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
,
33 from .brightcove
import (
37 from .nbc
import NBCSportsVPlayerIE
38 from .ooyala
import OoyalaIE
39 from .rutv
import RUTVIE
40 from .tvc
import TVCIE
41 from .sportbox
import SportBoxEmbedIE
42 from .smotri
import SmotriIE
43 from .myvi
import MyviIE
44 from .condenast
import CondeNastIE
45 from .udn
import UDNEmbedIE
46 from .senateisvp
import SenateISVPIE
47 from .svt
import SVTIE
48 from .pornhub
import PornHubIE
49 from .xhamster
import XHamsterEmbedIE
50 from .tnaflix
import TNAFlixNetworkEmbedIE
51 from .vimeo
import VimeoIE
52 from .dailymotion
import DailymotionCloudIE
53 from .onionstudios
import OnionStudiosIE
54 from .viewlift
import ViewLiftEmbedIE
55 from .screenwavemedia
import ScreenwaveMediaIE
56 from .mtv
import MTVServicesEmbeddedIE
57 from .pladform
import PladformIE
58 from .videomore
import VideomoreIE
59 from .googledrive
import GoogleDriveIE
60 from .jwplatform
import JWPlatformIE
61 from .digiteka
import DigitekaIE
62 from .instagram
import InstagramIE
63 from .liveleak
import LiveLeakIE
64 from .threeqsdn
import ThreeQSDNIE
65 from .theplatform
import ThePlatformIE
66 from .vessel
import VesselIE
69 class GenericIE(InfoExtractor
):
70 IE_DESC
= 'Generic downloader that works on some sites'
74 # Direct link to a video
76 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
77 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
82 'upload_date': '20100513',
85 # Direct link to media delivered compressed (until Accept-Encoding is *)
87 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
88 'md5': '128c42e68b13950268b648275386fc74',
90 'id': 'FictionJunction-Parallel_Hearts',
92 'title': 'FictionJunction-Parallel_Hearts',
93 'upload_date': '20140522',
95 'expected_warnings': [
96 'URL could be a direct video link, returning it as such.'
99 # Direct download with broken HEAD
101 'url': 'http://ai-radio.org:8000/radio.opus',
108 'skip_download': True, # infinite live stream
110 'expected_warnings': [
111 r
'501.*Not Implemented',
115 # Direct link with incorrect MIME type
117 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
118 'md5': '4ccbebe5f36706d85221f204d7eb5913',
120 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
121 'id': '5_Lennart_Poettering_-_Systemd',
123 'title': '5_Lennart_Poettering_-_Systemd',
124 'upload_date': '20141120',
126 'expected_warnings': [
127 'URL could be a direct video link, returning it as such.'
132 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
134 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
135 'title': 'Zero Punctuation',
136 'description': 're:.*groundbreaking video review series.*'
138 'playlist_mincount': 11,
140 # RSS feed with enclosure
142 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
144 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
146 'upload_date': '20150228',
147 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
150 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
152 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
156 'title': 'Automatics, robotics and biocybernetics',
157 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
158 'upload_date': '20130627',
159 'formats': 'mincount:16',
160 'subtitles': 'mincount:1',
163 'force_generic_extractor': True,
164 'skip_download': True,
167 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
169 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
174 'formats': 'mincount:1',
177 'skip_download': True,
180 # SMIL from https://www.restudy.dk/video/play/id/1637
182 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
186 'title': 'video_1637',
187 'formats': 'mincount:3',
190 'skip_download': True,
193 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
195 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
197 'id': 'smil-service',
199 'title': 'smil-service',
200 'formats': 'mincount:1',
203 'skip_download': True,
206 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
208 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
212 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
213 'formats': 'mincount:3',
216 'skip_download': True,
219 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
221 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
223 'id': 'mZlp2ctYIUEB',
225 'title': 'Tikibad ontruimd wegens brand',
226 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
227 'thumbnail': 're:^https?://.*\.jpg$',
231 'skip_download': True,
234 # MPD from http://dash-mse-test.appspot.com/media.html
236 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
237 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
239 'id': 'car-20120827-manifest',
241 'title': 'car-20120827-manifest',
242 'formats': 'mincount:9',
243 'upload_date': '20130904',
246 'format': 'bestvideo',
249 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
251 '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',
256 'formats': 'mincount:8',
260 'skip_download': True,
263 # m3u8 served with Content-Type: text/plain
265 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
270 'upload_date': '20140720',
271 'formats': 'mincount:11',
275 'skip_download': True,
280 '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',
284 'upload_date': '20130224',
285 'uploader_id': 'TheVerge',
286 'description': 're:^Chris Ziegler takes a look at the\.*',
287 'uploader': 'The Verge',
288 'title': 'First Firefox OS phones side-by-side',
291 'skip_download': False,
295 # redirect in Refresh HTTP header
296 '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',
300 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
301 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
302 'upload_date': '20150917',
303 'uploader_id': 'brtvofficial',
304 'uploader': 'Boiler Room',
307 'skip_download': False,
311 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
312 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
314 'id': '13601338388002',
316 'uploader': 'www.hodiho.fr',
317 'title': 'R\u00e9gis plante sa Jeep',
320 # bandcamp page with custom domain
322 'add_ie': ['Bandcamp'],
323 'url': 'http://bronyrock.com/track/the-pony-mash',
327 'title': 'The Pony Mash',
328 'uploader': 'M_Pallante',
330 'skip': 'There is a limit of 200 free downloads / month for the test song',
332 # embedded brightcove video
333 # it also tests brightcove videos that need to set the 'Referer' in the
336 'add_ie': ['BrightcoveLegacy'],
337 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
339 'id': '2765128793001',
341 'title': 'Le cours de bourse : l’analyse technique',
342 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
343 'uploader': 'BFM BUSINESS',
346 'skip_download': True,
350 # https://github.com/rg3/youtube-dl/issues/2253
351 'url': 'http://bcove.me/i6nfkrc3',
352 'md5': '0ba9446db037002366bab3b3eb30c88c',
354 'id': '3101154703001',
356 'title': 'Still no power',
357 'uploader': 'thestar.com',
358 '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.',
360 'add_ie': ['BrightcoveLegacy'],
363 'url': 'http://www.championat.com/video/football/v/87/87499.html',
364 'md5': 'fb973ecf6e4a78a67453647444222983',
366 'id': '3414141473001',
368 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
369 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
370 'uploader': 'Championat',
374 # https://github.com/rg3/youtube-dl/issues/3541
375 'add_ie': ['BrightcoveLegacy'],
376 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
378 'id': '3866516442001',
380 'title': 'Leer mij vrouwen kennen: Aflevering 1',
381 'description': 'Leer mij vrouwen kennen: Aflevering 1',
382 'uploader': 'SBS Broadcasting',
384 'skip': 'Restricted to Netherlands',
386 'skip_download': True, # m3u8 download
391 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
392 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
394 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
396 'title': '2cc213299525360.mov', # that's what we get
399 'add_ie': ['Ooyala'],
402 # ooyala video embedded with http://player.ooyala.com/iframe.js
403 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
405 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
407 'title': '"Steve Jobs: Man in the Machine" trailer',
408 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
412 'skip_download': True,
417 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
421 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
422 'upload_date': '20140225',
423 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
424 'uploader': 'Tested',
425 'uploader_id': 'testedcom',
427 # No need to test YoutubeIE here
429 'skip_download': True,
434 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
438 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
439 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
444 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
448 'title': 'Охотское море стало целиком российским',
449 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
453 'skip_download': True,
458 '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/',
462 'title': 'Дошкольное воспитание',
467 'url': 'http://www.vestifinance.ru/articles/25753',
470 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
475 'title': 'Госзаказ. День 3',
481 'title': 'Госзаказ. День 2',
487 'title': 'Госзаказ. День 1',
493 'skip_download': True,
498 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
500 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
502 'title': 'Ужастики, русский трейлер (2015)',
503 'thumbnail': 're:^https?://.*\.jpg$',
509 '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',
512 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
514 'playlist_mincount': 7,
518 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
519 'md5': '65fdff94098e4a607385a60c5177c638',
523 'title': 'Hidden miracles of the natural world',
524 'uploader': 'Louie Schwartzberg',
525 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
528 # Embedded Ustream video
530 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
531 'md5': '27b99cdb639c9b12a79bca876a073417',
535 'uploader': 'AU SPA: The NSA and Privacy',
536 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
539 # nowvideo embed hidden behind percent encoding
541 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
542 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
544 'id': '06e53103ca9aa',
546 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
547 'description': 'No description',
552 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
553 'md5': '7653032cbb25bf6c80d80f217055fa43',
555 'id': '048195-004_PLUS7-F',
558 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
559 'upload_date': '20140320',
562 'skip_download': 'Requires rtmpdump'
567 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
571 'title': 'Alcaline, le concert avec Calogero',
572 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
573 'upload_date': '20150226',
574 'timestamp': 1424989860,
579 'skip_download': True,
581 'expected_warnings': [
587 'url': 'http://www.wired.com/2014/04/honda-asimo/',
588 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
590 'id': '53501be369702d3275860000',
592 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
597 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
598 'md5': '441aeeb82eb72c422c7f14ec533999cd',
600 'id': 'k2mm4bCdJ6CQ2i7c8o2',
602 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
603 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
605 'uploader_id': 'xgditw',
606 'upload_date': '20140425',
607 'timestamp': 1398441542,
609 'add_ie': ['Dailymotion'],
613 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
617 'title': 'The NBL Auction 2014',
618 'uploader': 'BADMINTON England',
619 'uploader_id': 'BADMINTONEvents',
620 'upload_date': '20140603',
621 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
623 'add_ie': ['Youtube'],
625 'skip_download': True,
630 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
631 'md5': '35727f82f58c76d996fc188f9755b0d5',
633 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
636 'description': 'Mario\'s life in the fast lane has never looked so good.',
639 # YouTube embed via <data-embed-url="">
641 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
645 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
646 'uploader': 'Gameloft',
647 'uploader_id': 'gameloft',
648 'upload_date': '20140828',
649 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
652 'skip_download': True,
657 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
659 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
661 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
662 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
667 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
669 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
670 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
676 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
681 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
682 'md5': '9d65602bf31c6e20014319c7d07fba27',
684 'id': '5123ea6d5e5a7',
687 'uploader': 'www.handjobhub.com',
688 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
691 # Multiple brightcove videos
692 # https://github.com/rg3/youtube-dl/issues/2283
694 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
696 'id': 'always-never',
697 'title': 'Always / Never - The New Yorker',
701 'extract_flat': False,
702 'skip_download': True,
707 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
708 'md5': '96f09a37e44da40dd083e12d9a683327',
712 'title': 'Ump changes call to ball',
713 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
715 'timestamp': 1401537900,
716 'upload_date': '20140531',
717 'thumbnail': 're:^https?://.*\.jpg$',
722 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
723 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
727 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
728 'description': 'a Paywall Videos video from Remilon',
730 'uploader': 'study.com',
731 'timestamp': 1459678540,
732 'upload_date': '20160403',
733 'filesize': 24687186,
737 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
738 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
742 'title': 'Conversation about Hexagonal Rails Part 1',
743 'description': 'a Martin Fowler video from ThoughtWorks',
745 'uploader': 'thoughtworks.wistia.com',
746 'timestamp': 1401832161,
747 'upload_date': '20140603',
750 # Wistia standard embed (async)
752 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
756 'title': 'Drip Brennan Dunn Workshop',
757 'description': 'a JV Webinars video from getdrip-1',
759 'timestamp': 1463607249,
760 'upload_date': '20160518',
763 'skip_download': True,
768 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
772 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
773 'uploader': 'Sophos Security',
774 'title': 'Chet Chat 171 - Oct 29, 2014',
775 'upload_date': '20141029',
780 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
784 'upload_date': '20141112',
785 'title': 'Rosetta #CometLanding webcast HL 10',
788 # Another Livestream embed, without 'new.' in URL
790 'url': 'https://www.freespeech.org/',
794 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
798 'skip_download': True,
803 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
806 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
808 'playlist_mincount': 2,
812 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
816 'upload_date': '20141126',
817 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
822 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
824 'id': '730m_DandD_1901_512k',
826 'uploader': 'www.abc.net.au',
827 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
830 # embedded viddler video
832 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
836 'uploader': 'deadspin',
837 'title': 'WALL-TO-GORTAT',
838 'timestamp': 1422285291,
839 'upload_date': '20150126',
841 'add_ie': ['Viddler'],
845 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
849 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
850 'description': 'md5:601cb790edd05908957dae8aaa866465',
851 'upload_date': '20150220',
856 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
860 'upload_date': '20150212',
861 'uploader': 'The National Archives UK',
862 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
863 'uploader_id': 'NationalArchives08',
864 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
869 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
870 'playlist_mincount': 5,
872 'id': 'aanslagen-kopenhagen',
873 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
878 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
882 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
885 # Kaltura embed (different embed code)
887 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
891 'upload_date': '20150127',
892 'uploader_id': 'PremierMedia',
894 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
897 # Kaltura embed protected with referrer
899 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
903 'title': 'Violetta - Achter De Schermen - Ruggero',
904 'description': 'Achter de schermen met Ruggero',
905 'timestamp': 1435133761,
906 'upload_date': '20150624',
907 'uploader_id': 'echojecka',
910 # Kaltura embed with single quotes
912 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
917 'timestamp': 1355743100,
918 'upload_date': '20121217',
919 'uploader_id': 'batchUser',
921 'add_ie': ['Kaltura'],
923 # Eagle.Platform embed (generic URL)
925 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
926 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
930 'title': 'Навальный вышел на свободу',
931 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
932 'thumbnail': 're:^https?://.*\.jpg$',
938 # ClipYou (Eagle.Platform) embed (custom URL)
940 'url': 'http://muz-tv.ru/play/7129/',
941 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
945 'title': "'O Sole Mio",
946 'thumbnail': 're:^https?://.*\.jpg$',
953 'url': 'http://muz-tv.ru/kinozal/view/7400/',
957 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
958 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
959 'thumbnail': 're:^https?://.*\.jpg$',
966 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
970 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
971 'thumbnail': 're:^https?://.*\.png$',
977 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
978 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
982 'title': 'Facebook Creates "On This Day" | Crunch Report',
987 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
991 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
996 # Crooks and Liars embed
998 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1002 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1003 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1004 'timestamp': 1428207000,
1005 'upload_date': '20150405',
1006 'uploader': 'Heather',
1009 # Crooks and Liars external embed
1011 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1013 'id': 'MTE3MjUtMzQ2MzA',
1015 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1016 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1017 'timestamp': 1265032391,
1018 'upload_date': '20100201',
1019 'uploader': 'Heather',
1022 # NBC Sports vplayer embed
1024 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1026 'id': 'ln7x1qSThw4k',
1028 'title': "PFT Live: New leader in the 'new-look' defense",
1029 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1030 'uploader': 'NBCU-SPORTS',
1031 'upload_date': '20140107',
1032 'timestamp': 1389118457,
1037 'url': 'https://video.udn.com/news/300346',
1038 'md5': 'fd2060e988c326991037b9aff9df21a6',
1042 'title': '中一中男師變性 全校師生力挺',
1043 'thumbnail': 're:^https?://.*\.jpg$',
1047 'skip_download': True,
1052 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1054 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1056 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1057 'title': 'This is what separates the Excel masters from the wannabes',
1058 'duration': 191.933,
1062 'skip_download': True,
1065 # Contains a SMIL manifest
1067 'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
1071 'title': '+ Football: Lottery Champions League Europe',
1072 'uploader': 'www.telewebion.com',
1076 'skip_download': True,
1079 # Brightcove URL in single quotes
1081 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1082 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1084 'id': '4255764656001',
1086 'title': 'SN Presents: Russell Martin, World Citizen',
1087 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1088 'uploader': 'Rogers Sportsnet',
1089 'uploader_id': '1704050871',
1090 'upload_date': '20150525',
1091 'timestamp': 1432570283,
1094 # Dailymotion Cloud video
1096 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1097 'md5': '49444254273501a64675a7e68c502681',
1099 'id': '5585de919473990de4bee11b',
1101 'title': 'Le débat',
1102 'thumbnail': 're:^https?://.*\.jpe?g$',
1105 # OnionStudios embed
1107 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1111 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1112 'thumbnail': 're:^https?://.*\.jpe?g$',
1113 'uploader': 'ClickHole',
1114 'uploader_id': 'clickhole',
1119 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1121 'id': '74849a00-85a9-11e1-9660-123139220831',
1123 'title': '#whilewewatch',
1126 # AdobeTVVideo embed
1128 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1129 'md5': '43662b577c018ad707a63766462b1e87',
1133 'title': 'New experience with Acrobat DC',
1134 'description': 'New experience with Acrobat DC',
1135 'duration': 248.667,
1138 # ScreenwaveMedia embed
1140 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1141 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1143 'id': 'cinemasnob-55d26273809dd',
1145 'title': 'cinemasnob',
1148 # BrightcoveInPageEmbed embed
1150 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1152 'id': '4238694884001',
1154 'title': 'Tabletop: Dread, Last Thoughts',
1155 'description': 'Tabletop: Dread, Last Thoughts',
1159 # JWPlayer with M3U8
1161 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1165 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1166 'uploader': 'ren.tv',
1170 'skip_download': True,
1173 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1174 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1176 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1178 'id': '4785848093001',
1180 'title': 'The Cardinal Pell Interview',
1181 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1182 'uploader': 'GlobeCast Australia - GlobeStream',
1183 'uploader_id': '2733773828001',
1184 'upload_date': '20160304',
1185 'timestamp': 1457083087,
1189 'skip_download': True,
1192 # Another form of arte.tv embed
1194 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1195 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1197 'id': '030273-562_PLUS7-F',
1199 'title': 'ARTE Reportage - Nulle part, en France',
1200 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1201 'upload_date': '20160409',
1206 'url': 'http://www.wykop.pl/link/3088787/',
1207 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1209 'id': '874_1459135191',
1211 'title': 'Man shows poor quality of new apartment building',
1212 'description': 'The wall is like a sand pile.',
1213 'uploader': 'Lake8737',
1216 # Duplicated embedded video URLs
1218 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1220 'id': '149298443_480_16c25b74_2',
1222 'title': 'vs. Blue Orange Spring Game',
1223 'uploader': 'www.hudl.com',
1228 def report_following_redirect(self
, new_url
):
1229 """Report information extraction."""
1230 self
._downloader
.to_screen('[redirect] Following redirect to %s' % new_url
)
1232 def _extract_rss(self
, url
, video_id
, doc
):
1233 playlist_title
= doc
.find('./channel/title').text
1234 playlist_desc_el
= doc
.find('./channel/description')
1235 playlist_desc
= None if playlist_desc_el
is None else playlist_desc_el
.text
1238 for it
in doc
.findall('./channel/item'):
1239 next_url
= xpath_text(it
, 'link', fatal
=False)
1241 enclosure_nodes
= it
.findall('./enclosure')
1242 for e
in enclosure_nodes
:
1243 next_url
= e
.attrib
.get('url')
1253 'title': it
.find('title').text
,
1257 '_type': 'playlist',
1259 'title': playlist_title
,
1260 'description': playlist_desc
,
1264 def _extract_camtasia(self
, url
, video_id
, webpage
):
1265 """ Returns None if no camtasia video can be found. """
1267 camtasia_cfg
= self
._search
_regex
(
1268 r
'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1269 webpage
, 'camtasia configuration file', default
=None)
1270 if camtasia_cfg
is None:
1273 title
= self
._html
_search
_meta
('DC.title', webpage
, fatal
=True)
1275 camtasia_url
= compat_urlparse
.urljoin(url
, camtasia_cfg
)
1276 camtasia_cfg
= self
._download
_xml
(
1277 camtasia_url
, video_id
,
1278 note
='Downloading camtasia configuration',
1279 errnote
='Failed to download camtasia configuration')
1280 fileset_node
= camtasia_cfg
.find('./playlist/array/fileset')
1283 for n
in fileset_node
.getchildren():
1284 url_n
= n
.find('./uri')
1289 'id': os
.path
.splitext(url_n
.text
.rpartition('/')[2])[0],
1290 'title': '%s - %s' % (title
, n
.tag
),
1291 'url': compat_urlparse
.urljoin(url
, url_n
.text
),
1292 'duration': float_or_none(n
.find('./duration').text
),
1296 '_type': 'playlist',
1301 def _real_extract(self
, url
):
1302 if url
.startswith('//'):
1305 'url': self
.http_scheme() + url
,
1308 parsed_url
= compat_urlparse
.urlparse(url
)
1309 if not parsed_url
.scheme
:
1310 default_search
= self
._downloader
.params
.get('default_search')
1311 if default_search
is None:
1312 default_search
= 'fixup_error'
1314 if default_search
in ('auto', 'auto_warning', 'fixup_error'):
1316 self
._downloader
.report_warning('The url doesn\'t specify the protocol, trying with http')
1317 return self
.url_result('http://' + url
)
1318 elif default_search
!= 'fixup_error':
1319 if default_search
== 'auto_warning':
1320 if re
.match(r
'^(?:url|URL)$', url
):
1321 raise ExtractorError(
1322 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url
,
1325 self
._downloader
.report_warning(
1326 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url
)
1327 return self
.url_result('ytsearch:' + url
)
1329 if default_search
in ('error', 'fixup_error'):
1330 raise ExtractorError(
1331 '%r is not a valid URL. '
1332 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1333 % (url
, url
), expected
=True)
1335 if ':' not in default_search
:
1336 default_search
+= ':'
1337 return self
.url_result(default_search
+ url
)
1339 url
, smuggled_data
= unsmuggle_url(url
)
1340 force_videoid
= None
1341 is_intentional
= smuggled_data
and smuggled_data
.get('to_generic')
1342 if smuggled_data
and 'force_videoid' in smuggled_data
:
1343 force_videoid
= smuggled_data
['force_videoid']
1344 video_id
= force_videoid
1346 video_id
= compat_urllib_parse_unquote(os
.path
.splitext(url
.rstrip('/').split('/')[-1])[0])
1348 self
.to_screen('%s: Requesting header' % video_id
)
1350 head_req
= HEADRequest(url
)
1351 head_response
= self
._request
_webpage
(
1353 note
=False, errnote
='Could not send HEAD request to %s' % url
,
1356 if head_response
is not False:
1357 # Check for redirect
1358 new_url
= head_response
.geturl()
1360 self
.report_following_redirect(new_url
)
1362 new_url
= smuggle_url(
1363 new_url
, {'force_videoid': force_videoid}
)
1364 return self
.url_result(new_url
)
1366 full_response
= None
1367 if head_response
is False:
1368 request
= sanitized_Request(url
)
1369 request
.add_header('Accept-Encoding', '*')
1370 full_response
= self
._request
_webpage
(request
, video_id
)
1371 head_response
= full_response
1375 'title': compat_urllib_parse_unquote(os
.path
.splitext(url_basename(url
))[0]),
1376 'upload_date': unified_strdate(head_response
.headers
.get('Last-Modified'))
1379 # Check for direct link to a video
1380 content_type
= head_response
.headers
.get('Content-Type', '').lower()
1381 m
= re
.match(r
'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type
)
1383 format_id
= m
.group('format_id')
1384 if format_id
.endswith('mpegurl'):
1385 formats
= self
._extract
_m
3u8_formats
(url
, video_id
, 'mp4')
1386 elif format_id
== 'f4m':
1387 formats
= self
._extract
_f
4m
_formats
(url
, video_id
)
1390 'format_id': m
.group('format_id'),
1392 'vcodec': 'none' if m
.group('type') == 'audio' else None
1394 info_dict
['direct'] = True
1395 self
._sort
_formats
(formats
)
1396 info_dict
['formats'] = formats
1399 if not self
._downloader
.params
.get('test', False) and not is_intentional
:
1400 force
= self
._downloader
.params
.get('force_generic_extractor', False)
1401 self
._downloader
.report_warning(
1402 '%s on generic information extractor.' % ('Forcing' if force
else 'Falling back'))
1404 if not full_response
:
1405 request
= sanitized_Request(url
)
1406 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1407 # making it impossible to download only chunk of the file (yet we need only 512kB to
1408 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1409 # that will always result in downloading the whole file that is not desirable.
1410 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1411 # to accept raw bytes and being able to download only a chunk.
1412 # It may probably better to solve this by checking Content-Type for application/octet-stream
1413 # after HEAD request finishes, but not sure if we can rely on this.
1414 request
.add_header('Accept-Encoding', '*')
1415 full_response
= self
._request
_webpage
(request
, video_id
)
1417 first_bytes
= full_response
.read(512)
1419 # Is it an M3U playlist?
1420 if first_bytes
.startswith(b
'#EXTM3U'):
1421 info_dict
['formats'] = self
._extract
_m
3u8_formats
(url
, video_id
, 'mp4')
1422 self
._sort
_formats
(info_dict
['formats'])
1425 # Maybe it's a direct link to a video?
1426 # Be careful not to download the whole thing!
1427 if not is_html(first_bytes
):
1428 self
._downloader
.report_warning(
1429 'URL could be a direct video link, returning it as such.')
1436 webpage
= self
._webpage
_read
_content
(
1437 full_response
, url
, video_id
, prefix
=first_bytes
)
1439 self
.report_extraction(video_id
)
1441 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1443 doc
= compat_etree_fromstring(webpage
.encode('utf-8'))
1444 if doc
.tag
== 'rss':
1445 return self
._extract
_rss
(url
, video_id
, doc
)
1446 elif re
.match(r
'^(?:{[^}]+})?smil$', doc
.tag
):
1447 smil
= self
._parse
_smil
(doc
, url
, video_id
)
1448 self
._sort
_formats
(smil
['formats'])
1450 elif doc
.tag
== '{http://xspf.org/ns/0/}playlist':
1451 return self
.playlist_result(self
._parse
_xspf
(doc
, video_id
), video_id
)
1452 elif re
.match(r
'(?i)^(?:{[^}]+})?MPD$', doc
.tag
):
1453 info_dict
['formats'] = self
._parse
_mpd
_formats
(
1454 doc
, video_id
, mpd_base_url
=url
.rpartition('/')[0])
1455 self
._sort
_formats
(info_dict
['formats'])
1457 elif re
.match(r
'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc
.tag
):
1458 info_dict
['formats'] = self
._parse
_f
4m
_formats
(doc
, url
, video_id
)
1459 self
._sort
_formats
(info_dict
['formats'])
1461 except compat_xml_parse_error
:
1464 # Is it a Camtasia project?
1465 camtasia_res
= self
._extract
_camtasia
(url
, video_id
, webpage
)
1466 if camtasia_res
is not None:
1469 # Sometimes embedded video player is hidden behind percent encoding
1470 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1471 # Unescaping the whole page allows to handle those cases in a generic way
1472 webpage
= compat_urllib_parse_unquote(webpage
)
1474 # it's tempting to parse this further, but you would
1475 # have to take into account all the variations like
1476 # Video Title - Site Name
1477 # Site Name | Video Title
1478 # Video Title - Tagline | Site Name
1479 # and so on and so forth; it's just not practical
1480 video_title
= self
._og
_search
_title
(
1481 webpage
, default
=None) or self
._html
_search
_regex
(
1482 r
'(?s)<title>(.*?)</title>', webpage
, 'video title',
1485 # Try to detect age limit automatically
1486 age_limit
= self
._rta
_search
(webpage
)
1487 # And then there are the jokers who advertise that they use RTA,
1488 # but actually don't.
1489 AGE_LIMIT_MARKERS
= [
1490 r
'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1492 if any(re
.search(marker
, webpage
) for marker
in AGE_LIMIT_MARKERS
):
1495 # video uploader is domain name
1496 video_uploader
= self
._search
_regex
(
1497 r
'^(?:https?://)?([^/]*)/.*', url
, 'video uploader')
1499 video_description
= self
._og
_search
_description
(webpage
, default
=None)
1500 video_thumbnail
= self
._og
_search
_thumbnail
(webpage
, default
=None)
1503 def _playlist_from_matches(matches
, getter
=None, ie
=None):
1505 self
.url_result(self
._proto
_relative
_url
(getter(m
) if getter
else m
), ie
)
1507 return self
.playlist_result(
1508 urlrs
, playlist_id
=video_id
, playlist_title
=video_title
)
1510 # Look for Brightcove Legacy Studio embeds
1511 bc_urls
= BrightcoveLegacyIE
._extract
_brightcove
_urls
(webpage
)
1513 self
.to_screen('Brightcove video detected.')
1516 'url': smuggle_url(bc_url
, {'Referer': url}
),
1517 'ie_key': 'BrightcoveLegacy'
1518 } for bc_url
in bc_urls
]
1521 '_type': 'playlist',
1522 'title': video_title
,
1527 # Look for Brightcove New Studio embeds
1528 bc_urls
= BrightcoveNewIE
._extract
_urls
(webpage
)
1530 return _playlist_from_matches(bc_urls
, ie
='BrightcoveNew')
1532 # Look for ThePlatform embeds
1533 tp_urls
= ThePlatformIE
._extract
_urls
(webpage
)
1535 return _playlist_from_matches(tp_urls
, ie
='ThePlatform')
1537 # Look for Vessel embeds
1538 vessel_urls
= VesselIE
._extract
_urls
(webpage
)
1540 return _playlist_from_matches(vessel_urls
, ie
=VesselIE
.ie_key())
1542 # Look for embedded rtl.nl player
1543 matches
= re
.findall(
1544 r
'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1547 return _playlist_from_matches(matches
, ie
='RtlNl')
1549 vimeo_url
= VimeoIE
._extract
_vimeo
_url
(url
, webpage
)
1550 if vimeo_url
is not None:
1551 return self
.url_result(vimeo_url
)
1553 vid_me_embed_url
= self
._search
_regex
(
1554 r
'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1555 webpage, 'vid.me embed', default=None)
1556 if vid_me_embed_url is not None:
1557 return self.url_result(vid_me_embed_url, 'Vidme')
1559 # Look for embedded YouTube player
1560 matches = re.findall(r'''(?x)
1569 (?P
<url
>(?
:https?
:)?
//(?
:www\
.)?
youtube(?
:-nocookie
)?\
.com
/
1573 return _playlist_from_matches(
1574 matches, lambda m: unescapeHTML(m[1]))
1576 # Look for lazyYT YouTube embed
1577 matches = re.findall(
1578 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1580 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1582 # Look for embedded Dailymotion player
1583 matches = re.findall(
1584 r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
1586 return _playlist_from_matches(
1587 matches, lambda m: unescapeHTML(m[1]))
1589 # Look for embedded Dailymotion playlist player (#3822)
1591 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1593 playlists = re.findall(
1594 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1596 return _playlist_from_matches(
1597 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1599 # Look for embedded Wistia player
1601 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1603 embed_url = self._proto_relative_url(
1604 unescapeHTML(match.group('url')))
1606 '_type': 'url_transparent',
1609 'uploader': video_uploader,
1612 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1615 '_type': 'url_transparent',
1616 'url': 'wistia:%s' % match.group('id'),
1618 'uploader': video_uploader,
1623 <script
[^
>]+src
=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1624 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1627 return self.url_result(self._proto_relative_url(
1628 'wistia
:%s' % match.group('id')), 'Wistia
')
1630 # Look for SVT player
1631 svt_url = SVTIE._extract_url(webpage)
1633 return self.url_result(svt_url, 'SVT
')
1635 # Look for embedded condenast player
1636 matches = re.findall(
1637 r'<iframe\s
+(?
:[a
-zA
-Z
-]+="[^"]+"\s+)*?src="(https?
://player\
.cnevids\
.com
/embed
/[^
"]+")',
1641 '_type
': 'playlist
',
1644 'ie_key
': 'CondeNast
',
1646 } for ma in matches],
1647 'title
': video_title,
1651 # Look for Bandcamp pages with custom domain
1652 mobj = re.search(r'<meta
property="og:url"[^
>]*?content
="(.*?bandcamp\.com.*?)"', webpage)
1653 if mobj is not None:
1654 burl = unescapeHTML(mobj.group(1))
1655 # Don't
set the extractor because it can be a track url
or an album
1656 return self
.url_result(burl
)
1658 # Look for embedded Vevo player
1660 r
'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:cache\
.)?vevo\
.com
/.+?
)\
1', webpage)
1661 if mobj is not None:
1662 return self.url_result(mobj.group('url
'))
1664 # Look for embedded Viddler player
1666 r'<(?
:iframe
[^
>]+?src|param
[^
>]+?value
)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1668 if mobj is not None:
1669 return self.url_result(mobj.group('url'))
1671 # Look for NYTimes player
1673 r'<iframe[^>]+src=(["\'])(?P
<url
>(?
:https?
:)?
//graphics8\
.nytimes\
.com
/bcvideo
/[^
/]+/iframe
/embed\
.html
.+?
)\
1>',
1675 if mobj is not None:
1676 return self.url_result(mobj.group('url
'))
1678 # Look for Libsyn player
1680 r'<iframe
[^
>]+src
=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1681 if mobj is not None:
1682 return self.url_result(mobj.group('url'))
1684 # Look for Ooyala videos
1685 mobj = (re.search(r'player\.ooyala\.com/[^"?
]+[?
#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1686 re
.search(r
'OO\.Player\.create\([\'"].*?[\'"],\s
*[\'"](?P<ec>.{32})[\'"]', webpage) or
1687 re.search(r'SBN\
.VideoLinkset\
.ooyala\
([\'"](?P<ec>.{32})[\'"]\
)', webpage) or
1688 re.search(r'data
-ooyala
-video
-id\s
*=\s
*[\'"](?P<ec>.{32})[\'"]', webpage))
1689 if mobj is not None:
1690 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec
'), {'domain': url}))
1692 # Look for multiple Ooyala embeds on SBN network websites
1693 mobj = re.search(r'SBN\
.VideoLinkset\
.entryGroup\
((\
[.*?\
])', webpage)
1694 if mobj is not None:
1695 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1697 return _playlist_from_matches(
1698 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id
'], {'domain': url})), ie='Ooyala
')
1700 # Look for Aparat videos
1701 mobj = re.search(r'<iframe
.*?src
="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1702 if mobj is not None:
1703 return self.url_result(mobj.group(1), 'Aparat')
1705 # Look for MPORA videos
1706 mobj = re.search(r'<iframe .*?src="(http
://mpora\
.(?
:com|de
)/videos
/[^
"]+)"', webpage)
1707 if mobj is not None:
1708 return self.url_result(mobj.group(1), 'Mpora
')
1710 # Look for embedded NovaMov-based player
1712 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1713 (?P<url>http://(?:(?:embed|www)\.)?
1715 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1716 videoweed\.(?:es|com)|
1717 movshare\.(?:net|sx|ag)|
1718 divxstage\.(?:eu|net|ch|co|at|ag))
1719 /embed\.php.+?)\1''', webpage)
1720 if mobj is not None:
1721 return self.url_result(mobj.group('url
'))
1723 # Look for embedded Facebook player
1725 r'<iframe
[^
>]+?src
=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1726 if mobj is not None:
1727 return self.url_result(mobj.group('url'), 'Facebook')
1729 # Look for embedded VK player
1730 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://vk\
.com
/video_ext\
.php
.+?
)\
1', webpage)
1731 if mobj is not None:
1732 return self.url_result(mobj.group('url
'), 'VK
')
1734 # Look for embedded Odnoklassniki player
1735 mobj = re.search(r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1736 if mobj is not None:
1737 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1739 # Look for embedded ivi player
1740 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P
<url
>https?
://(?
:www\
.)?ivi\
.ru
/video
/player
.+?
)\
1', webpage)
1741 if mobj is not None:
1742 return self.url_result(mobj.group('url
'), 'Ivi
')
1744 # Look for embedded Huffington Post player
1746 r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1747 if mobj is not None:
1748 return self.url_result(mobj.group('url'), 'HuffPost')
1751 mobj = re.search(r'class=["\']embedly
-card
["\'][^>]href=["\'](?P
<url
>[^
"\']+)', webpage)
1752 if mobj is not None:
1753 return self.url_result(mobj.group('url'))
1754 mobj = re.search(r'class=["\']embedly
-embed
["\'][^>]src=["\'][^
"\']*url=(?P<url>[^&]+)', webpage)
1755 if mobj is not None:
1756 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1758 # Look for funnyordie embed
1759 matches = re.findall(r'<iframe[^>]+?src="(https?
://(?
:www\
.)?funnyordie\
.com
/embed
/[^
"]+)"', webpage)
1761 return _playlist_from_matches(
1762 matches, getter=unescapeHTML, ie='FunnyOrDie
')
1764 # Look for BBC iPlayer embed
1765 matches = re.findall(r'setPlaylist\
("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\
)', webpage)
1767 return _playlist_from_matches(matches, ie='BBCCoUk
')
1769 # Look for embedded RUTV player
1770 rutv_url = RUTVIE._extract_url(webpage)
1772 return self.url_result(rutv_url, 'RUTV
')
1774 # Look for embedded TVC player
1775 tvc_url = TVCIE._extract_url(webpage)
1777 return self.url_result(tvc_url, 'TVC
')
1779 # Look for embedded SportBox player
1780 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1782 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed
')
1784 # Look for embedded PornHub player
1785 pornhub_url = PornHubIE._extract_url(webpage)
1787 return self.url_result(pornhub_url, 'PornHub
')
1789 # Look for embedded XHamster player
1790 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1792 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed
')
1794 # Look for embedded TNAFlixNetwork player
1795 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1797 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1799 # Look for embedded Tvigle player
1801 r'<iframe
[^
>]+?src
=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1802 if mobj is not None:
1803 return self.url_result(mobj.group('url'), 'Tvigle')
1805 # Look for embedded TED player
1807 r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://embed(?
:-ssl
)?\
.ted\
.com
/.+?
)\
1', webpage)
1808 if mobj is not None:
1809 return self.url_result(mobj.group('url
'), 'TED
')
1811 # Look for embedded Ustream videos
1813 r'<iframe
[^
>]+?src
=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1814 if mobj is not None:
1815 return self.url_result(mobj.group('url'), 'Ustream')
1817 # Look for embedded arte.tv player
1819 r'<(?:script|iframe) [^>]*?src="(?P
<url
>http
://www\
.arte\
.tv
/(?
:playerv2
/embed|arte_vp
/index
)[^
"]+)"',
1821 if mobj is not None:
1822 return self.url_result(mobj.group('url
'), 'ArteTVEmbed
')
1824 # Look for embedded francetv player
1826 r'<iframe
[^
>]+?src
=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1828 if mobj is not None:
1829 return self.url_result(mobj.group('url'))
1831 # Look for embedded smotri.com player
1832 smotri_url = SmotriIE._extract_url(webpage)
1834 return self.url_result(smotri_url, 'Smotri')
1836 # Look for embedded Myvi.ru player
1837 myvi_url = MyviIE._extract_url(webpage)
1839 return self.url_result(myvi_url)
1841 # Look for embedded soundcloud player
1843 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^
"]+"\s
+)*src
="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1845 if mobj is not None:
1846 url = unescapeHTML(mobj.group('url'))
1847 return self.url_result(url)
1849 # Look for embedded vulture.com player
1851 r'<iframe src="(?P
<url
>https?
://video\
.vulture\
.com
/[^
"]+)"',
1853 if mobj is not None:
1854 url = unescapeHTML(mobj.group('url
'))
1855 return self.url_result(url, ie='Vulture
')
1857 # Look for embedded mtvservices player
1858 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1860 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded
')
1862 # Look for embedded yahoo player
1864 r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1866 if mobj is not None:
1867 return self.url_result(mobj.group('url'), 'Yahoo')
1869 # Look for embedded sbs.com.au player
1873 <meta\s+property="og
:video
"\s+content=|
1876 (["\'])(?P
<url
>https?
://(?
:www\
.)?sbs\
.com\
.au
/ondemand
/video
/.+?
)\
1''',
1878 if mobj is not None:
1879 return self.url_result(mobj.group('url'), 'SBS')
1881 # Look for embedded Cinchcast player
1883 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1885 if mobj is not None:
1886 return self.url_result(mobj.group('url'), 'Cinchcast')
1889 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1893 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1895 if mobj is not None:
1896 return self.url_result(mobj.group('url'), 'MLB')
1899 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1901 if mobj is not None:
1902 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1905 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
1907 if mobj is not None:
1908 return self.url_result(mobj.group('url'), 'Livestream')
1910 # Look for Zapiks embed
1912 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1913 if mobj is not None:
1914 return self.url_result(mobj.group('url'), 'Zapiks')
1916 # Look for Kaltura embeds
1917 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?(?P<q1>['\"])wid(?P=q1)\s*:\s*(?P<q2>['\"])_?(?P<partner_id>[^'\"]+)(?P=q2),.*?(?P<q3>['\"])entry_?[Ii]d(?P=q3)\s*:\s*(?P<q4>['\"])(?P<id>[^'\"]+)(?P=q4),", webpage) or
1918 re.search(r'(?s)(?P<q1>["\'])(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?(?P=q1).*?entry_?[Ii]d\s*:\s*(?P<q2>["\'])(?P<id>.+?)(?P=q2)', webpage))
1919 if mobj is not None:
1920 return self.url_result(smuggle_url(
1921 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1922 {'source_url': url}), 'Kaltura')
1924 # Look for Eagle.Platform embeds
1926 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1927 if mobj is not None:
1928 return self.url_result(mobj.group('url'), 'EaglePlatform')
1930 # Look for ClipYou (uses Eagle.Platform) embeds
1932 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1933 if mobj is not None:
1934 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1936 # Look for Pladform embeds
1937 pladform_url = PladformIE._extract_url(webpage)
1939 return self.url_result(pladform_url)
1941 # Look for Videomore embeds
1942 videomore_url = VideomoreIE._extract_url(webpage)
1944 return self.url_result(videomore_url)
1946 # Look for Playwire embeds
1948 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1949 if mobj is not None:
1950 return self.url_result(mobj.group('url'))
1952 # Look for 5min embeds
1954 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1955 if mobj is not None:
1956 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1958 # Look for Crooks and Liars embeds
1960 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1961 if mobj is not None:
1962 return self.url_result(mobj.group('url'))
1964 # Look for NBC Sports VPlayer embeds
1965 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1967 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1969 # Look for Google Drive embeds
1970 google_drive_url = GoogleDriveIE._extract_url(webpage)
1971 if google_drive_url:
1972 return self.url_result(google_drive_url, 'GoogleDrive')
1974 # Look for UDN embeds
1976 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1977 if mobj is not None:
1978 return self.url_result(
1979 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1981 # Look for Senate ISVP iframe
1982 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1984 return self.url_result(senate_isvp_url, 'SenateISVP')
1986 # Look for Dailymotion Cloud videos
1987 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1989 return self.url_result(dmcloud_url, 'DailymotionCloud')
1991 # Look for OnionStudios embeds
1992 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1993 if onionstudios_url:
1994 return self.url_result(onionstudios_url)
1996 # Look for ViewLift embeds
1997 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
1999 return self.url_result(viewlift_url)
2001 # Look for JWPlatform embeds
2002 jwplatform_url = JWPlatformIE._extract_url(webpage)
2004 return self.url_result(jwplatform_url, 'JWPlatform')
2006 # Look for ScreenwaveMedia embeds
2007 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
2008 if mobj is not None:
2009 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
2011 # Look for Digiteka embeds
2012 digiteka_url = DigitekaIE._extract_url(webpage)
2014 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2016 # Look for Limelight embeds
2017 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2021 'Channel': 'channel',
2022 'ChannelList': 'channel_list',
2024 return self.url_result('limelight:%s:%s' % (
2025 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2027 # Look for AdobeTVVideo embeds
2029 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2031 if mobj is not None:
2032 return self.url_result(
2033 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2036 # Look for Vine embeds
2038 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2040 if mobj is not None:
2041 return self.url_result(
2042 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2044 # Look for Instagram embeds
2045 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2046 if instagram_embed_url is not None:
2047 return self.url_result(
2048 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2050 # Look for LiveLeak embeds
2051 liveleak_url = LiveLeakIE._extract_url(webpage)
2053 return self.url_result(liveleak_url, 'LiveLeak')
2055 # Look for 3Q SDN embeds
2056 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2059 '_type': 'url_transparent',
2060 'ie_key': ThreeQSDNIE.ie_key(),
2061 'url': self._proto_relative_url(threeqsdn_url),
2062 'title': video_title,
2063 'description': video_description,
2064 'thumbnail': video_thumbnail,
2065 'uploader': video_uploader,
2068 def check_video(vurl):
2069 if YoutubeIE.suitable(vurl):
2071 vpath = compat_urlparse.urlparse(vurl).path
2072 vext = determine_ext(vpath)
2073 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2075 def filter_video(urls):
2076 return list(filter(check_video, urls))
2078 # Start with something easy: JW Player in SWFObject
2079 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2081 # Look for gorilla-vid style embedding
2082 found = filter_video(re.findall(r'''(?sx
)
2086 jwplayer\s
*\
(\s
*["'][^'"]+["']\s*\)\s*\.setup
2089 ['"]?
file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2091 # Broaden the search a little bit
2092 found = filter_video(re.findall(r'[^A
-Za
-z0
-9]?
(?
:file|source
)=(http
[^
\'"&]*)', webpage))
2094 # Broaden the findall a little bit: JWPlayer JS loader
2095 found = filter_video(re.findall(
2096 r'[^A-Za-z0-9]?(?:file|video_url)["\']?
:\s
*["\'](http(?![^\'"]+\
.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2099 found = filter_video(re.findall(r'''(?xs)
2100 flowplayer\("[^
"]+",\s
*
2102 \s
*\{[^}
]+?
["']?clip["']?\s*:\s*\{\s*
2103 ["']?url
["']?\s*:\s*["']([^"']+)["']
2108 r"cinerama\
.embedPlayer\
(\s
*\'[^
']+\',\s*'([^
']+)'", webpage)
2110 # Try to find twitter cards info
2111 found = filter_video(re.findall(
2112 r'<meta (?:property|name)="twitter
:player
:stream
" (?:content|value)="(.+?
)"', webpage))
2114 # We look for Open Graph info:
2115 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2116 m_video_type = re.findall(r'<meta.*?property="og
:video
:type".*?content="video
/(.*?
)"', webpage)
2117 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2118 if m_video_type is not None:
2119 found = filter_video(re.findall(r'<meta.*?property="og
:video
".*?content="(.*?
)"', webpage))
2122 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?
)["\']', webpage)
2124 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2126 r'(?i
)<meta\s
+(?
=(?
:[a
-z
-]+="[^"]+"\s+)*http-equiv="refresh
")'
2127 r'(?:[a-z-]+="[^
"]+"\s
+)*?content
="%s' % REDIRECT_REGEX,
2130 # Look also in Refresh HTTP header
2131 refresh_header = head_response.headers.get('Refresh')
2133 # In python 2 response HTTP headers are bytestrings
2134 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2135 refresh_header = refresh_header.decode('iso-8859-1')
2136 found = re.search(REDIRECT_REGEX, refresh_header)
2138 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2139 self.report_following_redirect(new_url)
2145 raise UnsupportedError(url)
2148 for video_url in orderedSet(found):
2149 video_url = unescapeHTML(video_url)
2150 video_url = video_url.replace('\\/', '/')
2151 video_url = compat_urlparse.urljoin(url, video_url)
2152 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2154 # Sometimes, jwplayer extraction will result in a YouTube URL
2155 if YoutubeIE.suitable(video_url):
2156 entries.append(self.url_result(video_url, 'Youtube'))
2159 # here's a fun little line of code for you:
2160 video_id = os.path.splitext(video_id)[0]
2164 'uploader': video_uploader,
2165 'title': video_title,
2166 'age_limit': age_limit,
2169 ext = determine_ext(video_url)
2171 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2173 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2175 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2177 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2179 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2181 entry_info_dict['url'] = video_url
2183 if entry_info_dict.get('formats'):
2184 self._sort_formats(entry_info_dict['formats'])
2186 entries.append(entry_info_dict)
2188 if len(entries) == 1:
2191 for num, e in enumerate(entries, start=1):
2192 # 'url' results don't have a title
2193 if e.get('title') is not None:
2194 e['title'] = '%s (%d)' % (e['title'], num)
2196 '_type': 'playlist',