-            return res
+            return []
         m3u8_doc, urlh = res
         m3u8_url = urlh.geturl()
         last_info = None
@@ -1146,10 +1166,8 @@ class InfoExtractor(object):
             src_url = src if src.startswith('http') else compat_urlparse.urljoin(base, src)
 
             if proto == 'm3u8' or src_ext == 'm3u8':
-                m3u8_formats = self._extract_m3u8_formats(
-                    src_url, video_id, ext or 'mp4', m3u8_id='hls', fatal=False)
-                if m3u8_formats:
-                    formats.extend(m3u8_formats)
+                formats.extend(self._extract_m3u8_formats(
+                    src_url, video_id, ext or 'mp4', m3u8_id='hls', fatal=False))
                 continue
 
             if src_ext == 'f4m':
@@ -1161,9 +1179,7 @@ class InfoExtractor(object):
                     }
                 f4m_url += '&' if '?' in f4m_url else '?'
                 f4m_url += compat_urllib_parse.urlencode(f4m_params)
-                f4m_formats = self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds', fatal=False)
-                if f4m_formats:
-                    formats.extend(f4m_formats)
+                formats.extend(self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds', fatal=False))
                 continue
 
             if src_url.startswith('http') and self._is_valid_url(src, video_id):

youtube_dl/extractor/crunchyroll.py

@@ -329,8 +329,10 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
                 streamdata_req, video_id,
                 note='Downloading media info for %s' % video_format)
             stream_info = streamdata.find('./{default}preload/stream_info')
-            video_url = stream_info.find('./host').text
-            video_play_path = stream_info.find('./file').text
+            video_url = xpath_text(stream_info, './host')
+            video_play_path = xpath_text(stream_info, './file')
+            if not video_url or not video_play_path:
+                continue
             metadata = stream_info.find('./metadata')
             format_info = {
                 'format': video_format,

youtube_dl/extractor/cspan.py

@@ -58,18 +58,23 @@ class CSpanIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
+        video_type = None
         webpage = self._download_webpage(url, video_id)
-        matches = re.search(r'data-(prog|clip)id=\'([0-9]+)\'', webpage)
-        if matches:
+        # We first look for clipid, because clipprog always appears before
+        patterns = [r'id=\'clip(%s)\'\s*value=\'([0-9]+)\'' % t for t in ('id', 'prog')]
+        results = list(filter(None, (re.search(p, webpage) for p in patterns)))
+        if results:
+            matches = results[0]
             video_type, video_id = matches.groups()
-            if video_type == 'prog':
-                video_type = 'program'
+            video_type = 'clip' if video_type == 'id' else 'program'
         else:
             senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
             if senate_isvp_url:
                 title = self._og_search_title(webpage)
                 surl = smuggle_url(senate_isvp_url, {'force_title': title})
                 return self.url_result(surl, 'SenateISVP', video_id, title)
+        if video_type is None or video_id is None:
+            raise ExtractorError('unable to find video id and type')
 
         def get_text_attr(d, attr):
             return d.get(attr, {}).get('#text')

youtube_dl/extractor/dailymotion.py

@@ -7,10 +7,10 @@ import itertools
 
 from .common import InfoExtractor
 
-from ..compat import compat_str
 from ..utils import (
-    ExtractorError,
     determine_ext,
+    error_to_compat_str,
+    ExtractorError,
     int_or_none,
     parse_iso8601,
     sanitized_Request,
@@ -148,19 +148,16 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
                         continue
                     ext = determine_ext(media_url)
                     if type_ == 'application/x-mpegURL' or ext == 'm3u8':
-                        m3u8_formats = self._extract_m3u8_formats(
-                            media_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
-                        if m3u8_formats:
-                            formats.extend(m3u8_formats)
+                        formats.extend(self._extract_m3u8_formats(
+                            media_url, video_id, 'mp4', preference=-1,
+                            m3u8_id='hls', fatal=False))
                     elif type_ == 'application/f4m' or ext == 'f4m':
-                        f4m_formats = self._extract_f4m_formats(
-                            media_url, video_id, preference=-1, f4m_id='hds', fatal=False)
-                        if f4m_formats:
-                            formats.extend(f4m_formats)
+                        formats.extend(self._extract_f4m_formats(
+                            media_url, video_id, preference=-1, f4m_id='hds', fatal=False))
                     else:
                         f = {
                             'url': media_url,
-                            'format_id': quality,
+                            'format_id': 'http-%s' % quality,
                         }
                         m = re.search(r'H264-(?P<width>\d+)x(?P<height>\d+)', media_url)
                         if m:
@@ -278,7 +275,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
                 'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id,
                 video_id, note=False)
         except ExtractorError as err:
-            self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err))
+            self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err))
             return {}
         info = json.loads(sub_list)
         if (info['total'] > 0):

youtube_dl/extractor/daum.py

@@ -2,18 +2,83 @@
 
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse,
+from ..compat import compat_urllib_parse
+from ..utils import (
+    int_or_none,
+    str_to_int,
+    xpath_text,
 )
 
 
 class DaumIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:v/|.*?clipid=)(?P<id>[^?#&]+)'
+    _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/v/(?P<id>[^?#&]+)'
     IE_NAME = 'daum.net'
 
+    _TESTS = [{
+        'url': 'http://tvpot.daum.net/v/vab4dyeDBysyBssyukBUjBz',
+        'info_dict': {
+            'id': 'vab4dyeDBysyBssyukBUjBz',
+            'ext': 'mp4',
+            'title': '마크 헌트 vs 안토니오 실바',
+            'description': 'Mark Hunt vs Antonio Silva',
+            'upload_date': '20131217',
+            'duration': 2117,
+            'view_count': int,
+            'comment_count': int,
+        },
+    }, {
+        'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        query = compat_urllib_parse.urlencode({'vid': video_id})
+        info = self._download_xml(
+            'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,
+            'Downloading video info')
+        movie_data = self._download_json(
+            'http://videofarm.daum.net/controller/api/closed/v1_2/IntegratedMovieData.json?' + query,
+            video_id, 'Downloading video formats info')
+
+        formats = []
+        for format_el in movie_data['output_list']['output_list']:
+            profile = format_el['profile']
+            format_query = compat_urllib_parse.urlencode({
+                'vid': video_id,
+                'profile': profile,
+            })
+            url_doc = self._download_xml(
+                'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
+                video_id, note='Downloading video data for %s format' % profile)
+            format_url = url_doc.find('result/url').text
+            formats.append({
+                'url': format_url,
+                'format_id': profile,
+                'width': int_or_none(format_el.get('width')),
+                'height': int_or_none(format_el.get('height')),
+                'filesize': int_or_none(format_el.get('filesize')),
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': info.find('TITLE').text,
+            'formats': formats,
+            'thumbnail': xpath_text(info, 'THUMB_URL'),
+            'description': xpath_text(info, 'CONTENTS'),
+            'duration': int_or_none(xpath_text(info, 'DURATION')),
+            'upload_date': info.find('REGDTTM').text[:8],
+            'view_count': str_to_int(xpath_text(info, 'PLAY_CNT')),
+            'comment_count': str_to_int(xpath_text(info, 'COMMENT_CNT')),
+        }
+
+
+class DaumClipIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:clip/ClipView.do|mypot/View.do)\?.*?clipid=(?P<id>\d+)'
+    IE_NAME = 'daum.net:clip'
+
     _TESTS = [{
         'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
         'info_dict': {
@@ -23,53 +88,25 @@ class DaumIE(InfoExtractor):
             'description': 'DOTA 2GETHER 시즌2 6회 - 2부',
             'upload_date': '20130831',
             'duration': 3868,
+            'view_count': int,
         },
-    }, {
-        'url': 'http://tvpot.daum.net/v/vab4dyeDBysyBssyukBUjBz',
-        'only_matching': True,
-    }, {
-        'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24',
-        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
-        webpage = self._download_webpage(canonical_url, video_id)
-        full_id = self._search_regex(
-            r'src=["\']http://videofarm\.daum\.net/controller/video/viewer/Video\.html\?.*?vid=(.+?)[&"\']',
-            webpage, 'full id')
-        query = compat_urllib_parse.urlencode({'vid': full_id})
-        info = self._download_xml(
-            'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,
-            'Downloading video info')
-        urls = self._download_xml(
-            'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query,
-            video_id, 'Downloading video formats info')
-
-        formats = []
-        for format_el in urls.findall('result/output_list/output_list'):
-            profile = format_el.attrib['profile']
-            format_query = compat_urllib_parse.urlencode({
-                'vid': full_id,
-                'profile': profile,
-            })
-            url_doc = self._download_xml(
-                'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
-                video_id, note='Downloading video data for %s format' % profile)
-            format_url = url_doc.find('result/url').text
-            formats.append({
-                'url': format_url,
-                'format_id': profile,
-            })
+        video_id = self._match_id(url)
+        clip_info = self._download_json(
+            'http://tvpot.daum.net/mypot/json/GetClipInfo.do?clipid=%s' % video_id,
+            video_id, 'Downloading clip info')['clip_bean']
 
         return {
+            '_type': 'url_transparent',
             'id': video_id,
-            'title': info.find('TITLE').text,
-            'formats': formats,
-            'thumbnail': self._og_search_thumbnail(webpage),
-            'description': info.find('CONTENTS').text,
-            'duration': int(info.find('DURATION').text),
-            'upload_date': info.find('REGDTTM').text[:8],
+            'url': 'http://tvpot.daum.net/v/%s' % clip_info['vid'],
+            'title': clip_info['title'],
+            'thumbnail': clip_info.get('thumb_url'),
+            'description': clip_info.get('contents'),
+            'duration': int_or_none(clip_info.get('duration')),
+            'upload_date': clip_info.get('up_date')[:8],
+            'view_count': int_or_none(clip_info.get('play_count')),
+            'ie_key': 'Daum',
         }

youtube_dl/extractor/dcn.py

@@ -1,26 +1,90 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+import base64
+
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse
+from ..compat import (
+    compat_urllib_parse,
+    compat_str,
+)
 from ..utils import (
     int_or_none,
     parse_iso8601,
     sanitized_Request,
+    smuggle_url,
+    unsmuggle_url,
 )
 
 
 class DCNIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/.+|show/\d+/.+?)/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?show/(?P<show_id>\d+)/[^/]+(?:/(?P<video_id>\d+)/(?P<season_id>\d+))?'
+
+    def _real_extract(self, url):
+        show_id, video_id, season_id = re.match(self._VALID_URL, url).groups()
+        if video_id and int(video_id) > 0:
+            return self.url_result(
+                'http://www.dcndigital.ae/media/%s' % video_id, 'DCNVideo')
+        elif season_id and int(season_id) > 0:
+            return self.url_result(smuggle_url(
+                'http://www.dcndigital.ae/program/season/%s' % season_id,
+                {'show_id': show_id}), 'DCNSeason')
+        else:
+            return self.url_result(
+                'http://www.dcndigital.ae/program/%s' % show_id, 'DCNSeason')
+
+
+class DCNBaseIE(InfoExtractor):
+    def _extract_video_info(self, video_data, video_id, is_live):
+        title = video_data.get('title_en') or video_data['title_ar']
+        img = video_data.get('img')
+        thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None
+        duration = int_or_none(video_data.get('duration'))
+        description = video_data.get('description_en') or video_data.get('description_ar')
+        timestamp = parse_iso8601(video_data.get('create_time'), ' ')
+
+        return {
+            'id': video_id,
+            'title': self._live_title(title) if is_live else title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'timestamp': timestamp,
+            'is_live': is_live,
+        }
+
+    def _extract_video_formats(self, webpage, video_id, entry_protocol):
+        formats = []
+        m3u8_url = self._html_search_regex(
+            r'file\s*:\s*"([^"]+)', webpage, 'm3u8 url', fatal=False)
+        if m3u8_url:
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, video_id, 'mp4', entry_protocol, m3u8_id='hls', fatal=None))
+
+        rtsp_url = self._search_regex(
+            r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False)
+        if rtsp_url:
+            formats.append({
+                'url': rtsp_url,
+                'format_id': 'rtsp',
+            })
+
+        self._sort_formats(formats)
+        return formats
+
+
+class DCNVideoIE(DCNBaseIE):
+    IE_NAME = 'dcn:video'
+    _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/[^/]+|media|catchup/[^/]+/[^/]+)/(?P<id>\d+)'
     _TEST = {
-        'url': 'http://www.dcndigital.ae/#/show/199074/%D8%B1%D8%AD%D9%84%D8%A9-%D8%A7%D9%84%D8%B9%D9%85%D8%B1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/17375/6887',
+        'url': 'http://www.dcndigital.ae/#/video/%D8%B1%D8%AD%D9%84%D8%A9-%D8%A7%D9%84%D8%B9%D9%85%D8%B1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/17375',
         'info_dict':
         {
             'id': '17375',
             'ext': 'mp4',
             'title': 'رحلة العمر : الحلقة 1',
             'description': 'md5:0156e935d870acb8ef0a66d24070c6d6',
-            'thumbnail': 're:^https?://.*\.jpg$',
             'duration': 2041,
             'timestamp': 1227504126,
             'upload_date': '20081124',
@@ -37,46 +101,96 @@ class DCNIE(InfoExtractor):
         request = sanitized_Request(
             'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
             headers={'Origin': 'http://www.dcndigital.ae'})
-
-        video = self._download_json(request, video_id)
-        title = video.get('title_en') or video['title_ar']
+        video_data = self._download_json(request, video_id)
+        info = self._extract_video_info(video_data, video_id, False)
 
         webpage = self._download_webpage(
             'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' +
             compat_urllib_parse.urlencode({
-                'id': video['id'],
-                'user_id': video['user_id'],
-                'signature': video['signature'],
+                'id': video_data['id'],
+                'user_id': video_data['user_id'],
+                'signature': video_data['signature'],
                 'countries': 'Q0M=',
                 'filter': 'DENY',
             }), video_id)
+        info['formats'] = self._extract_video_formats(webpage, video_id, 'm3u8_native')
+        return info
 
-        m3u8_url = self._html_search_regex(r'file:\s*"([^"]+)', webpage, 'm3u8 url')
-        formats = self._extract_m3u8_formats(
-            m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
 
-        rtsp_url = self._search_regex(
-            r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False)
-        if rtsp_url:
-            formats.append({
-                'url': rtsp_url,
-                'format_id': 'rtsp',
+class DCNLiveIE(DCNBaseIE):
+    IE_NAME = 'dcn:live'
+    _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?live/(?P<id>\d+)'
+
+    def _real_extract(self, url):
+        channel_id = self._match_id(url)
+
+        request = sanitized_Request(
+            'http://admin.mangomolo.com/analytics/index.php/plus/getchanneldetails?channel_id=%s' % channel_id,
+            headers={'Origin': 'http://www.dcndigital.ae'})
+
+        channel_data = self._download_json(request, channel_id)
+        info = self._extract_video_info(channel_data, channel_id, True)
+
+        webpage = self._download_webpage(
+            'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' +
+            compat_urllib_parse.urlencode({
+                'id': base64.b64encode(channel_data['user_id'].encode()).decode(),
+                'channelid': base64.b64encode(channel_data['id'].encode()).decode(),
+                'signature': channel_data['signature'],
+                'countries': 'Q0M=',
+                'filter': 'DENY',
+            }), channel_id)
+        info['formats'] = self._extract_video_formats(webpage, channel_id, 'm3u8')
+        return info
+
+
+class DCNSeasonIE(InfoExtractor):
+    IE_NAME = 'dcn:season'
+    _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?program/(?:(?P<show_id>\d+)|season/(?P<season_id>\d+))'
+    _TEST = {
+        'url': 'http://dcndigital.ae/#/program/205024/%D9%85%D8%AD%D8%A7%D8%B6%D8%B1%D8%A7%D8%AA-%D8%A7%D9%84%D8%B4%D9%8A%D8%AE-%D8%A7%D9%84%D8%B4%D8%B9%D8%B1%D8%A7%D9%88%D9%8A',
+        'info_dict':
+        {
+            'id': '7910',
+            'title': 'محاضرات الشيخ الشعراوي',
+        },
+        'playlist_mincount': 27,
+    }
+
+    def _real_extract(self, url):
+        url, smuggled_data = unsmuggle_url(url, {})
+        show_id, season_id = re.match(self._VALID_URL, url).groups()
+
+        data = {}
+        if season_id:
+            data['season'] = season_id
+            show_id = smuggled_data.get('show_id')
+            if show_id is None:
+                request = sanitized_Request(
+                    'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id=%s' % season_id,
+                    headers={'Origin': 'http://www.dcndigital.ae'})
+                season = self._download_json(request, season_id)
+                show_id = season['id']
+        data['show_id'] = show_id
+        request = sanitized_Request(
+            'http://admin.mangomolo.com/analytics/index.php/plus/show',
+            compat_urllib_parse.urlencode(data),
+            {
+                'Origin': 'http://www.dcndigital.ae',
+                'Content-Type': 'application/x-www-form-urlencoded'
             })
 
-        self._sort_formats(formats)
+        show = self._download_json(request, show_id)
+        if not season_id:
+            season_id = show['default_season']
+        for season in show['seasons']:
+            if season['id'] == season_id:
+                title = season.get('title_en') or season['title_ar']
 
-        img = video.get('img')
-        thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None
-        duration = int_or_none(video.get('duration'))
-        description = video.get('description_en') or video.get('description_ar')
-        timestamp = parse_iso8601(video.get('create_time') or video.get('update_time'), ' ')
+                entries = []
+                for video in show['videos']:
+                    video_id = compat_str(video['id'])
+                    entries.append(self.url_result(
+                        'http://www.dcndigital.ae/media/%s' % video_id, 'DCNVideo', video_id))
 
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'duration': duration,
-            'timestamp': timestamp,
-            'formats': formats,
-        }
+                return self.playlist_result(entries, season_id, title)

youtube_dl/extractor/discovery.py

@@ -9,7 +9,17 @@ from ..compat import compat_str
 
 
 class DiscoveryIE(InfoExtractor):
-    _VALID_URL = r'http://www\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9_\-]*)(?:\.htm)?'
+    _VALID_URL = r'''(?x)http://(?:www\.)?(?:
+            discovery|
+            investigationdiscovery|
+            discoverylife|
+            animalplanet|
+            ahctv|
+            destinationamerica|
+            sciencechannel|
+            tlc|
+            velocity
+        )\.com/(?:[^/]+/)*(?P<id>[^./?#]+)'''
     _TESTS = [{
         'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm',
         'info_dict': {
@@ -21,8 +31,8 @@ class DiscoveryIE(InfoExtractor):
                             'don\'t miss Adam moon-walking as Jamie ... behind Jamie\'s'
                             ' back.'),
             'duration': 156,
-            'timestamp': 1303099200,
-            'upload_date': '20110418',
+            'timestamp': 1302032462,
+            'upload_date': '20110405',
         },
         'params': {
             'skip_download': True,  # requires ffmpeg
@@ -33,27 +43,38 @@ class DiscoveryIE(InfoExtractor):
             'id': 'mythbusters-the-simpsons',
             'title': 'MythBusters: The Simpsons',
         },
-        'playlist_count': 9,
+        'playlist_mincount': 10,
+    }, {
+        'url': 'http://www.animalplanet.com/longfin-eels-maneaters/',
+        'info_dict': {
+            'id': '78326',
+            'ext': 'mp4',
+            'title': 'Longfin Eels: Maneaters?',
+            'description': 'Jeremy Wade tests whether or not New Zealand\'s longfin eels are man-eaters by covering himself in fish guts and getting in the water with them.',
+            'upload_date': '20140725',
+            'timestamp': 1406246400,
+            'duration': 116,
+        },
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        info = self._download_json(url + '?flat=1', video_id)
+        display_id = self._match_id(url)
+        info = self._download_json(url + '?flat=1', display_id)
 
         video_title = info.get('playlist_title') or info.get('video_title')
 
         entries = [{
             'id': compat_str(video_info['id']),
             'formats': self._extract_m3u8_formats(
-                video_info['src'], video_id, ext='mp4',
+                video_info['src'], display_id, 'mp4', 'm3u8_native', m3u8_id='hls',
                 note='Download m3u8 information for video %d' % (idx + 1)),
             'title': video_info['title'],
             'description': video_info.get('description'),
             'duration': parse_duration(video_info.get('video_length')),
-            'webpage_url': video_info.get('href'),
+            'webpage_url': video_info.get('href') or video_info.get('url'),
             'thumbnail': video_info.get('thumbnailURL'),
             'alt_title': video_info.get('secondary_title'),
             'timestamp': parse_iso8601(video_info.get('publishedDate')),
         } for idx, video_info in enumerate(info['playlist'])]
 
-        return self.playlist_result(entries, video_id, video_title)
+        return self.playlist_result(entries, display_id, video_title)

youtube_dl/extractor/dramafever.py

@@ -3,7 +3,7 @@ from __future__ import unicode_literals
 
 import itertools
 
-from .common import InfoExtractor
+from .amp import AMPIE
 from ..compat import (
     compat_HTTPError,
     compat_urllib_parse,
@@ -12,14 +12,12 @@ from ..compat import (
 from ..utils import (
     ExtractorError,
     clean_html,
-    determine_ext,
     int_or_none,
-    parse_iso8601,
     sanitized_Request,
 )
 
 
-class DramaFeverBaseIE(InfoExtractor):
+class DramaFeverBaseIE(AMPIE):
     _LOGIN_URL = 'https://www.dramafever.com/accounts/login/'
     _NETRC_MACHINE = 'dramafever'
 
@@ -69,71 +67,56 @@ class DramaFeverBaseIE(InfoExtractor):
 class DramaFeverIE(DramaFeverBaseIE):
     IE_NAME = 'dramafever'
     _VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+/[0-9]+)(?:/|$)'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.dramafever.com/drama/4512/1/Cooking_with_Shin/',
         'info_dict': {
             'id': '4512.1',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Cooking with Shin 4512.1',
             'description': 'md5:a8eec7942e1664a6896fcd5e1287bfd0',
+            'episode': 'Episode 1',
+            'episode_number': 1,
             'thumbnail': 're:^https?://.*\.jpg',
             'timestamp': 1404336058,
             'upload_date': '20140702',
             'duration': 343,
-        }
-    }
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://www.dramafever.com/drama/4826/4/Mnet_Asian_Music_Awards_2015/?ap=1',
+        'info_dict': {
+            'id': '4826.4',
+            'ext': 'mp4',
+            'title': 'Mnet Asian Music Awards 2015 4826.4',
+            'description': 'md5:3ff2ee8fedaef86e076791c909cf2e91',
+            'episode': 'Mnet Asian Music Awards 2015 - Part 3',
+            'episode_number': 4,
+            'thumbnail': 're:^https?://.*\.jpg',
+            'timestamp': 1450213200,
+            'upload_date': '20151215',
+            'duration': 5602,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url).replace('/', '.')
 
         try:
-            feed = self._download_json(
-                'http://www.dramafever.com/amp/episode/feed.json?guid=%s' % video_id,
-                video_id, 'Downloading episode JSON')['channel']['item']
+            info = self._extract_feed_info(
+                'http://www.dramafever.com/amp/episode/feed.json?guid=%s' % video_id)
         except ExtractorError as e:
             if isinstance(e.cause, compat_HTTPError):
                 raise ExtractorError(
                     'Currently unavailable in your country.', expected=True)
             raise
 
-        media_group = feed.get('media-group', {})
-
-        formats = []
-        for media_content in media_group['media-content']:
-            src = media_content.get('@attributes', {}).get('url')
-            if not src:
-                continue
-            ext = determine_ext(src)
-            if ext == 'f4m':
-                formats.extend(self._extract_f4m_formats(
-                    src, video_id, f4m_id='hds'))
-            elif ext == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(
-                    src, video_id, 'mp4', m3u8_id='hls'))
-            else:
-                formats.append({
-                    'url': src,
-                })
-        self._sort_formats(formats)
-
-        title = media_group.get('media-title')
-        description = media_group.get('media-description')
-        duration = int_or_none(media_group['media-content'][0].get('@attributes', {}).get('duration'))
-        thumbnail = self._proto_relative_url(
-            media_group.get('media-thumbnail', {}).get('@attributes', {}).get('url'))
-        timestamp = parse_iso8601(feed.get('pubDate'), ' ')
-
-        subtitles = {}
-        for media_subtitle in media_group.get('media-subTitle', []):
-            lang = media_subtitle.get('@attributes', {}).get('lang')
-            href = media_subtitle.get('@attributes', {}).get('href')
-            if not lang or not href:
-                continue
-            subtitles[lang] = [{
-                'ext': 'ttml',
-                'url': href,
-            }]
-
         series_id, episode_number = video_id.split('.')
         episode_info = self._download_json(
             # We only need a single episode info, so restricting page size to one episode
@@ -143,24 +126,24 @@ class DramaFeverIE(DramaFeverBaseIE):
             video_id, 'Downloading episode info JSON', fatal=False)
         if episode_info:
             value = episode_info.get('value')
-            if value:
-                subfile = value[0].get('subfile') or value[0].get('new_subfile')
-                if subfile and subfile != 'http://www.dramafever.com/st/':
-                    subtitles.setdefault('English', []).append({
-                        'ext': 'srt',
-                        'url': subfile,
-                    })
+            if isinstance(value, list):
+                for v in value:
+                    if v.get('type') == 'Episode':
+                        subfile = v.get('subfile') or v.get('new_subfile')
+                        if subfile and subfile != 'http://www.dramafever.com/st/':
+                            info.setdefault('subtitles', {}).setdefault('English', []).append({
+                                'ext': 'srt',
+                                'url': subfile,
+                            })
+                        episode_number = int_or_none(v.get('number'))
+                        episode_fallback = 'Episode'
+                        if episode_number:
+                            episode_fallback += ' %d' % episode_number
+                        info['episode'] = v.get('title') or episode_fallback
+                        info['episode_number'] = episode_number
+                        break
 
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'timestamp': timestamp,
-            'duration': duration,
-            'formats': formats,
-            'subtitles': subtitles,
-        }
+        return info
 
 
 class DramaFeverSeriesIE(DramaFeverBaseIE):

youtube_dl/extractor/dreisat.py

@@ -2,14 +2,10 @@ from __future__ import unicode_literals
 
 import re
 
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    unified_strdate,
-)
+from .zdf import ZDFIE
 
 
-class DreiSatIE(InfoExtractor):
+class DreiSatIE(ZDFIE):
     IE_NAME = '3sat'
     _VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/(?:index\.php|mediathek\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
     _TESTS = [
@@ -35,53 +31,4 @@ class DreiSatIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         details_url = 'http://www.3sat.de/mediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
-        details_doc = self._download_xml(details_url, video_id, 'Downloading video details')
-
-        status_code = details_doc.find('./status/statuscode')
-        if status_code is not None and status_code.text != 'ok':
-            code = status_code.text
-            if code == 'notVisibleAnymore':
-                message = 'Video %s is not available' % video_id
-            else:
-                message = '%s returned error: %s' % (self.IE_NAME, code)
-            raise ExtractorError(message, expected=True)
-
-        thumbnail_els = details_doc.findall('.//teaserimage')
-        thumbnails = [{
-            'width': int(te.attrib['key'].partition('x')[0]),
-            'height': int(te.attrib['key'].partition('x')[2]),
-            'url': te.text,
-        } for te in thumbnail_els]
-
-        information_el = details_doc.find('.//information')
-        video_title = information_el.find('./title').text
-        video_description = information_el.find('./detail').text
-
-        details_el = details_doc.find('.//details')
-        video_uploader = details_el.find('./channel').text
-        upload_date = unified_strdate(details_el.find('./airtime').text)
-
-        format_els = details_doc.findall('.//formitaet')
-        formats = [{
-            'format_id': fe.attrib['basetype'],
-            'width': int(fe.find('./width').text),
-            'height': int(fe.find('./height').text),
-            'url': fe.find('./url').text,
-            'filesize': int(fe.find('./filesize').text),
-            'video_bitrate': int(fe.find('./videoBitrate').text),
-        } for fe in format_els
-            if not fe.find('./url').text.startswith('http://www.metafilegenerator.de/')]
-
-        self._sort_formats(formats)
-
-        return {
-            '_type': 'video',
-            'id': video_id,
-            'title': video_title,
-            'formats': formats,
-            'description': video_description,
-            'thumbnails': thumbnails,
-            'thumbnail': thumbnails[-1]['url'],
-            'uploader': video_uploader,
-            'upload_date': upload_date,
-        }
+        return self.extract_from_xml_url(video_id, details_url)

youtube_dl/extractor/einthusan.py

@@ -1,9 +1,12 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
+from ..compat import compat_urlparse
+from ..utils import (
+    remove_start,
+    sanitized_Request,
+)
 
 
 class EinthusanIE(InfoExtractor):
@@ -34,27 +37,33 @@ class EinthusanIE(InfoExtractor):
     ]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        webpage = self._download_webpage(url, video_id)
+        video_id = self._match_id(url)
 
-        video_title = self._html_search_regex(
-            r'<h1><a class="movie-title".*?>(.*?)</a></h1>', webpage, 'title')
+        request = sanitized_Request(url)
+        request.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:43.0) Gecko/20100101 Firefox/43.0')
+        webpage = self._download_webpage(request, video_id)
 
-        video_url = self._html_search_regex(
-            r'''(?s)jwplayer\("mediaplayer"\)\.setup\({.*?'file': '([^']+)'.*?}\);''',
-            webpage, 'video url')
+        title = self._html_search_regex(
+            r'<h1><a[^>]+class=["\']movie-title["\'][^>]*>(.+?)</a></h1>',
+            webpage, 'title')
+
+        video_id = self._search_regex(
+            r'data-movieid=["\'](\d+)', webpage, 'video id', default=video_id)
+
+        video_url = self._download_webpage(
+            'http://cdn.einthusan.com/geturl/%s/hd/London,Washington,Toronto,Dallas,San,Sydney/'
+            % video_id, video_id)
 
         description = self._html_search_meta('description', webpage)
         thumbnail = self._html_search_regex(
             r'''<a class="movie-cover-wrapper".*?><img src=["'](.*?)["'].*?/></a>''',
             webpage, "thumbnail url", fatal=False)
         if thumbnail is not None:
-            thumbnail = thumbnail.replace('..', 'http://www.einthusan.com')
+            thumbnail = compat_urlparse.urljoin(url, remove_start(thumbnail, '..'))
 
         return {
             'id': video_id,
-            'title': video_title,
+            'title': title,
             'url': video_url,
             'thumbnail': thumbnail,
             'description': description,

youtube_dl/extractor/eitb.py

@@ -65,18 +65,14 @@ class EitbIE(InfoExtractor):
             if token_data:
                 token = token_data.get('token')
                 if token:
-                    m3u8_formats = self._extract_m3u8_formats(
-                        '%s?hdnts=%s' % (hls_url, token), video_id, m3u8_id='hls', fatal=False)
-                    if m3u8_formats:
-                        formats.extend(m3u8_formats)
+                    formats.extend(self._extract_m3u8_formats(
+                        '%s?hdnts=%s' % (hls_url, token), video_id, m3u8_id='hls', fatal=False))
 
         hds_url = media.get('HDS_SURL')
         if hds_url:
-            f4m_formats = self._extract_f4m_formats(
+            formats.extend(self._extract_f4m_formats(
                 '%s?hdcore=3.7.0' % hds_url.replace('euskalsvod', 'euskalvod'),
-                video_id, f4m_id='hds', fatal=False)
-            if f4m_formats:
-                formats.extend(f4m_formats)
+                video_id, f4m_id='hds', fatal=False))
 
         self._sort_formats(formats)
 

youtube_dl/extractor/ellentv.py

@@ -13,12 +13,12 @@ class EllenTVIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)'
     _TEST = {
         'url': 'http://www.ellentv.com/videos/0-ipq1gsai/',
-        'md5': '8e3c576bf2e9bfff4d76565f56f94c9c',
+        'md5': '4294cf98bc165f218aaa0b89e0fd8042',
         'info_dict': {
             'id': '0_ipq1gsai',
-            'ext': 'mp4',
+            'ext': 'mov',
             'title': 'Fast Fingers of Fate',
-            'description': 'md5:587e79fbbd0d73b148bc596d99ce48e6',
+            'description': 'md5:3539013ddcbfa64b2a6d1b38d910868a',
             'timestamp': 1428035648,
             'upload_date': '20150403',
             'uploader_id': 'batchUser',

youtube_dl/extractor/espn.py

@@ -1,18 +1,30 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..utils import remove_end
 
 
 class ESPNIE(InfoExtractor):
     _VALID_URL = r'https?://espn\.go\.com/(?:[^/]+/)*(?P<id>[^/]+)'
-    _WORKING = False
     _TESTS = [{
         'url': 'http://espn.go.com/video/clip?id=10365079',
         'info_dict': {
             'id': 'FkYWtmazr6Ed8xmvILvKLWjd4QvYZpzG',
             'ext': 'mp4',
-            'title': 'dm_140128_30for30Shorts___JudgingJewellv2',
-            'description': '',
+            'title': '30 for 30 Shorts: Judging Jewell',
+            'description': None,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        # 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',
+        'info_dict': {
+            'id': '50NDFkeTqRHB0nXBOK-RGdSG5YQPuxHg',
+            'ext': 'mp4',
+            'title': 'Must-See Moments: Best of the MLS season',
         },
         'params': {
             # m3u8 download
@@ -44,12 +56,23 @@ class ESPNIE(InfoExtractor):
             r'class="video-play-button"[^>]+data-id="(\d+)',
             webpage, 'video 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(
-            'https://espn.go.com/video/iframe/twitter/?id=%s' % video_id, video_id)
+            player_url, video_id)
 
         pcode = self._search_regex(
             r'["\']pcode=([^"\']+)["\']', player, 'pcode')
 
-        return self.url_result(
-            'ooyalaexternal:espn:%s:%s' % (video_id, pcode),
-            'OoyalaExternal')
+        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,
+        }

youtube_dl/extractor/esri.py

@@ -61,7 +61,7 @@ class EsriVideoIE(InfoExtractor):
             webpage, 'duration', fatal=False))
 
         upload_date = unified_strdate(self._html_search_meta(
-            'last-modified', webpage, 'upload date', fatal=None))
+            'last-modified', webpage, 'upload date', fatal=False))
 
         return {
             'id': video_id,

youtube_dl/extractor/facebook.py

@@ -7,11 +7,11 @@ import socket
 from .common import InfoExtractor
 from ..compat import (
     compat_http_client,
-    compat_str,
     compat_urllib_error,
     compat_urllib_parse_unquote,
 )
 from ..utils import (
+    error_to_compat_str,
     ExtractorError,
     limit_length,
     sanitized_Request,
@@ -74,7 +74,7 @@ class FacebookIE(InfoExtractor):
             return
 
         login_page_req = sanitized_Request(self._LOGIN_URL)
-        login_page_req.add_header('Cookie', 'locale=en_US')
+        self._set_cookie('facebook.com', 'locale', 'en_US')
         login_page = self._download_webpage(login_page_req, None,
                                             note='Downloading login page',
                                             errnote='Unable to download login page')
@@ -100,13 +100,25 @@ class FacebookIE(InfoExtractor):
             login_results = self._download_webpage(request, None,
                                                    note='Logging in', errnote='unable to fetch login page')
             if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None:
-                self._downloader.report_warning('unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
+                error = self._html_search_regex(
+                    r'(?s)<div[^>]+class=(["\']).*?login_error_box.*?\1[^>]*><div[^>]*>.*?</div><div[^>]*>(?P<error>.+?)</div>',
+                    login_results, 'login error', default=None, group='error')
+                if error:
+                    raise ExtractorError('Unable to login: %s' % error, expected=True)
+                self._downloader.report_warning('unable to log in: bad username/password, or exceeded login rate limit (~3/min). Check credentials or wait.')
+                return
+
+            fb_dtsg = self._search_regex(
+                r'name="fb_dtsg" value="(.+?)"', login_results, 'fb_dtsg', default=None)
+            h = self._search_regex(
+                r'name="h"\s+(?:\w+="[^"]+"\s+)*?value="([^"]+)"', login_results, 'h', default=None)
+
+            if not fb_dtsg or not h:
                 return
 
             check_form = {
-                'fb_dtsg': self._search_regex(r'name="fb_dtsg" value="(.+?)"', login_results, 'fb_dtsg'),
-                'h': self._search_regex(
-                    r'name="h"\s+(?:\w+="[^"]+"\s+)*?value="([^"]+)"', login_results, 'h'),
+                'fb_dtsg': fb_dtsg,
+                'h': h,
                 'name_action_selected': 'dont_save',
             }
             check_req = sanitized_Request(self._CHECKPOINT_URL, urlencode_postdata(check_form))
@@ -114,9 +126,9 @@ class FacebookIE(InfoExtractor):
             check_response = self._download_webpage(check_req, None,
                                                     note='Confirming login')
             if re.search(r'id="checkpointSubmitButton"', check_response) is not None:
-                self._downloader.report_warning('Unable to confirm login, you have to login in your brower and authorize the login.')
+                self._downloader.report_warning('Unable to confirm login, you have to login in your browser and authorize the login.')
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-            self._downloader.report_warning('unable to log in: %s' % compat_str(err))
+            self._downloader.report_warning('unable to log in: %s' % error_to_compat_str(err))
             return
 
     def _real_initialize(self):

youtube_dl/extractor/faz.py

@@ -2,6 +2,11 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..utils import (
+    xpath_element,
+    xpath_text,
+    int_or_none,
+)
 
 
 class FazIE(InfoExtractor):
@@ -37,31 +42,32 @@ class FazIE(InfoExtractor):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
+        description = self._og_search_description(webpage)
         config_xml_url = self._search_regex(
-            r'writeFLV\(\'(.+?)\',', webpage, 'config xml url')
+            r'videoXMLURL\s*=\s*"([^"]+)', webpage, 'config xml url')
         config = self._download_xml(
             config_xml_url, video_id, 'Downloading config xml')
 
-        encodings = config.find('ENCODINGS')
+        encodings = xpath_element(config, 'ENCODINGS', 'encodings', True)
         formats = []
         for pref, code in enumerate(['LOW', 'HIGH', 'HQ']):
-            encoding = encodings.find(code)
-            if encoding is None:
-                continue
-            encoding_url = encoding.find('FILENAME').text
-            formats.append({
-                'url': encoding_url,
-                'format_id': code.lower(),
-                'quality': pref,
-            })
+            encoding = xpath_element(encodings, code)
+            if encoding:
+                encoding_url = xpath_text(encoding, 'FILENAME')
+                if encoding_url:
+                    formats.append({
+                        'url': encoding_url,
+                        'format_id': code.lower(),
+                        'quality': pref,
+                        'tbr': int_or_none(xpath_text(encoding, 'AVERAGEBITRATE')),
+                    })
         self._sort_formats(formats)
 
-        descr = self._html_search_regex(
-            r'<p class="Content Copy">(.*?)</p>', webpage, 'description', fatal=False)
         return {
             'id': video_id,
             'title': self._og_search_title(webpage),
             'formats': formats,
-            'description': descr,
-            'thumbnail': config.find('STILL/STILL_BIG').text,
+            'description': description.strip() if description else None,
+            'thumbnail': xpath_text(config, 'STILL/STILL_BIG'),
+            'duration': int_or_none(xpath_text(config, 'DURATION')),
         }

youtube_dl/extractor/fktv.py

@@ -1,12 +1,10 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     clean_html,
     determine_ext,
-    ExtractorError,
+    js_to_json,
 )
 
 
@@ -32,24 +30,22 @@ class FKTVIE(InfoExtractor):
             'http://fernsehkritik.tv/folge-%s/play' % episode, episode)
         title = clean_html(self._html_search_regex(
             '<h3>([^<]+)</h3>', webpage, 'title'))
-        matches = re.search(
-            r'(?s)<video(?:(?!poster)[^>])+(?:poster="([^"]+)")?[^>]*>(.*)</video>',
-            webpage)
-        if matches is None:
-            raise ExtractorError('Unable to extract the video')
+        thumbnail = self._search_regex(r'POSTER\s*=\s*"([^"]+)', webpage, 'thumbnail', fatal=False)
+        sources = self._parse_json(self._search_regex(r'(?s)MEDIA\s*=\s*(\[.+?\]);', webpage, 'media'), episode, js_to_json)
 
-        poster, sources = matches.groups()
-        if poster is None:
-            self.report_warning('unable to extract thumbnail')
+        formats = []
+        for source in sources:
+            furl = source.get('src')
+            if furl:
+                formats.append({
+                    'url': furl,
+                    'format_id': determine_ext(furl),
+                })
+        self._sort_formats(formats)
 
-        urls = re.findall(r'<source[^>]+src="([^"]+)"', sources)
-        formats = [{
-            'url': furl,
-            'format_id': determine_ext(furl),
-        } for furl in urls]
         return {
             'id': episode,
             'title': title,
             'formats': formats,
-            'thumbnail': poster,
+            'thumbnail': thumbnail,
         }

youtube_dl/extractor/flickr.py

@@ -1,67 +1,93 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
+from ..compat import compat_urllib_parse
 from ..utils import (
     ExtractorError,
-    find_xpath_attr,
-    sanitized_Request,
+    int_or_none,
+    qualities,
 )
 
 
 class FlickrIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.|secure\.)?flickr\.com/photos/(?P<uploader_id>[\w\-_@]+)/(?P<id>\d+).*'
+    _VALID_URL = r'https?://(?:www\.|secure\.)?flickr\.com/photos/[\w\-_@]+/(?P<id>\d+)'
     _TEST = {
         'url': 'http://www.flickr.com/photos/forestwander-nature-pictures/5645318632/in/photostream/',
-        'md5': '6fdc01adbc89d72fc9c4f15b4a4ba87b',
+        'md5': '164fe3fa6c22e18d448d4d5af2330f31',
         'info_dict': {
             'id': '5645318632',
-            'ext': 'mp4',
-            "description": "Waterfalls in the Springtime at Dark Hollow Waterfalls. These are located just off of Skyline Drive in Virginia. They are only about 6/10 of a mile hike but it is a pretty steep hill and a good climb back up.",
-            "uploader_id": "forestwander-nature-pictures",
-            "title": "Dark Hollow Waterfalls"
+            'ext': 'mpg',
+            'description': 'Waterfalls in the Springtime at Dark Hollow Waterfalls. These are located just off of Skyline Drive in Virginia. They are only about 6/10 of a mile hike but it is a pretty steep hill and a good climb back up.',
+            'title': 'Dark Hollow Waterfalls',
+            'duration': 19,
+            'timestamp': 1303528740,
+            'upload_date': '20110423',
+            'uploader_id': '10922353@N03',
+            'uploader': 'Forest Wander',
+            'comment_count': int,
+            'view_count': int,
+            'tags': list,
         }
     }
 
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+    _API_BASE_URL = 'https://api.flickr.com/services/rest?'
 
-        video_id = mobj.group('id')
-        video_uploader_id = mobj.group('uploader_id')
-        webpage_url = 'http://www.flickr.com/photos/' + video_uploader_id + '/' + video_id
-        req = sanitized_Request(webpage_url)
-        req.add_header(
-            'User-Agent',
-            # it needs a more recent version
-            'Mozilla/5.0 (X11; Linux x86_64; rv:38.0) Gecko/20150101 Firefox/38.0 (Chrome)')
-        webpage = self._download_webpage(req, video_id)
-
-        secret = self._search_regex(r'secret"\s*:\s*"(\w+)"', webpage, 'secret')
-
-        first_url = 'https://secure.flickr.com/apps/video/video_mtl_xml.gne?v=x&photo_id=' + video_id + '&secret=' + secret + '&bitrate=700&target=_self'
-        first_xml = self._download_xml(first_url, video_id, 'Downloading first data webpage')
-
-        node_id = find_xpath_attr(
-            first_xml, './/{http://video.yahoo.com/YEP/1.0/}Item', 'id',
-            'id').text
-
-        second_url = 'https://secure.flickr.com/video_playlist.gne?node_id=' + node_id + '&tech=flash&mode=playlist&bitrate=700&secret=' + secret + '&rd=video.yahoo.com&noad=1'
-        second_xml = self._download_xml(second_url, video_id, 'Downloading second data webpage')
-
-        self.report_extraction(video_id)
-
-        stream = second_xml.find('.//STREAM')
-        if stream is None:
-            raise ExtractorError('Unable to extract video url')
-        video_url = stream.attrib['APP'] + stream.attrib['FULLPATH']
-
-        return {
-            'id': video_id,
-            'url': video_url,
-            'ext': 'mp4',
-            'title': self._og_search_title(webpage),
-            'description': self._og_search_description(webpage),
-            'thumbnail': self._og_search_thumbnail(webpage),
-            'uploader_id': video_uploader_id,
+    def _call_api(self, method, video_id, api_key, note, secret=None):
+        query = {
+            'photo_id': video_id,
+            'method': 'flickr.%s' % method,
+            'api_key': api_key,
+            'format': 'json',
+            'nojsoncallback': 1,
         }
+        if secret:
+            query['secret'] = secret
+        data = self._download_json(self._API_BASE_URL + compat_urllib_parse.urlencode(query), video_id, note)
+        if data['stat'] != 'ok':
+            raise ExtractorError(data['message'])
+        return data
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        api_key = self._download_json(
+            'https://www.flickr.com/hermes_error_beacon.gne', video_id,
+            'Downloading api key')['site_key']
+
+        video_info = self._call_api(
+            'photos.getInfo', video_id, api_key, 'Downloading video info')['photo']
+        if video_info['media'] == 'video':
+            streams = self._call_api(
+                'video.getStreamInfo', video_id, api_key,
+                'Downloading streams info', video_info['secret'])['streams']
+
+            preference = qualities(
+                ['288p', 'iphone_wifi', '100', '300', '700', '360p', 'appletv', '720p', '1080p', 'orig'])
+
+            formats = []
+            for stream in streams['stream']:
+                stream_type = str(stream.get('type'))
+                formats.append({
+                    'format_id': stream_type,
+                    'url': stream['_content'],
+                    'preference': preference(stream_type),
+                })
+            self._sort_formats(formats)
+
+            owner = video_info.get('owner', {})
+
+            return {
+                'id': video_id,
+                'title': video_info['title']['_content'],
+                'description': video_info.get('description', {}).get('_content'),
+                'formats': formats,
+                'timestamp': int_or_none(video_info.get('dateuploaded')),
+                'duration': int_or_none(video_info.get('video', {}).get('duration')),
+                'uploader_id': owner.get('nsid'),
+                'uploader': owner.get('realname'),
+                'comment_count': int_or_none(video_info.get('comments', {}).get('_content')),
+                'view_count': int_or_none(video_info.get('views')),
+                'tags': [tag.get('_content') for tag in video_info.get('tags', {}).get('tag', [])]
+            }
+        else:
+            raise ExtractorError('not a video', expected=True)

youtube_dl/extractor/footyroom.py

@@ -13,6 +13,7 @@ class FootyRoomIE(InfoExtractor):
             'title': 'Schalke 04 0 – 2 Real Madrid',
         },
         'playlist_count': 3,
+        'skip': 'Video for this match is not available',
     }, {
         'url': 'http://footyroom.com/georgia-0-2-germany-2015-03/',
         'info_dict': {

youtube_dl/extractor/fox.py

@@ -0,0 +1,39 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import smuggle_url
+
+
+class FOXIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?fox\.com/watch/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.fox.com/watch/255180355939/7684182528',
+        'info_dict': {
+            'id': '255180355939',
+            'ext': 'mp4',
+            'title': 'Official Trailer: Gotham',
+            'description': 'Tracing the rise of the great DC Comics Super-Villains and vigilantes, Gotham reveals an entirely new chapter that has never been told.',
+            'duration': 129,
+        },
+        'add_ie': ['ThePlatform'],
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        release_url = self._parse_json(self._search_regex(
+            r'"fox_pdk_player"\s*:\s*({[^}]+?})', webpage, 'fox_pdk_player'),
+            video_id)['release_url'] + '&manifest=m3u'
+
+        return {
+            '_type': 'url_transparent',
+            'ie_key': 'ThePlatform',
+            'url': smuggle_url(release_url, {'force_smil_url': True}),
+            'id': video_id,
+        }

youtube_dl/extractor/foxnews.py

@@ -2,14 +2,10 @@ from __future__ import unicode_literals
 
 import re
 
-from .common import InfoExtractor
-from ..utils import (
-    parse_iso8601,
-    int_or_none,
-)
+from .amp import AMPIE
 
 
-class FoxNewsIE(InfoExtractor):
+class FoxNewsIE(AMPIE):
     IE_DESC = 'Fox News and Fox Business Video'
     _VALID_URL = r'https?://(?P<host>video\.fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'
     _TESTS = [
@@ -20,10 +16,10 @@ class FoxNewsIE(InfoExtractor):
                 'id': '3937480',
                 'ext': 'flv',
                 'title': 'Frozen in Time',
-                'description': 'Doctors baffled by 16-year-old girl that is the size of a toddler',
+                'description': '16-year-old girl is size of toddler',
                 'duration': 265,
-                'timestamp': 1304411491,
-                'upload_date': '20110503',
+                # 'timestamp': 1304411491,
+                # 'upload_date': '20110503',
                 'thumbnail': 're:^https?://.*\.jpg$',
             },
         },
@@ -34,10 +30,10 @@ class FoxNewsIE(InfoExtractor):
                 'id': '3922535568001',
                 'ext': 'mp4',
                 'title': "Rep. Luis Gutierrez on if Obama's immigration plan is legal",
-                'description': "Congressman discusses the president's executive action",
+                'description': "Congressman discusses president's plan",
                 'duration': 292,
-                'timestamp': 1417662047,
-                'upload_date': '20141204',
+                # 'timestamp': 1417662047,
+                # 'upload_date': '20141204',
                 'thumbnail': 're:^https?://.*\.jpg$',
             },
         },
@@ -52,52 +48,9 @@ class FoxNewsIE(InfoExtractor):
     ]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        host = mobj.group('host')
+        host, video_id = re.match(self._VALID_URL, url).groups()
 
-        video = self._download_json(
-            'http://%s/v/feed/video/%s.js?template=fox' % (host, video_id), video_id)
-
-        item = video['channel']['item']
-        title = item['title']
-        description = item['description']
-        timestamp = parse_iso8601(item['dc-date'])
-
-        media_group = item['media-group']
-        duration = None
-        formats = []
-        for media in media_group['media-content']:
-            attributes = media['@attributes']
-            video_url = attributes['url']
-            if video_url.endswith('.f4m'):
-                formats.extend(self._extract_f4m_formats(video_url + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124', video_id))
-            elif video_url.endswith('.m3u8'):
-                formats.extend(self._extract_m3u8_formats(video_url, video_id, 'flv'))
-            elif not video_url.endswith('.smil'):
-                duration = int_or_none(attributes.get('duration'))
-                formats.append({
-                    'url': video_url,
-                    'format_id': media['media-category']['@attributes']['label'],
-                    'preference': 1,
-                    'vbr': int_or_none(attributes.get('bitrate')),
-                    'filesize': int_or_none(attributes.get('fileSize'))
-                })
-        self._sort_formats(formats)
-
-        media_thumbnail = media_group['media-thumbnail']['@attributes']
-        thumbnails = [{
-            'url': media_thumbnail['url'],
-            'width': int_or_none(media_thumbnail.get('width')),
-            'height': int_or_none(media_thumbnail.get('height')),
-        }] if media_thumbnail else []
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'duration': duration,
-            'timestamp': timestamp,
-            'formats': formats,
-            'thumbnails': thumbnails,
-        }
+        info = self._extract_feed_info(
+            'http://%s/v/feed/video/%s.js?template=fox' % (host, video_id))
+        info['id'] = video_id
+        return info

youtube_dl/extractor/franceculture.py

@@ -8,6 +8,7 @@ from ..compat import (
 from ..utils import (
     determine_ext,
     int_or_none,
+    ExtractorError,
 )
 
 
@@ -22,14 +23,13 @@ class FranceCultureIE(InfoExtractor):
             'alt_title': 'Carnet nomade | 13-14',
             'vcodec': 'none',
             'upload_date': '20140301',
-            'thumbnail': r're:^http://www\.franceculture\.fr/.*/images/player/Carnet-nomade\.jpg$',
-            'description': 'startswith:Avec :Jean-Baptiste Péretié pour son documentaire sur Arte "La revanche des « geeks », une enquête menée aux Etats',
+            'thumbnail': r're:^http://static\.franceculture\.fr/.*/images/player/Carnet-nomade\.jpg$',
+            'description': 'startswith:Avec :Jean-Baptiste Péretié pour son documentaire sur Arte "La revanche',
             'timestamp': 1393700400,
         }
     }
 
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
+    def _extract_from_player(self, url, video_id):
         webpage = self._download_webpage(url, video_id)
 
         video_path = self._search_regex(
@@ -42,6 +42,9 @@ class FranceCultureIE(InfoExtractor):
             r'<a id="player".*?>\s+<img src="([^"]+)"',
             webpage, 'thumbnail', fatal=False)
 
+        display_id = self._search_regex(
+            r'<span class="path-diffusion">emission-(.*?)</span>', webpage, 'display_id')
+
         title = self._html_search_regex(
             r'<span class="title-diffusion">(.*?)</span>', webpage, 'title')
         alt_title = self._html_search_regex(
@@ -66,4 +69,37 @@ class FranceCultureIE(InfoExtractor):
             'alt_title': alt_title,
             'thumbnail': thumbnail,
             'description': description,
+            'display_id': display_id,
         }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        return self._extract_from_player(url, video_id)
+
+
+class FranceCultureEmissionIE(FranceCultureIE):
+    _VALID_URL = r'https?://(?:www\.)?franceculture\.fr/emission-(?P<id>[^?#]+)'
+    _TEST = {
+        'url': 'http://www.franceculture.fr/emission-les-carnets-de-la-creation-jean-gabriel-periot-cineaste-2015-10-13',
+        'info_dict': {
+            'title': 'Jean-Gabriel Périot, cinéaste',
+            'alt_title': 'Les Carnets de la création',
+            'id': '5093239',
+            'display_id': 'les-carnets-de-la-creation-jean-gabriel-periot-cineaste-2015-10-13',
+            'ext': 'mp3',
+            'timestamp': 1444762500,
+            'upload_date': '20151013',
+            'description': 'startswith:Aujourd\'hui dans "Les carnets de la création", le cinéaste',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        video_path = self._html_search_regex(
+            r'<a class="rf-player-open".*?href="([^"]+)"', webpage, 'video path', 'no_path_player')
+        if video_path == 'no_path_player':
+            raise ExtractorError('no player : no sound in this page.', expected=True)
+        new_id = self._search_regex('play=(?P<id>[0-9]+)', video_path, 'new_id', group='id')
+        video_url = compat_urlparse.urljoin(url, video_path)
+        return self._extract_from_player(video_url, new_id)

youtube_dl/extractor/franceinter.py

@@ -1,8 +1,6 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import int_or_none
 
@@ -23,8 +21,7 @@ class FranceInterIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
 
@@ -33,7 +30,7 @@ class FranceInterIE(InfoExtractor):
         video_url = 'http://www.franceinter.fr/' + path
 
         title = self._html_search_regex(
-            r'<span class="title">(.+?)</span>', webpage, 'title')
+            r'<span class="title-diffusion">(.+?)</span>', webpage, 'title')
         description = self._html_search_regex(
             r'<span class="description">(.*?)</span>',
             webpage, 'description', fatal=False)

youtube_dl/extractor/funimation.py

@@ -151,11 +151,9 @@ class FunimationIE(InfoExtractor):
                         errors.append(format_url)
                         continue
                     if determine_ext(format_url) == 'm3u8':
-                        m3u8_formats = self._extract_m3u8_formats(
+                        formats.extend(self._extract_m3u8_formats(
                             format_url + auth_token, display_id, 'mp4', entry_protocol='m3u8_native',
-                            preference=preference, m3u8_id='%s-hls' % funimation_id, fatal=False)
-                        if m3u8_formats:
-                            formats.extend(m3u8_formats)
+                            preference=preference, m3u8_id='%s-hls' % funimation_id, fatal=False))
                     else:
                         tbr = int_or_none(self._search_regex(
                             r'-(\d+)[Kk]', format_url, 'tbr', default=None))

youtube_dl/extractor/funnyordie.py

@@ -51,10 +51,8 @@ class FunnyOrDieIE(InfoExtractor):
 
         formats = []
 
-        m3u8_formats = self._extract_m3u8_formats(
-            m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
-        if m3u8_formats:
-            formats.extend(m3u8_formats)
+        formats.extend(self._extract_m3u8_formats(
+            m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
 
         bitrates = [int(bitrate) for bitrate in re.findall(r'[,/]v(\d+)[,/]', m3u8_url)]
         bitrates.sort()

youtube_dl/extractor/generic.py

@@ -44,7 +44,6 @@ from .myvi import MyviIE
 from .condenast import CondeNastIE
 from .udn import UDNEmbedIE
 from .senateisvp import SenateISVPIE
-from .bliptv import BlipTVIE
 from .svt import SVTIE
 from .pornhub import PornHubIE
 from .xhamster import XHamsterEmbedIE
@@ -55,6 +54,10 @@ from .snagfilms import SnagFilmsEmbedIE
 from .screenwavemedia import ScreenwaveMediaIE
 from .mtv import MTVServicesEmbeddedIE
 from .pladform import PladformIE
+from .videomore import VideomoreIE
+from .googledrive import GoogleDriveIE
+from .jwplatform import JWPlatformIE
+from .ultimedia import UltimediaIE
 
 
 class GenericIE(InfoExtractor):
@@ -484,7 +487,7 @@ class GenericIE(InfoExtractor):
                 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
             }
         },
-        # Embeded Ustream video
+        # Embedded Ustream video
         {
             'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
             'md5': '27b99cdb639c9b12a79bca876a073417',
@@ -1440,11 +1443,6 @@ class GenericIE(InfoExtractor):
                 'id': match.group('id')
             }
 
-        # Look for embedded blip.tv player
-        bliptv_url = BlipTVIE._extract_url(webpage)
-        if bliptv_url:
-            return self.url_result(bliptv_url, 'BlipTV')
-
         # Look for SVT player
         svt_url = SVTIE._extract_url(webpage)
         if svt_url:
@@ -1646,7 +1644,7 @@ class GenericIE(InfoExtractor):
         if myvi_url:
             return self.url_result(myvi_url)
 
-        # Look for embeded soundcloud player
+        # Look for embedded soundcloud player
         mobj = re.search(
             r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
             webpage)
@@ -1746,6 +1744,11 @@ class GenericIE(InfoExtractor):
         if pladform_url:
             return self.url_result(pladform_url)
 
+        # Look for Videomore embeds
+        videomore_url = VideomoreIE._extract_url(webpage)
+        if videomore_url:
+            return self.url_result(videomore_url)
+
         # Look for Playwire embeds
         mobj = re.search(
             r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
@@ -1769,6 +1772,11 @@ class GenericIE(InfoExtractor):
         if nbc_sports_url:
             return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
 
+        # Look for Google Drive embeds
+        google_drive_url = GoogleDriveIE._extract_url(webpage)
+        if google_drive_url:
+            return self.url_result(google_drive_url, 'GoogleDrive')
+
         # Look for UDN embeds
         mobj = re.search(
             r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
@@ -1796,11 +1804,21 @@ class GenericIE(InfoExtractor):
         if snagfilms_url:
             return self.url_result(snagfilms_url)
 
+        # Look for JWPlatform embeds
+        jwplatform_url = JWPlatformIE._extract_url(webpage)
+        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 Ulltimedia embeds
+        ultimedia_url = UltimediaIE._extract_url(webpage)
+        if ultimedia_url:
+            return self.url_result(self._proto_relative_url(ultimedia_url), 'Ultimedia')
+
         # Look for AdobeTVVideo embeds
         mobj = re.search(
             r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',

youtube_dl/extractor/globo.py

@@ -369,11 +369,9 @@ class GloboIE(InfoExtractor):
             resource_url = resource['url']
             signed_url = '%s?h=%s&k=%s' % (resource_url, signed_hash, 'flash')
             if resource_id.endswith('m3u8') or resource_url.endswith('.m3u8'):
-                m3u8_formats = self._extract_m3u8_formats(
+                formats.extend(self._extract_m3u8_formats(
                     signed_url, resource_id, 'mp4', entry_protocol='m3u8_native',
-                    m3u8_id='hls', fatal=False)
-                if m3u8_formats:
-                    formats.extend(m3u8_formats)
+                    m3u8_id='hls', fatal=False))
             else:
                 formats.append({
                     'url': signed_url,

youtube_dl/extractor/googledrive.py

@@ -0,0 +1,88 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+)
+
+
+class GoogleDriveIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/)|video\.google\.com/get_player\?.*?docid=)(?P<id>[a-zA-Z0-9_-]{28})'
+    _TEST = {
+        'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1',
+        'md5': '881f7700aec4f538571fa1e0eed4a7b6',
+        'info_dict': {
+            'id': '0ByeS4oOUV-49Zzh4R1J6R09zazQ',
+            'ext': 'mp4',
+            'title': 'Big Buck Bunny.mp4',
+            'duration': 46,
+        }
+    }
+    _FORMATS_EXT = {
+        '5': 'flv',
+        '6': 'flv',
+        '13': '3gp',
+        '17': '3gp',
+        '18': 'mp4',
+        '22': 'mp4',
+        '34': 'flv',
+        '35': 'flv',
+        '36': '3gp',
+        '37': 'mp4',
+        '38': 'mp4',
+        '43': 'webm',
+        '44': 'webm',
+        '45': 'webm',
+        '46': 'webm',
+        '59': 'mp4',
+    }
+
+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(
+            r'<iframe[^>]+src="https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28})',
+            webpage)
+        if mobj:
+            return 'https://drive.google.com/file/d/%s' % mobj.group('id')
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(
+            'http://docs.google.com/file/d/%s' % video_id, video_id, encoding='unicode_escape')
+
+        reason = self._search_regex(r'"reason"\s*,\s*"([^"]+)', webpage, 'reason', default=None)
+        if reason:
+            raise ExtractorError(reason)
+
+        title = self._search_regex(r'"title"\s*,\s*"([^"]+)', webpage, 'title')
+        duration = int_or_none(self._search_regex(
+            r'"length_seconds"\s*,\s*"([^"]+)', webpage, 'length seconds', default=None))
+        fmt_stream_map = self._search_regex(
+            r'"fmt_stream_map"\s*,\s*"([^"]+)', webpage, 'fmt stream map').split(',')
+        fmt_list = self._search_regex(r'"fmt_list"\s*,\s*"([^"]+)', webpage, 'fmt_list').split(',')
+
+        formats = []
+        for fmt, fmt_stream in zip(fmt_list, fmt_stream_map):
+            fmt_id, fmt_url = fmt_stream.split('|')
+            resolution = fmt.split('/')[1]
+            width, height = resolution.split('x')
+            formats.append({
+                'url': fmt_url,
+                'format_id': fmt_id,
+                'resolution': resolution,
+                'width': int_or_none(width),
+                'height': int_or_none(height),
+                'ext': self._FORMATS_EXT[fmt_id],
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/gputechconf.py

@@ -0,0 +1,55 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    xpath_element,
+    xpath_text,
+    int_or_none,
+    parse_duration,
+)
+
+
+class GPUTechConfIE(InfoExtractor):
+    _VALID_URL = r'https?://on-demand\.gputechconf\.com/gtc/2015/video/S(?P<id>\d+)\.html'
+    _TEST = {
+        'url': 'http://on-demand.gputechconf.com/gtc/2015/video/S5156.html',
+        'md5': 'a8862a00a0fd65b8b43acc5b8e33f798',
+        'info_dict': {
+            'id': '5156',
+            'ext': 'mp4',
+            'title': 'Coordinating More Than 3 Million CUDA Threads for Social Network Analysis',
+            'duration': 1219,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        root_path = self._search_regex(r'var\s+rootPath\s*=\s*"([^"]+)', webpage, 'root path', 'http://evt.dispeak.com/nvidia/events/gtc15/')
+        xml_file_id = self._search_regex(r'var\s+xmlFileId\s*=\s*"([^"]+)', webpage, 'xml file id')
+
+        doc = self._download_xml('%sxml/%s.xml' % (root_path, xml_file_id), video_id)
+
+        metadata = xpath_element(doc, 'metadata')
+        http_host = xpath_text(metadata, 'httpHost', 'http host', True)
+        mbr_videos = xpath_element(metadata, 'MBRVideos')
+
+        formats = []
+        for mbr_video in mbr_videos.findall('MBRVideo'):
+            stream_name = xpath_text(mbr_video, 'streamName')
+            if stream_name:
+                formats.append({
+                    'url': 'http://%s/%s' % (http_host, stream_name.replace('mp4:', '')),
+                    'tbr': int_or_none(xpath_text(mbr_video, 'bitrate')),
+                })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': xpath_text(metadata, 'title'),
+            'duration': parse_duration(xpath_text(metadata, 'endTime')),
+            'creator': xpath_text(metadata, 'speaker'),
+            'formats': formats,
+        }

youtube_dl/extractor/hotstar.py

@@ -0,0 +1,77 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    determine_ext,
+    int_or_none,
+)
+
+
+class HotStarIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?hotstar\.com/.*?[/-](?P<id>\d{10})'
+    _TEST = {
+        'url': 'http://www.hotstar.com/on-air-with-aib--english-1000076273',
+        'info_dict': {
+            'id': '1000076273',
+            'ext': 'mp4',
+            'title': 'On Air With AIB - English',
+            'description': 'md5:c957d8868e9bc793ccb813691cc4c434',
+            'timestamp': 1447227000,
+            'upload_date': '20151111',
+            'duration': 381,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
+    }
+
+    _GET_CONTENT_TEMPLATE = 'http://account.hotstar.com/AVS/besc?action=GetAggregatedContentDetails&channel=PCTV&contentId=%s'
+    _GET_CDN_TEMPLATE = 'http://getcdn.hotstar.com/AVS/besc?action=GetCDN&asJson=Y&channel=%s&id=%s&type=%s'
+
+    def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata', fatal=True):
+        json_data = super(HotStarIE, self)._download_json(url_or_request, video_id, note, fatal=fatal)
+        if json_data['resultCode'] != 'OK':
+            if fatal:
+                raise ExtractorError(json_data['errorDescription'])
+            return None
+        return json_data['resultObj']
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        video_data = self._download_json(
+            self._GET_CONTENT_TEMPLATE % video_id,
+            video_id)['contentInfo'][0]
+
+        formats = []
+        # PCTV for extracting f4m manifest
+        for f in ('TABLET',):
+            format_data = self._download_json(
+                self._GET_CDN_TEMPLATE % (f, video_id, 'VOD'),
+                video_id, 'Downloading %s JSON metadata' % f, fatal=False)
+            if format_data:
+                format_url = format_data['src']
+                ext = determine_ext(format_url)
+                if ext == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(format_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
+                elif ext == 'f4m':
+                    # produce broken files
+                    continue
+                else:
+                    formats.append({
+                        'url': format_url,
+                        'width': int_or_none(format_data.get('width')),
+                        'height': int_or_none(format_data.get('height')),
+                    })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': video_data['episodeTitle'],
+            'description': video_data.get('description'),
+            'duration': int_or_none(video_data.get('duration')),
+            'timestamp': int_or_none(video_data.get('broadcastDate')),
+            'formats': formats,
+        }

youtube_dl/extractor/ign.py

@@ -3,6 +3,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+)
 
 
 class IGNIE(InfoExtractor):
@@ -11,25 +15,24 @@ class IGNIE(InfoExtractor):
     Some videos of it.ign.com are also supported
     """
 
-    _VALID_URL = r'https?://.+?\.ign\.com/(?P<type>videos|show_videos|articles|(?:[^/]*/feature))(/.+)?/(?P<name_or_id>.+)'
+    _VALID_URL = r'https?://.+?\.ign\.com/(?:[^/]+/)?(?P<type>videos|show_videos|articles|feature|(?:[^/]+/\d+/video))(/.+)?/(?P<name_or_id>.+)'
     IE_NAME = 'ign.com'
 
-    _CONFIG_URL_TEMPLATE = 'http://www.ign.com/videos/configs/id/%s.config'
-    _DESCRIPTION_RE = [
-        r'<span class="page-object-description">(.+?)</span>',
-        r'id="my_show_video">.*?<p>(.*?)</p>',
-        r'<meta name="description" content="(.*?)"',
-    ]
+    _API_URL_TEMPLATE = 'http://apis.ign.com/video/v3/videos/%s'
+    _EMBED_RE = r'<iframe[^>]+?["\']((?:https?:)?//.+?\.ign\.com.+?/embed.+?)["\']'
 
     _TESTS = [
         {
             'url': 'http://www.ign.com/videos/2013/06/05/the-last-of-us-review',
-            'md5': 'eac8bdc1890980122c3b66f14bdd02e9',
+            'md5': 'febda82c4bafecd2d44b6e1a18a595f8',
             'info_dict': {
                 'id': '8f862beef863986b2785559b9e1aa599',
                 'ext': 'mp4',
                 'title': 'The Last of Us Review',
                 'description': 'md5:c8946d4260a4d43a00d5ae8ed998870c',
+                'timestamp': 1370440800,
+                'upload_date': '20130605',
+                'uploader_id': 'cberidon@ign.com',
             }
         },
         {
@@ -44,6 +47,9 @@ class IGNIE(InfoExtractor):
                         'ext': 'mp4',
                         'title': 'GTA 5 Video Review',
                         'description': 'Rockstar drops the mic on this generation of games. Watch our review of the masterly Grand Theft Auto V.',
+                        'timestamp': 1379339880,
+                        'upload_date': '20130916',
+                        'uploader_id': 'danieljkrupa@gmail.com',
                     },
                 },
                 {
@@ -52,6 +58,9 @@ class IGNIE(InfoExtractor):
                         'ext': 'mp4',
                         'title': '26 Twisted Moments from GTA 5 in Slow Motion',
                         'description': 'The twisted beauty of GTA 5 in stunning slow motion.',
+                        'timestamp': 1386878820,
+                        'upload_date': '20131212',
+                        'uploader_id': 'togilvie@ign.com',
                     },
                 },
             ],
@@ -66,12 +75,20 @@ class IGNIE(InfoExtractor):
                 'id': '078fdd005f6d3c02f63d795faa1b984f',
                 'ext': 'mp4',
                 'title': 'Rewind Theater - Wild Trailer Gamescom 2014',
-                'description': (
-                    'Giant skeletons, bloody hunts, and captivating'
-                    ' natural beauty take our breath away.'
-                ),
+                'description': 'Brian and Jared explore Michel Ancel\'s captivating new preview.',
+                'timestamp': 1408047180,
+                'upload_date': '20140814',
+                'uploader_id': 'jamesduggan1990@gmail.com',
             },
         },
+        {
+            'url': 'http://me.ign.com/en/videos/112203/video/how-hitman-aims-to-be-different-than-every-other-s',
+            'only_matching': True,
+        },
+        {
+            'url': 'http://me.ign.com/ar/angry-birds-2/106533/video/lrd-ldyy-lwl-lfylm-angry-birds',
+            'only_matching': True,
+        },
     ]
 
     def _find_video_id(self, webpage):
@@ -82,7 +99,7 @@ class IGNIE(InfoExtractor):
             r'<object id="vid_(.+?)"',
             r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"',
         ]
-        return self._search_regex(res_id, webpage, 'video id')
+        return self._search_regex(res_id, webpage, 'video id', default=None)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -91,7 +108,7 @@ class IGNIE(InfoExtractor):
         webpage = self._download_webpage(url, name_or_id)
         if page_type != 'video':
             multiple_urls = re.findall(
-                '<param name="flashvars"[^>]*value="[^"]*?url=(https?://www\.ign\.com/videos/.*?)["&]',
+                r'<param name="flashvars"[^>]*value="[^"]*?url=(https?://www\.ign\.com/videos/.*?)["&]',
                 webpage)
             if multiple_urls:
                 entries = [self.url_result(u, ie='IGN') for u in multiple_urls]
@@ -102,22 +119,51 @@ class IGNIE(InfoExtractor):
                 }
 
         video_id = self._find_video_id(webpage)
-        result = self._get_video_info(video_id)
-        description = self._html_search_regex(self._DESCRIPTION_RE,
-                                              webpage, 'video description', flags=re.DOTALL)
-        result['description'] = description
-        return result
+        if not video_id:
+            return self.url_result(self._search_regex(
+                self._EMBED_RE, webpage, 'embed url'))
+        return self._get_video_info(video_id)
 
     def _get_video_info(self, video_id):
-        config_url = self._CONFIG_URL_TEMPLATE % video_id
-        config = self._download_json(config_url, video_id)
-        media = config['playlist']['media']
+        api_data = self._download_json(
+            self._API_URL_TEMPLATE % video_id, video_id)
+
+        formats = []
+        m3u8_url = api_data['refs'].get('m3uUrl')
+        if m3u8_url:
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, video_id, 'mp4', 'm3u8_native',
+                m3u8_id='hls', fatal=False))
+        f4m_url = api_data['refs'].get('f4mUrl')
+        if f4m_url:
+            formats.extend(self._extract_f4m_formats(
+                f4m_url, video_id, f4m_id='hds', fatal=False))
+        for asset in api_data['assets']:
+            formats.append({
+                'url': asset['url'],
+                'tbr': asset.get('actual_bitrate_kbps'),
+                'fps': asset.get('frame_rate'),
+                'height': int_or_none(asset.get('height')),
+                'width': int_or_none(asset.get('width')),
+            })
+        self._sort_formats(formats)
+
+        thumbnails = [{
+            'url': thumbnail['url']
+        } for thumbnail in api_data.get('thumbnails', [])]
+
+        metadata = api_data['metadata']
 
         return {
-            'id': media['metadata']['videoId'],
-            'url': media['url'],
-            'title': media['metadata']['title'],
-            'thumbnail': media['poster'][0]['url'].replace('{size}', 'grande'),
+            'id': api_data.get('videoId') or video_id,
+            'title': metadata.get('longTitle') or metadata.get('name') or metadata.get['title'],
+            'description': metadata.get('description'),
+            'timestamp': parse_iso8601(metadata.get('publishDate')),
+            'duration': int_or_none(metadata.get('duration')),
+            'display_id': metadata.get('slug') or video_id,
+            'uploader_id': metadata.get('creator'),
+            'thumbnails': thumbnails,
+            'formats': formats,
         }
 
 
@@ -125,16 +171,17 @@ class OneUPIE(IGNIE):
     _VALID_URL = r'https?://gamevideos\.1up\.com/(?P<type>video)/id/(?P<name_or_id>.+)\.html'
     IE_NAME = '1up.com'
 
-    _DESCRIPTION_RE = r'<div id="vid_summary">(.+?)</div>'
-
     _TESTS = [{
         'url': 'http://gamevideos.1up.com/video/id/34976.html',
-        'md5': '68a54ce4ebc772e4b71e3123d413163d',
+        'md5': 'c9cc69e07acb675c31a16719f909e347',
         'info_dict': {
             'id': '34976',
             'ext': 'mp4',
             'title': 'Sniper Elite V2 - Trailer',
-            'description': 'md5:5d289b722f5a6d940ca3136e9dae89cf',
+            'description': 'md5:bf0516c5ee32a3217aa703e9b1bc7826',
+            'timestamp': 1313099220,
+            'upload_date': '20110811',
+            'uploader_id': 'IGN',
         }
     }]
 
@@ -143,3 +190,36 @@ class OneUPIE(IGNIE):
         result = super(OneUPIE, self)._real_extract(url)
         result['id'] = mobj.group('name_or_id')
         return result
+
+
+class PCMagIE(IGNIE):
+    _VALID_URL = r'https?://(?:www\.)?pcmag\.com/(?P<type>videos|article2)(/.+)?/(?P<name_or_id>.+)'
+    IE_NAME = 'pcmag'
+
+    _EMBED_RE = r'iframe.setAttribute\("src",\s*__util.objToUrlString\("http://widgets\.ign\.com/video/embed/content.html?[^"]*url=([^"]+)["&]'
+
+    _TESTS = [{
+        'url': 'http://www.pcmag.com/videos/2015/01/06/010615-whats-new-now-is-gogo-snooping-on-your-data',
+        'md5': '212d6154fd0361a2781075f1febbe9ad',
+        'info_dict': {
+            'id': 'ee10d774b508c9b8ec07e763b9125b91',
+            'ext': 'mp4',
+            'title': '010615_What\'s New Now: Is GoGo Snooping on Your Data?',
+            'description': 'md5:a7071ae64d2f68cc821c729d4ded6bb3',
+            'timestamp': 1420571160,
+            'upload_date': '20150106',
+            'uploader_id': 'cozzipix@gmail.com',
+        }
+    }, {
+        'url': 'http://www.pcmag.com/article2/0,2817,2470156,00.asp',
+        'md5': '94130c1ca07ba0adb6088350681f16c1',
+        'info_dict': {
+            'id': '042e560ba94823d43afcb12ddf7142ca',
+            'ext': 'mp4',
+            'title': 'HTC\'s Weird New Re Camera - What\'s New Now',
+            'description': 'md5:53433c45df96d2ea5d0fda18be2ca908',
+            'timestamp': 1412953920,
+            'upload_date': '20141010',
+            'uploader_id': 'chris_snyder@pcmag.com',
+        }
+    }]

youtube_dl/extractor/imgur.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 
 class ImgurIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?!gallery)(?P<id>[a-zA-Z0-9]+)'
+    _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:(?:gallery|topic/[^/]+)/)?(?P<id>[a-zA-Z0-9]{6,})(?:[/?#&]+|\.[a-z]+)?$'
 
     _TESTS = [{
         'url': 'https://i.imgur.com/A61SaA1.gifv',
@@ -21,7 +21,7 @@ class ImgurIE(InfoExtractor):
             'id': 'A61SaA1',
             'ext': 'mp4',
             'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$',
-            'description': 're:The origin of the Internet\'s most viral images$|The Internet\'s visual storytelling community\. Explore, share, and discuss the best visual stories the Internet has to offer\.$',
+            'description': 'Imgur: The most awesome images on the Internet.',
         },
     }, {
         'url': 'https://imgur.com/A61SaA1',
@@ -29,8 +29,20 @@ class ImgurIE(InfoExtractor):
             'id': 'A61SaA1',
             'ext': 'mp4',
             'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$',
-            'description': 're:The origin of the Internet\'s most viral images$|The Internet\'s visual storytelling community\. Explore, share, and discuss the best visual stories the Internet has to offer\.$',
+            'description': 'Imgur: The most awesome images on the Internet.',
         },
+    }, {
+        'url': 'https://imgur.com/gallery/YcAQlkx',
+        'info_dict': {
+            'id': 'YcAQlkx',
+            'ext': 'mp4',
+            'title': 'Classic Steve Carell gif...cracks me up everytime....damn the repost downvotes....',
+            'description': 'Imgur: The most awesome images on the Internet.'
+
+        }
+    }, {
+        'url': 'http://imgur.com/topic/Funny/N8rOudd',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -100,25 +112,38 @@ class ImgurIE(InfoExtractor):
 
 
 class ImgurAlbumIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:i\.)?imgur\.com/gallery/(?P<id>[a-zA-Z0-9]+)'
+    _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:(?:a|gallery|topic/[^/]+)/)?(?P<id>[a-zA-Z0-9]{5})(?:[/?#&]+)?$'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://imgur.com/gallery/Q95ko',
         'info_dict': {
             'id': 'Q95ko',
         },
         'playlist_count': 25,
-    }
+    }, {
+        'url': 'http://imgur.com/a/j6Orj',
+        'only_matching': True,
+    }, {
+        'url': 'http://imgur.com/topic/Aww/ll5Vk',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         album_id = self._match_id(url)
 
         album_images = self._download_json(
             'http://imgur.com/gallery/%s/album_images/hit.json?all=true' % album_id,
-            album_id)['data']['images']
+            album_id, fatal=False)
 
-        entries = [
-            self.url_result('http://imgur.com/%s' % image['hash'])
-            for image in album_images if image.get('hash')]
+        if album_images:
+            data = album_images.get('data')
+            if data and isinstance(data, dict):
+                images = data.get('images')
+                if images and isinstance(images, list):
+                    entries = [
+                        self.url_result('http://imgur.com/%s' % image['hash'])
+                        for image in images if image.get('hash')]
+                    return self.playlist_result(entries, album_id)
 
-        return self.playlist_result(entries, album_id)
+        # Fallback to single video
+        return self.url_result('http://imgur.com/%s' % album_id, ImgurIE.ie_key())

youtube_dl/extractor/infoq.py

@@ -1,9 +1,15 @@
+# coding: utf-8
+
 from __future__ import unicode_literals
 
 import base64
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse_unquote
+from ..compat import (
+    compat_urllib_parse_unquote,
+    compat_parse_qs,
+)
+from ..utils import determine_ext
 
 
 class InfoQIE(InfoExtractor):
@@ -13,7 +19,7 @@ class InfoQIE(InfoExtractor):
         'url': 'http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things',
         'md5': 'b5ca0e0a8c1fed93b0e65e48e462f9a2',
         'info_dict': {
-            'id': '12-jan-pythonthings',
+            'id': 'A-Few-of-My-Favorite-Python-Things',
             'ext': 'mp4',
             'description': 'Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.',
             'title': 'A Few of My Favorite [Python] Things',
@@ -21,8 +27,71 @@ class InfoQIE(InfoExtractor):
     }, {
         'url': 'http://www.infoq.com/fr/presentations/changez-avis-sur-javascript',
         'only_matching': True,
+    }, {
+        'url': 'http://www.infoq.com/cn/presentations/openstack-continued-delivery',
+        'md5': '4918d0cca1497f2244572caf626687ef',
+        'info_dict': {
+            'id': 'openstack-continued-delivery',
+            'title': 'OpenStack持续交付之路',
+            'ext': 'flv',
+            'description': 'md5:308d981fb28fa42f49f9568322c683ff',
+        },
     }]
 
+    def _extract_bokecc_videos(self, webpage, video_id):
+        # TODO: bokecc.com is a Chinese video cloud platform
+        # It should have an independent extractor but I don't have other
+        # examples using bokecc
+        player_params_str = self._html_search_regex(
+            r'<script[^>]+src="http://p\.bokecc\.com/player\?([^"]+)',
+            webpage, 'player params', default=None)
+
+        player_params = compat_parse_qs(player_params_str)
+
+        info_xml = self._download_xml(
+            'http://p.bokecc.com/servlet/playinfo?uid=%s&vid=%s&m=1' % (
+                player_params['siteid'][0], player_params['vid'][0]), video_id)
+
+        return [{
+            'format_id': 'bokecc',
+            'url': quality.find('./copy').attrib['playurl'],
+            'preference': int(quality.attrib['value']),
+        } for quality in info_xml.findall('./video/quality')]
+
+    def _extract_rtmp_videos(self, webpage):
+        # The server URL is hardcoded
+        video_url = 'rtmpe://video.infoq.com/cfx/st/'
+
+        # Extract video URL
+        encoded_id = self._search_regex(
+            r"jsclassref\s*=\s*'([^']*)'", webpage, 'encoded id', default=None)
+
+        real_id = compat_urllib_parse_unquote(base64.b64decode(encoded_id.encode('ascii')).decode('utf-8'))
+        playpath = 'mp4:' + real_id
+
+        return [{
+            'format_id': 'rtmp',
+            'url': video_url,
+            'ext': determine_ext(playpath),
+            'play_path': playpath,
+        }]
+
+    def _extract_http_videos(self, webpage):
+        http_video_url = self._search_regex(r'P\.s\s*=\s*\'([^\']+)\'', webpage, 'video URL')
+
+        policy = self._search_regex(r'InfoQConstants.scp\s*=\s*\'([^\']+)\'', webpage, 'policy')
+        signature = self._search_regex(r'InfoQConstants.scs\s*=\s*\'([^\']+)\'', webpage, 'signature')
+        key_pair_id = self._search_regex(r'InfoQConstants.sck\s*=\s*\'([^\']+)\'', webpage, 'key-pair-id')
+
+        return [{
+            'format_id': 'http',
+            'url': http_video_url,
+            'http_headers': {
+                'Cookie': 'CloudFront-Policy=%s; CloudFront-Signature=%s; CloudFront-Key-Pair-Id=%s' % (
+                    policy, signature, key_pair_id),
+            },
+        }]
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
@@ -30,37 +99,12 @@ class InfoQIE(InfoExtractor):
         video_title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
         video_description = self._html_search_meta('description', webpage, 'description')
 
-        # The server URL is hardcoded
-        video_url = 'rtmpe://video.infoq.com/cfx/st/'
+        if '/cn/' in url:
+            # for China videos, HTTP video URL exists but always fails with 403
+            formats = self._extract_bokecc_videos(webpage, video_id)
+        else:
+            formats = self._extract_rtmp_videos(webpage) + self._extract_http_videos(webpage)
 
-        # Extract video URL
-        encoded_id = self._search_regex(
-            r"jsclassref\s*=\s*'([^']*)'", webpage, 'encoded id')
-        real_id = compat_urllib_parse_unquote(base64.b64decode(encoded_id.encode('ascii')).decode('utf-8'))
-        playpath = 'mp4:' + real_id
-
-        video_filename = playpath.split('/')[-1]
-        video_id, extension = video_filename.split('.')
-
-        http_video_url = self._search_regex(r'P\.s\s*=\s*\'([^\']+)\'', webpage, 'video URL')
-
-        policy = self._search_regex(r'InfoQConstants.scp\s*=\s*\'([^\']+)\'', webpage, 'policy')
-        signature = self._search_regex(r'InfoQConstants.scs\s*=\s*\'([^\']+)\'', webpage, 'signature')
-        key_pair_id = self._search_regex(r'InfoQConstants.sck\s*=\s*\'([^\']+)\'', webpage, 'key-pair-id')
-
-        formats = [{
-            'format_id': 'rtmp',
-            'url': video_url,
-            'ext': extension,
-            'play_path': playpath,
-        }, {
-            'format_id': 'http',
-            'url': http_video_url,
-            'http_headers': {
-                'Cookie': 'CloudFront-Policy=%s; CloudFront-Signature=%s; CloudFront-Key-Pair-Id=%s' % (
-                    policy, signature, key_pair_id),
-            },
-        }]
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/instagram.py

@@ -47,7 +47,7 @@ class InstagramIE(InfoExtractor):
 
 
 class InstagramUserIE(InfoExtractor):
-    _VALID_URL = r'https://instagram\.com/(?P<username>[^/]{2,})/?(?:$|[?#])'
+    _VALID_URL = r'https?://(?:www\.)?instagram\.com/(?P<username>[^/]{2,})/?(?:$|[?#])'
     IE_DESC = 'Instagram user profile'
     IE_NAME = 'instagram:user'
     _TEST = {

youtube_dl/extractor/iprima.py

@@ -14,6 +14,7 @@ from ..utils import (
 
 
 class IPrimaIE(InfoExtractor):
+    _WORKING = False
     _VALID_URL = r'https?://play\.iprima\.cz/(?:[^/]+/)*(?P<id>[^?#]+)'
 
     _TESTS = [{

youtube_dl/extractor/iqiyi.py

@@ -16,7 +16,7 @@ class IqiyiIE(InfoExtractor):
     IE_NAME = 'iqiyi'
     IE_DESC = '爱奇艺'
 
-    _VALID_URL = r'http://(?:www\.)iqiyi.com/v_.+?\.html'
+    _VALID_URL = r'http://(?:[^.]+\.)?iqiyi\.com/.+\.html'
 
     _TESTS = [{
         'url': 'http://www.iqiyi.com/v_19rrojlavg.html',
@@ -84,6 +84,15 @@ class IqiyiIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+    }, {
+        'url': 'http://www.iqiyi.com/w_19rt6o8t9p.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.iqiyi.com/a_19rrhbc6kt.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://yule.iqiyi.com/pcb.html',
+        'only_matching': True,
     }]
 
     _FORMATS_MAP = [
@@ -205,8 +214,8 @@ class IqiyiIE(InfoExtractor):
 
     def get_enc_key(self, swf_url, video_id):
         # TODO: automatic key extraction
-        # last update at 2015-12-06 for Zombie::bite
-        enc_key = '3719f6a1da83ee0aee3488d8802d7696'[::-1]
+        # last update at 2015-12-18 for Zombie::bite
+        enc_key = '8b6b683780897eb8d9a48a02ccc4817d'[::-1]
         return enc_key
 
     def _real_extract(self, url):

youtube_dl/extractor/ivi.py

@@ -7,6 +7,7 @@ import json
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
+    int_or_none,
     sanitized_Request,
 )
 
@@ -27,44 +28,36 @@ class IviIE(InfoExtractor):
                 'title': 'Иван Васильевич меняет профессию',
                 'description': 'md5:b924063ea1677c8fe343d8a72ac2195f',
                 'duration': 5498,
-                'thumbnail': 'http://thumbs.ivi.ru/f20.vcp.digitalaccess.ru/contents/d/1/c3c885163a082c29bceeb7b5a267a6.jpg',
+                'thumbnail': 're:^https?://.*\.jpg$',
             },
             'skip': 'Only works from Russia',
         },
-        # Serial's serie
+        # Serial's series
         {
             'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/9549',
             'md5': '221f56b35e3ed815fde2df71032f4b3e',
             'info_dict': {
                 'id': '9549',
                 'ext': 'mp4',
-                'title': 'Двое из ларца - Серия 1',
+                'title': 'Двое из ларца - Дело Гольдберга (1 часть)',
+                'series': 'Двое из ларца',
+                'season': 'Сезон 1',
+                'season_number': 1,
+                'episode': 'Дело Гольдберга (1 часть)',
+                'episode_number': 1,
                 'duration': 2655,
-                'thumbnail': 'http://thumbs.ivi.ru/f15.vcp.digitalaccess.ru/contents/8/4/0068dc0677041f3336b7c2baad8fc0.jpg',
+                'thumbnail': 're:^https?://.*\.jpg$',
             },
             'skip': 'Only works from Russia',
         }
     ]
 
     # Sorted by quality
-    _known_formats = ['MP4-low-mobile', 'MP4-mobile', 'FLV-lo', 'MP4-lo', 'FLV-hi', 'MP4-hi', 'MP4-SHQ']
-
-    # Sorted by size
-    _known_thumbnails = ['Thumb-120x90', 'Thumb-160', 'Thumb-640x480']
-
-    def _extract_description(self, html):
-        m = re.search(r'<meta name="description" content="(?P<description>[^"]+)"/>', html)
-        return m.group('description') if m is not None else None
-
-    def _extract_comment_count(self, html):
-        m = re.search('(?s)<a href="#" id="view-comments" class="action-button dim gradient">\s*Комментарии:\s*(?P<commentcount>\d+)\s*</a>', html)
-        return int(m.group('commentcount')) if m is not None else 0
+    _KNOWN_FORMATS = ['MP4-low-mobile', 'MP4-mobile', 'FLV-lo', 'MP4-lo', 'FLV-hi', 'MP4-hi', 'MP4-SHQ']
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        api_url = 'http://api.digitalaccess.ru/api/json/'
-
         data = {
             'method': 'da.content.get',
             'params': [
@@ -76,11 +69,10 @@ class IviIE(InfoExtractor):
             ]
         }
 
-        request = sanitized_Request(api_url, json.dumps(data))
-
-        video_json_page = self._download_webpage(
+        request = sanitized_Request(
+            'http://api.digitalaccess.ru/api/json/', json.dumps(data))
+        video_json = self._download_json(
             request, video_id, 'Downloading video JSON')
-        video_json = json.loads(video_json_page)
 
         if 'error' in video_json:
             error = video_json['error']
@@ -95,35 +87,51 @@ class IviIE(InfoExtractor):
         formats = [{
             'url': x['url'],
             'format_id': x['content_format'],
-            'preference': self._known_formats.index(x['content_format']),
-        } for x in result['files'] if x['content_format'] in self._known_formats]
+            'preference': self._KNOWN_FORMATS.index(x['content_format']),
+        } for x in result['files'] if x['content_format'] in self._KNOWN_FORMATS]
 
         self._sort_formats(formats)
 
-        if not formats:
-            raise ExtractorError('No media links available for %s' % video_id)
-
-        duration = result['duration']
-        compilation = result['compilation']
         title = result['title']
 
+        duration = int_or_none(result.get('duration'))
+        compilation = result.get('compilation')
+        episode = title if compilation else None
+
         title = '%s - %s' % (compilation, title) if compilation is not None else title
 
-        previews = result['preview']
-        previews.sort(key=lambda fmt: self._known_thumbnails.index(fmt['content_format']))
-        thumbnail = previews[-1]['url'] if len(previews) > 0 else None
+        thumbnails = [{
+            'url': preview['url'],
+            'id': preview.get('content_format'),
+        } for preview in result.get('preview', []) if preview.get('url')]
 
-        video_page = self._download_webpage(url, video_id, 'Downloading video page')
-        description = self._extract_description(video_page)
-        comment_count = self._extract_comment_count(video_page)
+        webpage = self._download_webpage(url, video_id)
+
+        season = self._search_regex(
+            r'<li[^>]+class="season active"[^>]*><a[^>]+>([^<]+)',
+            webpage, 'season', default=None)
+        season_number = int_or_none(self._search_regex(
+            r'<li[^>]+class="season active"[^>]*><a[^>]+data-season(?:-index)?="(\d+)"',
+            webpage, 'season number', default=None))
+
+        episode_number = int_or_none(self._search_regex(
+            r'<meta[^>]+itemprop="episode"[^>]*>\s*<meta[^>]+itemprop="episodeNumber"[^>]+content="(\d+)',
+            webpage, 'episode number', default=None))
+
+        description = self._og_search_description(webpage, default=None) or self._html_search_meta(
+            'description', webpage, 'description', default=None)
 
         return {
             'id': video_id,
             'title': title,
-            'thumbnail': thumbnail,
+            'series': compilation,
+            'season': season,
+            'season_number': season_number,
+            'episode': episode,
+            'episode_number': episode_number,
+            'thumbnails': thumbnails,
             'description': description,
             'duration': duration,
-            'comment_count': comment_count,
             'formats': formats,
         }
 
@@ -149,8 +157,11 @@ class IviCompilationIE(InfoExtractor):
     }]
 
     def _extract_entries(self, html, compilation_id):
-        return [self.url_result('http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), 'Ivi')
-                for serie in re.findall(r'<strong><a href="/watch/%s/(\d+)">(?:[^<]+)</a></strong>' % compilation_id, html)]
+        return [
+            self.url_result(
+                'http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), IviIE.ie_key())
+            for serie in re.findall(
+                r'<a href="/watch/%s/(\d+)"[^>]+data-id="\1"' % compilation_id, html)]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -158,7 +169,8 @@ class IviCompilationIE(InfoExtractor):
         season_id = mobj.group('seasonid')
 
         if season_id is not None:  # Season link
-            season_page = self._download_webpage(url, compilation_id, 'Downloading season %s web page' % season_id)
+            season_page = self._download_webpage(
+                url, compilation_id, 'Downloading season %s web page' % season_id)
             playlist_id = '%s/season%s' % (compilation_id, season_id)
             playlist_title = self._html_search_meta('title', season_page, 'title')
             entries = self._extract_entries(season_page, compilation_id)
@@ -166,8 +178,9 @@ class IviCompilationIE(InfoExtractor):
             compilation_page = self._download_webpage(url, compilation_id, 'Downloading compilation web page')
             playlist_id = compilation_id
             playlist_title = self._html_search_meta('title', compilation_page, 'title')
-            seasons = re.findall(r'<a href="/watch/%s/season(\d+)">[^<]+</a>' % compilation_id, compilation_page)
-            if len(seasons) == 0:  # No seasons in this compilation
+            seasons = re.findall(
+                r'<a href="/watch/%s/season(\d+)' % compilation_id, compilation_page)
+            if not seasons:  # No seasons in this compilation
                 entries = self._extract_entries(compilation_page, compilation_id)
             else:
                 entries = []

youtube_dl/extractor/ivideon.py

@@ -0,0 +1,83 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_parse,
+    compat_urlparse,
+)
+from ..utils import qualities
+
+
+class IvideonIE(InfoExtractor):
+    IE_NAME = 'ivideon'
+    IE_DESC = 'Ivideon TV'
+    _VALID_URL = r'https?://(?:www\.)?ivideon\.com/tv/(?:[^/]+/)*camera/(?P<id>\d+-[\da-f]+)/(?P<camera_id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.ivideon.com/tv/camera/100-916ca13b5c4ad9f564266424a026386d/0/',
+        'info_dict': {
+            'id': '100-916ca13b5c4ad9f564266424a026386d',
+            'ext': 'flv',
+            'title': 're:^Касса [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'description': 'Основное предназначение - запись действий кассиров. Плюс общий вид.',
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        'url': 'https://www.ivideon.com/tv/camera/100-c4ee4cb9ede885cf62dfbe93d7b53783/589824/?lang=ru',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.ivideon.com/tv/map/22.917923/-31.816406/16/camera/100-e7bc16c7d4b5bbd633fd5350b66dfa9a/0',
+        'only_matching': True,
+    }]
+
+    _QUALITIES = ('low', 'mid', 'hi')
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        server_id, camera_id = mobj.group('id'), mobj.group('camera_id')
+        camera_name, description = None, None
+        camera_url = compat_urlparse.urljoin(
+            url, '/tv/camera/%s/%s/' % (server_id, camera_id))
+
+        webpage = self._download_webpage(camera_url, server_id, fatal=False)
+        if webpage:
+            config_string = self._search_regex(
+                r'var\s+config\s*=\s*({.+?});', webpage, 'config', default=None)
+            if config_string:
+                config = self._parse_json(config_string, server_id, fatal=False)
+                camera_info = config.get('ivTvAppOptions', {}).get('currentCameraInfo')
+                if camera_info:
+                    camera_name = camera_info.get('camera_name')
+                    description = camera_info.get('misc', {}).get('description')
+            if not camera_name:
+                camera_name = self._html_search_meta(
+                    'name', webpage, 'camera name', default=None) or self._search_regex(
+                    r'<h1[^>]+class="b-video-title"[^>]*>([^<]+)', webpage, 'camera name', default=None)
+
+        quality = qualities(self._QUALITIES)
+
+        formats = [{
+            'url': 'https://streaming.ivideon.com/flv/live?%s' % compat_urllib_parse.urlencode({
+                'server': server_id,
+                'camera': camera_id,
+                'sessionId': 'demo',
+                'q': quality(format_id),
+            }),
+            'format_id': format_id,
+            'ext': 'flv',
+            'quality': quality(format_id),
+        } for format_id in self._QUALITIES]
+        self._sort_formats(formats)
+
+        return {
+            'id': server_id,
+            'title': self._live_title(camera_name or server_id),
+            'description': description,
+            'is_live': True,
+            'formats': formats,
+        }

youtube_dl/extractor/jukebox.py

@@ -1,59 +0,0 @@
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    RegexNotFoundError,
-    unescapeHTML,
-)
-
-
-class JukeboxIE(InfoExtractor):
-    _VALID_URL = r'^http://www\.jukebox?\..+?\/.+[,](?P<id>[a-z0-9\-]+)\.html'
-    _TEST = {
-        'url': 'http://www.jukebox.es/kosheen/videoclip,pride,r303r.html',
-        'info_dict': {
-            'id': 'r303r',
-            'ext': 'flv',
-            'title': 'Kosheen-En Vivo Pride',
-            'uploader': 'Kosheen',
-        },
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        html = self._download_webpage(url, video_id)
-        iframe_url = unescapeHTML(self._search_regex(r'<iframe .*src="([^"]*)"', html, 'iframe url'))
-
-        iframe_html = self._download_webpage(iframe_url, video_id, 'Downloading iframe')
-        if re.search(r'class="jkb_waiting"', iframe_html) is not None:
-            raise ExtractorError('Video is not available(in your country?)!')
-
-        self.report_extraction(video_id)
-
-        try:
-            video_url = self._search_regex(r'"config":{"file":"(?P<video_url>http:[^"]+\?mdtk=[0-9]+)"',
-                                           iframe_html, 'video url')
-            video_url = unescapeHTML(video_url).replace('\/', '/')
-        except RegexNotFoundError:
-            youtube_url = self._search_regex(
-                r'config":{"file":"(http:\\/\\/www\.youtube\.com\\/watch\?v=[^"]+)"',
-                iframe_html, 'youtube url')
-            youtube_url = unescapeHTML(youtube_url).replace('\/', '/')
-            self.to_screen('Youtube video detected')
-            return self.url_result(youtube_url, ie='Youtube')
-
-        title = self._html_search_regex(r'<h1 class="inline">([^<]+)</h1>',
-                                        html, 'title')
-        artist = self._html_search_regex(r'<span id="infos_article_artist">([^<]+)</span>',
-                                         html, 'artist')
-
-        return {
-            'id': video_id,
-            'url': video_url,
-            'title': artist + '-' + title,
-            'uploader': artist,
-        }

youtube_dl/extractor/jwplatform.py

@@ -0,0 +1,70 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class JWPlatformIE(InfoExtractor):
+    _VALID_URL = r'(?:https?://content\.jwplatform\.com/(?:feeds|players|jw6)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})'
+    _TEST = {
+        'url': 'http://content.jwplatform.com/players/nPripu9l-ALJ3XQCI.js',
+        'md5': 'fa8899fa601eb7c83a64e9d568bdf325',
+        'info_dict': {
+            'id': 'nPripu9l',
+            'ext': 'mov',
+            'title': 'Big Buck Bunny Trailer',
+            'description': 'Big Buck Bunny is a short animated film by the Blender Institute. It is made using free and open source software.',
+            'upload_date': '20081127',
+            'timestamp': 1227796140,
+        }
+    }
+
+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(
+            r'<script[^>]+?src=["\'](?P<url>(?:https?:)?//content.jwplatform.com/players/[a-zA-Z0-9]{8})',
+            webpage)
+        if mobj:
+            return mobj.group('url')
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        json_data = self._download_json('http://content.jwplatform.com/feeds/%s.json' % video_id, video_id)
+        video_data = json_data['playlist'][0]
+        subtitles = {}
+        for track in video_data['tracks']:
+            if track['kind'] == 'captions':
+                subtitles[track['label']] = [{'url': self._proto_relative_url(track['file'])}]
+
+        formats = []
+        for source in video_data['sources']:
+            source_url = self._proto_relative_url(source['file'])
+            source_type = source.get('type') or ''
+            if source_type == 'application/vnd.apple.mpegurl':
+                formats.extend(self._extract_m3u8_formats(
+                    source_url, video_id, 'mp4', 'm3u8_native', fatal=False))
+            elif source_type.startswith('audio'):
+                formats.append({
+                    'url': source_url,
+                    'vcodec': 'none',
+                })
+            else:
+                formats.append({
+                    'url': source_url,
+                    'width': int_or_none(source.get('width')),
+                    'height': int_or_none(source.get('height')),
+                })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': video_data['title'],
+            'description': video_data.get('description'),
+            'thumbnail': self._proto_relative_url(video_data.get('image')),
+            'timestamp': int_or_none(video_data.get('pubdate')),
+            'subtitles': subtitles,
+            'formats': formats,
+        }

youtube_dl/extractor/kaltura.py

@@ -45,7 +45,7 @@ class KalturaIE(InfoExtractor):
             'info_dict': {
                 'id': '1_1jc2y3e4',
                 'ext': 'mp4',
-                'title': 'Track 4',
+                'title': 'Straight from the Heart',
                 'upload_date': '20131219',
                 'uploader_id': 'mlundberg@wolfgangsvault.com',
                 'description': 'The Allman Brothers Band, 12/16/1981',
@@ -115,12 +115,9 @@ class KalturaIE(InfoExtractor):
                 'version': '-1',
             },
             {
-                'action': 'getContextData',
-                'contextDataParams:objectType': 'KalturaEntryContextDataParams',
-                'contextDataParams:referrer': 'http://www.kaltura.com/',
-                'contextDataParams:streamerType': 'http',
+                'action': 'getbyentryid',
                 'entryId': video_id,
-                'service': 'baseentry',
+                'service': 'flavorAsset',
             },
         ]
         return self._kaltura_api_call(
@@ -133,7 +130,7 @@ class KalturaIE(InfoExtractor):
         partner_id = mobj.group('partner_id_s') or mobj.group('partner_id') or mobj.group('partner_id_html5')
         entry_id = mobj.group('id_s') or mobj.group('id') or mobj.group('id_html5')
 
-        info, source_data = self._get_video_info(entry_id, partner_id)
+        info, flavor_assets = self._get_video_info(entry_id, partner_id)
 
         source_url = smuggled_data.get('source_url')
         if source_url:
@@ -144,7 +141,10 @@ class KalturaIE(InfoExtractor):
             referrer = None
 
         formats = []
-        for f in source_data['flavorAssets']:
+        for f in flavor_assets:
+            # Continue if asset is not ready
+            if f['status'] != 2:
+                continue
             video_url = '%s/flavorId/%s' % (info['dataUrl'], f['id'])
             if referrer:
                 video_url += '?referrer=%s' % referrer
@@ -160,6 +160,12 @@ class KalturaIE(InfoExtractor):
                 'width': int_or_none(f.get('width')),
                 'url': video_url,
             })
+        m3u8_url = info['dataUrl'].replace('format/url', 'format/applehttp')
+        if referrer:
+            m3u8_url += '?referrer=%s' % referrer
+        formats.extend(self._extract_m3u8_formats(
+            m3u8_url, entry_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
+
         self._check_formats(formats, entry_id)
         self._sort_formats(formats)
 

youtube_dl/extractor/livestream.py

@@ -1,27 +1,29 @@
 from __future__ import unicode_literals
 
 import re
-import json
 import itertools
 
 from .common import InfoExtractor
 from ..compat import (
     compat_str,
-    compat_urllib_parse_urlparse,
     compat_urlparse,
 )
 from ..utils import (
-    ExtractorError,
     find_xpath_attr,
-    int_or_none,
-    orderedSet,
+    xpath_attr,
     xpath_with_ns,
+    xpath_text,
+    orderedSet,
+    int_or_none,
+    float_or_none,
+    parse_iso8601,
+    determine_ext,
 )
 
 
 class LivestreamIE(InfoExtractor):
     IE_NAME = 'livestream'
-    _VALID_URL = r'https?://(?:new\.)?livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>[0-9]+)(?:/player)?)?/?(?:$|[?#])'
+    _VALID_URL = r'https?://(?:new\.)?livestream\.com/(?:accounts/(?P<account_id>\d+)|(?P<account_name>[^/]+))/(?:events/(?P<event_id>\d+)|(?P<event_name>[^/]+))(?:/videos/(?P<id>\d+))?'
     _TESTS = [{
         'url': 'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
         'md5': '53274c76ba7754fb0e8d072716f2292b',
@@ -29,7 +31,9 @@ class LivestreamIE(InfoExtractor):
             'id': '4719370',
             'ext': 'mp4',
             'title': 'Live from Webster Hall NYC',
+            'timestamp': 1350008072,
             'upload_date': '20121012',
+            'duration': 5968.0,
             'like_count': int,
             'view_count': int,
             'thumbnail': 're:^http://.*\.jpg$'
@@ -55,39 +59,20 @@ class LivestreamIE(InfoExtractor):
         'url': 'http://livestream.com/bsww/concacafbeachsoccercampeonato2015',
         'only_matching': True,
     }]
+    _API_URL_TEMPLATE = 'http://livestream.com/api/accounts/%s/events/%s'
+
+    def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None):
+        base_ele = find_xpath_attr(
+            smil, self._xpath_ns('.//meta', namespace), 'name', 'httpBase')
+        base = base_ele.get('content') if base_ele else 'http://livestreamvod-f.akamaihd.net/'
 
-    def _parse_smil(self, video_id, smil_url):
         formats = []
-        _SWITCH_XPATH = (
-            './/{http://www.w3.org/2001/SMIL20/Language}body/'
-            '{http://www.w3.org/2001/SMIL20/Language}switch')
-        smil_doc = self._download_xml(
-            smil_url, video_id,
-            note='Downloading SMIL information',
-            errnote='Unable to download SMIL information',
-            fatal=False)
-        if smil_doc is False:  # Download failed
-            return formats
-        title_node = find_xpath_attr(
-            smil_doc, './/{http://www.w3.org/2001/SMIL20/Language}meta',
-            'name', 'title')
-        if title_node is None:
-            self.report_warning('Cannot find SMIL id')
-            switch_node = smil_doc.find(_SWITCH_XPATH)
-        else:
-            title_id = title_node.attrib['content']
-            switch_node = find_xpath_attr(
-                smil_doc, _SWITCH_XPATH, 'id', title_id)
-        if switch_node is None:
-            raise ExtractorError('Cannot find switch node')
-        video_nodes = switch_node.findall(
-            '{http://www.w3.org/2001/SMIL20/Language}video')
+        video_nodes = smil.findall(self._xpath_ns('.//video', namespace))
 
         for vn in video_nodes:
-            tbr = int_or_none(vn.attrib.get('system-bitrate'))
+            tbr = int_or_none(vn.attrib.get('system-bitrate'), 1000)
             furl = (
-                'http://livestream-f.akamaihd.net/%s?v=3.0.3&fp=WIN%%2014,0,0,145' %
-                (vn.attrib['src']))
+                '%s%s?v=3.0.3&fp=WIN%%2014,0,0,145' % (base, vn.attrib['src']))
             if 'clipBegin' in vn.attrib:
                 furl += '&ssek=' + vn.attrib['clipBegin']
             formats.append({
@@ -106,97 +91,141 @@ class LivestreamIE(InfoExtractor):
             ('sd', 'progressive_url'),
             ('hd', 'progressive_url_hd'),
         )
-        formats = [{
-            'format_id': format_id,
-            'url': video_data[key],
-            'quality': i + 1,
-        } for i, (format_id, key) in enumerate(FORMAT_KEYS)
-            if video_data.get(key)]
+
+        formats = []
+        for format_id, key in FORMAT_KEYS:
+            video_url = video_data.get(key)
+            if video_url:
+                ext = determine_ext(video_url)
+                if ext == 'm3u8':
+                    continue
+                bitrate = int_or_none(self._search_regex(
+                    r'(\d+)\.%s' % ext, video_url, 'bitrate', default=None))
+                formats.append({
+                    'url': video_url,
+                    'format_id': format_id,
+                    'tbr': bitrate,
+                    'ext': ext,
+                })
 
         smil_url = video_data.get('smil_url')
         if smil_url:
-            formats.extend(self._parse_smil(video_id, smil_url))
+            formats.extend(self._extract_smil_formats(smil_url, video_id))
+
+        m3u8_url = video_data.get('m3u8_url')
+        if m3u8_url:
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
+
+        f4m_url = video_data.get('f4m_url')
+        if f4m_url:
+            formats.extend(self._extract_f4m_formats(
+                f4m_url, video_id, f4m_id='hds', fatal=False))
         self._sort_formats(formats)
 
+        comments = [{
+            'author_id': comment.get('author_id'),
+            'author': comment.get('author', {}).get('full_name'),
+            'id': comment.get('id'),
+            'text': comment['text'],
+            'timestamp': parse_iso8601(comment.get('created_at')),
+        } for comment in video_data.get('comments', {}).get('data', [])]
+
         return {
             'id': video_id,
             'formats': formats,
             'title': video_data['caption'],
+            'description': video_data.get('description'),
             'thumbnail': video_data.get('thumbnail_url'),
-            'upload_date': video_data['updated_at'].replace('-', '')[:8],
+            'duration': float_or_none(video_data.get('duration'), 1000),
+            'timestamp': parse_iso8601(video_data.get('publish_at')),
             'like_count': video_data.get('likes', {}).get('total'),
+            'comment_count': video_data.get('comments', {}).get('total'),
             'view_count': video_data.get('views'),
+            'comments': comments,
         }
 
-    def _extract_event(self, info):
-        event_id = compat_str(info['id'])
-        account = compat_str(info['owner_account_id'])
-        root_url = (
-            'https://new.livestream.com/api/accounts/{account}/events/{event}/'
-            'feed.json'.format(account=account, event=event_id))
+    def _extract_stream_info(self, stream_info):
+        broadcast_id = stream_info['broadcast_id']
+        is_live = stream_info.get('is_live')
 
-        def _extract_videos():
-            last_video = None
-            for i in itertools.count(1):
-                if last_video is None:
-                    info_url = root_url
-                else:
-                    info_url = '{root}?&id={id}&newer=-1&type=video'.format(
-                        root=root_url, id=last_video)
-                videos_info = self._download_json(info_url, event_id, 'Downloading page {0}'.format(i))['data']
-                videos_info = [v['data'] for v in videos_info if v['type'] == 'video']
-                if not videos_info:
-                    break
-                for v in videos_info:
-                    yield self._extract_video_info(v)
-                last_video = videos_info[-1]['id']
-        return self.playlist_result(_extract_videos(), event_id, info['full_name'])
+        formats = []
+        smil_url = stream_info.get('play_url')
+        if smil_url:
+            formats.extend(self._extract_smil_formats(smil_url, broadcast_id))
+
+        entry_protocol = 'm3u8' if is_live else 'm3u8_native'
+        m3u8_url = stream_info.get('m3u8_url')
+        if m3u8_url:
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, broadcast_id, 'mp4', entry_protocol, m3u8_id='hls', fatal=False))
+
+        rtsp_url = stream_info.get('rtsp_url')
+        if rtsp_url:
+            formats.append({
+                'url': rtsp_url,
+                'format_id': 'rtsp',
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': broadcast_id,
+            'formats': formats,
+            'title': self._live_title(stream_info['stream_title']) if is_live else stream_info['stream_title'],
+            'thumbnail': stream_info.get('thumbnail_url'),
+            'is_live': is_live,
+        }
+
+    def _extract_event(self, event_data):
+        event_id = compat_str(event_data['id'])
+        account_id = compat_str(event_data['owner_account_id'])
+        feed_root_url = self._API_URL_TEMPLATE % (account_id, event_id) + '/feed.json'
+
+        stream_info = event_data.get('stream_info')
+        if stream_info:
+            return self._extract_stream_info(stream_info)
+
+        last_video = None
+        entries = []
+        for i in itertools.count(1):
+            if last_video is None:
+                info_url = feed_root_url
+            else:
+                info_url = '{root}?&id={id}&newer=-1&type=video'.format(
+                    root=feed_root_url, id=last_video)
+            videos_info = self._download_json(
+                info_url, event_id, 'Downloading page {0}'.format(i))['data']
+            videos_info = [v['data'] for v in videos_info if v['type'] == 'video']
+            if not videos_info:
+                break
+            for v in videos_info:
+                entries.append(self.url_result(
+                    'http://livestream.com/accounts/%s/events/%s/videos/%s' % (account_id, event_id, v['id']),
+                    'Livestream', v['id'], v['caption']))
+            last_video = videos_info[-1]['id']
+        return self.playlist_result(entries, event_id, event_data['full_name'])
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        event_name = mobj.group('event_name')
-        webpage = self._download_webpage(url, video_id or event_name)
-
-        og_video = self._og_search_video_url(
-            webpage, 'player url', fatal=False, default=None)
-        if og_video is not None:
-            query_str = compat_urllib_parse_urlparse(og_video).query
-            query = compat_urlparse.parse_qs(query_str)
-            if 'play_url' in query:
-                api_url = query['play_url'][0].replace('.smil', '')
-                info = json.loads(self._download_webpage(
-                    api_url, video_id, 'Downloading video info'))
-                return self._extract_video_info(info)
-
-        config_json = self._search_regex(
-            r'window.config = ({.*?});', webpage, 'window config')
-        info = json.loads(config_json)['event']
-
-        def is_relevant(vdata, vid):
-            result = vdata['type'] == 'video'
-            if video_id is not None:
-                result = result and compat_str(vdata['data']['id']) == vid
-            return result
-
-        if video_id is None:
-            # This is an event page:
-            return self._extract_event(info)
+        event = mobj.group('event_id') or mobj.group('event_name')
+        account = mobj.group('account_id') or mobj.group('account_name')
+        api_url = self._API_URL_TEMPLATE % (account, event)
+        if video_id:
+            video_data = self._download_json(
+                api_url + '/videos/%s' % video_id, video_id)
+            return self._extract_video_info(video_data)
         else:
-            videos = [self._extract_video_info(video_data['data'])
-                      for video_data in info['feed']['data']
-                      if is_relevant(video_data, video_id)]
-            if not videos:
-                raise ExtractorError('Cannot find video %s' % video_id)
-            return videos[0]
+            event_data = self._download_json(api_url, video_id)
+            return self._extract_event(event_data)
 
 
 # The original version of Livestream uses a different system
 class LivestreamOriginalIE(InfoExtractor):
     IE_NAME = 'livestream:original'
     _VALID_URL = r'''(?x)https?://original\.livestream\.com/
-        (?P<user>[^/]+)/(?P<type>video|folder)
-        (?:\?.*?Id=|/)(?P<id>.*?)(&|$)
+        (?P<user>[^/\?#]+)(?:/(?P<type>video|folder)
+        (?:(?:\?.*?Id=|/)(?P<id>.*?)(&|$))?)?
         '''
     _TESTS = [{
         'url': 'http://original.livestream.com/dealbook/video?clipId=pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
@@ -204,6 +233,8 @@ class LivestreamOriginalIE(InfoExtractor):
             'id': 'pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
             'ext': 'mp4',
             'title': 'Spark 1 (BitCoin) with Cameron Winklevoss & Tyler Winklevoss of Winklevoss Capital',
+            'duration': 771.301,
+            'view_count': int,
         },
     }, {
         'url': 'https://original.livestream.com/newplay/folder?dirId=a07bf706-d0e4-4e75-a747-b021d84f2fd3',
@@ -211,26 +242,60 @@ class LivestreamOriginalIE(InfoExtractor):
             'id': 'a07bf706-d0e4-4e75-a747-b021d84f2fd3',
         },
         'playlist_mincount': 4,
+    }, {
+        # live stream
+        'url': 'http://original.livestream.com/znsbahamas',
+        'only_matching': True,
     }]
 
-    def _extract_video(self, user, video_id):
-        api_url = 'http://x{0}x.api.channel.livestream.com/2.0/clipdetails?extendedInfo=true&id={1}'.format(user, video_id)
-
+    def _extract_video_info(self, user, video_id):
+        api_url = 'http://x%sx.api.channel.livestream.com/2.0/clipdetails?extendedInfo=true&id=%s' % (user, video_id)
         info = self._download_xml(api_url, video_id)
-        # this url is used on mobile devices
-        stream_url = 'http://x{0}x.api.channel.livestream.com/3.0/getstream.json?id={1}'.format(user, video_id)
-        stream_info = self._download_json(stream_url, video_id)
+
         item = info.find('channel').find('item')
-        ns = {'media': 'http://search.yahoo.com/mrss'}
-        thumbnail_url = item.find(xpath_with_ns('media:thumbnail', ns)).attrib['url']
+        title = xpath_text(item, 'title')
+        media_ns = {'media': 'http://search.yahoo.com/mrss'}
+        thumbnail_url = xpath_attr(
+            item, xpath_with_ns('media:thumbnail', media_ns), 'url')
+        duration = float_or_none(xpath_attr(
+            item, xpath_with_ns('media:content', media_ns), 'duration'))
+        ls_ns = {'ls': 'http://api.channel.livestream.com/2.0'}
+        view_count = int_or_none(xpath_text(
+            item, xpath_with_ns('ls:viewsCount', ls_ns)))
 
         return {
             'id': video_id,
-            'title': item.find('title').text,
-            'url': stream_info['progressiveUrl'],
+            'title': title,
             'thumbnail': thumbnail_url,
+            'duration': duration,
+            'view_count': view_count,
         }
 
+    def _extract_video_formats(self, video_data, video_id, entry_protocol):
+        formats = []
+
+        progressive_url = video_data.get('progressiveUrl')
+        if progressive_url:
+            formats.append({
+                'url': progressive_url,
+                'format_id': 'http',
+            })
+
+        m3u8_url = video_data.get('httpUrl')
+        if m3u8_url:
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, video_id, 'mp4', entry_protocol, m3u8_id='hls', fatal=False))
+
+        rtsp_url = video_data.get('rtspUrl')
+        if rtsp_url:
+            formats.append({
+                'url': rtsp_url,
+                'format_id': 'rtsp',
+            })
+
+        self._sort_formats(formats)
+        return formats
+
     def _extract_folder(self, url, folder_id):
         webpage = self._download_webpage(url, folder_id)
         paths = orderedSet(re.findall(
@@ -239,24 +304,45 @@ class LivestreamOriginalIE(InfoExtractor):
                 <a\s+href="(?=https?://livestre\.am/)
             )([^"]+)"''', webpage))
 
-        return {
-            '_type': 'playlist',
-            'id': folder_id,
-            'entries': [{
-                '_type': 'url',
-                'url': compat_urlparse.urljoin(url, p),
-            } for p in paths],
-        }
+        entries = [{
+            '_type': 'url',
+            'url': compat_urlparse.urljoin(url, p),
+        } for p in paths]
+
+        return self.playlist_result(entries, folder_id)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        id = mobj.group('id')
         user = mobj.group('user')
         url_type = mobj.group('type')
+        content_id = mobj.group('id')
         if url_type == 'folder':
-            return self._extract_folder(url, id)
+            return self._extract_folder(url, content_id)
         else:
-            return self._extract_video(user, id)
+            # this url is used on mobile devices
+            stream_url = 'http://x%sx.api.channel.livestream.com/3.0/getstream.json' % user
+            info = {}
+            if content_id:
+                stream_url += '?id=%s' % content_id
+                info = self._extract_video_info(user, content_id)
+            else:
+                content_id = user
+                webpage = self._download_webpage(url, content_id)
+                info = {
+                    'title': self._og_search_title(webpage),
+                    'description': self._og_search_description(webpage),
+                    'thumbnail': self._search_regex(r'channelLogo.src\s*=\s*"([^"]+)"', webpage, 'thumbnail', None),
+                }
+            video_data = self._download_json(stream_url, content_id)
+            is_live = video_data.get('isLive')
+            entry_protocol = 'm3u8' if is_live else 'm3u8_native'
+            info.update({
+                'id': content_id,
+                'title': self._live_title(info['title']) if is_live else info['title'],
+                'formats': self._extract_video_formats(video_data, content_id, entry_protocol),
+                'is_live': is_live,
+            })
+            return info
 
 
 # The server doesn't support HEAD request, the generic extractor can't detect

youtube_dl/extractor/lrt.py

@@ -1,12 +1,9 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
-    determine_ext,
-    js_to_json,
+    int_or_none,
     parse_duration,
     remove_end,
 )
@@ -23,9 +20,11 @@ class LRTIE(InfoExtractor):
             'title': 'Septynios Kauno dienos',
             'description': 'md5:24d84534c7dc76581e59f5689462411a',
             'duration': 1783,
+            'view_count': int,
+            'like_count': int,
         },
         'params': {
-            'skip_download': True,  # HLS download
+            'skip_download': True,  # m3u8 download
         },
     }
 
@@ -34,29 +33,23 @@ class LRTIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         title = remove_end(self._og_search_title(webpage), ' - LRT')
+        m3u8_url = self._search_regex(
+            r'file\s*:\s*(["\'])(?P<url>.+?)\1\s*\+\s*location\.hash\.substring\(1\)',
+            webpage, 'm3u8 url', group='url')
+        formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4')
+
         thumbnail = self._og_search_thumbnail(webpage)
         description = self._og_search_description(webpage)
         duration = parse_duration(self._search_regex(
-            r"'duration':\s*'([^']+)',", webpage,
-            'duration', fatal=False, default=None))
+            r'var\s+record_len\s*=\s*(["\'])(?P<duration>[0-9]+:[0-9]+:[0-9]+)\1',
+            webpage, 'duration', default=None, group='duration'))
 
-        formats = []
-        for js in re.findall(r'(?s)config:\s*(\{.*?\})', webpage):
-            data = self._parse_json(js, video_id, transform_source=js_to_json)
-            if 'provider' not in data:
-                continue
-            if data['provider'] == 'rtmp':
-                formats.append({
-                    'format_id': 'rtmp',
-                    'ext': determine_ext(data['file']),
-                    'url': data['streamer'],
-                    'play_path': 'mp4:%s' % data['file'],
-                    'preference': -1,
-                    'rtmp_real_time': True,
-                })
-            else:
-                formats.extend(
-                    self._extract_m3u8_formats(data['file'], video_id, 'mp4'))
+        view_count = int_or_none(self._html_search_regex(
+            r'<div[^>]+class=(["\']).*?record-desc-seen.*?\1[^>]*>(?P<count>.+?)</div>',
+            webpage, 'view count', fatal=False, group='count'))
+        like_count = int_or_none(self._search_regex(
+            r'<span[^>]+id=(["\'])flikesCount.*?\1>(?P<count>\d+)<',
+            webpage, 'like count', fatal=False, group='count'))
 
         return {
             'id': video_id,
@@ -65,4 +58,6 @@ class LRTIE(InfoExtractor):
             'thumbnail': thumbnail,
             'description': description,
             'duration': duration,
+            'view_count': view_count,
+            'like_count': like_count,
         }

youtube_dl/extractor/makertv.py

@@ -0,0 +1,32 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class MakerTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:(?:www\.)?maker\.tv/(?:[^/]+/)*video|makerplayer.com/embed/maker)/(?P<id>[a-zA-Z0-9]{12})'
+    _TEST = {
+        'url': 'http://www.maker.tv/video/Fh3QgymL9gsc',
+        'md5': 'ca237a53a8eb20b6dc5bd60564d4ab3e',
+        'info_dict': {
+            'id': 'Fh3QgymL9gsc',
+            'ext': 'mp4',
+            'title': 'Maze Runner: The Scorch Trials Official Movie Review',
+            'description': 'md5:11ff3362d7ef1d679fdb649f6413975a',
+            'upload_date': '20150918',
+            'timestamp': 1442549540,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        jwplatform_id = self._search_regex(r'jw_?id="([^"]+)"', webpage, 'jwplatform id')
+
+        return {
+            '_type': 'url_transparent',
+            'id': video_id,
+            'url': 'jwplatform:%s' % jwplatform_id,
+            'ie_key': 'JWPlatform',
+        }

youtube_dl/extractor/mdr.py

@@ -17,7 +17,7 @@ class MDRIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?(?:mdr|kika)\.de/(?:.*)/[a-z]+(?P<id>\d+)(?:_.+?)?\.html'
 
     _TESTS = [{
-        # MDR regularily deletes its videos
+        # MDR regularly deletes its videos
         'url': 'http://www.mdr.de/fakt/video189002.html',
         'only_matching': True,
     }, {

youtube_dl/extractor/mtv.py

@@ -167,14 +167,16 @@ class MTVServicesInfoExtractor(InfoExtractor):
             'description': description,
         }
 
+    def _get_feed_query(self, uri):
+        data = {'uri': uri}
+        if self._LANG:
+            data['lang'] = self._LANG
+        return compat_urllib_parse.urlencode(data)
+
     def _get_videos_info(self, uri):
         video_id = self._id_from_uri(uri)
         feed_url = self._get_feed_url(uri)
-        data = compat_urllib_parse.urlencode({'uri': uri})
-        info_url = feed_url + '?'
-        if self._LANG:
-            info_url += 'lang=%s&' % self._LANG
-        info_url += data
+        info_url = feed_url + '?' + self._get_feed_query(uri)
         return self._get_videos_info_from_url(info_url, video_id)
 
     def _get_videos_info_from_url(self, url, video_id):
@@ -184,9 +186,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
         return self.playlist_result(
             [self._get_video_info(item) for item in idoc.findall('.//item')])
 
-    def _real_extract(self, url):
-        title = url_basename(url)
-        webpage = self._download_webpage(url, title)
+    def _extract_mgid(self, webpage):
         try:
             # the url can be http://media.mtvnservices.com/fb/{mgid}.swf
             # or http://media.mtvnservices.com/{mgid}
@@ -207,7 +207,12 @@ class MTVServicesInfoExtractor(InfoExtractor):
                 'sm4:video:embed', webpage, 'sm4 embed', default='')
             mgid = self._search_regex(
                 r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid')
+        return mgid
 
+    def _real_extract(self, url):
+        title = url_basename(url)
+        webpage = self._download_webpage(url, title)
+        mgid = self._extract_mgid(webpage)
         videos_info = self._get_videos_info(mgid)
         return videos_info
 

youtube_dl/extractor/nba.py

@@ -68,13 +68,9 @@ class NBAIE(InfoExtractor):
             if video_url.startswith('/'):
                 continue
             if video_url.endswith('.m3u8'):
-                m3u8_formats = self._extract_m3u8_formats(video_url, video_id, m3u8_id='hls', fatal=False)
-                if m3u8_formats:
-                    formats.extend(m3u8_formats)
+                formats.extend(self._extract_m3u8_formats(video_url, video_id, m3u8_id='hls', fatal=False))
             elif video_url.endswith('.f4m'):
-                f4m_formats = self._extract_f4m_formats(video_url + '?hdcore=3.4.1.1', video_id, f4m_id='hds', fatal=False)
-                if f4m_formats:
-                    formats.extend(f4m_formats)
+                formats.extend(self._extract_f4m_formats(video_url + '?hdcore=3.4.1.1', video_id, f4m_id='hds', fatal=False))
             else:
                 key = video_file.attrib.get('bitrate')
                 format_info = {

youtube_dl/extractor/nbc.py

@@ -3,10 +3,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_str,
-    compat_HTTPError,
-)
+from ..compat import compat_HTTPError
 from ..utils import (
     ExtractorError,
     find_xpath_attr,
@@ -103,7 +100,7 @@ class NBCSportsVPlayerIE(InfoExtractor):
 
 
 class NBCSportsIE(InfoExtractor):
-    # Does not include https becuase its certificate is invalid
+    # Does not include https because its certificate is invalid
     _VALID_URL = r'http://www\.nbcsports\.com//?(?:[^/]+/)+(?P<id>[0-9a-z-]+)'
 
     _TEST = {
@@ -189,7 +186,7 @@ class NBCNewsIE(InfoExtractor):
                 'title': info.find('headline').text,
                 'ext': 'flv',
                 'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text,
-                'description': compat_str(info.find('caption').text),
+                'description': info.find('caption').text,
                 'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
             }
         else:

youtube_dl/extractor/ndr.py

@@ -88,10 +88,10 @@ class NDRIE(NDRBaseIE):
             'embedURL', webpage, 'embed URL', fatal=True)
         description = self._search_regex(
             r'<p[^>]+itemprop="description">([^<]+)</p>',
-            webpage, 'description', fatal=False)
+            webpage, 'description', default=None) or self._og_search_description(webpage)
         timestamp = parse_iso8601(
             self._search_regex(
-                r'<span itemprop="datePublished" content="([^"]+)">',
+                r'<span[^>]+itemprop="(?:datePublished|uploadDate)"[^>]+content="([^"]+)"',
                 webpage, 'upload date', fatal=False))
         return {
             '_type': 'url_transparent',

youtube_dl/extractor/nextmovie.py

@@ -0,0 +1,30 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .mtv import MTVServicesInfoExtractor
+from ..compat import compat_urllib_parse
+
+
+class NextMovieIE(MTVServicesInfoExtractor):
+    IE_NAME = 'nextmovie.com'
+    _VALID_URL = r'https?://(?:www\.)?nextmovie\.com/shows/[^/]+/\d{4}-\d{2}-\d{2}/(?P<id>[^/?#]+)'
+    _FEED_URL = 'http://lite.dextr.mtvi.com/service1/dispatch.htm'
+    _TESTS = [{
+        'url': 'http://www.nextmovie.com/shows/exclusives/2013-03-10/mgid:uma:videolist:nextmovie.com:1715019/',
+        'md5': '09a9199f2f11f10107d04fcb153218aa',
+        'info_dict': {
+            'id': '961726',
+            'ext': 'mp4',
+            'title': 'The Muppets\' Gravity',
+        },
+    }]
+
+    def _get_feed_query(self, uri):
+        return compat_urllib_parse.urlencode({
+            'feed': '1505',
+            'mgid': uri,
+        })
+
+    def _real_extract(self, url):
+        mgid = self._match_id(url)
+        return self._get_videos_info(mgid)

youtube_dl/extractor/nhl.py

@@ -223,7 +223,7 @@ class NHLVideocenterIE(NHLBaseInfoExtractor):
         response = self._download_webpage(request_url, playlist_title)
         response = self._fix_json(response)
         if not response.strip():
-            self._downloader.report_warning('Got an empty reponse, trying '
+            self._downloader.report_warning('Got an empty response, trying '
                                             'adding the "newvideos" parameter')
             response = self._download_webpage(request_url + '&newvideos=true',
                                               playlist_title)

youtube_dl/extractor/nick.py

@@ -0,0 +1,63 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .mtv import MTVServicesInfoExtractor
+from ..compat import compat_urllib_parse
+
+
+class NickIE(MTVServicesInfoExtractor):
+    IE_NAME = 'nick.com'
+    _VALID_URL = r'https?://(?:www\.)?nick\.com/videos/clip/(?P<id>[^/?#.]+)'
+    _FEED_URL = 'http://udat.mtvnservices.com/service1/dispatch.htm'
+    _TESTS = [{
+        'url': 'http://www.nick.com/videos/clip/alvinnn-and-the-chipmunks-112-full-episode.html',
+        'playlist': [
+            {
+                'md5': '6e5adc1e28253bbb1b28ab05403dd4d4',
+                'info_dict': {
+                    'id': 'be6a17b0-412d-11e5-8ff7-0026b9414f30',
+                    'ext': 'mp4',
+                    'title': 'ALVINNN!!! and The Chipmunks: "Mojo Missing/Who\'s The Animal" S1',
+                    'description': 'Alvin is convinced his mojo was in a cap he gave to a fan, and must find a way to get his hat back before the Chipmunks’ big concert.\nDuring a costume visit to the zoo, Alvin finds himself mistaken for the real Tasmanian devil.',
+
+                }
+            },
+            {
+                'md5': 'd7be441fc53a1d4882fa9508a1e5b3ce',
+                'info_dict': {
+                    'id': 'be6b8f96-412d-11e5-8ff7-0026b9414f30',
+                    'ext': 'mp4',
+                    'title': 'ALVINNN!!! and The Chipmunks: "Mojo Missing/Who\'s The Animal" S2',
+                    'description': 'Alvin is convinced his mojo was in a cap he gave to a fan, and must find a way to get his hat back before the Chipmunks’ big concert.\nDuring a costume visit to the zoo, Alvin finds himself mistaken for the real Tasmanian devil.',
+
+                }
+            },
+            {
+                'md5': 'efffe1728a234b2b0d2f2b343dd1946f',
+                'info_dict': {
+                    'id': 'be6cf7e6-412d-11e5-8ff7-0026b9414f30',
+                    'ext': 'mp4',
+                    'title': 'ALVINNN!!! and The Chipmunks: "Mojo Missing/Who\'s The Animal" S3',
+                    'description': 'Alvin is convinced his mojo was in a cap he gave to a fan, and must find a way to get his hat back before the Chipmunks’ big concert.\nDuring a costume visit to the zoo, Alvin finds himself mistaken for the real Tasmanian devil.',
+                }
+            },
+            {
+                'md5': '1ec6690733ab9f41709e274a1d5c7556',
+                'info_dict': {
+                    'id': 'be6e3354-412d-11e5-8ff7-0026b9414f30',
+                    'ext': 'mp4',
+                    'title': 'ALVINNN!!! and The Chipmunks: "Mojo Missing/Who\'s The Animal" S4',
+                    'description': 'Alvin is convinced his mojo was in a cap he gave to a fan, and must find a way to get his hat back before the Chipmunks’ big concert.\nDuring a costume visit to the zoo, Alvin finds himself mistaken for the real Tasmanian devil.',
+                }
+            },
+        ],
+    }]
+
+    def _get_feed_query(self, uri):
+        return compat_urllib_parse.urlencode({
+            'feed': 'nick_arc_player_prime',
+            'mgid': uri,
+        })
+
+    def _extract_mgid(self, webpage):
+        return self._search_regex(r'data-contenturi="([^"]+)', webpage, 'mgid')

youtube_dl/extractor/noco.py

@@ -9,6 +9,7 @@ from .common import InfoExtractor
 from ..compat import (
     compat_str,
     compat_urllib_parse,
+    compat_urlparse,
 )
 from ..utils import (
     clean_html,
@@ -82,14 +83,21 @@ class NocoIE(InfoExtractor):
         if 'erreur' in login:
             raise ExtractorError('Unable to login: %s' % clean_html(login['erreur']), expected=True)
 
+    @staticmethod
+    def _ts():
+        return int(time.time() * 1000)
+
     def _call_api(self, path, video_id, note, sub_lang=None):
-        ts = compat_str(int(time.time() * 1000))
+        ts = compat_str(self._ts() + self._ts_offset)
         tk = hashlib.md5((hashlib.md5(ts.encode('ascii')).hexdigest() + '#8S?uCraTedap6a').encode('ascii')).hexdigest()
         url = self._API_URL_TEMPLATE % (path, ts, tk)
         if sub_lang:
             url += self._SUB_LANG_TEMPLATE % sub_lang
 
-        resp = self._download_json(url, video_id, note)
+        request = sanitized_Request(url)
+        request.add_header('Referer', self._referer)
+
+        resp = self._download_json(request, video_id, note)
 
         if isinstance(resp, dict) and resp.get('error'):
             self._raise_error(resp['error'], resp['description'])
@@ -102,8 +110,22 @@ class NocoIE(InfoExtractor):
             expected=True)
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
+
+        # Timestamp adjustment offset between server time and local time
+        # must be calculated in order to use timestamps closest to server's
+        # in all API requests (see https://github.com/rg3/youtube-dl/issues/7864)
+        webpage = self._download_webpage(url, video_id)
+
+        player_url = self._search_regex(
+            r'(["\'])(?P<player>https?://noco\.tv/(?:[^/]+/)+NocoPlayer.+?\.swf.*?)\1',
+            webpage, 'noco player', group='player',
+            default='http://noco.tv/cdata/js/player/NocoPlayer-v1.2.40.swf')
+
+        qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(player_url).query)
+        ts = int_or_none(qs.get('ts', [None])[0])
+        self._ts_offset = ts - self._ts() if ts else 0
+        self._referer = player_url
 
         medias = self._call_api(
             'shows/%s/medias' % video_id,
@@ -155,8 +177,8 @@ class NocoIE(InfoExtractor):
                         'format_id': format_id_extended,
                         'width': int_or_none(fmt.get('res_width')),
                         'height': int_or_none(fmt.get('res_lines')),
-                        'abr': int_or_none(fmt.get('audiobitrate')),
-                        'vbr': int_or_none(fmt.get('videobitrate')),
+                        'abr': int_or_none(fmt.get('audiobitrate'), 1000),
+                        'vbr': int_or_none(fmt.get('videobitrate'), 1000),
                         'filesize': int_or_none(fmt.get('filesize')),
                         'format_note': qualities[format_id].get('quality_name'),
                         'quality': qualities[format_id].get('priority'),

youtube_dl/extractor/novamov.py

@@ -17,7 +17,7 @@ class NovaMovIE(InfoExtractor):
     IE_NAME = 'novamov'
     IE_DESC = 'NovaMov'
 
-    _VALID_URL_TEMPLATE = r'http://(?:(?:www\.)?%(host)s/(?:file|video)/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<id>[a-z\d]{13})'
+    _VALID_URL_TEMPLATE = r'http://(?:(?:www\.)?%(host)s/(?:file|video|mobile/#/videos)/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<id>[a-z\d]{13})'
     _VALID_URL = _VALID_URL_TEMPLATE % {'host': 'novamov\.com'}
 
     _HOST = 'www.novamov.com'
@@ -59,7 +59,7 @@ class NovaMovIE(InfoExtractor):
                 self._FILEKEY_REGEX, webpage, 'filekey', default=default)
             if filekey is not default and (filekey[0] != '"' or filekey[-1] != '"'):
                 return self._search_regex(
-                    r'var\s*%s\s*=\s*"([^"]+)"', webpage, 'filekey', default=default)
+                    r'var\s+%s\s*=\s*"([^"]+)"' % re.escape(filekey), webpage, 'filekey', default=default)
             else:
                 return filekey
 
@@ -141,15 +141,14 @@ class NowVideoIE(NovaMovIE):
     _DESCRIPTION_REGEX = r'</h4>\s*<p>([^<]+)</p>'
 
     _TEST = {
-        'url': 'http://www.nowvideo.to/video/0mw0yow7b6dxa',
-        'md5': 'f8fbbc8add72bd95b7850c6a02fc8817',
+        'url': 'http://www.nowvideo.sx/video/f1d6fce9a968b',
+        'md5': '12c82cad4f2084881d8bc60ee29df092',
         'info_dict': {
-            'id': '0mw0yow7b6dxa',
+            'id': 'f1d6fce9a968b',
             'ext': 'flv',
-            'title': 'youtubedl test video _BaW_jenozKc.mp4',
+            'title': 'youtubedl test video BaWjenozKc',
             'description': 'Description',
         },
-        'skip': 'Video 0mw0yow7b6dxa does not exist',
     }
 
 

youtube_dl/extractor/nowness.py

@@ -1,7 +1,10 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
-from .brightcove import BrightcoveLegacyIE
+from .brightcove import (
+    BrightcoveLegacyIE,
+    BrightcoveNewIE,
+)
 from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
@@ -23,9 +26,12 @@ class NownessBaseIE(InfoExtractor):
                             note='Downloading player JavaScript',
                             errnote='Unable to download player JavaScript')
                         bc_url = BrightcoveLegacyIE._extract_brightcove_url(player_code)
-                        if bc_url is None:
-                            raise ExtractorError('Could not find player definition')
-                        return self.url_result(bc_url, 'BrightcoveLegacy')
+                        if bc_url:
+                            return self.url_result(bc_url, BrightcoveLegacyIE.ie_key())
+                        bc_url = BrightcoveNewIE._extract_url(player_code)
+                        if bc_url:
+                            return self.url_result(bc_url, BrightcoveNewIE.ie_key())
+                        raise ExtractorError('Could not find player definition')
                     elif source == 'vimeo':
                         return self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo')
                     elif source == 'youtube':

youtube_dl/extractor/nowtv.py

@@ -71,6 +71,7 @@ class NowTVBaseIE(InfoExtractor):
 
 
 class NowTVIE(NowTVBaseIE):
+    _WORKING = False
     _VALID_URL = r'https?://(?:www\.)?nowtv\.(?:de|at|ch)/(?:rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P<show_id>[^/]+)/(?:(?:list/[^/]+|jahr/\d{4}/\d{1,2})/)?(?P<id>[^/]+)/(?:player|preview)'
 
     _TESTS = [{

youtube_dl/extractor/npr.py

@@ -0,0 +1,82 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_parse
+from ..utils import (
+    int_or_none,
+    qualities,
+)
+
+
+class NprIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?npr\.org/player/v2/mediaPlayer\.html\?.*\bid=(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://www.npr.org/player/v2/mediaPlayer.html?id=449974205',
+        'info_dict': {
+            'id': '449974205',
+            'title': 'New Music From Beach House, Chairlift, CMJ Discoveries And More'
+        },
+        'playlist_count': 7,
+    }, {
+        'url': 'http://www.npr.org/player/v2/mediaPlayer.html?action=1&t=1&islist=false&id=446928052&m=446929930&live=1',
+        'info_dict': {
+            'id': '446928052',
+            'title': "Songs We Love: Tigran Hamasyan, 'Your Mercy is Boundless'"
+        },
+        'playlist': [{
+            'md5': '12fa60cb2d3ed932f53609d4aeceabf1',
+            'info_dict': {
+                'id': '446929930',
+                'ext': 'mp3',
+                'title': 'Your Mercy is Boundless (Bazum en Qo gtutyunqd)',
+                'duration': 402,
+            },
+        }],
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        config = self._download_json(
+            'http://api.npr.org/query?%s' % compat_urllib_parse.urlencode({
+                'id': playlist_id,
+                'fields': 'titles,audio,show',
+                'format': 'json',
+                'apiKey': 'MDAzMzQ2MjAyMDEyMzk4MTU1MDg3ZmM3MQ010',
+            }), playlist_id)
+
+        story = config['list']['story'][0]
+
+        KNOWN_FORMATS = ('threegp', 'mp4', 'mp3')
+        quality = qualities(KNOWN_FORMATS)
+
+        entries = []
+        for audio in story.get('audio', []):
+            title = audio.get('title', {}).get('$text')
+            duration = int_or_none(audio.get('duration', {}).get('$text'))
+            formats = []
+            for format_id, formats_entry in audio.get('format', {}).items():
+                if not formats_entry:
+                    continue
+                if isinstance(formats_entry, list):
+                    formats_entry = formats_entry[0]
+                format_url = formats_entry.get('$text')
+                if not format_url:
+                    continue
+                if format_id in KNOWN_FORMATS:
+                    formats.append({
+                        'url': format_url,
+                        'format_id': format_id,
+                        'ext': formats_entry.get('type'),
+                        'quality': quality(format_id),
+                    })
+            self._sort_formats(formats)
+            entries.append({
+                'id': audio['id'],
+                'title': title,
+                'duration': duration,
+                'formats': formats,
+            })
+
+        playlist_title = story.get('title', {}).get('$text')
+        return self.playlist_result(entries, playlist_id, playlist_title)

youtube_dl/extractor/ooyala.py

@@ -13,6 +13,9 @@ from ..compat import compat_urllib_parse
 
 
 class OoyalaBaseIE(InfoExtractor):
+    _PLAYER_BASE = 'http://player.ooyala.com/'
+    _CONTENT_TREE_BASE = _PLAYER_BASE + 'player_api/v1/content_tree/'
+    _AUTHORIZATION_URL_TEMPLATE = _PLAYER_BASE + 'sas/player_api/v1/authorization/embed_code/%s/%s?'
 
     def _extract(self, content_tree_url, video_id, domain='example.org'):
         content_tree = self._download_json(content_tree_url, video_id)['content_tree']
@@ -31,30 +34,33 @@ class OoyalaBaseIE(InfoExtractor):
         formats = []
         for supported_format in ('mp4', 'm3u8', 'hds', 'rtmp'):
             auth_data = self._download_json(
-                'http://player.ooyala.com/sas/player_api/v1/authorization/embed_code/%s/%s?' % (pcode, embed_code) + compat_urllib_parse.urlencode({'domain': domain, 'supportedFormats': supported_format}),
+                self._AUTHORIZATION_URL_TEMPLATE % (pcode, embed_code) +
+                compat_urllib_parse.urlencode({
+                    'domain': domain,
+                    'supportedFormats': supported_format
+                }),
                 video_id, 'Downloading %s JSON' % supported_format)
 
             cur_auth_data = auth_data['authorization_data'][embed_code]
 
             if cur_auth_data['authorized']:
                 for stream in cur_auth_data['streams']:
-                    url = base64.b64decode(stream['url']['data'].encode('ascii')).decode('utf-8')
+                    url = base64.b64decode(
+                        stream['url']['data'].encode('ascii')).decode('utf-8')
                     if url in urls:
                         continue
                     urls.append(url)
                     delivery_type = stream['delivery_type']
                     if delivery_type == 'hls' or '.m3u8' in url:
-                        m3u8_formats = self._extract_m3u8_formats(url, embed_code, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
-                        if m3u8_formats:
-                            formats.extend(m3u8_formats)
+                        formats.extend(self._extract_m3u8_formats(
+                            url, embed_code, 'mp4', 'm3u8_native',
+                            m3u8_id='hls', fatal=False))
                     elif delivery_type == 'hds' or '.f4m' in url:
-                        f4m_formats = self._extract_f4m_formats(url, embed_code, f4m_id='hds', fatal=False)
-                        if f4m_formats:
-                            formats.extend(f4m_formats)
+                        formats.extend(self._extract_f4m_formats(
+                            url + '?hdcore=3.7.0', embed_code, f4m_id='hds', fatal=False))
                     elif '.smil' in url:
-                        smil_formats = self._extract_smil_formats(url, embed_code, fatal=False)
-                        if smil_formats:
-                            formats.extend(smil_formats)
+                        formats.extend(self._extract_smil_formats(
+                            url, embed_code, fatal=False))
                     else:
                         formats.append({
                             'url': url,
@@ -68,7 +74,8 @@ class OoyalaBaseIE(InfoExtractor):
                             'fps': float_or_none(stream.get('framerate')),
                         })
             else:
-                raise ExtractorError('%s said: %s' % (self.IE_NAME, cur_auth_data['message']), expected=True)
+                raise ExtractorError('%s said: %s' % (
+                    self.IE_NAME, cur_auth_data['message']), expected=True)
         self._sort_formats(formats)
 
         video_info['formats'] = formats
@@ -126,7 +133,7 @@ class OoyalaIE(OoyalaBaseIE):
         url, smuggled_data = unsmuggle_url(url, {})
         embed_code = self._match_id(url)
         domain = smuggled_data.get('domain')
-        content_tree_url = 'http://player.ooyala.com/player_api/v1/content_tree/embed_code/%s/%s' % (embed_code, embed_code)
+        content_tree_url = self._CONTENT_TREE_BASE + 'embed_code/%s/%s' % (embed_code, embed_code)
         return self._extract(content_tree_url, embed_code, domain)
 
 
@@ -153,7 +160,7 @@ class OoyalaExternalIE(OoyalaBaseIE):
             'id': 'FkYWtmazr6Ed8xmvILvKLWjd4QvYZpzG',
             'ext': 'mp4',
             'title': 'dm_140128_30for30Shorts___JudgingJewellv2',
-            'duration': 1302000,
+            'duration': 1302.0,
         },
         'params': {
             # m3u8 download
@@ -163,5 +170,5 @@ class OoyalaExternalIE(OoyalaBaseIE):
 
     def _real_extract(self, url):
         partner_id, video_id, pcode = re.match(self._VALID_URL, url).groups()
-        content_tree_url = 'http://player.ooyala.com/player_api/v1/content_tree/external_id/%s/%s:%s' % (pcode, partner_id, video_id)
+        content_tree_url = self._CONTENT_TREE_BASE + 'external_id/%s/%s:%s' % (pcode, partner_id, video_id)
         return self._extract(content_tree_url, video_id)