3 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
14 compat_urllib_parse_unquote,
16 compat_xml_parse_error,
34 from .commonprotocols import RtmpIE
35 from .brightcove import (
43 from .nbc import NBCSportsVPlayerIE
44 from .ooyala import OoyalaIE
45 from .rutv import RUTVIE
46 from .tvc import TVCIE
47 from .sportbox import SportBoxEmbedIE
48 from .smotri import SmotriIE
49 from .myvi import MyviIE
50 from .condenast import CondeNastIE
51 from .udn import UDNEmbedIE
52 from .senateisvp import SenateISVPIE
53 from .svt import SVTIE
54 from .pornhub import PornHubIE
55 from .xhamster import XHamsterEmbedIE
56 from .tnaflix import TNAFlixNetworkEmbedIE
57 from .drtuber import DrTuberIE
58 from .redtube import RedTubeIE
59 from .vimeo import VimeoIE
60 from .dailymotion import (
64 from .dailymail import DailyMailIE
65 from .onionstudios import OnionStudiosIE
66 from .viewlift import ViewLiftEmbedIE
67 from .mtv import MTVServicesEmbeddedIE
68 from .pladform import PladformIE
69 from .videomore import VideomoreIE
70 from .webcaster import WebcasterFeedIE
71 from .googledrive import GoogleDriveIE
72 from .jwplatform import JWPlatformIE
73 from .digiteka import DigitekaIE
74 from .arkena import ArkenaIE
75 from .instagram import InstagramIE
76 from .liveleak import LiveLeakIE
77 from .threeqsdn import ThreeQSDNIE
78 from .theplatform import ThePlatformIE
79 from .vessel import VesselIE
80 from .kaltura import KalturaIE
81 from .eagleplatform import EaglePlatformIE
82 from .facebook import FacebookIE
83 from .soundcloud import SoundcloudIE
84 from .tunein import TuneInBaseIE
85 from .vbox7 import Vbox7IE
86 from .dbtv import DBTVIE
87 from .piksel import PikselIE
88 from .videa import VideaIE
89 from .twentymin import TwentyMinutenIE
90 from .ustream import UstreamIE
91 from .openload import OpenloadIE
92 from .videopress import VideoPressIE
93 from .rutube import RutubeIE
94 from .limelight import LimelightBaseIE
95 from .anvato import AnvatoIE
96 from .washingtonpost import WashingtonPostIE
97 from .wistia import WistiaIE
98 from .mediaset import MediasetIE
99 from .joj import JojIE
102 class GenericIE(InfoExtractor):
103 IE_DESC = 'Generic downloader that works on some sites'
107 # Direct link to a video
109 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
110 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
115 'upload_date': '20100513',
118 # Direct link to media delivered compressed (until Accept-Encoding is *)
120 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
121 'md5': '128c42e68b13950268b648275386fc74',
123 'id': 'FictionJunction-Parallel_Hearts',
125 'title': 'FictionJunction-Parallel_Hearts',
126 'upload_date': '20140522',
128 'expected_warnings': [
129 'URL could be a direct video link, returning it as such.'
131 'skip': 'URL invalid',
133 # Direct download with broken HEAD
135 'url': 'http://ai-radio.org:8000/radio.opus',
142 'skip_download': True, # infinite live stream
144 'expected_warnings': [
145 r'501.*Not Implemented',
149 # Direct link with incorrect MIME type
151 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
152 'md5': '4ccbebe5f36706d85221f204d7eb5913',
154 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
155 'id': '5_Lennart_Poettering_-_Systemd',
157 'title': '5_Lennart_Poettering_-_Systemd',
158 'upload_date': '20141120',
160 'expected_warnings': [
161 'URL could be a direct video link, returning it as such.'
166 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
168 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
169 'title': 'Zero Punctuation',
170 'description': 're:.*groundbreaking video review series.*'
172 'playlist_mincount': 11,
174 # RSS feed with enclosure
176 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
178 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
180 'upload_date': '20150228',
181 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
184 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
186 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
190 'title': 'Automatics, robotics and biocybernetics',
191 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
192 'upload_date': '20130627',
193 'formats': 'mincount:16',
194 'subtitles': 'mincount:1',
197 'force_generic_extractor': True,
198 'skip_download': True,
201 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
203 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
208 'formats': 'mincount:1',
211 'skip_download': True,
214 # SMIL from https://www.restudy.dk/video/play/id/1637
216 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
220 'title': 'video_1637',
221 'formats': 'mincount:3',
224 'skip_download': True,
227 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
229 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
231 'id': 'smil-service',
233 'title': 'smil-service',
234 'formats': 'mincount:1',
237 'skip_download': True,
240 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
242 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
246 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
247 'formats': 'mincount:3',
250 'skip_download': True,
253 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
255 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
257 'id': 'mZlp2ctYIUEB',
259 'title': 'Tikibad ontruimd wegens brand',
260 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
261 'thumbnail': r're:^https?://.*\.jpg$',
265 'skip_download': True,
268 # MPD from http://dash-mse-test.appspot.com/media.html
270 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
271 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
273 'id': 'car-20120827-manifest',
275 'title': 'car-20120827-manifest',
276 'formats': 'mincount:9',
277 'upload_date': '20130904',
280 'format': 'bestvideo',
283 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
285 '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',
290 'formats': 'mincount:8',
294 'skip_download': True,
296 'skip': 'video gone',
298 # m3u8 served with Content-Type: text/plain
300 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
305 'upload_date': '20140720',
306 'formats': 'mincount:11',
310 'skip_download': True,
312 'skip': 'video gone',
316 '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',
320 'upload_date': '20130224',
321 'uploader_id': 'TheVerge',
322 'description': r're:^Chris Ziegler takes a look at the\.*',
323 'uploader': 'The Verge',
324 'title': 'First Firefox OS phones side-by-side',
327 'skip_download': False,
331 # redirect in Refresh HTTP header
332 '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',
336 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
337 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
338 'upload_date': '20150917',
339 'uploader_id': 'brtvofficial',
340 'uploader': 'Boiler Room',
343 'skip_download': False,
347 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
348 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
350 'id': '13601338388002',
352 'uploader': 'www.hodiho.fr',
353 'title': 'R\u00e9gis plante sa Jeep',
356 # bandcamp page with custom domain
358 'add_ie': ['Bandcamp'],
359 'url': 'http://bronyrock.com/track/the-pony-mash',
363 'title': 'The Pony Mash',
364 'uploader': 'M_Pallante',
366 'skip': 'There is a limit of 200 free downloads / month for the test song',
369 # embedded brightcove video
370 # it also tests brightcove videos that need to set the 'Referer'
371 # in the http requests
372 'add_ie': ['BrightcoveLegacy'],
373 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
375 'id': '2765128793001',
377 'title': 'Le cours de bourse : l’analyse technique',
378 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
379 'uploader': 'BFM BUSINESS',
382 'skip_download': True,
386 # embedded with itemprop embedURL and video id spelled as `idVideo`
387 'add_id': ['BrightcoveLegacy'],
388 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
390 'id': '5255628253001',
392 'title': 'md5:37c519b1128915607601e75a87995fc0',
393 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
394 'uploader': 'BFM BUSINESS',
395 'uploader_id': '876450612001',
396 'timestamp': 1482255315,
397 'upload_date': '20161220',
400 'skip_download': True,
404 # https://github.com/rg3/youtube-dl/issues/2253
405 'url': 'http://bcove.me/i6nfkrc3',
406 'md5': '0ba9446db037002366bab3b3eb30c88c',
408 'id': '3101154703001',
410 'title': 'Still no power',
411 'uploader': 'thestar.com',
412 '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.',
414 'add_ie': ['BrightcoveLegacy'],
415 'skip': 'video gone',
418 'url': 'http://www.championat.com/video/football/v/87/87499.html',
419 'md5': 'fb973ecf6e4a78a67453647444222983',
421 'id': '3414141473001',
423 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
424 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
425 'uploader': 'Championat',
429 # https://github.com/rg3/youtube-dl/issues/3541
430 'add_ie': ['BrightcoveLegacy'],
431 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
433 'id': '3866516442001',
435 'title': 'Leer mij vrouwen kennen: Aflevering 1',
436 'description': 'Leer mij vrouwen kennen: Aflevering 1',
437 'uploader': 'SBS Broadcasting',
439 'skip': 'Restricted to Netherlands',
441 'skip_download': True, # m3u8 download
445 # Brightcove video in <iframe>
446 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
447 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
449 'id': '5360463607001',
451 'title': '叙利亚失明儿童在废墟上演唱《心跳》 呼吁获得正常童年生活',
452 'description': '联合国儿童基金会中东和北非区域大使、作曲家扎德·迪拉尼(Zade Dirani)在3月15日叙利亚冲突爆发7周年纪念日之际发布了为叙利亚谱写的歌曲《心跳》(HEARTBEAT),为受到六年冲突影响的叙利亚儿童发出强烈呐喊,呼吁世界做出共同努力,使叙利亚儿童重新获得享有正常童年生活的权利。',
453 'uploader': 'United Nations',
454 'uploader_id': '1362235914001',
455 'timestamp': 1489593889,
456 'upload_date': '20170315',
458 'add_ie': ['BrightcoveLegacy'],
461 # Brightcove with alternative playerID key
462 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
464 'id': 'nmeth.2062_SV1',
465 'title': 'Simultaneous multiview imaging of the Drosophila syncytial blastoderm : Quantitative high-speed imaging of entire developing embryos with simultaneous multiview light-sheet microscopy : Nature Methods : Nature Research',
469 'id': '2228375078001',
471 'title': 'nmeth.2062-sv1',
472 'description': 'nmeth.2062-sv1',
473 'timestamp': 1363357591,
474 'upload_date': '20130315',
475 'uploader': 'Nature Publishing Group',
476 'uploader_id': '1964492299001',
481 # Brightcove with UUID in videoPlayer
482 'url': 'http://www8.hp.com/cn/zh/home.html',
484 'id': '5255815316001',
486 'title': 'Sprocket Video - China',
487 'description': 'Sprocket Video - China',
488 'uploader': 'HP-Video Gallery',
489 'timestamp': 1482263210,
490 'upload_date': '20161220',
491 'uploader_id': '1107601872001',
494 'skip_download': True, # m3u8 download
496 'skip': 'video rotates...weekly?',
499 # Brightcove:new type [2].
500 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
501 'md5': '2b35148fcf48da41c9fb4591650784f3',
503 'id': '5348741021001',
505 'upload_date': '20170306',
506 'uploader_id': '4191638492001',
507 'timestamp': 1488769918,
508 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
513 # Alternative brightcove <video> attributes
514 'url': 'http://www.programme-tv.net/videos/extraits/81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche/',
516 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
517 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
520 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
522 'id': '5311302538001',
524 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
525 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
526 'timestamp': 1486321708,
527 'upload_date': '20170205',
528 'uploader_id': '800000640001',
530 'only_matching': True,
534 # Brightcove with UUID in videoPlayer
535 'url': 'http://www8.hp.com/cn/zh/home.html',
537 'id': '5255815316001',
539 'title': 'Sprocket Video - China',
540 'description': 'Sprocket Video - China',
541 'uploader': 'HP-Video Gallery',
542 'timestamp': 1482263210,
543 'upload_date': '20161220',
544 'uploader_id': '1107601872001',
547 'skip_download': True, # m3u8 download
552 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
553 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
555 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
557 'title': '2cc213299525360.mov', # that's what we get
560 'add_ie': ['Ooyala'],
563 # ooyala video embedded with http://player.ooyala.com/iframe.js
564 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
566 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
568 'title': '"Steve Jobs: Man in the Machine" trailer',
569 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
573 'skip_download': True,
575 'skip': 'movie expired',
579 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
583 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
584 'upload_date': '20140225',
585 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
586 'uploader': 'Tested',
587 'uploader_id': 'testedcom',
589 # No need to test YoutubeIE here
591 'skip_download': True,
596 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
600 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
601 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
603 # HEAD requests lead to endless 301, while GET is OK
604 'expected_warnings': ['301'],
608 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
612 'title': 'Охотское море стало целиком российским',
613 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
617 'skip_download': True,
622 '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/',
626 'title': 'Дошкольное воспитание',
631 'url': 'http://www.vestifinance.ru/articles/25753',
634 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
639 'title': 'Госзаказ. День 3',
645 'title': 'Госзаказ. День 2',
651 'title': 'Госзаказ. День 1',
657 'skip_download': True,
662 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
664 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
666 'title': 'Ужастики, русский трейлер (2015)',
667 'thumbnail': r're:^https?://.*\.jpg$',
673 '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',
676 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
678 'playlist_mincount': 7,
679 # This forum does not allow <iframe> syntaxes anymore
680 # Now HTML tags are displayed as-is
681 'skip': 'No videos on this page',
685 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
686 'md5': '65fdff94098e4a607385a60c5177c638',
690 'title': 'Hidden miracles of the natural world',
691 'uploader': 'Louie Schwartzberg',
692 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
695 # nowvideo embed hidden behind percent encoding
697 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
698 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
700 'id': '06e53103ca9aa',
702 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
703 'description': 'No description',
708 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
709 'md5': '7653032cbb25bf6c80d80f217055fa43',
711 'id': '048195-004_PLUS7-F',
714 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
715 'upload_date': '20140320',
718 'skip_download': 'Requires rtmpdump'
720 'skip': 'video gone',
724 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
728 'title': 'Alcaline, le concert avec Calogero',
729 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
730 'upload_date': '20150226',
731 'timestamp': 1424989860,
736 'skip_download': True,
738 'expected_warnings': [
744 'url': 'http://www.wired.com/2014/04/honda-asimo/',
745 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
747 'id': '53501be369702d3275860000',
749 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
754 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
755 'md5': '441aeeb82eb72c422c7f14ec533999cd',
757 'id': 'k2mm4bCdJ6CQ2i7c8o2',
759 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
760 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
762 'uploader_id': 'xgditw',
763 'upload_date': '20140425',
764 'timestamp': 1398441542,
766 'add_ie': ['Dailymotion'],
770 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
774 'title': 'Care worker punches elderly dementia patient in head 11 times',
775 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
777 'add_ie': ['DailyMail'],
779 'skip_download': True,
784 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
788 'title': 'The NBL Auction 2014',
789 'uploader': 'BADMINTON England',
790 'uploader_id': 'BADMINTONEvents',
791 'upload_date': '20140603',
792 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
794 'add_ie': ['Youtube'],
796 'skip_download': True,
801 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
802 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
804 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
806 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
807 'description': 'Two valets share their love for movie star Liam Neesons.',
808 'timestamp': 1349922600,
809 'upload_date': '20121011',
812 # YouTube embed via <data-embed-url="">
814 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
818 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
819 'uploader': 'Gameloft',
820 'uploader_id': 'gameloft',
821 'upload_date': '20140828',
822 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
825 'skip_download': True,
828 # YouTube <object> embed
830 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
831 'md5': '516718101ec834f74318df76259fb3cc',
835 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
836 'upload_date': '20080526',
837 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
838 'uploader': 'Christopher Sykes',
839 'uploader_id': 'ChristopherJSykes',
841 'add_ie': ['Youtube'],
845 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
847 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
849 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
850 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
855 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
857 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
858 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
864 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
869 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
870 'md5': '9d65602bf31c6e20014319c7d07fba27',
872 'id': '5123ea6d5e5a7',
875 'uploader': 'www.handjobhub.com',
876 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
879 # Multiple brightcove videos
880 # https://github.com/rg3/youtube-dl/issues/2283
882 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
884 'id': 'always-never',
885 'title': 'Always / Never - The New Yorker',
889 'extract_flat': False,
890 'skip_download': True,
895 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
896 'md5': '96f09a37e44da40dd083e12d9a683327',
900 'title': 'Ump changes call to ball',
901 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
903 'timestamp': 1401537900,
904 'upload_date': '20140531',
905 'thumbnail': r're:^https?://.*\.jpg$',
910 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
911 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
915 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
916 'description': 'a Paywall Videos video from Remilon',
918 'uploader': 'study.com',
919 'timestamp': 1459678540,
920 'upload_date': '20160403',
921 'filesize': 24687186,
925 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
926 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
930 'title': 'Conversation about Hexagonal Rails Part 1',
931 'description': 'a Martin Fowler video from ThoughtWorks',
933 'uploader': 'thoughtworks.wistia.com',
934 'timestamp': 1401832161,
935 'upload_date': '20140603',
938 # Wistia standard embed (async)
940 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
944 'title': 'Drip Brennan Dunn Workshop',
945 'description': 'a JV Webinars video from getdrip-1',
947 'timestamp': 1463607249,
948 'upload_date': '20160518',
951 'skip_download': True,
956 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
960 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
961 'uploader': 'Sophos Security',
962 'title': 'Chet Chat 171 - Oct 29, 2014',
963 'upload_date': '20141029',
966 # Soundcloud multiple embeds
968 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
971 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
973 'playlist_mincount': 7,
975 # TuneIn station embed
977 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
982 'location': 'Paris, France',
987 'skip_download': True,
992 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
996 'upload_date': '20141112',
997 'title': 'Rosetta #CometLanding webcast HL 10',
1000 # Another Livestream embed, without 'new.' in URL
1002 'url': 'https://www.freespeech.org/',
1006 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1010 'skip_download': True,
1015 'url': 'https://skiplagged.com/',
1018 'title': 'Skiplagged: The smart way to find cheap flights',
1020 'playlist_mincount': 1,
1021 'add_ie': ['Youtube'],
1025 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1029 'upload_date': '20141126',
1030 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1035 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1037 'id': '730m_DandD_1901_512k',
1039 'uploader': 'www.abc.net.au',
1040 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1043 # embedded viddler video
1045 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1049 'uploader': 'deadspin',
1050 'title': 'WALL-TO-GORTAT',
1051 'timestamp': 1422285291,
1052 'upload_date': '20150126',
1054 'add_ie': ['Viddler'],
1058 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1062 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1063 'description': 'md5:601cb790edd05908957dae8aaa866465',
1064 'upload_date': '20150220',
1066 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1070 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1072 'id': 'Mrj4DVp2zeA',
1074 'upload_date': '20150212',
1075 'uploader': 'The National Archives UK',
1076 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1077 'uploader_id': 'NationalArchives08',
1078 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1083 'url': 'http://www.suffolk.edu/sjc/',
1087 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1088 'uploader': 'www.suffolk.edu',
1091 'skip_download': True,
1096 'url': 'http://www.indiedb.com/games/king-machine/videos',
1100 'title': 'king machine trailer 1',
1101 'thumbnail': r're:^https?://.*\.jpg$',
1105 # JWPlayer config passed as variable
1106 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1110 'title': 'ARIELE | Tube Cup',
1111 'uploader': 'www.txxx.com',
1115 'skip_download': True,
1120 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1121 'playlist_mincount': 5,
1123 'id': 'aanslagen-kopenhagen',
1124 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1129 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1133 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1136 # Kaltura embed (different embed code)
1138 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1142 'upload_date': '20150127',
1143 'uploader_id': 'PremierMedia',
1145 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1148 # Kaltura embed with single quotes
1150 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1155 'timestamp': 1355743100,
1156 'upload_date': '20121217',
1157 'uploader_id': 'batchUser',
1159 'add_ie': ['Kaltura'],
1162 # Kaltura embedded via quoted entry_id
1163 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1167 'title': '06_matthew_brender_raj_dutt',
1168 'timestamp': 1466638791,
1169 'upload_date': '20160622',
1171 'add_ie': ['Kaltura'],
1172 'expected_warnings': [
1173 'Could not send HEAD request'
1176 'skip_download': True,
1180 # Kaltura embedded, some fileExt broken (#11480)
1181 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1185 'title': 'Our "Standard Models" of particle physics and cosmology',
1186 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1187 'timestamp': 1321158993,
1188 'upload_date': '20111113',
1189 'uploader_id': 'kps1',
1191 'add_ie': ['Kaltura'],
1194 # Kaltura iframe embed
1195 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1196 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1200 'title': 'I. M. Pei: A Centennial Celebration',
1201 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1202 'upload_date': '20170403',
1203 'uploader_id': 'batchUser',
1204 'timestamp': 1491232186,
1206 'add_ie': ['Kaltura'],
1208 # EaglePlatform embed (generic URL)
1210 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1211 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1215 'title': 'Навальный вышел на свободу',
1216 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1217 'thumbnail': r're:^https?://.*\.jpg$',
1223 'skip_download': True,
1226 # referrer protected EaglePlatform embed
1228 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1232 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1233 'thumbnail': r're:^https?://.*\.jpg$',
1238 'skip_download': True,
1241 # ClipYou (EaglePlatform) embed (custom URL)
1243 'url': 'http://muz-tv.ru/play/7129/',
1244 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1248 'title': "'O Sole Mio",
1249 'thumbnail': r're:^https?://.*\.jpg$',
1254 'skip_download': True,
1259 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1263 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1264 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1265 'thumbnail': r're:^https?://.*\.jpg$',
1272 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1276 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1277 'thumbnail': r're:^https?://.*\.png$',
1283 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1284 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1288 'title': 'Facebook Creates "On This Day" | Crunch Report',
1293 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1297 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1302 # Crooks and Liars embed
1304 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1308 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1309 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1310 'timestamp': 1428207000,
1311 'upload_date': '20150405',
1312 'uploader': 'Heather',
1315 # Crooks and Liars external embed
1317 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1319 'id': 'MTE3MjUtMzQ2MzA',
1321 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1322 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1323 'timestamp': 1265032391,
1324 'upload_date': '20100201',
1325 'uploader': 'Heather',
1328 # NBC Sports vplayer embed
1330 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1332 'id': 'ln7x1qSThw4k',
1334 'title': "PFT Live: New leader in the 'new-look' defense",
1335 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1336 'uploader': 'NBCU-SPORTS',
1337 'upload_date': '20140107',
1338 'timestamp': 1389118457,
1343 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1344 'md5': '1aa589c675898ae6d37a17913cf68d66',
1346 'id': '701714499682',
1348 'title': 'PREVIEW: On Assignment: David Letterman',
1349 '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.',
1354 'url': 'https://video.udn.com/news/300346',
1355 'md5': 'fd2060e988c326991037b9aff9df21a6',
1359 'title': '中一中男師變性 全校師生力挺',
1360 'thumbnail': r're:^https?://.*\.jpg$',
1364 'skip_download': True,
1369 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1371 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1373 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1374 'title': 'This is what separates the Excel masters from the wannabes',
1375 'duration': 191.933,
1379 'skip_download': True,
1382 # Brightcove URL in single quotes
1384 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1385 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1387 'id': '4255764656001',
1389 'title': 'SN Presents: Russell Martin, World Citizen',
1390 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1391 'uploader': 'Rogers Sportsnet',
1392 'uploader_id': '1704050871',
1393 'upload_date': '20150525',
1394 'timestamp': 1432570283,
1397 # Dailymotion Cloud video
1399 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1400 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1404 'title': 'Sauvons les abeilles ! - Le débat',
1405 'description': 'md5:d9082128b1c5277987825d684939ca26',
1406 'thumbnail': r're:^https?://.*\.jpe?g$',
1407 'timestamp': 1434970506,
1408 'upload_date': '20150622',
1409 'uploader': 'Public Sénat',
1410 'uploader_id': 'xa9gza',
1413 # OnionStudios embed
1415 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1419 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1420 'thumbnail': r're:^https?://.*\.jpe?g$',
1421 'uploader': 'ClickHole',
1422 'uploader_id': 'clickhole',
1427 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1429 'id': '74849a00-85a9-11e1-9660-123139220831',
1431 'title': '#whilewewatch',
1434 # AdobeTVVideo embed
1436 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1437 'md5': '43662b577c018ad707a63766462b1e87',
1441 'title': 'New experience with Acrobat DC',
1442 'description': 'New experience with Acrobat DC',
1443 'duration': 248.667,
1446 # BrightcoveInPageEmbed embed
1448 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1450 'id': '4238694884001',
1452 'title': 'Tabletop: Dread, Last Thoughts',
1453 'description': 'Tabletop: Dread, Last Thoughts',
1457 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1458 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1460 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1462 'id': '4785848093001',
1464 'title': 'The Cardinal Pell Interview',
1465 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1466 'uploader': 'GlobeCast Australia - GlobeStream',
1467 'uploader_id': '2733773828001',
1468 'upload_date': '20160304',
1469 'timestamp': 1457083087,
1473 'skip_download': True,
1477 # Brightcove embed with whitespace around attribute names
1478 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1480 'id': '3167554373001',
1482 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1483 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1484 'uploader_id': '1079349493',
1485 'upload_date': '20140207',
1486 'timestamp': 1391810548,
1489 'skip_download': True,
1492 # Another form of arte.tv embed
1494 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1495 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1497 'id': '030273-562_PLUS7-F',
1499 'title': 'ARTE Reportage - Nulle part, en France',
1500 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1501 'upload_date': '20160409',
1506 'url': 'http://www.wykop.pl/link/3088787/',
1507 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1509 'id': '874_1459135191',
1511 'title': 'Man shows poor quality of new apartment building',
1512 'description': 'The wall is like a sand pile.',
1513 'uploader': 'Lake8737',
1516 # Duplicated embedded video URLs
1518 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1520 'id': '149298443_480_16c25b74_2',
1522 'title': 'vs. Blue Orange Spring Game',
1523 'uploader': 'www.hudl.com',
1526 # twitter:player:stream embed
1528 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1532 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1533 'uploader': 'www.rtl.be',
1537 'skip_download': True,
1540 # twitter:player embed
1542 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1543 'md5': 'a3e0df96369831de324f0778e126653c',
1545 'id': '4909620399001',
1547 'title': 'What Do Black Holes Sound Like?',
1548 'description': 'what do black holes sound like',
1549 'upload_date': '20160524',
1550 'uploader_id': '29913724001',
1551 'timestamp': 1464107587,
1552 'uploader': 'TheAtlantic',
1554 'add_ie': ['BrightcoveLegacy'],
1558 'url': 'https://www.funk.net/serien/5940e15073f6120001657956/items/593efbb173f6120001657503',
1562 'title': "Yesterday's Jam (OV)",
1563 'description': 'md5:09bc0984723fed34e2581624a84e05f0',
1564 'timestamp': 1492594816,
1565 'upload_date': '20170419',
1568 'format': 'bestvideo',
1569 'skip_download': True,
1572 # Facebook <iframe> embed
1574 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1575 'md5': 'fbcde74f534176ecb015849146dd3aee',
1577 'id': '599637780109885',
1579 'title': 'Facebook video #599637780109885',
1582 # Facebook <iframe> embed, plugin video
1584 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1586 'id': '1754168231264132',
1588 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1589 'uploader': 'Tariq Ramadan (official)',
1590 'timestamp': 1496758379,
1591 'upload_date': '20170606',
1594 'skip_download': True,
1597 # Facebook API embed
1599 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1600 'md5': 'a47372ee61b39a7b90287094d447d94e',
1602 'id': '10153467542406923',
1604 'title': 'Facebook video #10153467542406923',
1607 # Wordpress "YouTube Video Importer" plugin
1609 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1610 'md5': 'd16797741b560b485194eddda8121b48',
1612 'id': 'HNTXWDXV9Is',
1614 'title': 'Blue Devils Drumline Stanford lot 2016',
1615 'upload_date': '20160627',
1616 'uploader_id': 'GENOCIDE8GENERAL10',
1617 'uploader': 'cylus cyrus',
1621 # video stored on custom kaltura server
1622 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1623 'md5': '537617d06e64dfed891fa1593c4b30cc',
1627 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1628 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1629 'uploader_id': 'videos.expansion@el-mundo.net',
1630 'upload_date': '20150429',
1631 'timestamp': 1430303472,
1633 'add_ie': ['Kaltura'],
1636 # Non-standard Vimeo embed
1637 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1638 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1642 'title': 'Understanding the web - Teaser',
1643 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1644 'upload_date': '20151214',
1645 'uploader': 'OpenClassrooms',
1646 'uploader_id': 'openclassrooms',
1648 'add_ie': ['Vimeo'],
1651 # generic vimeo embed that requires original URL passed as Referer
1652 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1653 'only_matching': True,
1656 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1657 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1659 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1661 'title': 'Big Buck Bunny',
1662 'description': 'Royalty free test video',
1663 'timestamp': 1432816365,
1664 'upload_date': '20150528',
1668 'skip_download': True,
1670 'add_ie': [ArkenaIE.ie_key()],
1673 'url': 'http://nova.bg/news/view/2016/08/16/156543/%D0%BD%D0%B0-%D0%BA%D0%BE%D1%81%D1%8A%D0%BC-%D0%BE%D1%82-%D0%B2%D0%B7%D1%80%D0%B8%D0%B2-%D0%BE%D1%82%D1%86%D0%B5%D0%BF%D0%B8%D1%85%D0%B0-%D1%86%D1%8F%D0%BB-%D0%BA%D0%B2%D0%B0%D1%80%D1%82%D0%B0%D0%BB-%D0%B7%D0%B0%D1%80%D0%B0%D0%B4%D0%B8-%D0%B8%D0%B7%D1%82%D0%B8%D1%87%D0%B0%D0%BD%D0%B5-%D0%BD%D0%B0-%D0%B3%D0%B0%D0%B7-%D0%B2-%D0%BF%D0%BB%D0%BE%D0%B2%D0%B4%D0%B8%D0%B2/',
1677 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1680 'skip_download': True,
1682 'add_ie': [Vbox7IE.ie_key()],
1686 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1689 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1691 'playlist_mincount': 3,
1695 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1697 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1698 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1700 'playlist_mincount': 2,
1704 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1708 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1709 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1712 'skip_download': True,
1714 'add_ie': [TwentyMinutenIE.ie_key()],
1718 'url': 'https://en.support.wordpress.com/videopress/',
1722 'title': 'IMG_5786',
1723 'timestamp': 1435711927,
1724 'upload_date': '20150701',
1727 'skip_download': True,
1729 'add_ie': [VideoPressIE.ie_key()],
1733 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1735 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1737 'title': 'Магаззино: Казань 2',
1738 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1739 'uploader': 'Магаззино',
1740 'upload_date': '20170228',
1741 'uploader_id': '996642',
1744 'skip_download': True,
1746 'add_ie': [RutubeIE.ie_key()],
1749 # ThePlatform embedded with whitespaces in URLs
1750 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1751 'only_matching': True,
1754 # Senate ISVP iframe https
1755 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1756 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1758 'id': 'govtaff020316',
1760 'title': 'Integrated Senate Video Player',
1762 'add_ie': [SenateISVPIE.ie_key()],
1765 # Limelight embeds (1 channel embed + 4 media embeds)
1766 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1768 'id': 'FacilitatorTraining2017',
1769 'title': 'Facilitator Training 2017',
1771 'playlist_mincount': 5,
1774 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1776 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1777 'title': 'Standoff with Walnut Creek murder suspect ends',
1778 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1780 'playlist_mincount': 4,
1783 # WashingtonPost embed
1784 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1786 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1788 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1789 'description': 'Donald Trump wanted a weekly TV drama based on his life. It never aired. But The Washington Post recently obtained a scene from the pilot script — and enlisted actors.',
1790 'timestamp': 1455216756,
1791 'uploader': 'The Washington Post',
1792 'upload_date': '20160211',
1794 'add_ie': [WashingtonPostIE.ie_key()],
1798 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1802 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1805 'skip_download': True,
1807 'add_ie': [MediasetIE.ie_key()],
1811 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1813 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1814 'title': 'Slovenskom sa prehnala vlna silných búrok',
1816 'playlist_mincount': 5,
1817 'add_ie': [JojIE.ie_key()],
1820 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1821 'url': 'https://tvrain.ru/amp/418921/',
1822 'md5': 'cc00413936695987e8de148b67d14f1d',
1826 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1830 # # TODO: find another test
1831 # # http://schema.org/VideoObject
1832 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1833 # 'md5': '888dcf08b7ea671381f00fab74692755',
1835 # 'id': 'nyvTSJMKId',
1837 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1838 # 'description': '#love for cats.',
1839 # 'timestamp': 1461244995,
1840 # 'upload_date': '20160421',
1843 # 'force_generic_extractor': True,
1848 def report_following_redirect(self, new_url):
1849 """Report information extraction."""
1850 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1852 def _extract_rss(self, url, video_id, doc):
1853 playlist_title = doc.find('./channel/title').text
1854 playlist_desc_el = doc.find('./channel/description')
1855 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1858 for it in doc.findall('./channel/item'):
1859 next_url = xpath_text(it, 'link', fatal=False)
1861 enclosure_nodes = it.findall('./enclosure')
1862 for e in enclosure_nodes:
1863 next_url = e.attrib.get('url')
1871 '_type': 'url_transparent',
1873 'title': it.find('title').text,
1877 '_type': 'playlist',
1879 'title': playlist_title,
1880 'description': playlist_desc,
1884 def _extract_camtasia(self, url, video_id, webpage):
1885 """ Returns None if no camtasia video can be found. """
1887 camtasia_cfg = self._search_regex(
1888 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1889 webpage, 'camtasia configuration file', default=None)
1890 if camtasia_cfg is None:
1893 title = self._html_search_meta('DC.title', webpage, fatal=True)
1895 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1896 camtasia_cfg = self._download_xml(
1897 camtasia_url, video_id,
1898 note='Downloading camtasia configuration',
1899 errnote='Failed to download camtasia configuration')
1900 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1903 for n in fileset_node.getchildren():
1904 url_n = n.find('./uri')
1909 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1910 'title': '%s - %s' % (title, n.tag),
1911 'url': compat_urlparse.urljoin(url, url_n.text),
1912 'duration': float_or_none(n.find('./duration').text),
1916 '_type': 'playlist',
1921 def _real_extract(self, url):
1922 if url.startswith('//'):
1925 'url': self.http_scheme() + url,
1928 parsed_url = compat_urlparse.urlparse(url)
1929 if not parsed_url.scheme:
1930 default_search = self._downloader.params.get('default_search')
1931 if default_search is None:
1932 default_search = 'fixup_error'
1934 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1936 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1937 return self.url_result('http://' + url)
1938 elif default_search != 'fixup_error':
1939 if default_search == 'auto_warning':
1940 if re.match(r'^(?:url|URL)$', url):
1941 raise ExtractorError(
1942 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1945 self._downloader.report_warning(
1946 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1947 return self.url_result('ytsearch:' + url)
1949 if default_search in ('error', 'fixup_error'):
1950 raise ExtractorError(
1951 '%r is not a valid URL. '
1952 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1953 % (url, url), expected=True)
1955 if ':' not in default_search:
1956 default_search += ':'
1957 return self.url_result(default_search + url)
1959 url, smuggled_data = unsmuggle_url(url)
1960 force_videoid = None
1961 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1962 if smuggled_data and 'force_videoid' in smuggled_data:
1963 force_videoid = smuggled_data['force_videoid']
1964 video_id = force_videoid
1966 video_id = self._generic_id(url)
1968 self.to_screen('%s: Requesting header' % video_id)
1970 head_req = HEADRequest(url)
1971 head_response = self._request_webpage(
1973 note=False, errnote='Could not send HEAD request to %s' % url,
1976 if head_response is not False:
1977 # Check for redirect
1978 new_url = head_response.geturl()
1980 self.report_following_redirect(new_url)
1982 new_url = smuggle_url(
1983 new_url, {'force_videoid': force_videoid})
1984 return self.url_result(new_url)
1986 full_response = None
1987 if head_response is False:
1988 request = sanitized_Request(url)
1989 request.add_header('Accept-Encoding', '*')
1990 full_response = self._request_webpage(request, video_id)
1991 head_response = full_response
1995 'title': self._generic_title(url),
1996 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1999 # Check for direct link to a video
2000 content_type = head_response.headers.get('Content-Type', '').lower()
2001 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2003 format_id = compat_str(m.group('format_id'))
2004 if format_id.endswith('mpegurl'):
2005 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2006 elif format_id == 'f4m':
2007 formats = self._extract_f4m_formats(url, video_id)
2010 'format_id': format_id,
2012 'vcodec': 'none' if m.group('type') == 'audio' else None
2014 info_dict['direct'] = True
2015 self._sort_formats(formats)
2016 info_dict['formats'] = formats
2019 if not self._downloader.params.get('test', False) and not is_intentional:
2020 force = self._downloader.params.get('force_generic_extractor', False)
2021 self._downloader.report_warning(
2022 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2024 if not full_response:
2025 request = sanitized_Request(url)
2026 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2027 # making it impossible to download only chunk of the file (yet we need only 512kB to
2028 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2029 # that will always result in downloading the whole file that is not desirable.
2030 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2031 # to accept raw bytes and being able to download only a chunk.
2032 # It may probably better to solve this by checking Content-Type for application/octet-stream
2033 # after HEAD request finishes, but not sure if we can rely on this.
2034 request.add_header('Accept-Encoding', '*')
2035 full_response = self._request_webpage(request, video_id)
2037 first_bytes = full_response.read(512)
2039 # Is it an M3U playlist?
2040 if first_bytes.startswith(b'#EXTM3U'):
2041 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2042 self._sort_formats(info_dict['formats'])
2045 # Maybe it's a direct link to a video?
2046 # Be careful not to download the whole thing!
2047 if not is_html(first_bytes):
2048 self._downloader.report_warning(
2049 'URL could be a direct video link, returning it as such.')
2056 webpage = self._webpage_read_content(
2057 full_response, url, video_id, prefix=first_bytes)
2059 self.report_extraction(video_id)
2061 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2063 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2064 if doc.tag == 'rss':
2065 return self._extract_rss(url, video_id, doc)
2066 elif doc.tag == 'SmoothStreamingMedia':
2067 info_dict['formats'] = self._parse_ism_formats(doc, url)
2068 self._sort_formats(info_dict['formats'])
2070 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2071 smil = self._parse_smil(doc, url, video_id)
2072 self._sort_formats(smil['formats'])
2074 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2075 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
2076 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2077 info_dict['formats'] = self._parse_mpd_formats(
2079 mpd_base_url=full_response.geturl().rpartition('/')[0],
2081 self._sort_formats(info_dict['formats'])
2083 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2084 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2085 self._sort_formats(info_dict['formats'])
2087 except compat_xml_parse_error:
2090 # Is it a Camtasia project?
2091 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2092 if camtasia_res is not None:
2095 # Sometimes embedded video player is hidden behind percent encoding
2096 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2097 # Unescaping the whole page allows to handle those cases in a generic way
2098 webpage = compat_urllib_parse_unquote(webpage)
2100 # it's tempting to parse this further, but you would
2101 # have to take into account all the variations like
2102 # Video Title - Site Name
2103 # Site Name | Video Title
2104 # Video Title - Tagline | Site Name
2105 # and so on and so forth; it's just not practical
2106 video_title = self._og_search_title(
2107 webpage, default=None) or self._html_search_regex(
2108 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2111 # Try to detect age limit automatically
2112 age_limit = self._rta_search(webpage)
2113 # And then there are the jokers who advertise that they use RTA,
2114 # but actually don't.
2115 AGE_LIMIT_MARKERS = [
2116 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
2118 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2121 # video uploader is domain name
2122 video_uploader = self._search_regex(
2123 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2125 video_description = self._og_search_description(webpage, default=None)
2126 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2129 'title': video_title,
2130 'description': video_description,
2131 'thumbnail': video_thumbnail,
2132 'age_limit': age_limit,
2135 # Look for Brightcove Legacy Studio embeds
2136 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2140 'url': smuggle_url(bc_url, {'Referer': url}),
2141 'ie_key': 'BrightcoveLegacy'
2142 } for bc_url in bc_urls]
2145 '_type': 'playlist',
2146 'title': video_title,
2151 # Look for Brightcove New Studio embeds
2152 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2154 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2156 # Look for Nexx embeds
2157 nexx_urls = NexxIE._extract_urls(webpage)
2159 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2161 # Look for Nexx iFrame embeds
2162 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2164 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2166 # Look for ThePlatform embeds
2167 tp_urls = ThePlatformIE._extract_urls(webpage)
2169 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2171 # Look for Vessel embeds
2172 vessel_urls = VesselIE._extract_urls(webpage)
2174 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2176 # Look for embedded rtl.nl player
2177 matches = re.findall(
2178 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
2181 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2183 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2185 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2187 vid_me_embed_url = self._search_regex(
2188 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2189 webpage, 'vid.me embed', default=None)
2190 if vid_me_embed_url is not None:
2191 return self.url_result(vid_me_embed_url, 'Vidme')
2193 # Look for embedded YouTube player
2194 matches = re.findall(r'''(?x)
2204 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2208 return self.playlist_from_matches(
2209 matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
2211 # Look for lazyYT YouTube embed
2212 matches = re.findall(
2213 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
2215 return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
2217 # Look for Wordpress "YouTube Video Importer" plugin
2218 matches = re.findall(r'''(?x)<div[^>]+
2219 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2220 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2222 return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
2224 matches = DailymotionIE._extract_urls(webpage)
2226 return self.playlist_from_matches(matches, video_id, video_title)
2228 # Look for embedded Dailymotion playlist player (#3822)
2230 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2232 playlists = re.findall(
2233 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2235 return self.playlist_from_matches(
2236 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2238 # Look for DailyMail embeds
2239 dailymail_urls = DailyMailIE._extract_urls(webpage)
2241 return self.playlist_from_matches(
2242 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2244 # Look for embedded Wistia player
2245 wistia_url = WistiaIE._extract_url(webpage)
2248 '_type': 'url_transparent',
2249 'url': self._proto_relative_url(wistia_url),
2250 'ie_key': WistiaIE.ie_key(),
2251 'uploader': video_uploader,
2254 # Look for SVT player
2255 svt_url = SVTIE._extract_url(webpage)
2257 return self.url_result(svt_url, 'SVT')
2259 # Look for Bandcamp pages with custom domain
2260 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2261 if mobj is not None:
2262 burl = unescapeHTML(mobj.group(1))
2263 # Don't set the extractor because it can be a track url or an album
2264 return self.url_result(burl)
2266 # Look for embedded Vevo player
2268 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2269 if mobj is not None:
2270 return self.url_result(mobj.group('url'))
2272 # Look for embedded Viddler player
2274 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2276 if mobj is not None:
2277 return self.url_result(mobj.group('url'))
2279 # Look for NYTimes player
2281 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2283 if mobj is not None:
2284 return self.url_result(mobj.group('url'))
2286 # Look for Libsyn player
2288 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2289 if mobj is not None:
2290 return self.url_result(mobj.group('url'))
2292 # Look for Ooyala videos
2293 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2294 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2295 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2296 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2297 if mobj is not None:
2298 embed_token = self._search_regex(
2299 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2300 webpage, 'ooyala embed token', default=None)
2301 return OoyalaIE._build_url_result(smuggle_url(
2304 'embed_token': embed_token,
2307 # Look for multiple Ooyala embeds on SBN network websites
2308 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2309 if mobj is not None:
2310 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2312 return self.playlist_from_matches(
2313 embeds, video_id, video_title,
2314 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2316 # Look for Aparat videos
2317 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2318 if mobj is not None:
2319 return self.url_result(mobj.group(1), 'Aparat')
2321 # Look for MPORA videos
2322 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2323 if mobj is not None:
2324 return self.url_result(mobj.group(1), 'Mpora')
2326 # Look for embedded NovaMov-based player
2328 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2329 (?P<url>http://(?:(?:embed|www)\.)?
2331 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2332 videoweed\.(?:es|com)|
2333 movshare\.(?:net|sx|ag)|
2334 divxstage\.(?:eu|net|ch|co|at|ag))
2335 /embed\.php.+?)\1''', webpage)
2336 if mobj is not None:
2337 return self.url_result(mobj.group('url'))
2339 # Look for embedded Facebook player
2340 facebook_urls = FacebookIE._extract_urls(webpage)
2342 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2344 # Look for embedded VK player
2345 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2346 if mobj is not None:
2347 return self.url_result(mobj.group('url'), 'VK')
2349 # Look for embedded Odnoklassniki player
2350 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2351 if mobj is not None:
2352 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2354 # Look for embedded ivi player
2355 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2356 if mobj is not None:
2357 return self.url_result(mobj.group('url'), 'Ivi')
2359 # Look for embedded Huffington Post player
2361 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2362 if mobj is not None:
2363 return self.url_result(mobj.group('url'), 'HuffPost')
2366 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2367 if mobj is not None:
2368 return self.url_result(mobj.group('url'))
2369 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2370 if mobj is not None:
2371 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2373 # Look for funnyordie embed
2374 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2376 return self.playlist_from_matches(
2377 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2379 # Look for BBC iPlayer embed
2380 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2382 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2384 # Look for embedded RUTV player
2385 rutv_url = RUTVIE._extract_url(webpage)
2387 return self.url_result(rutv_url, 'RUTV')
2389 # Look for embedded TVC player
2390 tvc_url = TVCIE._extract_url(webpage)
2392 return self.url_result(tvc_url, 'TVC')
2394 # Look for embedded SportBox player
2395 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2397 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2399 # Look for embedded XHamster player
2400 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2402 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2404 # Look for embedded TNAFlixNetwork player
2405 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2407 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2409 # Look for embedded PornHub player
2410 pornhub_urls = PornHubIE._extract_urls(webpage)
2412 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2414 # Look for embedded DrTuber player
2415 drtuber_urls = DrTuberIE._extract_urls(webpage)
2417 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2419 # Look for embedded RedTube player
2420 redtube_urls = RedTubeIE._extract_urls(webpage)
2422 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2424 # Look for embedded Tvigle player
2426 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2427 if mobj is not None:
2428 return self.url_result(mobj.group('url'), 'Tvigle')
2430 # Look for embedded TED player
2432 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2433 if mobj is not None:
2434 return self.url_result(mobj.group('url'), 'TED')
2436 # Look for embedded Ustream videos
2437 ustream_url = UstreamIE._extract_url(webpage)
2439 return self.url_result(ustream_url, UstreamIE.ie_key())
2441 # Look for embedded arte.tv player
2443 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2445 if mobj is not None:
2446 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2448 # Look for embedded francetv player
2450 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2452 if mobj is not None:
2453 return self.url_result(mobj.group('url'))
2455 # Look for embedded smotri.com player
2456 smotri_url = SmotriIE._extract_url(webpage)
2458 return self.url_result(smotri_url, 'Smotri')
2460 # Look for embedded Myvi.ru player
2461 myvi_url = MyviIE._extract_url(webpage)
2463 return self.url_result(myvi_url)
2465 # Look for embedded soundcloud player
2466 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2468 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2470 # Look for tunein player
2471 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2473 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2475 # Look for embedded mtvservices player
2476 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2478 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2480 # Look for embedded yahoo player
2482 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2484 if mobj is not None:
2485 return self.url_result(mobj.group('url'), 'Yahoo')
2487 # Look for embedded sbs.com.au player
2491 <meta\s+property="og:video"\s+content=|
2494 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2496 if mobj is not None:
2497 return self.url_result(mobj.group('url'), 'SBS')
2499 # Look for embedded Cinchcast player
2501 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2503 if mobj is not None:
2504 return self.url_result(mobj.group('url'), 'Cinchcast')
2507 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2511 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2513 if mobj is not None:
2514 return self.url_result(mobj.group('url'), 'MLB')
2517 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2519 if mobj is not None:
2520 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2523 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2525 if mobj is not None:
2526 return self.url_result(mobj.group('url'), 'Livestream')
2528 # Look for Zapiks embed
2530 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2531 if mobj is not None:
2532 return self.url_result(mobj.group('url'), 'Zapiks')
2534 # Look for Kaltura embeds
2535 kaltura_url = KalturaIE._extract_url(webpage)
2537 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2539 # Look for EaglePlatform embeds
2540 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2541 if eagleplatform_url:
2542 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2544 # Look for ClipYou (uses EaglePlatform) embeds
2546 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2547 if mobj is not None:
2548 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2550 # Look for Pladform embeds
2551 pladform_url = PladformIE._extract_url(webpage)
2553 return self.url_result(pladform_url)
2555 # Look for Videomore embeds
2556 videomore_url = VideomoreIE._extract_url(webpage)
2558 return self.url_result(videomore_url)
2560 # Look for Webcaster embeds
2561 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2563 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2565 # Look for Playwire embeds
2567 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2568 if mobj is not None:
2569 return self.url_result(mobj.group('url'))
2571 # Look for 5min embeds
2573 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2574 if mobj is not None:
2575 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2577 # Look for Crooks and Liars embeds
2579 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2580 if mobj is not None:
2581 return self.url_result(mobj.group('url'))
2583 # Look for NBC Sports VPlayer embeds
2584 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2586 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2588 # Look for NBC News embeds
2589 nbc_news_embed_url = re.search(
2590 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2591 if nbc_news_embed_url:
2592 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2594 # Look for Google Drive embeds
2595 google_drive_url = GoogleDriveIE._extract_url(webpage)
2596 if google_drive_url:
2597 return self.url_result(google_drive_url, 'GoogleDrive')
2599 # Look for UDN embeds
2601 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2602 if mobj is not None:
2603 return self.url_result(
2604 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2606 # Look for Senate ISVP iframe
2607 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2609 return self.url_result(senate_isvp_url, 'SenateISVP')
2611 # Look for Dailymotion Cloud videos
2612 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2614 return self.url_result(dmcloud_url, 'DailymotionCloud')
2616 # Look for OnionStudios embeds
2617 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2618 if onionstudios_url:
2619 return self.url_result(onionstudios_url)
2621 # Look for ViewLift embeds
2622 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2624 return self.url_result(viewlift_url)
2626 # Look for JWPlatform embeds
2627 jwplatform_url = JWPlatformIE._extract_url(webpage)
2629 return self.url_result(jwplatform_url, 'JWPlatform')
2631 # Look for Digiteka embeds
2632 digiteka_url = DigitekaIE._extract_url(webpage)
2634 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2636 # Look for Arkena embeds
2637 arkena_url = ArkenaIE._extract_url(webpage)
2639 return self.url_result(arkena_url, ArkenaIE.ie_key())
2641 # Look for Piksel embeds
2642 piksel_url = PikselIE._extract_url(webpage)
2644 return self.url_result(piksel_url, PikselIE.ie_key())
2646 # Look for Limelight embeds
2647 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2649 return self.playlist_result(
2650 limelight_urls, video_id, video_title, video_description)
2652 # Look for Anvato embeds
2653 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2655 return self.playlist_result(
2656 anvato_urls, video_id, video_title, video_description)
2658 # Look for AdobeTVVideo embeds
2660 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2662 if mobj is not None:
2663 return self.url_result(
2664 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2667 # Look for Vine embeds
2669 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2671 if mobj is not None:
2672 return self.url_result(
2673 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2675 # Look for VODPlatform embeds
2677 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2679 if mobj is not None:
2680 return self.url_result(
2681 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2683 # Look for Mangomolo embeds
2685 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2687 video\?.*?\bid=(?P<video_id>\d+)|
2688 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2689 ).+?)\1''', webpage)
2690 if mobj is not None:
2692 '_type': 'url_transparent',
2693 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2694 'title': video_title,
2695 'description': video_description,
2696 'thumbnail': video_thumbnail,
2697 'uploader': video_uploader,
2699 video_id = mobj.group('video_id')
2702 'ie_key': 'MangomoloVideo',
2707 'ie_key': 'MangomoloLive',
2708 'id': mobj.group('channel_id'),
2712 # Look for Instagram embeds
2713 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2714 if instagram_embed_url is not None:
2715 return self.url_result(
2716 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2718 # Look for LiveLeak embeds
2719 liveleak_url = LiveLeakIE._extract_url(webpage)
2721 return self.url_result(liveleak_url, 'LiveLeak')
2723 # Look for 3Q SDN embeds
2724 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2727 '_type': 'url_transparent',
2728 'ie_key': ThreeQSDNIE.ie_key(),
2729 'url': self._proto_relative_url(threeqsdn_url),
2730 'title': video_title,
2731 'description': video_description,
2732 'thumbnail': video_thumbnail,
2733 'uploader': video_uploader,
2736 # Look for VBOX7 embeds
2737 vbox7_url = Vbox7IE._extract_url(webpage)
2739 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2741 # Look for DBTV embeds
2742 dbtv_urls = DBTVIE._extract_urls(webpage)
2744 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2746 # Look for Videa embeds
2747 videa_urls = VideaIE._extract_urls(webpage)
2749 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2751 # Look for 20 minuten embeds
2752 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2754 return self.playlist_from_matches(
2755 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2757 # Look for Openload embeds
2758 openload_urls = OpenloadIE._extract_urls(webpage)
2760 return self.playlist_from_matches(
2761 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2763 # Look for VideoPress embeds
2764 videopress_urls = VideoPressIE._extract_urls(webpage)
2766 return self.playlist_from_matches(
2767 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2769 # Look for Rutube embeds
2770 rutube_urls = RutubeIE._extract_urls(webpage)
2772 return self.playlist_from_matches(
2773 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2775 # Look for WashingtonPost embeds
2776 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2778 return self.playlist_from_matches(
2779 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2781 # Look for Mediaset embeds
2782 mediaset_urls = MediasetIE._extract_urls(webpage)
2784 return self.playlist_from_matches(
2785 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2787 # Look for JOJ.sk embeds
2788 joj_urls = JojIE._extract_urls(webpage)
2790 return self.playlist_from_matches(
2791 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2793 def merge_dicts(dict1, dict2):
2795 for k, v in dict1.items():
2798 for k, v in dict2.items():
2801 if (k not in merged or
2802 (isinstance(v, compat_str) and v and
2803 isinstance(merged[k], compat_str) and
2808 # Looking for http://schema.org/VideoObject
2809 json_ld = self._search_json_ld(
2810 webpage, video_id, default={}, expected_type='VideoObject')
2811 if json_ld.get('url'):
2812 return merge_dicts(json_ld, info_dict)
2814 # Look for HTML5 media
2815 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2817 for entry in entries:
2820 'title': video_title,
2822 self._sort_formats(entry['formats'])
2823 return self.playlist_result(entries)
2825 jwplayer_data = self._find_jwplayer_data(
2826 webpage, video_id, transform_source=js_to_json)
2828 info = self._parse_jwplayer_data(
2829 jwplayer_data, video_id, require_title=False, base_url=url)
2830 return merge_dicts(info, info_dict)
2832 def check_video(vurl):
2833 if YoutubeIE.suitable(vurl):
2835 if RtmpIE.suitable(vurl):
2837 vpath = compat_urlparse.urlparse(vurl).path
2838 vext = determine_ext(vpath)
2839 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2841 def filter_video(urls):
2842 return list(filter(check_video, urls))
2844 # Start with something easy: JW Player in SWFObject
2845 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2847 # Look for gorilla-vid style embedding
2848 found = filter_video(re.findall(r'''(?sx)
2852 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2855 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2857 # Broaden the search a little bit
2858 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2860 # Broaden the findall a little bit: JWPlayer JS loader
2861 found = filter_video(re.findall(
2862 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2865 found = filter_video(re.findall(r'''(?xs)
2866 flowplayer\("[^"]+",\s*
2868 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2869 ["']?url["']?\s*:\s*["']([^"']+)["']
2874 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2876 # Try to find twitter cards info
2877 # twitter:player:stream should be checked before twitter:player since
2878 # it is expected to contain a raw stream (see
2879 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2880 found = filter_video(re.findall(
2881 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2883 # We look for Open Graph info:
2884 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2885 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2886 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2887 if m_video_type is not None:
2888 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2890 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2892 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2893 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2896 # Look also in Refresh HTTP header
2897 refresh_header = head_response.headers.get('Refresh')
2899 # In python 2 response HTTP headers are bytestrings
2900 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2901 refresh_header = refresh_header.decode('iso-8859-1')
2902 found = re.search(REDIRECT_REGEX, refresh_header)
2904 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2906 self.report_following_redirect(new_url)
2915 # twitter:player is a https URL to iframe player that may or may not
2916 # be supported by youtube-dl thus this is checked the very last (see
2917 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2918 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2920 return self.url_result(embed_url)
2923 raise UnsupportedError(url)
2926 for video_url in orderedSet(found):
2927 video_url = unescapeHTML(video_url)
2928 video_url = video_url.replace('\\/', '/')
2929 video_url = compat_urlparse.urljoin(url, video_url)
2930 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2932 # Sometimes, jwplayer extraction will result in a YouTube URL
2933 if YoutubeIE.suitable(video_url):
2934 entries.append(self.url_result(video_url, 'Youtube'))
2937 # here's a fun little line of code for you:
2938 video_id = os.path.splitext(video_id)[0]
2942 'uploader': video_uploader,
2943 'title': video_title,
2944 'age_limit': age_limit,
2947 if RtmpIE.suitable(video_url):
2948 entry_info_dict.update({
2949 '_type': 'url_transparent',
2950 'ie_key': RtmpIE.ie_key(),
2953 entries.append(entry_info_dict)
2956 ext = determine_ext(video_url)
2958 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2960 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2962 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2964 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2966 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2967 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2968 # Just matching .ism/manifest is not enough to be reliably sure
2969 # whether it's actually an ISM manifest or some other streaming
2970 # manifest since there are various streaming URL formats
2971 # possible (see [1]) as well as some other shenanigans like
2972 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2974 # Thus the most reasonable way to solve this is to delegate
2975 # to generic extractor in order to look into the contents of
2976 # the manifest itself.
2977 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2978 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2979 entry_info_dict = self.url_result(
2980 smuggle_url(video_url, {'to_generic': True}),
2983 entry_info_dict['url'] = video_url
2985 if entry_info_dict.get('formats'):
2986 self._sort_formats(entry_info_dict['formats'])
2988 entries.append(entry_info_dict)
2990 if len(entries) == 1:
2993 for num, e in enumerate(entries, start=1):
2994 # 'url' results don't have a title
2995 if e.get('title') is not None:
2996 e['title'] = '%s (%d)' % (e['title'], num)
2998 '_type': 'playlist',