3 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
13 compat_urllib_parse_unquote,
15 compat_xml_parse_error,
32 from .brightcove import (
36 from .nbc import NBCSportsVPlayerIE
37 from .ooyala import OoyalaIE
38 from .rutv import RUTVIE
39 from .tvc import TVCIE
40 from .sportbox import SportBoxEmbedIE
41 from .smotri import SmotriIE
42 from .myvi import MyviIE
43 from .condenast import CondeNastIE
44 from .udn import UDNEmbedIE
45 from .senateisvp import SenateISVPIE
46 from .svt import SVTIE
47 from .pornhub import PornHubIE
48 from .xhamster import XHamsterEmbedIE
49 from .tnaflix import TNAFlixNetworkEmbedIE
50 from .drtuber import DrTuberIE
51 from .redtube import RedTubeIE
52 from .vimeo import VimeoIE
53 from .dailymotion import (
57 from .onionstudios import OnionStudiosIE
58 from .viewlift import ViewLiftEmbedIE
59 from .mtv import MTVServicesEmbeddedIE
60 from .pladform import PladformIE
61 from .videomore import VideomoreIE
62 from .webcaster import WebcasterFeedIE
63 from .googledrive import GoogleDriveIE
64 from .jwplatform import JWPlatformIE
65 from .digiteka import DigitekaIE
66 from .arkena import ArkenaIE
67 from .instagram import InstagramIE
68 from .liveleak import LiveLeakIE
69 from .threeqsdn import ThreeQSDNIE
70 from .theplatform import ThePlatformIE
71 from .vessel import VesselIE
72 from .kaltura import KalturaIE
73 from .eagleplatform import EaglePlatformIE
74 from .facebook import FacebookIE
75 from .soundcloud import SoundcloudIE
76 from .vbox7 import Vbox7IE
77 from .dbtv import DBTVIE
80 class GenericIE(InfoExtractor):
81 IE_DESC = 'Generic downloader that works on some sites'
85 # Direct link to a video
87 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
88 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
93 'upload_date': '20100513',
96 # Direct link to media delivered compressed (until Accept-Encoding is *)
98 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
99 'md5': '128c42e68b13950268b648275386fc74',
101 'id': 'FictionJunction-Parallel_Hearts',
103 'title': 'FictionJunction-Parallel_Hearts',
104 'upload_date': '20140522',
106 'expected_warnings': [
107 'URL could be a direct video link, returning it as such.'
109 'skip': 'URL invalid',
111 # Direct download with broken HEAD
113 'url': 'http://ai-radio.org:8000/radio.opus',
120 'skip_download': True, # infinite live stream
122 'expected_warnings': [
123 r'501.*Not Implemented',
127 # Direct link with incorrect MIME type
129 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
130 'md5': '4ccbebe5f36706d85221f204d7eb5913',
132 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
133 'id': '5_Lennart_Poettering_-_Systemd',
135 'title': '5_Lennart_Poettering_-_Systemd',
136 'upload_date': '20141120',
138 'expected_warnings': [
139 'URL could be a direct video link, returning it as such.'
144 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
146 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
147 'title': 'Zero Punctuation',
148 'description': 're:.*groundbreaking video review series.*'
150 'playlist_mincount': 11,
152 # RSS feed with enclosure
154 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
156 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
158 'upload_date': '20150228',
159 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
162 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
164 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
168 'title': 'Automatics, robotics and biocybernetics',
169 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
170 'upload_date': '20130627',
171 'formats': 'mincount:16',
172 'subtitles': 'mincount:1',
175 'force_generic_extractor': True,
176 'skip_download': True,
179 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
181 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
186 'formats': 'mincount:1',
189 'skip_download': True,
192 # SMIL from https://www.restudy.dk/video/play/id/1637
194 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
198 'title': 'video_1637',
199 'formats': 'mincount:3',
202 'skip_download': True,
205 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
207 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
209 'id': 'smil-service',
211 'title': 'smil-service',
212 'formats': 'mincount:1',
215 'skip_download': True,
218 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
220 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
224 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
225 'formats': 'mincount:3',
228 'skip_download': True,
231 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
233 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
235 'id': 'mZlp2ctYIUEB',
237 'title': 'Tikibad ontruimd wegens brand',
238 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
239 'thumbnail': 're:^https?://.*\.jpg$',
243 'skip_download': True,
246 # MPD from http://dash-mse-test.appspot.com/media.html
248 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
249 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
251 'id': 'car-20120827-manifest',
253 'title': 'car-20120827-manifest',
254 'formats': 'mincount:9',
255 'upload_date': '20130904',
258 'format': 'bestvideo',
261 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
263 'url': 'http://once.unicornmedia.com/now/master/playlist/bb0b18ba-64f5-4b1b-a29f-0ac252f06b68/77a785f3-5188-4806-b788-0893a61634ed/93677179-2d99-4ef4-9e17-fe70d49abfbf/content.m3u8',
268 'formats': 'mincount:8',
272 'skip_download': True,
274 'skip': 'video gone',
276 # m3u8 served with Content-Type: text/plain
278 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
283 'upload_date': '20140720',
284 'formats': 'mincount:11',
288 'skip_download': True,
290 'skip': 'video gone',
294 'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
298 'upload_date': '20130224',
299 'uploader_id': 'TheVerge',
300 'description': 're:^Chris Ziegler takes a look at the\.*',
301 'uploader': 'The Verge',
302 'title': 'First Firefox OS phones side-by-side',
305 'skip_download': False,
309 # redirect in Refresh HTTP header
310 'url': 'https://www.facebook.com/l.php?u=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DpO8h3EaFRdo&h=TAQHsoToz&enc=AZN16h-b6o4Zq9pZkCCdOLNKMN96BbGMNtcFwHSaazus4JHT_MFYkAA-WARTX2kvsCIdlAIyHZjl6d33ILIJU7Jzwk_K3mcenAXoAzBNoZDI_Q7EXGDJnIhrGkLXo_LJ_pAa2Jzbx17UHMd3jAs--6j2zaeto5w9RTn8T_1kKg3fdC5WPX9Dbb18vzH7YFX0eSJmoa6SP114rvlkw6pkS1-T&s=1',
314 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
315 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
316 'upload_date': '20150917',
317 'uploader_id': 'brtvofficial',
318 'uploader': 'Boiler Room',
321 'skip_download': False,
325 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
326 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
328 'id': '13601338388002',
330 'uploader': 'www.hodiho.fr',
331 'title': 'R\u00e9gis plante sa Jeep',
334 # bandcamp page with custom domain
336 'add_ie': ['Bandcamp'],
337 'url': 'http://bronyrock.com/track/the-pony-mash',
341 'title': 'The Pony Mash',
342 'uploader': 'M_Pallante',
344 'skip': 'There is a limit of 200 free downloads / month for the test song',
346 # embedded brightcove video
347 # it also tests brightcove videos that need to set the 'Referer' in the
350 'add_ie': ['BrightcoveLegacy'],
351 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
353 'id': '2765128793001',
355 'title': 'Le cours de bourse : l’analyse technique',
356 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
357 'uploader': 'BFM BUSINESS',
360 'skip_download': True,
364 # https://github.com/rg3/youtube-dl/issues/2253
365 'url': 'http://bcove.me/i6nfkrc3',
366 'md5': '0ba9446db037002366bab3b3eb30c88c',
368 'id': '3101154703001',
370 'title': 'Still no power',
371 'uploader': 'thestar.com',
372 'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
374 'add_ie': ['BrightcoveLegacy'],
375 'skip': 'video gone',
378 'url': 'http://www.championat.com/video/football/v/87/87499.html',
379 'md5': 'fb973ecf6e4a78a67453647444222983',
381 'id': '3414141473001',
383 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
384 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
385 'uploader': 'Championat',
389 # https://github.com/rg3/youtube-dl/issues/3541
390 'add_ie': ['BrightcoveLegacy'],
391 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
393 'id': '3866516442001',
395 'title': 'Leer mij vrouwen kennen: Aflevering 1',
396 'description': 'Leer mij vrouwen kennen: Aflevering 1',
397 'uploader': 'SBS Broadcasting',
399 'skip': 'Restricted to Netherlands',
401 'skip_download': True, # m3u8 download
406 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
407 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
409 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
411 'title': '2cc213299525360.mov', # that's what we get
414 'add_ie': ['Ooyala'],
417 # ooyala video embedded with http://player.ooyala.com/iframe.js
418 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
420 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
422 'title': '"Steve Jobs: Man in the Machine" trailer',
423 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
427 'skip_download': True,
429 'skip': 'movie expired',
433 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
437 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
438 'upload_date': '20140225',
439 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
440 'uploader': 'Tested',
441 'uploader_id': 'testedcom',
443 # No need to test YoutubeIE here
445 'skip_download': True,
450 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
454 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
455 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
457 # HEAD requests lead to endless 301, while GET is OK
458 'expected_warnings': ['301'],
462 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
466 'title': 'Охотское море стало целиком российским',
467 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
471 'skip_download': True,
476 'url': 'http://sch1298sz.mskobr.ru/dou_edu/karamel_ki/filial_galleries/video/iframe_src_http_tvc_ru_video_iframe_id_55304_isplay_false_acc_video_id_channel_brand_id_11_show_episodes_episode_id_32307_frameb/',
480 'title': 'Дошкольное воспитание',
485 'url': 'http://www.vestifinance.ru/articles/25753',
488 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
493 'title': 'Госзаказ. День 3',
499 'title': 'Госзаказ. День 2',
505 'title': 'Госзаказ. День 1',
511 'skip_download': True,
516 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
518 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
520 'title': 'Ужастики, русский трейлер (2015)',
521 'thumbnail': 're:^https?://.*\.jpg$',
527 'url': 'http://www.numisc.com/forum/showthread.php?11696-FM15-which-pumiscer-was-this-%28-vid-%29-%28-alfa-as-fuck-srx-%29&s=711f5db534502e22260dec8c5e2d66d8',
530 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
532 'playlist_mincount': 7,
533 # This forum does not allow <iframe> syntaxes anymore
534 # Now HTML tags are displayed as-is
535 'skip': 'No videos on this page',
539 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
540 'md5': '65fdff94098e4a607385a60c5177c638',
544 'title': 'Hidden miracles of the natural world',
545 'uploader': 'Louie Schwartzberg',
546 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
549 # Embedded Ustream video
551 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
552 'md5': '27b99cdb639c9b12a79bca876a073417',
556 'uploader': 'AU SPA: The NSA and Privacy',
557 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
560 # nowvideo embed hidden behind percent encoding
562 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
563 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
565 'id': '06e53103ca9aa',
567 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
568 'description': 'No description',
573 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
574 'md5': '7653032cbb25bf6c80d80f217055fa43',
576 'id': '048195-004_PLUS7-F',
579 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
580 'upload_date': '20140320',
583 'skip_download': 'Requires rtmpdump'
585 'skip': 'video gone',
589 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
593 'title': 'Alcaline, le concert avec Calogero',
594 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
595 'upload_date': '20150226',
596 'timestamp': 1424989860,
601 'skip_download': True,
603 'expected_warnings': [
609 'url': 'http://www.wired.com/2014/04/honda-asimo/',
610 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
612 'id': '53501be369702d3275860000',
614 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
619 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
620 'md5': '441aeeb82eb72c422c7f14ec533999cd',
622 'id': 'k2mm4bCdJ6CQ2i7c8o2',
624 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
625 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
627 'uploader_id': 'xgditw',
628 'upload_date': '20140425',
629 'timestamp': 1398441542,
631 'add_ie': ['Dailymotion'],
635 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
639 'title': 'The NBL Auction 2014',
640 'uploader': 'BADMINTON England',
641 'uploader_id': 'BADMINTONEvents',
642 'upload_date': '20140603',
643 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
645 'add_ie': ['Youtube'],
647 'skip_download': True,
652 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
653 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
655 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
657 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
658 'description': 'Two valets share their love for movie star Liam Neesons.',
659 'timestamp': 1349922600,
660 'upload_date': '20121011',
663 # YouTube embed via <data-embed-url="">
665 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
669 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
670 'uploader': 'Gameloft',
671 'uploader_id': 'gameloft',
672 'upload_date': '20140828',
673 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
676 'skip_download': True,
681 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
683 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
685 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
686 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
691 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
693 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
694 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
700 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
705 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
706 'md5': '9d65602bf31c6e20014319c7d07fba27',
708 'id': '5123ea6d5e5a7',
711 'uploader': 'www.handjobhub.com',
712 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
715 # Multiple brightcove videos
716 # https://github.com/rg3/youtube-dl/issues/2283
718 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
720 'id': 'always-never',
721 'title': 'Always / Never - The New Yorker',
725 'extract_flat': False,
726 'skip_download': True,
731 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
732 'md5': '96f09a37e44da40dd083e12d9a683327',
736 'title': 'Ump changes call to ball',
737 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
739 'timestamp': 1401537900,
740 'upload_date': '20140531',
741 'thumbnail': 're:^https?://.*\.jpg$',
746 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
747 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
751 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
752 'description': 'a Paywall Videos video from Remilon',
754 'uploader': 'study.com',
755 'timestamp': 1459678540,
756 'upload_date': '20160403',
757 'filesize': 24687186,
761 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
762 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
766 'title': 'Conversation about Hexagonal Rails Part 1',
767 'description': 'a Martin Fowler video from ThoughtWorks',
769 'uploader': 'thoughtworks.wistia.com',
770 'timestamp': 1401832161,
771 'upload_date': '20140603',
774 # Wistia standard embed (async)
776 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
780 'title': 'Drip Brennan Dunn Workshop',
781 'description': 'a JV Webinars video from getdrip-1',
783 'timestamp': 1463607249,
784 'upload_date': '20160518',
787 'skip_download': True,
792 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
796 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
797 'uploader': 'Sophos Security',
798 'title': 'Chet Chat 171 - Oct 29, 2014',
799 'upload_date': '20141029',
802 # Soundcloud multiple embeds
804 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
807 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
809 'playlist_mincount': 7,
813 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
817 'upload_date': '20141112',
818 'title': 'Rosetta #CometLanding webcast HL 10',
821 # Another Livestream embed, without 'new.' in URL
823 'url': 'https://www.freespeech.org/',
827 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
831 'skip_download': True,
836 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
839 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
841 'playlist_mincount': 2,
845 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
849 'upload_date': '20141126',
850 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
855 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
857 'id': '730m_DandD_1901_512k',
859 'uploader': 'www.abc.net.au',
860 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
863 # embedded viddler video
865 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
869 'uploader': 'deadspin',
870 'title': 'WALL-TO-GORTAT',
871 'timestamp': 1422285291,
872 'upload_date': '20150126',
874 'add_ie': ['Viddler'],
878 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
882 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
883 'description': 'md5:601cb790edd05908957dae8aaa866465',
884 'upload_date': '20150220',
886 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
890 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
894 'upload_date': '20150212',
895 'uploader': 'The National Archives UK',
896 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
897 'uploader_id': 'NationalArchives08',
898 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
903 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
904 'playlist_mincount': 5,
906 'id': 'aanslagen-kopenhagen',
907 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
912 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
916 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
919 # Kaltura embed (different embed code)
921 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
925 'upload_date': '20150127',
926 'uploader_id': 'PremierMedia',
928 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
931 # Kaltura embed protected with referrer
933 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
937 'title': 'Violetta - Achter De Schermen - Ruggero',
938 'description': 'Achter de schermen met Ruggero',
939 'timestamp': 1435133761,
940 'upload_date': '20150624',
941 'uploader_id': 'echojecka',
944 # Kaltura embed with single quotes
946 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
951 'timestamp': 1355743100,
952 'upload_date': '20121217',
953 'uploader_id': 'batchUser',
955 'add_ie': ['Kaltura'],
958 # Kaltura embedded via quoted entry_id
959 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
963 'title': '06_matthew_brender_raj_dutt',
964 'timestamp': 1466638791,
965 'upload_date': '20160622',
967 'add_ie': ['Kaltura'],
968 'expected_warnings': [
969 'Could not send HEAD request'
972 'skip_download': True,
975 # Eagle.Platform embed (generic URL)
977 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
978 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
982 'title': 'Навальный вышел на свободу',
983 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
984 'thumbnail': 're:^https?://.*\.jpg$',
990 # ClipYou (Eagle.Platform) embed (custom URL)
992 'url': 'http://muz-tv.ru/play/7129/',
993 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
997 'title': "'O Sole Mio",
998 'thumbnail': 're:^https?://.*\.jpg$',
1005 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1009 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1010 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1011 'thumbnail': 're:^https?://.*\.jpg$',
1018 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1022 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1023 'thumbnail': 're:^https?://.*\.png$',
1029 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1030 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1034 'title': 'Facebook Creates "On This Day" | Crunch Report',
1039 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1043 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1048 # Crooks and Liars embed
1050 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1054 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1055 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1056 'timestamp': 1428207000,
1057 'upload_date': '20150405',
1058 'uploader': 'Heather',
1061 # Crooks and Liars external embed
1063 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1065 'id': 'MTE3MjUtMzQ2MzA',
1067 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1068 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1069 'timestamp': 1265032391,
1070 'upload_date': '20100201',
1071 'uploader': 'Heather',
1074 # NBC Sports vplayer embed
1076 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1078 'id': 'ln7x1qSThw4k',
1080 'title': "PFT Live: New leader in the 'new-look' defense",
1081 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1082 'uploader': 'NBCU-SPORTS',
1083 'upload_date': '20140107',
1084 'timestamp': 1389118457,
1089 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1090 'md5': '1aa589c675898ae6d37a17913cf68d66',
1092 'id': '701714499682',
1094 'title': 'PREVIEW: On Assignment: David Letterman',
1095 'description': 'A preview of Tom Brokaw\'s interview with David Letterman as part of the On Assignment series powered by Dateline. Airs Sunday June 12 at 7/6c.',
1100 'url': 'https://video.udn.com/news/300346',
1101 'md5': 'fd2060e988c326991037b9aff9df21a6',
1105 'title': '中一中男師變性 全校師生力挺',
1106 'thumbnail': 're:^https?://.*\.jpg$',
1110 'skip_download': True,
1115 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1117 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1119 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1120 'title': 'This is what separates the Excel masters from the wannabes',
1121 'duration': 191.933,
1125 'skip_download': True,
1128 # Brightcove URL in single quotes
1130 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1131 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1133 'id': '4255764656001',
1135 'title': 'SN Presents: Russell Martin, World Citizen',
1136 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1137 'uploader': 'Rogers Sportsnet',
1138 'uploader_id': '1704050871',
1139 'upload_date': '20150525',
1140 'timestamp': 1432570283,
1143 # Dailymotion Cloud video
1145 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1146 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1150 'title': 'Sauvons les abeilles ! - Le débat',
1151 'description': 'md5:d9082128b1c5277987825d684939ca26',
1152 'thumbnail': 're:^https?://.*\.jpe?g$',
1153 'timestamp': 1434970506,
1154 'upload_date': '20150622',
1155 'uploader': 'Public Sénat',
1156 'uploader_id': 'xa9gza',
1159 # OnionStudios embed
1161 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1165 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1166 'thumbnail': 're:^https?://.*\.jpe?g$',
1167 'uploader': 'ClickHole',
1168 'uploader_id': 'clickhole',
1173 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1175 'id': '74849a00-85a9-11e1-9660-123139220831',
1177 'title': '#whilewewatch',
1180 # AdobeTVVideo embed
1182 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1183 'md5': '43662b577c018ad707a63766462b1e87',
1187 'title': 'New experience with Acrobat DC',
1188 'description': 'New experience with Acrobat DC',
1189 'duration': 248.667,
1192 # BrightcoveInPageEmbed embed
1194 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1196 'id': '4238694884001',
1198 'title': 'Tabletop: Dread, Last Thoughts',
1199 'description': 'Tabletop: Dread, Last Thoughts',
1203 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1204 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1206 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1208 'id': '4785848093001',
1210 'title': 'The Cardinal Pell Interview',
1211 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1212 'uploader': 'GlobeCast Australia - GlobeStream',
1213 'uploader_id': '2733773828001',
1214 'upload_date': '20160304',
1215 'timestamp': 1457083087,
1219 'skip_download': True,
1222 # Another form of arte.tv embed
1224 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1225 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1227 'id': '030273-562_PLUS7-F',
1229 'title': 'ARTE Reportage - Nulle part, en France',
1230 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1231 'upload_date': '20160409',
1236 'url': 'http://www.wykop.pl/link/3088787/',
1237 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1239 'id': '874_1459135191',
1241 'title': 'Man shows poor quality of new apartment building',
1242 'description': 'The wall is like a sand pile.',
1243 'uploader': 'Lake8737',
1246 # Duplicated embedded video URLs
1248 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1250 'id': '149298443_480_16c25b74_2',
1252 'title': 'vs. Blue Orange Spring Game',
1253 'uploader': 'www.hudl.com',
1256 # twitter:player:stream embed
1258 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1262 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1263 'uploader': 'www.rtl.be',
1267 'skip_download': True,
1270 # twitter:player embed
1272 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1273 'md5': 'a3e0df96369831de324f0778e126653c',
1275 'id': '4909620399001',
1277 'title': 'What Do Black Holes Sound Like?',
1278 'description': 'what do black holes sound like',
1279 'upload_date': '20160524',
1280 'uploader_id': '29913724001',
1281 'timestamp': 1464107587,
1282 'uploader': 'TheAtlantic',
1284 'add_ie': ['BrightcoveLegacy'],
1286 # Facebook <iframe> embed
1288 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1289 'md5': 'fbcde74f534176ecb015849146dd3aee',
1291 'id': '599637780109885',
1293 'title': 'Facebook video #599637780109885',
1296 # Facebook API embed
1298 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1299 'md5': 'a47372ee61b39a7b90287094d447d94e',
1301 'id': '10153467542406923',
1303 'title': 'Facebook video #10153467542406923',
1306 # Wordpress "YouTube Video Importer" plugin
1308 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1309 'md5': 'd16797741b560b485194eddda8121b48',
1311 'id': 'HNTXWDXV9Is',
1313 'title': 'Blue Devils Drumline Stanford lot 2016',
1314 'upload_date': '20160627',
1315 'uploader_id': 'GENOCIDE8GENERAL10',
1316 'uploader': 'cylus cyrus',
1320 # video stored on custom kaltura server
1321 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1322 'md5': '537617d06e64dfed891fa1593c4b30cc',
1326 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1327 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1328 'uploader_id': 'videos.expansion@el-mundo.net',
1329 'upload_date': '20150429',
1330 'timestamp': 1430303472,
1332 'add_ie': ['Kaltura'],
1335 # Non-standard Vimeo embed
1336 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1337 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1341 'title': 'Understanding the web - Teaser',
1342 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1343 'upload_date': '20151214',
1344 'uploader': 'OpenClassrooms',
1345 'uploader_id': 'openclassrooms',
1347 'add_ie': ['Vimeo'],
1350 # generic vimeo embed that requires original URL passed as Referer
1351 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1352 'only_matching': True,
1355 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1356 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1358 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1360 'title': 'Big Buck Bunny',
1361 'description': 'Royalty free test video',
1362 'timestamp': 1432816365,
1363 'upload_date': '20150528',
1367 'skip_download': True,
1369 'add_ie': [ArkenaIE.ie_key()],
1372 'url': 'http://nova.bg/news/view/2016/08/16/156543/%D0%BD%D0%B0-%D0%BA%D0%BE%D1%81%D1%8A%D0%BC-%D0%BE%D1%82-%D0%B2%D0%B7%D1%80%D0%B8%D0%B2-%D0%BE%D1%82%D1%86%D0%B5%D0%BF%D0%B8%D1%85%D0%B0-%D1%86%D1%8F%D0%BB-%D0%BA%D0%B2%D0%B0%D1%80%D1%82%D0%B0%D0%BB-%D0%B7%D0%B0%D1%80%D0%B0%D0%B4%D0%B8-%D0%B8%D0%B7%D1%82%D0%B8%D1%87%D0%B0%D0%BD%D0%B5-%D0%BD%D0%B0-%D0%B3%D0%B0%D0%B7-%D0%B2-%D0%BF%D0%BB%D0%BE%D0%B2%D0%B4%D0%B8%D0%B2/',
1376 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1379 'skip_download': True,
1381 'add_ie': [Vbox7IE.ie_key()],
1385 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1388 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1390 'playlist_mincount': 3,
1393 # # TODO: find another test
1394 # # http://schema.org/VideoObject
1395 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1396 # 'md5': '888dcf08b7ea671381f00fab74692755',
1398 # 'id': 'nyvTSJMKId',
1400 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1401 # 'description': '#love for cats.',
1402 # 'timestamp': 1461244995,
1403 # 'upload_date': '20160421',
1406 # 'force_generic_extractor': True,
1411 def report_following_redirect(self, new_url):
1412 """Report information extraction."""
1413 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1415 def _extract_rss(self, url, video_id, doc):
1416 playlist_title = doc.find('./channel/title').text
1417 playlist_desc_el = doc.find('./channel/description')
1418 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1421 for it in doc.findall('./channel/item'):
1422 next_url = xpath_text(it, 'link', fatal=False)
1424 enclosure_nodes = it.findall('./enclosure')
1425 for e in enclosure_nodes:
1426 next_url = e.attrib.get('url')
1436 'title': it.find('title').text,
1440 '_type': 'playlist',
1442 'title': playlist_title,
1443 'description': playlist_desc,
1447 def _extract_camtasia(self, url, video_id, webpage):
1448 """ Returns None if no camtasia video can be found. """
1450 camtasia_cfg = self._search_regex(
1451 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1452 webpage, 'camtasia configuration file', default=None)
1453 if camtasia_cfg is None:
1456 title = self._html_search_meta('DC.title', webpage, fatal=True)
1458 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1459 camtasia_cfg = self._download_xml(
1460 camtasia_url, video_id,
1461 note='Downloading camtasia configuration',
1462 errnote='Failed to download camtasia configuration')
1463 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1466 for n in fileset_node.getchildren():
1467 url_n = n.find('./uri')
1472 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1473 'title': '%s - %s' % (title, n.tag),
1474 'url': compat_urlparse.urljoin(url, url_n.text),
1475 'duration': float_or_none(n.find('./duration').text),
1479 '_type': 'playlist',
1484 def _real_extract(self, url):
1485 if url.startswith('//'):
1488 'url': self.http_scheme() + url,
1491 parsed_url = compat_urlparse.urlparse(url)
1492 if not parsed_url.scheme:
1493 default_search = self._downloader.params.get('default_search')
1494 if default_search is None:
1495 default_search = 'fixup_error'
1497 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1499 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1500 return self.url_result('http://' + url)
1501 elif default_search != 'fixup_error':
1502 if default_search == 'auto_warning':
1503 if re.match(r'^(?:url|URL)$', url):
1504 raise ExtractorError(
1505 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1508 self._downloader.report_warning(
1509 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1510 return self.url_result('ytsearch:' + url)
1512 if default_search in ('error', 'fixup_error'):
1513 raise ExtractorError(
1514 '%r is not a valid URL. '
1515 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1516 % (url, url), expected=True)
1518 if ':' not in default_search:
1519 default_search += ':'
1520 return self.url_result(default_search + url)
1522 url, smuggled_data = unsmuggle_url(url)
1523 force_videoid = None
1524 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1525 if smuggled_data and 'force_videoid' in smuggled_data:
1526 force_videoid = smuggled_data['force_videoid']
1527 video_id = force_videoid
1529 video_id = self._generic_id(url)
1531 self.to_screen('%s: Requesting header' % video_id)
1533 head_req = HEADRequest(url)
1534 head_response = self._request_webpage(
1536 note=False, errnote='Could not send HEAD request to %s' % url,
1539 if head_response is not False:
1540 # Check for redirect
1541 new_url = head_response.geturl()
1543 self.report_following_redirect(new_url)
1545 new_url = smuggle_url(
1546 new_url, {'force_videoid': force_videoid})
1547 return self.url_result(new_url)
1549 full_response = None
1550 if head_response is False:
1551 request = sanitized_Request(url)
1552 request.add_header('Accept-Encoding', '*')
1553 full_response = self._request_webpage(request, video_id)
1554 head_response = full_response
1558 'title': self._generic_title(url),
1559 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1562 # Check for direct link to a video
1563 content_type = head_response.headers.get('Content-Type', '').lower()
1564 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1566 format_id = m.group('format_id')
1567 if format_id.endswith('mpegurl'):
1568 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1569 elif format_id == 'f4m':
1570 formats = self._extract_f4m_formats(url, video_id)
1573 'format_id': m.group('format_id'),
1575 'vcodec': 'none' if m.group('type') == 'audio' else None
1577 info_dict['direct'] = True
1578 self._sort_formats(formats)
1579 info_dict['formats'] = formats
1582 if not self._downloader.params.get('test', False) and not is_intentional:
1583 force = self._downloader.params.get('force_generic_extractor', False)
1584 self._downloader.report_warning(
1585 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1587 if not full_response:
1588 request = sanitized_Request(url)
1589 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1590 # making it impossible to download only chunk of the file (yet we need only 512kB to
1591 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1592 # that will always result in downloading the whole file that is not desirable.
1593 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1594 # to accept raw bytes and being able to download only a chunk.
1595 # It may probably better to solve this by checking Content-Type for application/octet-stream
1596 # after HEAD request finishes, but not sure if we can rely on this.
1597 request.add_header('Accept-Encoding', '*')
1598 full_response = self._request_webpage(request, video_id)
1600 first_bytes = full_response.read(512)
1602 # Is it an M3U playlist?
1603 if first_bytes.startswith(b'#EXTM3U'):
1604 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1605 self._sort_formats(info_dict['formats'])
1608 # Maybe it's a direct link to a video?
1609 # Be careful not to download the whole thing!
1610 if not is_html(first_bytes):
1611 self._downloader.report_warning(
1612 'URL could be a direct video link, returning it as such.')
1619 webpage = self._webpage_read_content(
1620 full_response, url, video_id, prefix=first_bytes)
1622 self.report_extraction(video_id)
1624 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1626 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1627 if doc.tag == 'rss':
1628 return self._extract_rss(url, video_id, doc)
1629 elif doc.tag == 'SmoothStreamingMedia':
1630 info_dict['formats'] = self._parse_ism_formats(doc, url)
1631 self._sort_formats(info_dict['formats'])
1633 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1634 smil = self._parse_smil(doc, url, video_id)
1635 self._sort_formats(smil['formats'])
1637 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1638 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1639 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1640 info_dict['formats'] = self._parse_mpd_formats(
1642 mpd_base_url=full_response.geturl().rpartition('/')[0],
1644 self._sort_formats(info_dict['formats'])
1646 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1647 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1648 self._sort_formats(info_dict['formats'])
1650 except compat_xml_parse_error:
1653 # Is it a Camtasia project?
1654 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1655 if camtasia_res is not None:
1658 # Sometimes embedded video player is hidden behind percent encoding
1659 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1660 # Unescaping the whole page allows to handle those cases in a generic way
1661 webpage = compat_urllib_parse_unquote(webpage)
1663 # it's tempting to parse this further, but you would
1664 # have to take into account all the variations like
1665 # Video Title - Site Name
1666 # Site Name | Video Title
1667 # Video Title - Tagline | Site Name
1668 # and so on and so forth; it's just not practical
1669 video_title = self._og_search_title(
1670 webpage, default=None) or self._html_search_regex(
1671 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1674 # Try to detect age limit automatically
1675 age_limit = self._rta_search(webpage)
1676 # And then there are the jokers who advertise that they use RTA,
1677 # but actually don't.
1678 AGE_LIMIT_MARKERS = [
1679 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1681 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1684 # video uploader is domain name
1685 video_uploader = self._search_regex(
1686 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1688 video_description = self._og_search_description(webpage, default=None)
1689 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1692 def _playlist_from_matches(matches, getter=None, ie=None):
1694 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1696 return self.playlist_result(
1697 urlrs, playlist_id=video_id, playlist_title=video_title)
1699 # Look for Brightcove Legacy Studio embeds
1700 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1702 self.to_screen('Brightcove video detected.')
1705 'url': smuggle_url(bc_url, {'Referer': url}),
1706 'ie_key': 'BrightcoveLegacy'
1707 } for bc_url in bc_urls]
1710 '_type': 'playlist',
1711 'title': video_title,
1716 # Look for Brightcove New Studio embeds
1717 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1719 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1721 # Look for ThePlatform embeds
1722 tp_urls = ThePlatformIE._extract_urls(webpage)
1724 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1726 # Look for Vessel embeds
1727 vessel_urls = VesselIE._extract_urls(webpage)
1729 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1731 # Look for embedded rtl.nl player
1732 matches = re.findall(
1733 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1736 return _playlist_from_matches(matches, ie='RtlNl')
1738 vimeo_urls = VimeoIE._extract_urls(url, webpage)
1740 return _playlist_from_matches(vimeo_urls, ie=VimeoIE.ie_key())
1742 vid_me_embed_url = self._search_regex(
1743 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1744 webpage, 'vid.me embed', default=None)
1745 if vid_me_embed_url is not None:
1746 return self.url_result(vid_me_embed_url, 'Vidme')
1748 # Look for embedded YouTube player
1749 matches = re.findall(r'''(?x)
1758 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1762 return _playlist_from_matches(
1763 matches, lambda m: unescapeHTML(m[1]))
1765 # Look for lazyYT YouTube embed
1766 matches = re.findall(
1767 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1769 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1771 # Look for Wordpress "YouTube Video Importer" plugin
1772 matches = re.findall(r'''(?x)<div[^>]+
1773 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1774 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1776 return _playlist_from_matches(matches, lambda m: m[-1])
1778 matches = DailymotionIE._extract_urls(webpage)
1780 return _playlist_from_matches(matches)
1782 # Look for embedded Dailymotion playlist player (#3822)
1784 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1786 playlists = re.findall(
1787 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1789 return _playlist_from_matches(
1790 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1792 # Look for embedded Wistia player
1794 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1796 embed_url = self._proto_relative_url(
1797 unescapeHTML(match.group('url')))
1799 '_type': 'url_transparent',
1802 'uploader': video_uploader,
1805 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1808 '_type': 'url_transparent',
1809 'url': 'wistia:%s' % match.group('id'),
1811 'uploader': video_uploader,
1816 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1817 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1820 return self.url_result(self._proto_relative_url(
1821 'wistia:%s' % match.group('id')), 'Wistia')
1823 # Look for SVT player
1824 svt_url = SVTIE._extract_url(webpage)
1826 return self.url_result(svt_url, 'SVT')
1828 # Look for embedded condenast player
1829 matches = re.findall(
1830 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1834 '_type': 'playlist',
1837 'ie_key': 'CondeNast',
1839 } for ma in matches],
1840 'title': video_title,
1844 # Look for Bandcamp pages with custom domain
1845 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1846 if mobj is not None:
1847 burl = unescapeHTML(mobj.group(1))
1848 # Don't set the extractor because it can be a track url or an album
1849 return self.url_result(burl)
1851 # Look for embedded Vevo player
1853 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1854 if mobj is not None:
1855 return self.url_result(mobj.group('url'))
1857 # Look for embedded Viddler player
1859 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1861 if mobj is not None:
1862 return self.url_result(mobj.group('url'))
1864 # Look for NYTimes player
1866 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1868 if mobj is not None:
1869 return self.url_result(mobj.group('url'))
1871 # Look for Libsyn player
1873 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1874 if mobj is not None:
1875 return self.url_result(mobj.group('url'))
1877 # Look for Ooyala videos
1878 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1879 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1880 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1881 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1882 if mobj is not None:
1883 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1885 # Look for multiple Ooyala embeds on SBN network websites
1886 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1887 if mobj is not None:
1888 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1890 return _playlist_from_matches(
1891 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1893 # Look for Aparat videos
1894 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1895 if mobj is not None:
1896 return self.url_result(mobj.group(1), 'Aparat')
1898 # Look for MPORA videos
1899 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1900 if mobj is not None:
1901 return self.url_result(mobj.group(1), 'Mpora')
1903 # Look for embedded NovaMov-based player
1905 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1906 (?P<url>http://(?:(?:embed|www)\.)?
1908 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1909 videoweed\.(?:es|com)|
1910 movshare\.(?:net|sx|ag)|
1911 divxstage\.(?:eu|net|ch|co|at|ag))
1912 /embed\.php.+?)\1''', webpage)
1913 if mobj is not None:
1914 return self.url_result(mobj.group('url'))
1916 # Look for embedded Facebook player
1917 facebook_url = FacebookIE._extract_url(webpage)
1918 if facebook_url is not None:
1919 return self.url_result(facebook_url, 'Facebook')
1921 # Look for embedded VK player
1922 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1923 if mobj is not None:
1924 return self.url_result(mobj.group('url'), 'VK')
1926 # Look for embedded Odnoklassniki player
1927 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1928 if mobj is not None:
1929 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1931 # Look for embedded ivi player
1932 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1933 if mobj is not None:
1934 return self.url_result(mobj.group('url'), 'Ivi')
1936 # Look for embedded Huffington Post player
1938 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1939 if mobj is not None:
1940 return self.url_result(mobj.group('url'), 'HuffPost')
1943 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1944 if mobj is not None:
1945 return self.url_result(mobj.group('url'))
1946 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1947 if mobj is not None:
1948 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1950 # Look for funnyordie embed
1951 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1953 return _playlist_from_matches(
1954 matches, getter=unescapeHTML, ie='FunnyOrDie')
1956 # Look for BBC iPlayer embed
1957 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1959 return _playlist_from_matches(matches, ie='BBCCoUk')
1961 # Look for embedded RUTV player
1962 rutv_url = RUTVIE._extract_url(webpage)
1964 return self.url_result(rutv_url, 'RUTV')
1966 # Look for embedded TVC player
1967 tvc_url = TVCIE._extract_url(webpage)
1969 return self.url_result(tvc_url, 'TVC')
1971 # Look for embedded SportBox player
1972 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1974 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1976 # Look for embedded XHamster player
1977 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1979 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1981 # Look for embedded TNAFlixNetwork player
1982 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1984 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1986 # Look for embedded PornHub player
1987 pornhub_urls = PornHubIE._extract_urls(webpage)
1989 return _playlist_from_matches(pornhub_urls, ie=PornHubIE.ie_key())
1991 # Look for embedded DrTuber player
1992 drtuber_urls = DrTuberIE._extract_urls(webpage)
1994 return _playlist_from_matches(drtuber_urls, ie=DrTuberIE.ie_key())
1996 # Look for embedded RedTube player
1997 redtube_urls = RedTubeIE._extract_urls(webpage)
1999 return _playlist_from_matches(redtube_urls, ie=RedTubeIE.ie_key())
2001 # Look for embedded Tvigle player
2003 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2004 if mobj is not None:
2005 return self.url_result(mobj.group('url'), 'Tvigle')
2007 # Look for embedded TED player
2009 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2010 if mobj is not None:
2011 return self.url_result(mobj.group('url'), 'TED')
2013 # Look for embedded Ustream videos
2015 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
2016 if mobj is not None:
2017 return self.url_result(mobj.group('url'), 'Ustream')
2019 # Look for embedded arte.tv player
2021 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2023 if mobj is not None:
2024 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2026 # Look for embedded francetv player
2028 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2030 if mobj is not None:
2031 return self.url_result(mobj.group('url'))
2033 # Look for embedded smotri.com player
2034 smotri_url = SmotriIE._extract_url(webpage)
2036 return self.url_result(smotri_url, 'Smotri')
2038 # Look for embedded Myvi.ru player
2039 myvi_url = MyviIE._extract_url(webpage)
2041 return self.url_result(myvi_url)
2043 # Look for embedded soundcloud player
2044 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2046 return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2048 # Look for embedded mtvservices player
2049 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2051 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2053 # Look for embedded yahoo player
2055 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2057 if mobj is not None:
2058 return self.url_result(mobj.group('url'), 'Yahoo')
2060 # Look for embedded sbs.com.au player
2064 <meta\s+property="og:video"\s+content=|
2067 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2069 if mobj is not None:
2070 return self.url_result(mobj.group('url'), 'SBS')
2072 # Look for embedded Cinchcast player
2074 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2076 if mobj is not None:
2077 return self.url_result(mobj.group('url'), 'Cinchcast')
2080 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2084 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2086 if mobj is not None:
2087 return self.url_result(mobj.group('url'), 'MLB')
2090 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2092 if mobj is not None:
2093 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2096 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2098 if mobj is not None:
2099 return self.url_result(mobj.group('url'), 'Livestream')
2101 # Look for Zapiks embed
2103 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2104 if mobj is not None:
2105 return self.url_result(mobj.group('url'), 'Zapiks')
2107 # Look for Kaltura embeds
2108 kaltura_url = KalturaIE._extract_url(webpage)
2110 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2112 # Look for Eagle.Platform embeds
2113 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2114 if eagleplatform_url:
2115 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2117 # Look for ClipYou (uses Eagle.Platform) embeds
2119 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2120 if mobj is not None:
2121 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2123 # Look for Pladform embeds
2124 pladform_url = PladformIE._extract_url(webpage)
2126 return self.url_result(pladform_url)
2128 # Look for Videomore embeds
2129 videomore_url = VideomoreIE._extract_url(webpage)
2131 return self.url_result(videomore_url)
2133 # Look for Webcaster embeds
2134 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2136 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2138 # Look for Playwire embeds
2140 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2141 if mobj is not None:
2142 return self.url_result(mobj.group('url'))
2144 # Look for 5min embeds
2146 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2147 if mobj is not None:
2148 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2150 # Look for Crooks and Liars embeds
2152 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2153 if mobj is not None:
2154 return self.url_result(mobj.group('url'))
2156 # Look for NBC Sports VPlayer embeds
2157 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2159 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2161 # Look for NBC News embeds
2162 nbc_news_embed_url = re.search(
2163 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2164 if nbc_news_embed_url:
2165 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2167 # Look for Google Drive embeds
2168 google_drive_url = GoogleDriveIE._extract_url(webpage)
2169 if google_drive_url:
2170 return self.url_result(google_drive_url, 'GoogleDrive')
2172 # Look for UDN embeds
2174 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2175 if mobj is not None:
2176 return self.url_result(
2177 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2179 # Look for Senate ISVP iframe
2180 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2182 return self.url_result(senate_isvp_url, 'SenateISVP')
2184 # Look for Dailymotion Cloud videos
2185 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2187 return self.url_result(dmcloud_url, 'DailymotionCloud')
2189 # Look for OnionStudios embeds
2190 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2191 if onionstudios_url:
2192 return self.url_result(onionstudios_url)
2194 # Look for ViewLift embeds
2195 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2197 return self.url_result(viewlift_url)
2199 # Look for JWPlatform embeds
2200 jwplatform_url = JWPlatformIE._extract_url(webpage)
2202 return self.url_result(jwplatform_url, 'JWPlatform')
2204 # Look for Digiteka embeds
2205 digiteka_url = DigitekaIE._extract_url(webpage)
2207 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2209 # Look for Arkena embeds
2210 arkena_url = ArkenaIE._extract_url(webpage)
2212 return self.url_result(arkena_url, ArkenaIE.ie_key())
2214 # Look for Limelight embeds
2215 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2219 'Channel': 'channel',
2220 'ChannelList': 'channel_list',
2222 return self.url_result('limelight:%s:%s' % (
2223 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2227 <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2229 name=(["\'])flashVars\2[^>]+
2230 value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2233 return self.url_result('limelight:media:%s' % mobj.group('id'))
2235 # Look for AdobeTVVideo embeds
2237 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2239 if mobj is not None:
2240 return self.url_result(
2241 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2244 # Look for Vine embeds
2246 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2248 if mobj is not None:
2249 return self.url_result(
2250 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2252 # Look for VODPlatform embeds
2254 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2256 if mobj is not None:
2257 return self.url_result(
2258 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2260 # Look for Mangomolo embeds
2262 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2264 video\?.*?\bid=(?P<video_id>\d+)|
2265 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2266 ).+?)\1''', webpage)
2267 if mobj is not None:
2269 '_type': 'url_transparent',
2270 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2271 'title': video_title,
2272 'description': video_description,
2273 'thumbnail': video_thumbnail,
2274 'uploader': video_uploader,
2276 video_id = mobj.group('video_id')
2279 'ie_key': 'MangomoloVideo',
2284 'ie_key': 'MangomoloLive',
2285 'id': mobj.group('channel_id'),
2289 # Look for Instagram embeds
2290 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2291 if instagram_embed_url is not None:
2292 return self.url_result(
2293 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2295 # Look for LiveLeak embeds
2296 liveleak_url = LiveLeakIE._extract_url(webpage)
2298 return self.url_result(liveleak_url, 'LiveLeak')
2300 # Look for 3Q SDN embeds
2301 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2304 '_type': 'url_transparent',
2305 'ie_key': ThreeQSDNIE.ie_key(),
2306 'url': self._proto_relative_url(threeqsdn_url),
2307 'title': video_title,
2308 'description': video_description,
2309 'thumbnail': video_thumbnail,
2310 'uploader': video_uploader,
2313 # Look for VBOX7 embeds
2314 vbox7_url = Vbox7IE._extract_url(webpage)
2316 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2318 # Look for DBTV embeds
2319 dbtv_urls = DBTVIE._extract_urls(webpage)
2321 return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
2323 # Looking for http://schema.org/VideoObject
2324 json_ld = self._search_json_ld(
2325 webpage, video_id, default={}, expected_type='VideoObject')
2326 if json_ld.get('url'):
2328 'title': video_title or info_dict['title'],
2329 'description': video_description,
2330 'thumbnail': video_thumbnail,
2331 'age_limit': age_limit
2333 info_dict.update(json_ld)
2336 # Look for HTML5 media
2337 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2339 for entry in entries:
2342 'title': video_title,
2344 self._sort_formats(entry['formats'])
2345 return self.playlist_result(entries)
2347 def check_video(vurl):
2348 if YoutubeIE.suitable(vurl):
2350 vpath = compat_urlparse.urlparse(vurl).path
2351 vext = determine_ext(vpath)
2352 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
2354 def filter_video(urls):
2355 return list(filter(check_video, urls))
2357 # Start with something easy: JW Player in SWFObject
2358 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2360 # Look for gorilla-vid style embedding
2361 found = filter_video(re.findall(r'''(?sx)
2365 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2368 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2370 # Broaden the search a little bit
2371 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2373 # Broaden the findall a little bit: JWPlayer JS loader
2374 found = filter_video(re.findall(
2375 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2378 found = filter_video(re.findall(r'''(?xs)
2379 flowplayer\("[^"]+",\s*
2381 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2382 ["']?url["']?\s*:\s*["']([^"']+)["']
2387 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2389 # Try to find twitter cards info
2390 # twitter:player:stream should be checked before twitter:player since
2391 # it is expected to contain a raw stream (see
2392 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2393 found = filter_video(re.findall(
2394 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2396 # We look for Open Graph info:
2397 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2398 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2399 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2400 if m_video_type is not None:
2401 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2403 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2405 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2406 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2409 # Look also in Refresh HTTP header
2410 refresh_header = head_response.headers.get('Refresh')
2412 # In python 2 response HTTP headers are bytestrings
2413 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2414 refresh_header = refresh_header.decode('iso-8859-1')
2415 found = re.search(REDIRECT_REGEX, refresh_header)
2417 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2418 self.report_following_redirect(new_url)
2425 # twitter:player is a https URL to iframe player that may or may not
2426 # be supported by youtube-dl thus this is checked the very last (see
2427 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2428 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2430 return self.url_result(embed_url)
2433 raise UnsupportedError(url)
2436 for video_url in orderedSet(found):
2437 video_url = unescapeHTML(video_url)
2438 video_url = video_url.replace('\\/', '/')
2439 video_url = compat_urlparse.urljoin(url, video_url)
2440 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2442 # Sometimes, jwplayer extraction will result in a YouTube URL
2443 if YoutubeIE.suitable(video_url):
2444 entries.append(self.url_result(video_url, 'Youtube'))
2447 # here's a fun little line of code for you:
2448 video_id = os.path.splitext(video_id)[0]
2452 'uploader': video_uploader,
2453 'title': video_title,
2454 'age_limit': age_limit,
2457 ext = determine_ext(video_url)
2459 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2461 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2463 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2465 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2467 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2468 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2469 # Just matching .ism/manifest is not enough to be reliably sure
2470 # whether it's actually an ISM manifest or some other streaming
2471 # manifest since there are various streaming URL formats
2472 # possible (see [1]) as well as some other shenanigans like
2473 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2475 # Thus the most reasonable way to solve this is to delegate
2476 # to generic extractor in order to look into the contents of
2477 # the manifest itself.
2478 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2479 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2480 entry_info_dict = self.url_result(
2481 smuggle_url(video_url, {'to_generic': True}),
2484 entry_info_dict['url'] = video_url
2486 if entry_info_dict.get('formats'):
2487 self._sort_formats(entry_info_dict['formats'])
2489 entries.append(entry_info_dict)
2491 if len(entries) == 1:
2494 for num, e in enumerate(entries, start=1):
2495 # 'url' results don't have a title
2496 if e.get('title') is not None:
2497 e['title'] = '%s (%d)' % (e['title'], num)
2499 '_type': 'playlist',