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
67 from .kaltura
import KalturaIE
70 class GenericIE(InfoExtractor
):
71 IE_DESC
= 'Generic downloader that works on some sites'
75 # Direct link to a video
77 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
78 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
83 'upload_date': '20100513',
86 # Direct link to media delivered compressed (until Accept-Encoding is *)
88 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
89 'md5': '128c42e68b13950268b648275386fc74',
91 'id': 'FictionJunction-Parallel_Hearts',
93 'title': 'FictionJunction-Parallel_Hearts',
94 'upload_date': '20140522',
96 'expected_warnings': [
97 'URL could be a direct video link, returning it as such.'
100 # Direct download with broken HEAD
102 'url': 'http://ai-radio.org:8000/radio.opus',
109 'skip_download': True, # infinite live stream
111 'expected_warnings': [
112 r
'501.*Not Implemented',
116 # Direct link with incorrect MIME type
118 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
119 'md5': '4ccbebe5f36706d85221f204d7eb5913',
121 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
122 'id': '5_Lennart_Poettering_-_Systemd',
124 'title': '5_Lennart_Poettering_-_Systemd',
125 'upload_date': '20141120',
127 'expected_warnings': [
128 'URL could be a direct video link, returning it as such.'
133 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
135 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
136 'title': 'Zero Punctuation',
137 'description': 're:.*groundbreaking video review series.*'
139 'playlist_mincount': 11,
141 # RSS feed with enclosure
143 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
145 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
147 'upload_date': '20150228',
148 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
151 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
153 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
157 'title': 'Automatics, robotics and biocybernetics',
158 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
159 'upload_date': '20130627',
160 'formats': 'mincount:16',
161 'subtitles': 'mincount:1',
164 'force_generic_extractor': True,
165 'skip_download': True,
168 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
170 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
175 'formats': 'mincount:1',
178 'skip_download': True,
181 # SMIL from https://www.restudy.dk/video/play/id/1637
183 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
187 'title': 'video_1637',
188 'formats': 'mincount:3',
191 'skip_download': True,
194 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
196 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
198 'id': 'smil-service',
200 'title': 'smil-service',
201 'formats': 'mincount:1',
204 'skip_download': True,
207 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
209 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
213 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
214 'formats': 'mincount:3',
217 'skip_download': True,
220 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
222 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
224 'id': 'mZlp2ctYIUEB',
226 'title': 'Tikibad ontruimd wegens brand',
227 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
228 'thumbnail': 're:^https?://.*\.jpg$',
232 'skip_download': True,
235 # MPD from http://dash-mse-test.appspot.com/media.html
237 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
238 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
240 'id': 'car-20120827-manifest',
242 'title': 'car-20120827-manifest',
243 'formats': 'mincount:9',
244 'upload_date': '20130904',
247 'format': 'bestvideo',
250 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
252 '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',
257 'formats': 'mincount:8',
261 'skip_download': True,
264 # m3u8 served with Content-Type: text/plain
266 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
271 'upload_date': '20140720',
272 'formats': 'mincount:11',
276 'skip_download': True,
281 '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',
285 'upload_date': '20130224',
286 'uploader_id': 'TheVerge',
287 'description': 're:^Chris Ziegler takes a look at the\.*',
288 'uploader': 'The Verge',
289 'title': 'First Firefox OS phones side-by-side',
292 'skip_download': False,
296 # redirect in Refresh HTTP header
297 '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',
301 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
302 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
303 'upload_date': '20150917',
304 'uploader_id': 'brtvofficial',
305 'uploader': 'Boiler Room',
308 'skip_download': False,
312 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
313 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
315 'id': '13601338388002',
317 'uploader': 'www.hodiho.fr',
318 'title': 'R\u00e9gis plante sa Jeep',
321 # bandcamp page with custom domain
323 'add_ie': ['Bandcamp'],
324 'url': 'http://bronyrock.com/track/the-pony-mash',
328 'title': 'The Pony Mash',
329 'uploader': 'M_Pallante',
331 'skip': 'There is a limit of 200 free downloads / month for the test song',
333 # embedded brightcove video
334 # it also tests brightcove videos that need to set the 'Referer' in the
337 'add_ie': ['BrightcoveLegacy'],
338 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
340 'id': '2765128793001',
342 'title': 'Le cours de bourse : l’analyse technique',
343 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
344 'uploader': 'BFM BUSINESS',
347 'skip_download': True,
351 # https://github.com/rg3/youtube-dl/issues/2253
352 'url': 'http://bcove.me/i6nfkrc3',
353 'md5': '0ba9446db037002366bab3b3eb30c88c',
355 'id': '3101154703001',
357 'title': 'Still no power',
358 'uploader': 'thestar.com',
359 '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.',
361 'add_ie': ['BrightcoveLegacy'],
364 'url': 'http://www.championat.com/video/football/v/87/87499.html',
365 'md5': 'fb973ecf6e4a78a67453647444222983',
367 'id': '3414141473001',
369 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
370 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
371 'uploader': 'Championat',
375 # https://github.com/rg3/youtube-dl/issues/3541
376 'add_ie': ['BrightcoveLegacy'],
377 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
379 'id': '3866516442001',
381 'title': 'Leer mij vrouwen kennen: Aflevering 1',
382 'description': 'Leer mij vrouwen kennen: Aflevering 1',
383 'uploader': 'SBS Broadcasting',
385 'skip': 'Restricted to Netherlands',
387 'skip_download': True, # m3u8 download
392 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
393 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
395 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
397 'title': '2cc213299525360.mov', # that's what we get
400 'add_ie': ['Ooyala'],
403 # ooyala video embedded with http://player.ooyala.com/iframe.js
404 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
406 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
408 'title': '"Steve Jobs: Man in the Machine" trailer',
409 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
413 'skip_download': True,
418 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
422 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
423 'upload_date': '20140225',
424 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
425 'uploader': 'Tested',
426 'uploader_id': 'testedcom',
428 # No need to test YoutubeIE here
430 'skip_download': True,
435 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
439 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
440 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
445 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
449 'title': 'Охотское море стало целиком российским',
450 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
454 'skip_download': True,
459 '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/',
463 'title': 'Дошкольное воспитание',
468 'url': 'http://www.vestifinance.ru/articles/25753',
471 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
476 'title': 'Госзаказ. День 3',
482 'title': 'Госзаказ. День 2',
488 'title': 'Госзаказ. День 1',
494 'skip_download': True,
499 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
501 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
503 'title': 'Ужастики, русский трейлер (2015)',
504 'thumbnail': 're:^https?://.*\.jpg$',
510 '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',
513 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
515 'playlist_mincount': 7,
519 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
520 'md5': '65fdff94098e4a607385a60c5177c638',
524 'title': 'Hidden miracles of the natural world',
525 'uploader': 'Louie Schwartzberg',
526 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
529 # Embedded Ustream video
531 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
532 'md5': '27b99cdb639c9b12a79bca876a073417',
536 'uploader': 'AU SPA: The NSA and Privacy',
537 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
540 # nowvideo embed hidden behind percent encoding
542 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
543 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
545 'id': '06e53103ca9aa',
547 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
548 'description': 'No description',
553 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
554 'md5': '7653032cbb25bf6c80d80f217055fa43',
556 'id': '048195-004_PLUS7-F',
559 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
560 'upload_date': '20140320',
563 'skip_download': 'Requires rtmpdump'
568 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
572 'title': 'Alcaline, le concert avec Calogero',
573 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
574 'upload_date': '20150226',
575 'timestamp': 1424989860,
580 'skip_download': True,
582 'expected_warnings': [
588 'url': 'http://www.wired.com/2014/04/honda-asimo/',
589 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
591 'id': '53501be369702d3275860000',
593 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
598 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
599 'md5': '441aeeb82eb72c422c7f14ec533999cd',
601 'id': 'k2mm4bCdJ6CQ2i7c8o2',
603 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
604 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
606 'uploader_id': 'xgditw',
607 'upload_date': '20140425',
608 'timestamp': 1398441542,
610 'add_ie': ['Dailymotion'],
614 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
618 'title': 'The NBL Auction 2014',
619 'uploader': 'BADMINTON England',
620 'uploader_id': 'BADMINTONEvents',
621 'upload_date': '20140603',
622 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
624 'add_ie': ['Youtube'],
626 'skip_download': True,
631 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
632 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
634 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
636 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
637 'description': 'Two valets share their love for movie star Liam Neesons.',
640 # YouTube embed via <data-embed-url="">
642 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
646 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
647 'uploader': 'Gameloft',
648 'uploader_id': 'gameloft',
649 'upload_date': '20140828',
650 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
653 'skip_download': True,
658 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
660 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
662 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
663 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
668 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
670 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
671 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
677 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
682 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
683 'md5': '9d65602bf31c6e20014319c7d07fba27',
685 'id': '5123ea6d5e5a7',
688 'uploader': 'www.handjobhub.com',
689 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
692 # Multiple brightcove videos
693 # https://github.com/rg3/youtube-dl/issues/2283
695 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
697 'id': 'always-never',
698 'title': 'Always / Never - The New Yorker',
702 'extract_flat': False,
703 'skip_download': True,
708 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
709 'md5': '96f09a37e44da40dd083e12d9a683327',
713 'title': 'Ump changes call to ball',
714 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
716 'timestamp': 1401537900,
717 'upload_date': '20140531',
718 'thumbnail': 're:^https?://.*\.jpg$',
723 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
724 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
728 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
729 'description': 'a Paywall Videos video from Remilon',
731 'uploader': 'study.com',
732 'timestamp': 1459678540,
733 'upload_date': '20160403',
734 'filesize': 24687186,
738 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
739 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
743 'title': 'Conversation about Hexagonal Rails Part 1',
744 'description': 'a Martin Fowler video from ThoughtWorks',
746 'uploader': 'thoughtworks.wistia.com',
747 'timestamp': 1401832161,
748 'upload_date': '20140603',
751 # Wistia standard embed (async)
753 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
757 'title': 'Drip Brennan Dunn Workshop',
758 'description': 'a JV Webinars video from getdrip-1',
760 'timestamp': 1463607249,
761 'upload_date': '20160518',
764 'skip_download': True,
769 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
773 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
774 'uploader': 'Sophos Security',
775 'title': 'Chet Chat 171 - Oct 29, 2014',
776 'upload_date': '20141029',
781 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
785 'upload_date': '20141112',
786 'title': 'Rosetta #CometLanding webcast HL 10',
789 # Another Livestream embed, without 'new.' in URL
791 'url': 'https://www.freespeech.org/',
795 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
799 'skip_download': True,
804 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
807 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
809 'playlist_mincount': 2,
813 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
817 'upload_date': '20141126',
818 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
823 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
825 'id': '730m_DandD_1901_512k',
827 'uploader': 'www.abc.net.au',
828 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
831 # embedded viddler video
833 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
837 'uploader': 'deadspin',
838 'title': 'WALL-TO-GORTAT',
839 'timestamp': 1422285291,
840 'upload_date': '20150126',
842 'add_ie': ['Viddler'],
846 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
850 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
851 'description': 'md5:601cb790edd05908957dae8aaa866465',
852 'upload_date': '20150220',
857 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
861 'upload_date': '20150212',
862 'uploader': 'The National Archives UK',
863 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
864 'uploader_id': 'NationalArchives08',
865 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
870 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
871 'playlist_mincount': 5,
873 'id': 'aanslagen-kopenhagen',
874 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
879 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
883 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
886 # Kaltura embed (different embed code)
888 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
892 'upload_date': '20150127',
893 'uploader_id': 'PremierMedia',
895 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
898 # Kaltura embed protected with referrer
900 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
904 'title': 'Violetta - Achter De Schermen - Ruggero',
905 'description': 'Achter de schermen met Ruggero',
906 'timestamp': 1435133761,
907 'upload_date': '20150624',
908 'uploader_id': 'echojecka',
911 # Kaltura embed with single quotes
913 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
918 'timestamp': 1355743100,
919 'upload_date': '20121217',
920 'uploader_id': 'batchUser',
922 'add_ie': ['Kaltura'],
925 # Kaltura embedded via quoted entry_id
926 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
930 'title': '06_matthew_brender_raj_dutt',
931 'timestamp': 1466638791,
932 'upload_date': '20160622',
934 'add_ie': ['Kaltura'],
935 'expected_warnings': [
936 'Could not send HEAD request'
939 'skip_download': True,
942 # Eagle.Platform embed (generic URL)
944 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
945 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
949 'title': 'Навальный вышел на свободу',
950 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
951 'thumbnail': 're:^https?://.*\.jpg$',
957 # ClipYou (Eagle.Platform) embed (custom URL)
959 'url': 'http://muz-tv.ru/play/7129/',
960 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
964 'title': "'O Sole Mio",
965 'thumbnail': 're:^https?://.*\.jpg$',
972 'url': 'http://muz-tv.ru/kinozal/view/7400/',
976 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
977 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
978 'thumbnail': 're:^https?://.*\.jpg$',
985 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
989 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
990 'thumbnail': 're:^https?://.*\.png$',
996 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
997 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1001 'title': 'Facebook Creates "On This Day" | Crunch Report',
1006 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1010 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1015 # Crooks and Liars embed
1017 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1021 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1022 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1023 'timestamp': 1428207000,
1024 'upload_date': '20150405',
1025 'uploader': 'Heather',
1028 # Crooks and Liars external embed
1030 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1032 'id': 'MTE3MjUtMzQ2MzA',
1034 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1035 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1036 'timestamp': 1265032391,
1037 'upload_date': '20100201',
1038 'uploader': 'Heather',
1041 # NBC Sports vplayer embed
1043 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1045 'id': 'ln7x1qSThw4k',
1047 'title': "PFT Live: New leader in the 'new-look' defense",
1048 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1049 'uploader': 'NBCU-SPORTS',
1050 'upload_date': '20140107',
1051 'timestamp': 1389118457,
1056 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1057 'md5': '1aa589c675898ae6d37a17913cf68d66',
1059 'id': '701714499682',
1061 'title': 'PREVIEW: On Assignment: David Letterman',
1062 '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.',
1067 'url': 'https://video.udn.com/news/300346',
1068 'md5': 'fd2060e988c326991037b9aff9df21a6',
1072 'title': '中一中男師變性 全校師生力挺',
1073 'thumbnail': 're:^https?://.*\.jpg$',
1077 'skip_download': True,
1082 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1084 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1086 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1087 'title': 'This is what separates the Excel masters from the wannabes',
1088 'duration': 191.933,
1092 'skip_download': True,
1095 # Brightcove URL in single quotes
1097 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1098 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1100 'id': '4255764656001',
1102 'title': 'SN Presents: Russell Martin, World Citizen',
1103 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1104 'uploader': 'Rogers Sportsnet',
1105 'uploader_id': '1704050871',
1106 'upload_date': '20150525',
1107 'timestamp': 1432570283,
1110 # Dailymotion Cloud video
1112 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1113 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1117 'title': 'Sauvons les abeilles ! - Le débat',
1118 'description': 'md5:d9082128b1c5277987825d684939ca26',
1119 'thumbnail': 're:^https?://.*\.jpe?g$',
1120 'timestamp': 1434970506,
1121 'upload_date': '20150622',
1122 'uploader': 'Public Sénat',
1123 'uploader_id': 'xa9gza',
1126 # OnionStudios embed
1128 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1132 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1133 'thumbnail': 're:^https?://.*\.jpe?g$',
1134 'uploader': 'ClickHole',
1135 'uploader_id': 'clickhole',
1140 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1142 'id': '74849a00-85a9-11e1-9660-123139220831',
1144 'title': '#whilewewatch',
1147 # AdobeTVVideo embed
1149 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1150 'md5': '43662b577c018ad707a63766462b1e87',
1154 'title': 'New experience with Acrobat DC',
1155 'description': 'New experience with Acrobat DC',
1156 'duration': 248.667,
1159 # ScreenwaveMedia embed
1161 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1162 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1164 'id': 'cinemasnob-55d26273809dd',
1166 'title': 'cinemasnob',
1169 # BrightcoveInPageEmbed embed
1171 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1173 'id': '4238694884001',
1175 'title': 'Tabletop: Dread, Last Thoughts',
1176 'description': 'Tabletop: Dread, Last Thoughts',
1180 # JWPlayer with M3U8
1182 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1186 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1187 'uploader': 'ren.tv',
1191 'skip_download': True,
1194 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1195 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1197 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1199 'id': '4785848093001',
1201 'title': 'The Cardinal Pell Interview',
1202 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1203 'uploader': 'GlobeCast Australia - GlobeStream',
1204 'uploader_id': '2733773828001',
1205 'upload_date': '20160304',
1206 'timestamp': 1457083087,
1210 'skip_download': True,
1213 # Another form of arte.tv embed
1215 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1216 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1218 'id': '030273-562_PLUS7-F',
1220 'title': 'ARTE Reportage - Nulle part, en France',
1221 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1222 'upload_date': '20160409',
1227 'url': 'http://www.wykop.pl/link/3088787/',
1228 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1230 'id': '874_1459135191',
1232 'title': 'Man shows poor quality of new apartment building',
1233 'description': 'The wall is like a sand pile.',
1234 'uploader': 'Lake8737',
1237 # Duplicated embedded video URLs
1239 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1241 'id': '149298443_480_16c25b74_2',
1243 'title': 'vs. Blue Orange Spring Game',
1244 'uploader': 'www.hudl.com',
1249 def report_following_redirect(self
, new_url
):
1250 """Report information extraction."""
1251 self
._downloader
.to_screen('[redirect] Following redirect to %s' % new_url
)
1253 def _extract_rss(self
, url
, video_id
, doc
):
1254 playlist_title
= doc
.find('./channel/title').text
1255 playlist_desc_el
= doc
.find('./channel/description')
1256 playlist_desc
= None if playlist_desc_el
is None else playlist_desc_el
.text
1259 for it
in doc
.findall('./channel/item'):
1260 next_url
= xpath_text(it
, 'link', fatal
=False)
1262 enclosure_nodes
= it
.findall('./enclosure')
1263 for e
in enclosure_nodes
:
1264 next_url
= e
.attrib
.get('url')
1274 'title': it
.find('title').text
,
1278 '_type': 'playlist',
1280 'title': playlist_title
,
1281 'description': playlist_desc
,
1285 def _extract_camtasia(self
, url
, video_id
, webpage
):
1286 """ Returns None if no camtasia video can be found. """
1288 camtasia_cfg
= self
._search
_regex
(
1289 r
'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1290 webpage
, 'camtasia configuration file', default
=None)
1291 if camtasia_cfg
is None:
1294 title
= self
._html
_search
_meta
('DC.title', webpage
, fatal
=True)
1296 camtasia_url
= compat_urlparse
.urljoin(url
, camtasia_cfg
)
1297 camtasia_cfg
= self
._download
_xml
(
1298 camtasia_url
, video_id
,
1299 note
='Downloading camtasia configuration',
1300 errnote
='Failed to download camtasia configuration')
1301 fileset_node
= camtasia_cfg
.find('./playlist/array/fileset')
1304 for n
in fileset_node
.getchildren():
1305 url_n
= n
.find('./uri')
1310 'id': os
.path
.splitext(url_n
.text
.rpartition('/')[2])[0],
1311 'title': '%s - %s' % (title
, n
.tag
),
1312 'url': compat_urlparse
.urljoin(url
, url_n
.text
),
1313 'duration': float_or_none(n
.find('./duration').text
),
1317 '_type': 'playlist',
1322 def _real_extract(self
, url
):
1323 if url
.startswith('//'):
1326 'url': self
.http_scheme() + url
,
1329 parsed_url
= compat_urlparse
.urlparse(url
)
1330 if not parsed_url
.scheme
:
1331 default_search
= self
._downloader
.params
.get('default_search')
1332 if default_search
is None:
1333 default_search
= 'fixup_error'
1335 if default_search
in ('auto', 'auto_warning', 'fixup_error'):
1337 self
._downloader
.report_warning('The url doesn\'t specify the protocol, trying with http')
1338 return self
.url_result('http://' + url
)
1339 elif default_search
!= 'fixup_error':
1340 if default_search
== 'auto_warning':
1341 if re
.match(r
'^(?:url|URL)$', url
):
1342 raise ExtractorError(
1343 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url
,
1346 self
._downloader
.report_warning(
1347 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url
)
1348 return self
.url_result('ytsearch:' + url
)
1350 if default_search
in ('error', 'fixup_error'):
1351 raise ExtractorError(
1352 '%r is not a valid URL. '
1353 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1354 % (url
, url
), expected
=True)
1356 if ':' not in default_search
:
1357 default_search
+= ':'
1358 return self
.url_result(default_search
+ url
)
1360 url
, smuggled_data
= unsmuggle_url(url
)
1361 force_videoid
= None
1362 is_intentional
= smuggled_data
and smuggled_data
.get('to_generic')
1363 if smuggled_data
and 'force_videoid' in smuggled_data
:
1364 force_videoid
= smuggled_data
['force_videoid']
1365 video_id
= force_videoid
1367 video_id
= compat_urllib_parse_unquote(os
.path
.splitext(url
.rstrip('/').split('/')[-1])[0])
1369 self
.to_screen('%s: Requesting header' % video_id
)
1371 head_req
= HEADRequest(url
)
1372 head_response
= self
._request
_webpage
(
1374 note
=False, errnote
='Could not send HEAD request to %s' % url
,
1377 if head_response
is not False:
1378 # Check for redirect
1379 new_url
= head_response
.geturl()
1381 self
.report_following_redirect(new_url
)
1383 new_url
= smuggle_url(
1384 new_url
, {'force_videoid': force_videoid}
)
1385 return self
.url_result(new_url
)
1387 full_response
= None
1388 if head_response
is False:
1389 request
= sanitized_Request(url
)
1390 request
.add_header('Accept-Encoding', '*')
1391 full_response
= self
._request
_webpage
(request
, video_id
)
1392 head_response
= full_response
1396 'title': compat_urllib_parse_unquote(os
.path
.splitext(url_basename(url
))[0]),
1397 'upload_date': unified_strdate(head_response
.headers
.get('Last-Modified'))
1400 # Check for direct link to a video
1401 content_type
= head_response
.headers
.get('Content-Type', '').lower()
1402 m
= re
.match(r
'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type
)
1404 format_id
= m
.group('format_id')
1405 if format_id
.endswith('mpegurl'):
1406 formats
= self
._extract
_m
3u8_formats
(url
, video_id
, 'mp4')
1407 elif format_id
== 'f4m':
1408 formats
= self
._extract
_f
4m
_formats
(url
, video_id
)
1411 'format_id': m
.group('format_id'),
1413 'vcodec': 'none' if m
.group('type') == 'audio' else None
1415 info_dict
['direct'] = True
1416 self
._sort
_formats
(formats
)
1417 info_dict
['formats'] = formats
1420 if not self
._downloader
.params
.get('test', False) and not is_intentional
:
1421 force
= self
._downloader
.params
.get('force_generic_extractor', False)
1422 self
._downloader
.report_warning(
1423 '%s on generic information extractor.' % ('Forcing' if force
else 'Falling back'))
1425 if not full_response
:
1426 request
= sanitized_Request(url
)
1427 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1428 # making it impossible to download only chunk of the file (yet we need only 512kB to
1429 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1430 # that will always result in downloading the whole file that is not desirable.
1431 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1432 # to accept raw bytes and being able to download only a chunk.
1433 # It may probably better to solve this by checking Content-Type for application/octet-stream
1434 # after HEAD request finishes, but not sure if we can rely on this.
1435 request
.add_header('Accept-Encoding', '*')
1436 full_response
= self
._request
_webpage
(request
, video_id
)
1438 first_bytes
= full_response
.read(512)
1440 # Is it an M3U playlist?
1441 if first_bytes
.startswith(b
'#EXTM3U'):
1442 info_dict
['formats'] = self
._extract
_m
3u8_formats
(url
, video_id
, 'mp4')
1443 self
._sort
_formats
(info_dict
['formats'])
1446 # Maybe it's a direct link to a video?
1447 # Be careful not to download the whole thing!
1448 if not is_html(first_bytes
):
1449 self
._downloader
.report_warning(
1450 'URL could be a direct video link, returning it as such.')
1457 webpage
= self
._webpage
_read
_content
(
1458 full_response
, url
, video_id
, prefix
=first_bytes
)
1460 self
.report_extraction(video_id
)
1462 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1464 doc
= compat_etree_fromstring(webpage
.encode('utf-8'))
1465 if doc
.tag
== 'rss':
1466 return self
._extract
_rss
(url
, video_id
, doc
)
1467 elif re
.match(r
'^(?:{[^}]+})?smil$', doc
.tag
):
1468 smil
= self
._parse
_smil
(doc
, url
, video_id
)
1469 self
._sort
_formats
(smil
['formats'])
1471 elif doc
.tag
== '{http://xspf.org/ns/0/}playlist':
1472 return self
.playlist_result(self
._parse
_xspf
(doc
, video_id
), video_id
)
1473 elif re
.match(r
'(?i)^(?:{[^}]+})?MPD$', doc
.tag
):
1474 info_dict
['formats'] = self
._parse
_mpd
_formats
(
1475 doc
, video_id
, mpd_base_url
=url
.rpartition('/')[0])
1476 self
._sort
_formats
(info_dict
['formats'])
1478 elif re
.match(r
'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc
.tag
):
1479 info_dict
['formats'] = self
._parse
_f
4m
_formats
(doc
, url
, video_id
)
1480 self
._sort
_formats
(info_dict
['formats'])
1482 except compat_xml_parse_error
:
1485 # Is it a Camtasia project?
1486 camtasia_res
= self
._extract
_camtasia
(url
, video_id
, webpage
)
1487 if camtasia_res
is not None:
1490 # Sometimes embedded video player is hidden behind percent encoding
1491 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1492 # Unescaping the whole page allows to handle those cases in a generic way
1493 webpage
= compat_urllib_parse_unquote(webpage
)
1495 # it's tempting to parse this further, but you would
1496 # have to take into account all the variations like
1497 # Video Title - Site Name
1498 # Site Name | Video Title
1499 # Video Title - Tagline | Site Name
1500 # and so on and so forth; it's just not practical
1501 video_title
= self
._og
_search
_title
(
1502 webpage
, default
=None) or self
._html
_search
_regex
(
1503 r
'(?s)<title>(.*?)</title>', webpage
, 'video title',
1506 # Try to detect age limit automatically
1507 age_limit
= self
._rta
_search
(webpage
)
1508 # And then there are the jokers who advertise that they use RTA,
1509 # but actually don't.
1510 AGE_LIMIT_MARKERS
= [
1511 r
'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1513 if any(re
.search(marker
, webpage
) for marker
in AGE_LIMIT_MARKERS
):
1516 # video uploader is domain name
1517 video_uploader
= self
._search
_regex
(
1518 r
'^(?:https?://)?([^/]*)/.*', url
, 'video uploader')
1520 video_description
= self
._og
_search
_description
(webpage
, default
=None)
1521 video_thumbnail
= self
._og
_search
_thumbnail
(webpage
, default
=None)
1524 def _playlist_from_matches(matches
, getter
=None, ie
=None):
1526 self
.url_result(self
._proto
_relative
_url
(getter(m
) if getter
else m
), ie
)
1528 return self
.playlist_result(
1529 urlrs
, playlist_id
=video_id
, playlist_title
=video_title
)
1531 # Look for Brightcove Legacy Studio embeds
1532 bc_urls
= BrightcoveLegacyIE
._extract
_brightcove
_urls
(webpage
)
1534 self
.to_screen('Brightcove video detected.')
1537 'url': smuggle_url(bc_url
, {'Referer': url}
),
1538 'ie_key': 'BrightcoveLegacy'
1539 } for bc_url
in bc_urls
]
1542 '_type': 'playlist',
1543 'title': video_title
,
1548 # Look for Brightcove New Studio embeds
1549 bc_urls
= BrightcoveNewIE
._extract
_urls
(webpage
)
1551 return _playlist_from_matches(bc_urls
, ie
='BrightcoveNew')
1553 # Look for ThePlatform embeds
1554 tp_urls
= ThePlatformIE
._extract
_urls
(webpage
)
1556 return _playlist_from_matches(tp_urls
, ie
='ThePlatform')
1558 # Look for Vessel embeds
1559 vessel_urls
= VesselIE
._extract
_urls
(webpage
)
1561 return _playlist_from_matches(vessel_urls
, ie
=VesselIE
.ie_key())
1563 # Look for embedded rtl.nl player
1564 matches
= re
.findall(
1565 r
'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1568 return _playlist_from_matches(matches
, ie
='RtlNl')
1570 vimeo_url
= VimeoIE
._extract
_vimeo
_url
(url
, webpage
)
1571 if vimeo_url
is not None:
1572 return self
.url_result(vimeo_url
)
1574 vid_me_embed_url
= self
._search
_regex
(
1575 r
'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1576 webpage, 'vid.me embed', default=None)
1577 if vid_me_embed_url is not None:
1578 return self.url_result(vid_me_embed_url, 'Vidme')
1580 # Look for embedded YouTube player
1581 matches = re.findall(r'''(?x)
1590 (?P
<url
>(?
:https?
:)?
//(?
:www\
.)?
youtube(?
:-nocookie
)?\
.com
/
1594 return _playlist_from_matches(
1595 matches, lambda m: unescapeHTML(m[1]))
1597 # Look for lazyYT YouTube embed
1598 matches = re.findall(
1599 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1601 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1603 # Look for embedded Dailymotion player
1604 matches = re.findall(
1605 r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
1607 return _playlist_from_matches(
1608 matches, lambda m: unescapeHTML(m[1]))
1610 # Look for embedded Dailymotion playlist player (#3822)
1612 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1614 playlists = re.findall(
1615 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1617 return _playlist_from_matches(
1618 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1620 # Look for embedded Wistia player
1622 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1624 embed_url = self._proto_relative_url(
1625 unescapeHTML(match.group('url')))
1627 '_type': 'url_transparent',
1630 'uploader': video_uploader,
1633 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1636 '_type': 'url_transparent',
1637 'url': 'wistia:%s' % match.group('id'),
1639 'uploader': video_uploader,
1644 <script
[^
>]+src
=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1645 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1648 return self.url_result(self._proto_relative_url(
1649 'wistia
:%s' % match.group('id')), 'Wistia
')
1651 # Look for SVT player
1652 svt_url = SVTIE._extract_url(webpage)
1654 return self.url_result(svt_url, 'SVT
')
1656 # Look for embedded condenast player
1657 matches = re.findall(
1658 r'<iframe\s
+(?
:[a
-zA
-Z
-]+="[^"]+"\s+)*?src="(https?
://player\
.cnevids\
.com
/embed
/[^
"]+")',
1662 '_type
': 'playlist
',
1665 'ie_key
': 'CondeNast
',
1667 } for ma in matches],
1668 'title
': video_title,
1672 # Look for Bandcamp pages with custom domain
1673 mobj = re.search(r'<meta
property="og:url"[^
>]*?content
="(.*?bandcamp\.com.*?)"', webpage)
1674 if mobj is not None:
1675 burl = unescapeHTML(mobj.group(1))
1676 # Don't
set the extractor because it can be a track url
or an album
1677 return self
.url_result(burl
)
1679 # Look for embedded Vevo player
1681 r
'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:cache\
.)?vevo\
.com
/.+?
)\
1', webpage)
1682 if mobj is not None:
1683 return self.url_result(mobj.group('url
'))
1685 # Look for embedded Viddler player
1687 r'<(?
:iframe
[^
>]+?src|param
[^
>]+?value
)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1689 if mobj is not None:
1690 return self.url_result(mobj.group('url'))
1692 # Look for NYTimes player
1694 r'<iframe[^>]+src=(["\'])(?P
<url
>(?
:https?
:)?
//graphics8\
.nytimes\
.com
/bcvideo
/[^
/]+/iframe
/embed\
.html
.+?
)\
1>',
1696 if mobj is not None:
1697 return self.url_result(mobj.group('url
'))
1699 # Look for Libsyn player
1701 r'<iframe
[^
>]+src
=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1702 if mobj is not None:
1703 return self.url_result(mobj.group('url'))
1705 # Look for Ooyala videos
1706 mobj = (re.search(r'player\.ooyala\.com/[^"?
]+[?
#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1707 re
.search(r
'OO\.Player\.create\([\'"].*?[\'"],\s
*[\'"](?P<ec>.{32})[\'"]', webpage) or
1708 re.search(r'SBN\
.VideoLinkset\
.ooyala\
([\'"](?P<ec>.{32})[\'"]\
)', webpage) or
1709 re.search(r'data
-ooyala
-video
-id\s
*=\s
*[\'"](?P<ec>.{32})[\'"]', webpage))
1710 if mobj is not None:
1711 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec
'), {'domain': url}))
1713 # Look for multiple Ooyala embeds on SBN network websites
1714 mobj = re.search(r'SBN\
.VideoLinkset\
.entryGroup\
((\
[.*?\
])', webpage)
1715 if mobj is not None:
1716 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1718 return _playlist_from_matches(
1719 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id
'], {'domain': url})), ie='Ooyala
')
1721 # Look for Aparat videos
1722 mobj = re.search(r'<iframe
.*?src
="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1723 if mobj is not None:
1724 return self.url_result(mobj.group(1), 'Aparat')
1726 # Look for MPORA videos
1727 mobj = re.search(r'<iframe .*?src="(http
://mpora\
.(?
:com|de
)/videos
/[^
"]+)"', webpage)
1728 if mobj is not None:
1729 return self.url_result(mobj.group(1), 'Mpora
')
1731 # Look for embedded NovaMov-based player
1733 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1734 (?P<url>http://(?:(?:embed|www)\.)?
1736 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1737 videoweed\.(?:es|com)|
1738 movshare\.(?:net|sx|ag)|
1739 divxstage\.(?:eu|net|ch|co|at|ag))
1740 /embed\.php.+?)\1''', webpage)
1741 if mobj is not None:
1742 return self.url_result(mobj.group('url
'))
1744 # Look for embedded Facebook player
1746 r'<iframe
[^
>]+?src
=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1747 if mobj is not None:
1748 return self.url_result(mobj.group('url'), 'Facebook')
1750 # Look for embedded VK player
1751 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://vk\
.com
/video_ext\
.php
.+?
)\
1', webpage)
1752 if mobj is not None:
1753 return self.url_result(mobj.group('url
'), 'VK
')
1755 # Look for embedded Odnoklassniki player
1756 mobj = re.search(r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1757 if mobj is not None:
1758 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1760 # Look for embedded ivi player
1761 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P
<url
>https?
://(?
:www\
.)?ivi\
.ru
/video
/player
.+?
)\
1', webpage)
1762 if mobj is not None:
1763 return self.url_result(mobj.group('url
'), 'Ivi
')
1765 # Look for embedded Huffington Post player
1767 r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1768 if mobj is not None:
1769 return self.url_result(mobj.group('url'), 'HuffPost')
1772 mobj = re.search(r'class=["\']embedly
-card
["\'][^>]href=["\'](?P
<url
>[^
"\']+)', webpage)
1773 if mobj is not None:
1774 return self.url_result(mobj.group('url'))
1775 mobj = re.search(r'class=["\']embedly
-embed
["\'][^>]src=["\'][^
"\']*url=(?P<url>[^&]+)', webpage)
1776 if mobj is not None:
1777 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1779 # Look for funnyordie embed
1780 matches = re.findall(r'<iframe[^>]+?src="(https?
://(?
:www\
.)?funnyordie\
.com
/embed
/[^
"]+)"', webpage)
1782 return _playlist_from_matches(
1783 matches, getter=unescapeHTML, ie='FunnyOrDie
')
1785 # Look for BBC iPlayer embed
1786 matches = re.findall(r'setPlaylist\
("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\
)', webpage)
1788 return _playlist_from_matches(matches, ie='BBCCoUk
')
1790 # Look for embedded RUTV player
1791 rutv_url = RUTVIE._extract_url(webpage)
1793 return self.url_result(rutv_url, 'RUTV
')
1795 # Look for embedded TVC player
1796 tvc_url = TVCIE._extract_url(webpage)
1798 return self.url_result(tvc_url, 'TVC
')
1800 # Look for embedded SportBox player
1801 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1803 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed
')
1805 # Look for embedded PornHub player
1806 pornhub_url = PornHubIE._extract_url(webpage)
1808 return self.url_result(pornhub_url, 'PornHub
')
1810 # Look for embedded XHamster player
1811 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1813 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed
')
1815 # Look for embedded TNAFlixNetwork player
1816 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1818 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1820 # Look for embedded Tvigle player
1822 r'<iframe
[^
>]+?src
=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1823 if mobj is not None:
1824 return self.url_result(mobj.group('url'), 'Tvigle')
1826 # Look for embedded TED player
1828 r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://embed(?
:-ssl
)?\
.ted\
.com
/.+?
)\
1', webpage)
1829 if mobj is not None:
1830 return self.url_result(mobj.group('url
'), 'TED
')
1832 # Look for embedded Ustream videos
1834 r'<iframe
[^
>]+?src
=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1835 if mobj is not None:
1836 return self.url_result(mobj.group('url'), 'Ustream')
1838 # Look for embedded arte.tv player
1840 r'<(?:script|iframe) [^>]*?src="(?P
<url
>http
://www\
.arte\
.tv
/(?
:playerv2
/embed|arte_vp
/index
)[^
"]+)"',
1842 if mobj is not None:
1843 return self.url_result(mobj.group('url
'), 'ArteTVEmbed
')
1845 # Look for embedded francetv player
1847 r'<iframe
[^
>]+?src
=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1849 if mobj is not None:
1850 return self.url_result(mobj.group('url'))
1852 # Look for embedded smotri.com player
1853 smotri_url = SmotriIE._extract_url(webpage)
1855 return self.url_result(smotri_url, 'Smotri')
1857 # Look for embedded Myvi.ru player
1858 myvi_url = MyviIE._extract_url(webpage)
1860 return self.url_result(myvi_url)
1862 # Look for embedded soundcloud player
1864 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^
"]+"\s
+)*src
="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1866 if mobj is not None:
1867 url = unescapeHTML(mobj.group('url'))
1868 return self.url_result(url)
1870 # Look for embedded mtvservices player
1871 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1873 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1875 # Look for embedded yahoo player
1877 r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://(?
:screen|movies
)\
.yahoo\
.com
/.+?\
.html
\?format
=embed
)\
1',
1879 if mobj is not None:
1880 return self.url_result(mobj.group('url
'), 'Yahoo
')
1882 # Look for embedded sbs.com.au player
1886 <meta\s+property="og:video"\s+content=|
1889 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1891 if mobj is not None:
1892 return self.url_result(mobj.group('url
'), 'SBS
')
1894 # Look for embedded Cinchcast player
1896 r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1898 if mobj is not None:
1899 return self.url_result(mobj.group('url'), 'Cinchcast')
1902 r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://m(?
:lb
)?\
.mlb\
.com
/shared
/video
/embed
/embed\
.html
\?.+?
)\
1',
1906 r'data
-video
-link
=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1908 if mobj is not None:
1909 return self.url_result(mobj.group('url
'), 'MLB
')
1912 r'<(?
:iframe|script
)[^
>]+?src
=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1914 if mobj is not None:
1915 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1918 r'<iframe[^>]+src="(?P
<url
>https?
://(?
:new\
.)?livestream\
.com
/[^
"]+/player[^"]+)"',
1920 if mobj is not None:
1921 return self.url_result(mobj.group('url'), 'Livestream')
1923 # Look for Zapiks embed
1925 r'<iframe[^>]+src="(?P
<url
>https?
://(?
:www\
.)?zapiks\
.fr
/index\
.php
\?.+?
)"', webpage)
1926 if mobj is not None:
1927 return self.url_result(mobj.group('url'), 'Zapiks')
1929 # Look for Kaltura embeds
1930 kaltura_url = KalturaIE._extract_url(webpage)
1932 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
1934 # Look for Eagle.Platform embeds
1936 r'<iframe[^>]+src="(?P
<url
>https?
://.+?\
.media\
.eagleplatform\
.com
/index
/player
\?.+?
)"', webpage)
1937 if mobj is not None:
1938 return self.url_result(mobj.group('url'), 'EaglePlatform')
1940 # Look for ClipYou (uses Eagle.Platform) embeds
1942 r'<iframe[^>]+src="https?
://(?P
<host
>media\
.clipyou\
.ru
)/index
/player
\?.*\brecord
_id
=(?P
<id>\d
+).*"', webpage)
1943 if mobj is not None:
1944 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1946 # Look for Pladform embeds
1947 pladform_url = PladformIE._extract_url(webpage)
1949 return self.url_result(pladform_url)
1951 # Look for Videomore embeds
1952 videomore_url = VideomoreIE._extract_url(webpage)
1954 return self.url_result(videomore_url)
1956 # Look for Playwire embeds
1958 r'<script[^>]+data-config=(["\'])(?P
<url
>(?
:https?
:)?
//config\
.playwire\
.com
/.+?
)\
1', webpage)
1959 if mobj is not None:
1960 return self.url_result(mobj.group('url
'))
1962 # Look for 5min embeds
1964 r'<meta
[^
>]+property="og:video"[^
>]+content
="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1965 if mobj is not None:
1966 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1968 # Look for Crooks and Liars embeds
1970 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P
<url
>(?
:https?
:)?
//embed\
.crooksandliars\
.com
/(?
:embed|v
)/.+?
)\
1', webpage)
1971 if mobj is not None:
1972 return self.url_result(mobj.group('url
'))
1974 # Look for NBC Sports VPlayer embeds
1975 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1977 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer
')
1979 # Look for NBC News embeds
1980 nbc_news_embed_url = re.search(
1981 r'<iframe
[^
>]+src
=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\
1', webpage)
1982 if nbc_news_embed_url:
1983 return self.url_result(nbc_news_embed_url.group('url
'), 'NBCNews
')
1985 # Look for Google Drive embeds
1986 google_drive_url = GoogleDriveIE._extract_url(webpage)
1987 if google_drive_url:
1988 return self.url_result(google_drive_url, 'GoogleDrive
')
1990 # Look for UDN embeds
1992 r'<iframe
[^
>]+src
="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1993 if mobj is not None:
1994 return self.url_result(
1995 compat_urlparse.urljoin(url, mobj.group('url
')), 'UDNEmbed
')
1997 # Look for Senate ISVP iframe
1998 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2000 return self.url_result(senate_isvp_url, 'SenateISVP
')
2002 # Look for Dailymotion Cloud videos
2003 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2005 return self.url_result(dmcloud_url, 'DailymotionCloud
')
2007 # Look for OnionStudios embeds
2008 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2009 if onionstudios_url:
2010 return self.url_result(onionstudios_url)
2012 # Look for ViewLift embeds
2013 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2015 return self.url_result(viewlift_url)
2017 # Look for JWPlatform embeds
2018 jwplatform_url = JWPlatformIE._extract_url(webpage)
2020 return self.url_result(jwplatform_url, 'JWPlatform
')
2022 # Look for ScreenwaveMedia embeds
2023 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
2024 if mobj is not None:
2025 return self.url_result(unescapeHTML(mobj.group('url
')), 'ScreenwaveMedia
')
2027 # Look for Digiteka embeds
2028 digiteka_url = DigitekaIE._extract_url(webpage)
2030 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2032 # Look for Limelight embeds
2033 mobj = re.search(r'LimelightPlayer\
.doLoad(Media|Channel|ChannelList
)\
(["\'](?P<id>[a-z0-9]{32})', webpage)
2037 'Channel': 'channel',
2038 'ChannelList': 'channel_list',
2040 return self.url_result('limelight:%s:%s' % (
2041 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2043 # Look for AdobeTVVideo embeds
2045 r'<iframe[^>]+src=[\'"]((?
:https?
:)?
//video\
.tv\
.adobe\
.com
/v
/\d
+[^
"]+)[\'"]',
2047 if mobj is not None:
2048 return self.url_result(
2049 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2052 # Look for Vine embeds
2054 r'<iframe
[^
>]+src
=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2056 if mobj is not None:
2057 return self.url_result(
2058 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2060 # Look for Instagram embeds
2061 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2062 if instagram_embed_url is not None:
2063 return self.url_result(
2064 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2066 # Look for LiveLeak embeds
2067 liveleak_url = LiveLeakIE._extract_url(webpage)
2069 return self.url_result(liveleak_url, 'LiveLeak')
2071 # Look for 3Q SDN embeds
2072 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2075 '_type': 'url_transparent',
2076 'ie_key': ThreeQSDNIE.ie_key(),
2077 'url': self._proto_relative_url(threeqsdn_url),
2078 'title': video_title,
2079 'description': video_description,
2080 'thumbnail': video_thumbnail,
2081 'uploader': video_uploader,
2084 def check_video(vurl):
2085 if YoutubeIE.suitable(vurl):
2087 vpath = compat_urlparse.urlparse(vurl).path
2088 vext = determine_ext(vpath)
2089 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2091 def filter_video(urls):
2092 return list(filter(check_video, urls))
2094 # Start with something easy: JW Player in SWFObject
2095 found = filter_video(re.findall(r'flashvars: [\'"](?
:.*&)?
file=(http
[^
\'"&]*)', webpage))
2097 # Look for gorilla-vid style embedding
2098 found = filter_video(re.findall(r'''(?sx)
2102 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2105 ['"]?file['"]?\s
*:\s
*["\'](.*?)["\']''', webpage))
2107 # Broaden the search a little bit
2108 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2110 # Broaden the findall a little bit: JWPlayer JS loader
2111 found = filter_video(re.findall(
2112 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2115 found = filter_video(re.findall(r'''(?xs
)
2116 flowplayer\
("[^"]+",\s*
2118 \s*\{[^}]+? ["']?clip["']?\s
*:\s
*\
{\s
*
2119 ["']?url["']?\s*:\s*["']([^
"']+)["']
2124 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s
*'([^']+)'", webpage)
2126 # Try to find twitter cards info
2127 found = filter_video(re.findall(
2128 r'<meta (?
:property|name
)="twitter:player:stream" (?
:content|value
)="(.+?)"', webpage))
2130 # We look for Open Graph info:
2131 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2132 m_video_type = re.findall(r'<meta
.*?
property="og:video:type".*?content
="video/(.*?)"', webpage)
2133 # We only look in og:video if the MIME type is a video, don't
try if it
's a Flash player:
2134 if m_video_type is not None:
2135 found = filter_video(re.findall(r'<meta
.*?
property="og:video".*?content
="(.*?)"', webpage))
2138 found = re.findall(r'(?s
)<(?
:video|audio
)[^
<]*(?
:>.*?
<source
[^
>]*)?\s
+src
=["\'](.*?)["\']', webpage)
2140 REDIRECT_REGEX = r'[0-9]{,2}
;\s
*(?
:URL|url
)=\'?
([^
\'"]+)'
2142 r'(?i)<meta\s+(?=(?:[a-z-]+="[^
"]+"\s
+)*http
-equiv
="refresh")'
2143 r'(?
:[a
-z
-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2146 # Look also in Refresh HTTP header
2147 refresh_header = head_response.headers.get('Refresh
')
2149 # In python 2 response HTTP headers are bytestrings
2150 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2151 refresh_header = refresh_header.decode('iso
-8859-1')
2152 found = re.search(REDIRECT_REGEX, refresh_header)
2154 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2155 self.report_following_redirect(new_url)
2161 raise UnsupportedError(url)
2164 for video_url in orderedSet(found):
2165 video_url = unescapeHTML(video_url)
2166 video_url = video_url.replace('\\/', '/')
2167 video_url = compat_urlparse.urljoin(url, video_url)
2168 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2170 # Sometimes, jwplayer extraction will result in a YouTube URL
2171 if YoutubeIE.suitable(video_url):
2172 entries.append(self.url_result(video_url, 'Youtube
'))
2175 # here's a fun little line of code
for you
:
2176 video_id
= os
.path
.splitext(video_id
)[0]
2180 'uploader': video_uploader
,
2181 'title': video_title
,
2182 'age_limit': age_limit
,
2185 ext
= determine_ext(video_url
)
2187 entry_info_dict
['formats'] = self
._extract
_smil
_formats
(video_url
, video_id
)
2189 return self
.playlist_result(self
._extract
_xspf
_playlist
(video_url
, video_id
), video_id
)
2191 entry_info_dict
['formats'] = self
._extract
_m
3u8_formats
(video_url
, video_id
, ext
='mp4')
2193 entry_info_dict
['formats'] = self
._extract
_mpd
_formats
(video_url
, video_id
)
2195 entry_info_dict
['formats'] = self
._extract
_f
4m
_formats
(video_url
, video_id
)
2197 entry_info_dict
['url'] = video_url
2199 if entry_info_dict
.get('formats'):
2200 self
._sort
_formats
(entry_info_dict
['formats'])
2202 entries
.append(entry_info_dict
)
2204 if len(entries
) == 1:
2207 for num
, e
in enumerate(entries
, start
=1):
2208 # 'url' results don't have a title
2209 if e
.get('title') is not None:
2210 e
['title'] = '%s (%d)' % (e
['title'], num
)
2212 '_type': 'playlist',