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,
36 from .commonprotocols import RtmpIE
37 from .brightcove import (
45 from .nbc import NBCSportsVPlayerIE
46 from .ooyala import OoyalaIE
47 from .rutv import RUTVIE
48 from .tvc import TVCIE
49 from .sportbox import SportBoxEmbedIE
50 from .smotri import SmotriIE
51 from .myvi import MyviIE
52 from .condenast import CondeNastIE
53 from .udn import UDNEmbedIE
54 from .senateisvp import SenateISVPIE
55 from .svt import SVTIE
56 from .pornhub import PornHubIE
57 from .xhamster import XHamsterEmbedIE
58 from .tnaflix import TNAFlixNetworkEmbedIE
59 from .drtuber import DrTuberIE
60 from .redtube import RedTubeIE
61 from .vimeo import VimeoIE
62 from .dailymotion import (
66 from .dailymail import DailyMailIE
67 from .onionstudios import OnionStudiosIE
68 from .viewlift import ViewLiftEmbedIE
69 from .mtv import MTVServicesEmbeddedIE
70 from .pladform import PladformIE
71 from .videomore import VideomoreIE
72 from .webcaster import WebcasterFeedIE
73 from .googledrive import GoogleDriveIE
74 from .jwplatform import JWPlatformIE
75 from .digiteka import DigitekaIE
76 from .arkena import ArkenaIE
77 from .instagram import InstagramIE
78 from .liveleak import LiveLeakIE
79 from .threeqsdn import ThreeQSDNIE
80 from .theplatform import ThePlatformIE
81 from .vessel import VesselIE
82 from .kaltura import KalturaIE
83 from .eagleplatform import EaglePlatformIE
84 from .facebook import FacebookIE
85 from .soundcloud import SoundcloudIE
86 from .tunein import TuneInBaseIE
87 from .vbox7 import Vbox7IE
88 from .dbtv import DBTVIE
89 from .piksel import PikselIE
90 from .videa import VideaIE
91 from .twentymin import TwentyMinutenIE
92 from .ustream import UstreamIE
93 from .openload import OpenloadIE
94 from .videopress import VideoPressIE
95 from .rutube import RutubeIE
96 from .limelight import LimelightBaseIE
97 from .anvato import AnvatoIE
98 from .washingtonpost import WashingtonPostIE
99 from .wistia import WistiaIE
100 from .mediaset import MediasetIE
101 from .joj import JojIE
102 from .megaphone import MegaphoneIE
103 from .vzaar import VzaarIE
104 from .channel9 import Channel9IE
107 class GenericIE(InfoExtractor):
108 IE_DESC = 'Generic downloader that works on some sites'
112 # Direct link to a video
114 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
115 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
120 'upload_date': '20100513',
123 # Direct link to media delivered compressed (until Accept-Encoding is *)
125 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
126 'md5': '128c42e68b13950268b648275386fc74',
128 'id': 'FictionJunction-Parallel_Hearts',
130 'title': 'FictionJunction-Parallel_Hearts',
131 'upload_date': '20140522',
133 'expected_warnings': [
134 'URL could be a direct video link, returning it as such.'
136 'skip': 'URL invalid',
138 # Direct download with broken HEAD
140 'url': 'http://ai-radio.org:8000/radio.opus',
147 'skip_download': True, # infinite live stream
149 'expected_warnings': [
150 r'501.*Not Implemented',
154 # Direct link with incorrect MIME type
156 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
157 'md5': '4ccbebe5f36706d85221f204d7eb5913',
159 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
160 'id': '5_Lennart_Poettering_-_Systemd',
162 'title': '5_Lennart_Poettering_-_Systemd',
163 'upload_date': '20141120',
165 'expected_warnings': [
166 'URL could be a direct video link, returning it as such.'
171 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
173 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
174 'title': 'Zero Punctuation',
175 'description': 're:.*groundbreaking video review series.*'
177 'playlist_mincount': 11,
179 # RSS feed with enclosure
181 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
183 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
185 'upload_date': '20150228',
186 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
189 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
191 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
195 'title': 'Automatics, robotics and biocybernetics',
196 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
197 'upload_date': '20130627',
198 'formats': 'mincount:16',
199 'subtitles': 'mincount:1',
202 'force_generic_extractor': True,
203 'skip_download': True,
206 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
208 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
213 'formats': 'mincount:1',
216 'skip_download': True,
219 # SMIL from https://www.restudy.dk/video/play/id/1637
221 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
225 'title': 'video_1637',
226 'formats': 'mincount:3',
229 'skip_download': True,
232 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
234 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
236 'id': 'smil-service',
238 'title': 'smil-service',
239 'formats': 'mincount:1',
242 'skip_download': True,
245 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
247 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
251 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
252 'formats': 'mincount:3',
255 'skip_download': True,
258 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
260 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
262 'id': 'mZlp2ctYIUEB',
264 'title': 'Tikibad ontruimd wegens brand',
265 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
266 'thumbnail': r're:^https?://.*\.jpg$',
270 'skip_download': True,
273 # MPD from http://dash-mse-test.appspot.com/media.html
275 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
276 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
278 'id': 'car-20120827-manifest',
280 'title': 'car-20120827-manifest',
281 'formats': 'mincount:9',
282 'upload_date': '20130904',
285 'format': 'bestvideo',
288 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
290 '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',
295 'formats': 'mincount:8',
299 'skip_download': True,
301 'skip': 'video gone',
303 # m3u8 served with Content-Type: text/plain
305 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
310 'upload_date': '20140720',
311 'formats': 'mincount:11',
315 'skip_download': True,
317 'skip': 'video gone',
321 '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',
325 'upload_date': '20130224',
326 'uploader_id': 'TheVerge',
327 'description': r're:^Chris Ziegler takes a look at the\.*',
328 'uploader': 'The Verge',
329 'title': 'First Firefox OS phones side-by-side',
332 'skip_download': False,
336 # redirect in Refresh HTTP header
337 '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',
341 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
342 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
343 'upload_date': '20150917',
344 'uploader_id': 'brtvofficial',
345 'uploader': 'Boiler Room',
348 'skip_download': False,
352 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
353 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
355 'id': '13601338388002',
357 'uploader': 'www.hodiho.fr',
358 'title': 'R\u00e9gis plante sa Jeep',
361 # bandcamp page with custom domain
363 'add_ie': ['Bandcamp'],
364 'url': 'http://bronyrock.com/track/the-pony-mash',
368 'title': 'The Pony Mash',
369 'uploader': 'M_Pallante',
371 'skip': 'There is a limit of 200 free downloads / month for the test song',
374 # embedded brightcove video
375 # it also tests brightcove videos that need to set the 'Referer'
376 # in the http requests
377 'add_ie': ['BrightcoveLegacy'],
378 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
380 'id': '2765128793001',
382 'title': 'Le cours de bourse : l’analyse technique',
383 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
384 'uploader': 'BFM BUSINESS',
387 'skip_download': True,
391 # embedded with itemprop embedURL and video id spelled as `idVideo`
392 'add_id': ['BrightcoveLegacy'],
393 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
395 'id': '5255628253001',
397 'title': 'md5:37c519b1128915607601e75a87995fc0',
398 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
399 'uploader': 'BFM BUSINESS',
400 'uploader_id': '876450612001',
401 'timestamp': 1482255315,
402 'upload_date': '20161220',
405 'skip_download': True,
409 # https://github.com/rg3/youtube-dl/issues/2253
410 'url': 'http://bcove.me/i6nfkrc3',
411 'md5': '0ba9446db037002366bab3b3eb30c88c',
413 'id': '3101154703001',
415 'title': 'Still no power',
416 'uploader': 'thestar.com',
417 '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.',
419 'add_ie': ['BrightcoveLegacy'],
420 'skip': 'video gone',
423 'url': 'http://www.championat.com/video/football/v/87/87499.html',
424 'md5': 'fb973ecf6e4a78a67453647444222983',
426 'id': '3414141473001',
428 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
429 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
430 'uploader': 'Championat',
434 # https://github.com/rg3/youtube-dl/issues/3541
435 'add_ie': ['BrightcoveLegacy'],
436 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
438 'id': '3866516442001',
440 'title': 'Leer mij vrouwen kennen: Aflevering 1',
441 'description': 'Leer mij vrouwen kennen: Aflevering 1',
442 'uploader': 'SBS Broadcasting',
444 'skip': 'Restricted to Netherlands',
446 'skip_download': True, # m3u8 download
450 # Brightcove video in <iframe>
451 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
452 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
454 'id': '5360463607001',
456 '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',
457 '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。',
458 'uploader': 'United Nations',
459 'uploader_id': '1362235914001',
460 'timestamp': 1489593889,
461 'upload_date': '20170315',
463 'add_ie': ['BrightcoveLegacy'],
466 # Brightcove with alternative playerID key
467 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
469 'id': 'nmeth.2062_SV1',
470 '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',
474 'id': '2228375078001',
476 'title': 'nmeth.2062-sv1',
477 'description': 'nmeth.2062-sv1',
478 'timestamp': 1363357591,
479 'upload_date': '20130315',
480 'uploader': 'Nature Publishing Group',
481 'uploader_id': '1964492299001',
486 # Brightcove with UUID in videoPlayer
487 'url': 'http://www8.hp.com/cn/zh/home.html',
489 'id': '5255815316001',
491 'title': 'Sprocket Video - China',
492 'description': 'Sprocket Video - China',
493 'uploader': 'HP-Video Gallery',
494 'timestamp': 1482263210,
495 'upload_date': '20161220',
496 'uploader_id': '1107601872001',
499 'skip_download': True, # m3u8 download
501 'skip': 'video rotates...weekly?',
504 # Brightcove:new type [2].
505 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
506 'md5': '2b35148fcf48da41c9fb4591650784f3',
508 'id': '5348741021001',
510 'upload_date': '20170306',
511 'uploader_id': '4191638492001',
512 'timestamp': 1488769918,
513 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
518 # Alternative brightcove <video> attributes
519 '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/',
521 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
522 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
525 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
527 'id': '5311302538001',
529 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
530 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
531 'timestamp': 1486321708,
532 'upload_date': '20170205',
533 'uploader_id': '800000640001',
535 'only_matching': True,
539 # Brightcove with UUID in videoPlayer
540 'url': 'http://www8.hp.com/cn/zh/home.html',
542 'id': '5255815316001',
544 'title': 'Sprocket Video - China',
545 'description': 'Sprocket Video - China',
546 'uploader': 'HP-Video Gallery',
547 'timestamp': 1482263210,
548 'upload_date': '20161220',
549 'uploader_id': '1107601872001',
552 'skip_download': True, # m3u8 download
557 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
558 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
560 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
562 'title': '2cc213299525360.mov', # that's what we get
565 'add_ie': ['Ooyala'],
568 # ooyala video embedded with http://player.ooyala.com/iframe.js
569 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
571 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
573 'title': '"Steve Jobs: Man in the Machine" trailer',
574 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
578 'skip_download': True,
580 'skip': 'movie expired',
582 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
584 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
586 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
588 'title': 'Steampunk Fest Comes to Honesdale',
592 'skip_download': True,
597 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
601 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
602 'upload_date': '20140225',
603 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
604 'uploader': 'Tested',
605 'uploader_id': 'testedcom',
607 # No need to test YoutubeIE here
609 'skip_download': True,
614 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
618 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
619 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
621 # HEAD requests lead to endless 301, while GET is OK
622 'expected_warnings': ['301'],
626 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
630 'title': 'Охотское море стало целиком российским',
631 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
635 'skip_download': True,
640 '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/',
644 'title': 'Дошкольное воспитание',
649 'url': 'http://www.vestifinance.ru/articles/25753',
652 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
657 'title': 'Госзаказ. День 3',
663 'title': 'Госзаказ. День 2',
669 'title': 'Госзаказ. День 1',
675 'skip_download': True,
680 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
682 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
684 'title': 'Ужастики, русский трейлер (2015)',
685 'thumbnail': r're:^https?://.*\.jpg$',
691 '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',
694 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
696 'playlist_mincount': 7,
697 # This forum does not allow <iframe> syntaxes anymore
698 # Now HTML tags are displayed as-is
699 'skip': 'No videos on this page',
703 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
704 'md5': '65fdff94098e4a607385a60c5177c638',
708 'title': 'Hidden miracles of the natural world',
709 'uploader': 'Louie Schwartzberg',
710 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
713 # nowvideo embed hidden behind percent encoding
715 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
716 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
718 'id': '06e53103ca9aa',
720 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
721 'description': 'No description',
726 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
727 'md5': '7653032cbb25bf6c80d80f217055fa43',
729 'id': '048195-004_PLUS7-F',
732 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
733 'upload_date': '20140320',
736 'skip_download': 'Requires rtmpdump'
738 'skip': 'video gone',
742 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
746 'title': 'Alcaline, le concert avec Calogero',
747 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
748 'upload_date': '20150226',
749 'timestamp': 1424989860,
754 'skip_download': True,
756 'expected_warnings': [
762 'url': 'http://www.wired.com/2014/04/honda-asimo/',
763 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
765 'id': '53501be369702d3275860000',
767 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
772 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
773 'md5': '441aeeb82eb72c422c7f14ec533999cd',
775 'id': 'k2mm4bCdJ6CQ2i7c8o2',
777 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
778 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
780 'uploader_id': 'xgditw',
781 'upload_date': '20140425',
782 'timestamp': 1398441542,
784 'add_ie': ['Dailymotion'],
788 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
792 'title': 'Care worker punches elderly dementia patient in head 11 times',
793 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
795 'add_ie': ['DailyMail'],
797 'skip_download': True,
802 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
806 'title': 'The NBL Auction 2014',
807 'uploader': 'BADMINTON England',
808 'uploader_id': 'BADMINTONEvents',
809 'upload_date': '20140603',
810 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
812 'add_ie': ['Youtube'],
814 'skip_download': True,
819 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
820 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
822 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
824 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
825 'description': 'Two valets share their love for movie star Liam Neesons.',
826 'timestamp': 1349922600,
827 'upload_date': '20121011',
830 # YouTube embed via <data-embed-url="">
832 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
836 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
837 'uploader': 'Gameloft',
838 'uploader_id': 'gameloft',
839 'upload_date': '20140828',
840 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
843 'skip_download': True,
846 # YouTube <object> embed
848 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
849 'md5': '516718101ec834f74318df76259fb3cc',
853 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
854 'upload_date': '20080526',
855 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
856 'uploader': 'Christopher Sykes',
857 'uploader_id': 'ChristopherJSykes',
859 'add_ie': ['Youtube'],
863 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
865 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
867 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
868 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
873 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
875 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
876 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
882 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
887 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
888 'md5': '9d65602bf31c6e20014319c7d07fba27',
890 'id': '5123ea6d5e5a7',
893 'uploader': 'www.handjobhub.com',
894 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
897 # Multiple brightcove videos
898 # https://github.com/rg3/youtube-dl/issues/2283
900 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
902 'id': 'always-never',
903 'title': 'Always / Never - The New Yorker',
907 'extract_flat': False,
908 'skip_download': True,
913 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
914 'md5': '96f09a37e44da40dd083e12d9a683327',
918 'title': 'Ump changes call to ball',
919 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
921 'timestamp': 1401537900,
922 'upload_date': '20140531',
923 'thumbnail': r're:^https?://.*\.jpg$',
928 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
929 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
933 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
934 'description': 'a Paywall Videos video from Remilon',
936 'uploader': 'study.com',
937 'timestamp': 1459678540,
938 'upload_date': '20160403',
939 'filesize': 24687186,
943 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
944 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
948 'title': 'Conversation about Hexagonal Rails Part 1',
949 'description': 'a Martin Fowler video from ThoughtWorks',
951 'uploader': 'thoughtworks.wistia.com',
952 'timestamp': 1401832161,
953 'upload_date': '20140603',
956 # Wistia standard embed (async)
958 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
962 'title': 'Drip Brennan Dunn Workshop',
963 'description': 'a JV Webinars video from getdrip-1',
965 'timestamp': 1463607249,
966 'upload_date': '20160518',
969 'skip_download': True,
974 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
978 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
979 'uploader': 'Sophos Security',
980 'title': 'Chet Chat 171 - Oct 29, 2014',
981 'upload_date': '20141029',
984 # Soundcloud multiple embeds
986 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
989 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
991 'playlist_mincount': 7,
993 # TuneIn station embed
995 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1000 'location': 'Paris, France',
1005 'skip_download': True,
1010 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1014 'upload_date': '20141112',
1015 'title': 'Rosetta #CometLanding webcast HL 10',
1018 # Another Livestream embed, without 'new.' in URL
1020 'url': 'https://www.freespeech.org/',
1024 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1028 'skip_download': True,
1033 'url': 'https://skiplagged.com/',
1036 'title': 'Skiplagged: The smart way to find cheap flights',
1038 'playlist_mincount': 1,
1039 'add_ie': ['Youtube'],
1043 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1047 'upload_date': '20141126',
1048 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1053 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1055 'id': '730m_DandD_1901_512k',
1057 'uploader': 'www.abc.net.au',
1058 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1061 # embedded viddler video
1063 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1067 'uploader': 'deadspin',
1068 'title': 'WALL-TO-GORTAT',
1069 'timestamp': 1422285291,
1070 'upload_date': '20150126',
1072 'add_ie': ['Viddler'],
1076 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1080 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1081 'description': 'md5:601cb790edd05908957dae8aaa866465',
1082 'upload_date': '20150220',
1084 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1088 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1090 'id': 'Mrj4DVp2zeA',
1092 'upload_date': '20150212',
1093 'uploader': 'The National Archives UK',
1094 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1095 'uploader_id': 'NationalArchives08',
1096 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1101 'url': 'http://www.suffolk.edu/sjc/',
1105 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1106 'uploader': 'www.suffolk.edu',
1109 'skip_download': True,
1114 'url': 'http://www.indiedb.com/games/king-machine/videos',
1118 'title': 'king machine trailer 1',
1119 'thumbnail': r're:^https?://.*\.jpg$',
1123 # JWPlayer config passed as variable
1124 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1128 'title': 'ARIELE | Tube Cup',
1129 'uploader': 'www.txxx.com',
1133 'skip_download': True,
1137 # Video.js embed, multiple formats
1138 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1140 'id': 'yygqldloqIk',
1142 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1143 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1144 'upload_date': '20130314',
1145 'uploader': 'PROстое3D',
1146 'uploader_id': 'PROstoe3D',
1149 'skip_download': True,
1153 # Video.js embed, single format
1154 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1158 'title': 'Step 1 - Good Foundation',
1159 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1162 'skip_download': True,
1167 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1168 'playlist_mincount': 5,
1170 'id': 'aanslagen-kopenhagen',
1171 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1176 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1180 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1183 # Kaltura embed (different embed code)
1185 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1189 'upload_date': '20150127',
1190 'uploader_id': 'PremierMedia',
1192 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1195 # Kaltura embed with single quotes
1197 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1202 'timestamp': 1355743100,
1203 'upload_date': '20121217',
1204 'uploader_id': 'batchUser',
1206 'add_ie': ['Kaltura'],
1209 # Kaltura embedded via quoted entry_id
1210 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1214 'title': '06_matthew_brender_raj_dutt',
1215 'timestamp': 1466638791,
1216 'upload_date': '20160622',
1218 'add_ie': ['Kaltura'],
1219 'expected_warnings': [
1220 'Could not send HEAD request'
1223 'skip_download': True,
1227 # Kaltura embedded, some fileExt broken (#11480)
1228 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1232 'title': 'Our "Standard Models" of particle physics and cosmology',
1233 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1234 'timestamp': 1321158993,
1235 'upload_date': '20111113',
1236 'uploader_id': 'kps1',
1238 'add_ie': ['Kaltura'],
1241 # Kaltura iframe embed
1242 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1243 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1247 'title': 'I. M. Pei: A Centennial Celebration',
1248 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1249 'upload_date': '20170403',
1250 'uploader_id': 'batchUser',
1251 'timestamp': 1491232186,
1253 'add_ie': ['Kaltura'],
1255 # EaglePlatform embed (generic URL)
1257 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1258 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1262 'title': 'Навальный вышел на свободу',
1263 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1264 'thumbnail': r're:^https?://.*\.jpg$',
1270 'skip_download': True,
1273 # referrer protected EaglePlatform embed
1275 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1279 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1280 'thumbnail': r're:^https?://.*\.jpg$',
1285 'skip_download': True,
1288 # ClipYou (EaglePlatform) embed (custom URL)
1290 'url': 'http://muz-tv.ru/play/7129/',
1291 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1295 'title': "'O Sole Mio",
1296 'thumbnail': r're:^https?://.*\.jpg$',
1301 'skip_download': True,
1306 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1310 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1311 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1312 'thumbnail': r're:^https?://.*\.jpg$',
1319 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1323 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1324 'thumbnail': r're:^https?://.*\.png$',
1330 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1331 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1335 'title': 'Facebook Creates "On This Day" | Crunch Report',
1340 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1344 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1349 # Crooks and Liars embed
1351 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1355 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1356 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1357 'timestamp': 1428207000,
1358 'upload_date': '20150405',
1359 'uploader': 'Heather',
1362 # Crooks and Liars external embed
1364 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1366 'id': 'MTE3MjUtMzQ2MzA',
1368 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1369 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1370 'timestamp': 1265032391,
1371 'upload_date': '20100201',
1372 'uploader': 'Heather',
1375 # NBC Sports vplayer embed
1377 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1379 'id': 'ln7x1qSThw4k',
1381 'title': "PFT Live: New leader in the 'new-look' defense",
1382 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1383 'uploader': 'NBCU-SPORTS',
1384 'upload_date': '20140107',
1385 'timestamp': 1389118457,
1390 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1391 'md5': '1aa589c675898ae6d37a17913cf68d66',
1393 'id': '701714499682',
1395 'title': 'PREVIEW: On Assignment: David Letterman',
1396 '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.',
1401 'url': 'https://video.udn.com/news/300346',
1402 'md5': 'fd2060e988c326991037b9aff9df21a6',
1406 'title': '中一中男師變性 全校師生力挺',
1407 'thumbnail': r're:^https?://.*\.jpg$',
1411 'skip_download': True,
1416 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1418 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1420 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1421 'title': 'This is what separates the Excel masters from the wannabes',
1422 'duration': 191.933,
1426 'skip_download': True,
1429 # Brightcove URL in single quotes
1431 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1432 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1434 'id': '4255764656001',
1436 'title': 'SN Presents: Russell Martin, World Citizen',
1437 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1438 'uploader': 'Rogers Sportsnet',
1439 'uploader_id': '1704050871',
1440 'upload_date': '20150525',
1441 'timestamp': 1432570283,
1444 # Dailymotion Cloud video
1446 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1447 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1451 'title': 'Sauvons les abeilles ! - Le débat',
1452 'description': 'md5:d9082128b1c5277987825d684939ca26',
1453 'thumbnail': r're:^https?://.*\.jpe?g$',
1454 'timestamp': 1434970506,
1455 'upload_date': '20150622',
1456 'uploader': 'Public Sénat',
1457 'uploader_id': 'xa9gza',
1460 # OnionStudios embed
1462 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1466 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1467 'thumbnail': r're:^https?://.*\.jpe?g$',
1468 'uploader': 'ClickHole',
1469 'uploader_id': 'clickhole',
1474 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1476 'id': '74849a00-85a9-11e1-9660-123139220831',
1478 'title': '#whilewewatch',
1481 # AdobeTVVideo embed
1483 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1484 'md5': '43662b577c018ad707a63766462b1e87',
1488 'title': 'New experience with Acrobat DC',
1489 'description': 'New experience with Acrobat DC',
1490 'duration': 248.667,
1493 # BrightcoveInPageEmbed embed
1495 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1497 'id': '4238694884001',
1499 'title': 'Tabletop: Dread, Last Thoughts',
1500 'description': 'Tabletop: Dread, Last Thoughts',
1504 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1505 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1507 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1509 'id': '4785848093001',
1511 'title': 'The Cardinal Pell Interview',
1512 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1513 'uploader': 'GlobeCast Australia - GlobeStream',
1514 'uploader_id': '2733773828001',
1515 'upload_date': '20160304',
1516 'timestamp': 1457083087,
1520 'skip_download': True,
1524 # Brightcove embed with whitespace around attribute names
1525 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1527 'id': '3167554373001',
1529 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1530 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1531 'uploader_id': '1079349493',
1532 'upload_date': '20140207',
1533 'timestamp': 1391810548,
1536 'skip_download': True,
1539 # Another form of arte.tv embed
1541 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1542 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1544 'id': '030273-562_PLUS7-F',
1546 'title': 'ARTE Reportage - Nulle part, en France',
1547 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1548 'upload_date': '20160409',
1553 'url': 'http://www.wykop.pl/link/3088787/',
1554 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1556 'id': '874_1459135191',
1558 'title': 'Man shows poor quality of new apartment building',
1559 'description': 'The wall is like a sand pile.',
1560 'uploader': 'Lake8737',
1562 'add_ie': [LiveLeakIE.ie_key()],
1564 # Another LiveLeak embed pattern (#13336)
1566 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1568 'id': '2eb_1496309988',
1570 'title': 'Thief robs place where everyone was armed',
1571 'description': 'md5:694d73ee79e535953cf2488562288eee',
1572 'uploader': 'brazilwtf',
1574 'add_ie': [LiveLeakIE.ie_key()],
1576 # Duplicated embedded video URLs
1578 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1580 'id': '149298443_480_16c25b74_2',
1582 'title': 'vs. Blue Orange Spring Game',
1583 'uploader': 'www.hudl.com',
1586 # twitter:player:stream embed
1588 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1592 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1593 'uploader': 'www.rtl.be',
1597 'skip_download': True,
1600 # twitter:player embed
1602 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1603 'md5': 'a3e0df96369831de324f0778e126653c',
1605 'id': '4909620399001',
1607 'title': 'What Do Black Holes Sound Like?',
1608 'description': 'what do black holes sound like',
1609 'upload_date': '20160524',
1610 'uploader_id': '29913724001',
1611 'timestamp': 1464107587,
1612 'uploader': 'TheAtlantic',
1614 'add_ie': ['BrightcoveLegacy'],
1616 # Facebook <iframe> embed
1618 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1619 'md5': 'fbcde74f534176ecb015849146dd3aee',
1621 'id': '599637780109885',
1623 'title': 'Facebook video #599637780109885',
1626 # Facebook <iframe> embed, plugin video
1628 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1630 'id': '1754168231264132',
1632 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1633 'uploader': 'Tariq Ramadan (official)',
1634 'timestamp': 1496758379,
1635 'upload_date': '20170606',
1638 'skip_download': True,
1641 # Facebook API embed
1643 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1644 'md5': 'a47372ee61b39a7b90287094d447d94e',
1646 'id': '10153467542406923',
1648 'title': 'Facebook video #10153467542406923',
1651 # Wordpress "YouTube Video Importer" plugin
1653 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1654 'md5': 'd16797741b560b485194eddda8121b48',
1656 'id': 'HNTXWDXV9Is',
1658 'title': 'Blue Devils Drumline Stanford lot 2016',
1659 'upload_date': '20160627',
1660 'uploader_id': 'GENOCIDE8GENERAL10',
1661 'uploader': 'cylus cyrus',
1665 # video stored on custom kaltura server
1666 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1667 'md5': '537617d06e64dfed891fa1593c4b30cc',
1671 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1672 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1673 'uploader_id': 'videos.expansion@el-mundo.net',
1674 'upload_date': '20150429',
1675 'timestamp': 1430303472,
1677 'add_ie': ['Kaltura'],
1680 # Non-standard Vimeo embed
1681 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1682 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1686 'title': 'Understanding the web - Teaser',
1687 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1688 'upload_date': '20151214',
1689 'uploader': 'OpenClassrooms',
1690 'uploader_id': 'openclassrooms',
1692 'add_ie': ['Vimeo'],
1695 # generic vimeo embed that requires original URL passed as Referer
1696 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1697 'only_matching': True,
1700 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1701 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1703 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1705 'title': 'Big Buck Bunny',
1706 'description': 'Royalty free test video',
1707 'timestamp': 1432816365,
1708 'upload_date': '20150528',
1712 'skip_download': True,
1714 'add_ie': [ArkenaIE.ie_key()],
1717 '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/',
1721 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1724 'skip_download': True,
1726 'add_ie': [Vbox7IE.ie_key()],
1730 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1733 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1735 'playlist_mincount': 3,
1739 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1741 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1742 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1744 'playlist_mincount': 2,
1748 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1752 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1753 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1756 'skip_download': True,
1758 'add_ie': [TwentyMinutenIE.ie_key()],
1762 'url': 'https://en.support.wordpress.com/videopress/',
1766 'title': 'IMG_5786',
1767 'timestamp': 1435711927,
1768 'upload_date': '20150701',
1771 'skip_download': True,
1773 'add_ie': [VideoPressIE.ie_key()],
1777 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1779 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1781 'title': 'Магаззино: Казань 2',
1782 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1783 'uploader': 'Магаззино',
1784 'upload_date': '20170228',
1785 'uploader_id': '996642',
1788 'skip_download': True,
1790 'add_ie': [RutubeIE.ie_key()],
1793 # ThePlatform embedded with whitespaces in URLs
1794 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1795 'only_matching': True,
1798 # Senate ISVP iframe https
1799 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1800 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1802 'id': 'govtaff020316',
1804 'title': 'Integrated Senate Video Player',
1806 'add_ie': [SenateISVPIE.ie_key()],
1809 # Limelight embeds (1 channel embed + 4 media embeds)
1810 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1812 'id': 'FacilitatorTraining2017',
1813 'title': 'Facilitator Training 2017',
1815 'playlist_mincount': 5,
1818 # Limelight embed (LimelightPlayerUtil.embed)
1819 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1821 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1823 'title': '07448641',
1824 'timestamp': 1499890639,
1825 'upload_date': '20170712',
1828 'skip_download': True,
1830 'add_ie': ['LimelightMedia'],
1833 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1835 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1836 'title': 'Standoff with Walnut Creek murder suspect ends',
1837 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1839 'playlist_mincount': 4,
1842 # WashingtonPost embed
1843 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1845 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1847 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1848 '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.',
1849 'timestamp': 1455216756,
1850 'uploader': 'The Washington Post',
1851 'upload_date': '20160211',
1853 'add_ie': [WashingtonPostIE.ie_key()],
1857 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1861 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1864 'skip_download': True,
1866 'add_ie': [MediasetIE.ie_key()],
1870 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1872 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1873 'title': 'Slovenskom sa prehnala vlna silných búrok',
1875 'playlist_mincount': 5,
1876 'add_ie': [JojIE.ie_key()],
1879 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1880 'url': 'https://tvrain.ru/amp/418921/',
1881 'md5': 'cc00413936695987e8de148b67d14f1d',
1885 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1890 'url': 'http://help.vzaar.com/article/165-embedding-video',
1891 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1895 'title': 'Building A Business Online: Principal Chairs Q & A',
1899 # multiple HTML5 videos on one page
1900 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1902 'id': 'keyscenarios',
1903 'title': 'Rescue Kit 14 Free Edition - Getting started',
1905 'playlist_count': 4,
1908 # # TODO: find another test
1909 # # http://schema.org/VideoObject
1910 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1911 # 'md5': '888dcf08b7ea671381f00fab74692755',
1913 # 'id': 'nyvTSJMKId',
1915 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1916 # 'description': '#love for cats.',
1917 # 'timestamp': 1461244995,
1918 # 'upload_date': '20160421',
1921 # 'force_generic_extractor': True,
1926 def report_following_redirect(self, new_url):
1927 """Report information extraction."""
1928 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1930 def _extract_rss(self, url, video_id, doc):
1931 playlist_title = doc.find('./channel/title').text
1932 playlist_desc_el = doc.find('./channel/description')
1933 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1936 for it in doc.findall('./channel/item'):
1937 next_url = xpath_text(it, 'link', fatal=False)
1939 enclosure_nodes = it.findall('./enclosure')
1940 for e in enclosure_nodes:
1941 next_url = e.attrib.get('url')
1949 '_type': 'url_transparent',
1951 'title': it.find('title').text,
1955 '_type': 'playlist',
1957 'title': playlist_title,
1958 'description': playlist_desc,
1962 def _extract_camtasia(self, url, video_id, webpage):
1963 """ Returns None if no camtasia video can be found. """
1965 camtasia_cfg = self._search_regex(
1966 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1967 webpage, 'camtasia configuration file', default=None)
1968 if camtasia_cfg is None:
1971 title = self._html_search_meta('DC.title', webpage, fatal=True)
1973 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1974 camtasia_cfg = self._download_xml(
1975 camtasia_url, video_id,
1976 note='Downloading camtasia configuration',
1977 errnote='Failed to download camtasia configuration')
1978 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1981 for n in fileset_node.getchildren():
1982 url_n = n.find('./uri')
1987 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1988 'title': '%s - %s' % (title, n.tag),
1989 'url': compat_urlparse.urljoin(url, url_n.text),
1990 'duration': float_or_none(n.find('./duration').text),
1994 '_type': 'playlist',
1999 def _real_extract(self, url):
2000 if url.startswith('//'):
2003 'url': self.http_scheme() + url,
2006 parsed_url = compat_urlparse.urlparse(url)
2007 if not parsed_url.scheme:
2008 default_search = self._downloader.params.get('default_search')
2009 if default_search is None:
2010 default_search = 'fixup_error'
2012 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2014 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2015 return self.url_result('http://' + url)
2016 elif default_search != 'fixup_error':
2017 if default_search == 'auto_warning':
2018 if re.match(r'^(?:url|URL)$', url):
2019 raise ExtractorError(
2020 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2023 self._downloader.report_warning(
2024 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2025 return self.url_result('ytsearch:' + url)
2027 if default_search in ('error', 'fixup_error'):
2028 raise ExtractorError(
2029 '%r is not a valid URL. '
2030 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2031 % (url, url), expected=True)
2033 if ':' not in default_search:
2034 default_search += ':'
2035 return self.url_result(default_search + url)
2037 url, smuggled_data = unsmuggle_url(url)
2038 force_videoid = None
2039 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2040 if smuggled_data and 'force_videoid' in smuggled_data:
2041 force_videoid = smuggled_data['force_videoid']
2042 video_id = force_videoid
2044 video_id = self._generic_id(url)
2046 self.to_screen('%s: Requesting header' % video_id)
2048 head_req = HEADRequest(url)
2049 head_response = self._request_webpage(
2051 note=False, errnote='Could not send HEAD request to %s' % url,
2054 if head_response is not False:
2055 # Check for redirect
2056 new_url = compat_str(head_response.geturl())
2058 self.report_following_redirect(new_url)
2060 new_url = smuggle_url(
2061 new_url, {'force_videoid': force_videoid})
2062 return self.url_result(new_url)
2064 full_response = None
2065 if head_response is False:
2066 request = sanitized_Request(url)
2067 request.add_header('Accept-Encoding', '*')
2068 full_response = self._request_webpage(request, video_id)
2069 head_response = full_response
2073 'title': self._generic_title(url),
2074 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2077 # Check for direct link to a video
2078 content_type = head_response.headers.get('Content-Type', '').lower()
2079 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2081 format_id = compat_str(m.group('format_id'))
2082 if format_id.endswith('mpegurl'):
2083 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2084 elif format_id == 'f4m':
2085 formats = self._extract_f4m_formats(url, video_id)
2088 'format_id': format_id,
2090 'vcodec': 'none' if m.group('type') == 'audio' else None
2092 info_dict['direct'] = True
2093 self._sort_formats(formats)
2094 info_dict['formats'] = formats
2097 if not self._downloader.params.get('test', False) and not is_intentional:
2098 force = self._downloader.params.get('force_generic_extractor', False)
2099 self._downloader.report_warning(
2100 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2102 if not full_response:
2103 request = sanitized_Request(url)
2104 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2105 # making it impossible to download only chunk of the file (yet we need only 512kB to
2106 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2107 # that will always result in downloading the whole file that is not desirable.
2108 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2109 # to accept raw bytes and being able to download only a chunk.
2110 # It may probably better to solve this by checking Content-Type for application/octet-stream
2111 # after HEAD request finishes, but not sure if we can rely on this.
2112 request.add_header('Accept-Encoding', '*')
2113 full_response = self._request_webpage(request, video_id)
2115 first_bytes = full_response.read(512)
2117 # Is it an M3U playlist?
2118 if first_bytes.startswith(b'#EXTM3U'):
2119 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2120 self._sort_formats(info_dict['formats'])
2123 # Maybe it's a direct link to a video?
2124 # Be careful not to download the whole thing!
2125 if not is_html(first_bytes):
2126 self._downloader.report_warning(
2127 'URL could be a direct video link, returning it as such.')
2134 webpage = self._webpage_read_content(
2135 full_response, url, video_id, prefix=first_bytes)
2137 self.report_extraction(video_id)
2139 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2141 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2142 if doc.tag == 'rss':
2143 return self._extract_rss(url, video_id, doc)
2144 elif doc.tag == 'SmoothStreamingMedia':
2145 info_dict['formats'] = self._parse_ism_formats(doc, url)
2146 self._sort_formats(info_dict['formats'])
2148 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2149 smil = self._parse_smil(doc, url, video_id)
2150 self._sort_formats(smil['formats'])
2152 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2153 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
2154 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2155 info_dict['formats'] = self._parse_mpd_formats(
2157 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2159 self._sort_formats(info_dict['formats'])
2161 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2162 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2163 self._sort_formats(info_dict['formats'])
2165 except compat_xml_parse_error:
2168 # Is it a Camtasia project?
2169 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2170 if camtasia_res is not None:
2173 # Sometimes embedded video player is hidden behind percent encoding
2174 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2175 # Unescaping the whole page allows to handle those cases in a generic way
2176 webpage = compat_urllib_parse_unquote(webpage)
2178 # it's tempting to parse this further, but you would
2179 # have to take into account all the variations like
2180 # Video Title - Site Name
2181 # Site Name | Video Title
2182 # Video Title - Tagline | Site Name
2183 # and so on and so forth; it's just not practical
2184 video_title = self._og_search_title(
2185 webpage, default=None) or self._html_search_regex(
2186 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2189 # Try to detect age limit automatically
2190 age_limit = self._rta_search(webpage)
2191 # And then there are the jokers who advertise that they use RTA,
2192 # but actually don't.
2193 AGE_LIMIT_MARKERS = [
2194 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2196 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2199 # video uploader is domain name
2200 video_uploader = self._search_regex(
2201 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2203 video_description = self._og_search_description(webpage, default=None)
2204 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2207 'title': video_title,
2208 'description': video_description,
2209 'thumbnail': video_thumbnail,
2210 'age_limit': age_limit,
2213 # Look for Brightcove Legacy Studio embeds
2214 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2218 'url': smuggle_url(bc_url, {'Referer': url}),
2219 'ie_key': 'BrightcoveLegacy'
2220 } for bc_url in bc_urls]
2223 '_type': 'playlist',
2224 'title': video_title,
2229 # Look for Brightcove New Studio embeds
2230 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2232 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2234 # Look for Nexx embeds
2235 nexx_urls = NexxIE._extract_urls(webpage)
2237 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2239 # Look for Nexx iFrame embeds
2240 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2242 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2244 # Look for ThePlatform embeds
2245 tp_urls = ThePlatformIE._extract_urls(webpage)
2247 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2249 # Look for Vessel embeds
2250 vessel_urls = VesselIE._extract_urls(webpage)
2252 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2254 # Look for embedded rtl.nl player
2255 matches = re.findall(
2256 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
2259 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2261 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2263 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2265 vid_me_embed_url = self._search_regex(
2266 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2267 webpage, 'vid.me embed', default=None)
2268 if vid_me_embed_url is not None:
2269 return self.url_result(vid_me_embed_url, 'Vidme')
2271 # Look for YouTube embeds
2272 youtube_urls = YoutubeIE._extract_urls(webpage)
2274 return self.playlist_from_matches(
2275 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2277 matches = DailymotionIE._extract_urls(webpage)
2279 return self.playlist_from_matches(matches, video_id, video_title)
2281 # Look for embedded Dailymotion playlist player (#3822)
2283 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2285 playlists = re.findall(
2286 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2288 return self.playlist_from_matches(
2289 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2291 # Look for DailyMail embeds
2292 dailymail_urls = DailyMailIE._extract_urls(webpage)
2294 return self.playlist_from_matches(
2295 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2297 # Look for embedded Wistia player
2298 wistia_url = WistiaIE._extract_url(webpage)
2301 '_type': 'url_transparent',
2302 'url': self._proto_relative_url(wistia_url),
2303 'ie_key': WistiaIE.ie_key(),
2304 'uploader': video_uploader,
2307 # Look for SVT player
2308 svt_url = SVTIE._extract_url(webpage)
2310 return self.url_result(svt_url, 'SVT')
2312 # Look for Bandcamp pages with custom domain
2313 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2314 if mobj is not None:
2315 burl = unescapeHTML(mobj.group(1))
2316 # Don't set the extractor because it can be a track url or an album
2317 return self.url_result(burl)
2319 # Look for embedded Vevo player
2321 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2322 if mobj is not None:
2323 return self.url_result(mobj.group('url'))
2325 # Look for embedded Viddler player
2327 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2329 if mobj is not None:
2330 return self.url_result(mobj.group('url'))
2332 # Look for NYTimes player
2334 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2336 if mobj is not None:
2337 return self.url_result(mobj.group('url'))
2339 # Look for Libsyn player
2341 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2342 if mobj is not None:
2343 return self.url_result(mobj.group('url'))
2345 # Look for Ooyala videos
2346 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2347 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2348 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2349 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2350 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2351 if mobj is not None:
2352 embed_token = self._search_regex(
2353 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2354 webpage, 'ooyala embed token', default=None)
2355 return OoyalaIE._build_url_result(smuggle_url(
2358 'embed_token': embed_token,
2361 # Look for multiple Ooyala embeds on SBN network websites
2362 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2363 if mobj is not None:
2364 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2366 return self.playlist_from_matches(
2367 embeds, video_id, video_title,
2368 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2370 # Look for Aparat videos
2371 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2372 if mobj is not None:
2373 return self.url_result(mobj.group(1), 'Aparat')
2375 # Look for MPORA videos
2376 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2377 if mobj is not None:
2378 return self.url_result(mobj.group(1), 'Mpora')
2380 # Look for embedded NovaMov-based player
2382 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2383 (?P<url>http://(?:(?:embed|www)\.)?
2385 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2386 videoweed\.(?:es|com)|
2387 movshare\.(?:net|sx|ag)|
2388 divxstage\.(?:eu|net|ch|co|at|ag))
2389 /embed\.php.+?)\1''', webpage)
2390 if mobj is not None:
2391 return self.url_result(mobj.group('url'))
2393 # Look for embedded Facebook player
2394 facebook_urls = FacebookIE._extract_urls(webpage)
2396 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2398 # Look for embedded VK player
2399 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2400 if mobj is not None:
2401 return self.url_result(mobj.group('url'), 'VK')
2403 # Look for embedded Odnoklassniki player
2404 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2405 if mobj is not None:
2406 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2408 # Look for embedded ivi player
2409 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2410 if mobj is not None:
2411 return self.url_result(mobj.group('url'), 'Ivi')
2413 # Look for embedded Huffington Post player
2415 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2416 if mobj is not None:
2417 return self.url_result(mobj.group('url'), 'HuffPost')
2420 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2421 if mobj is not None:
2422 return self.url_result(mobj.group('url'))
2423 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2424 if mobj is not None:
2425 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2427 # Look for funnyordie embed
2428 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2430 return self.playlist_from_matches(
2431 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2433 # Look for BBC iPlayer embed
2434 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2436 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2438 # Look for embedded RUTV player
2439 rutv_url = RUTVIE._extract_url(webpage)
2441 return self.url_result(rutv_url, 'RUTV')
2443 # Look for embedded TVC player
2444 tvc_url = TVCIE._extract_url(webpage)
2446 return self.url_result(tvc_url, 'TVC')
2448 # Look for embedded SportBox player
2449 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2451 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2453 # Look for embedded XHamster player
2454 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2456 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2458 # Look for embedded TNAFlixNetwork player
2459 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2461 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2463 # Look for embedded PornHub player
2464 pornhub_urls = PornHubIE._extract_urls(webpage)
2466 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2468 # Look for embedded DrTuber player
2469 drtuber_urls = DrTuberIE._extract_urls(webpage)
2471 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2473 # Look for embedded RedTube player
2474 redtube_urls = RedTubeIE._extract_urls(webpage)
2476 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2478 # Look for embedded Tvigle player
2480 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2481 if mobj is not None:
2482 return self.url_result(mobj.group('url'), 'Tvigle')
2484 # Look for embedded TED player
2486 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2487 if mobj is not None:
2488 return self.url_result(mobj.group('url'), 'TED')
2490 # Look for embedded Ustream videos
2491 ustream_url = UstreamIE._extract_url(webpage)
2493 return self.url_result(ustream_url, UstreamIE.ie_key())
2495 # Look for embedded arte.tv player
2497 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2499 if mobj is not None:
2500 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2502 # Look for embedded francetv player
2504 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2506 if mobj is not None:
2507 return self.url_result(mobj.group('url'))
2509 # Look for embedded smotri.com player
2510 smotri_url = SmotriIE._extract_url(webpage)
2512 return self.url_result(smotri_url, 'Smotri')
2514 # Look for embedded Myvi.ru player
2515 myvi_url = MyviIE._extract_url(webpage)
2517 return self.url_result(myvi_url)
2519 # Look for embedded soundcloud player
2520 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2522 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2524 # Look for tunein player
2525 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2527 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2529 # Look for embedded mtvservices player
2530 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2532 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2534 # Look for embedded yahoo player
2536 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2538 if mobj is not None:
2539 return self.url_result(mobj.group('url'), 'Yahoo')
2541 # Look for embedded sbs.com.au player
2545 <meta\s+property="og:video"\s+content=|
2548 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2550 if mobj is not None:
2551 return self.url_result(mobj.group('url'), 'SBS')
2553 # Look for embedded Cinchcast player
2555 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2557 if mobj is not None:
2558 return self.url_result(mobj.group('url'), 'Cinchcast')
2561 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2565 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2567 if mobj is not None:
2568 return self.url_result(mobj.group('url'), 'MLB')
2571 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2573 if mobj is not None:
2574 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2577 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2579 if mobj is not None:
2580 return self.url_result(mobj.group('url'), 'Livestream')
2582 # Look for Zapiks embed
2584 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2585 if mobj is not None:
2586 return self.url_result(mobj.group('url'), 'Zapiks')
2588 # Look for Kaltura embeds
2589 kaltura_url = KalturaIE._extract_url(webpage)
2591 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2593 # Look for EaglePlatform embeds
2594 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2595 if eagleplatform_url:
2596 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2598 # Look for ClipYou (uses EaglePlatform) embeds
2600 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2601 if mobj is not None:
2602 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2604 # Look for Pladform embeds
2605 pladform_url = PladformIE._extract_url(webpage)
2607 return self.url_result(pladform_url)
2609 # Look for Videomore embeds
2610 videomore_url = VideomoreIE._extract_url(webpage)
2612 return self.url_result(videomore_url)
2614 # Look for Webcaster embeds
2615 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2617 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2619 # Look for Playwire embeds
2621 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2622 if mobj is not None:
2623 return self.url_result(mobj.group('url'))
2625 # Look for 5min embeds
2627 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2628 if mobj is not None:
2629 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2631 # Look for Crooks and Liars embeds
2633 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2634 if mobj is not None:
2635 return self.url_result(mobj.group('url'))
2637 # Look for NBC Sports VPlayer embeds
2638 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2640 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2642 # Look for NBC News embeds
2643 nbc_news_embed_url = re.search(
2644 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2645 if nbc_news_embed_url:
2646 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2648 # Look for Google Drive embeds
2649 google_drive_url = GoogleDriveIE._extract_url(webpage)
2650 if google_drive_url:
2651 return self.url_result(google_drive_url, 'GoogleDrive')
2653 # Look for UDN embeds
2655 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2656 if mobj is not None:
2657 return self.url_result(
2658 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2660 # Look for Senate ISVP iframe
2661 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2663 return self.url_result(senate_isvp_url, 'SenateISVP')
2665 # Look for Dailymotion Cloud videos
2666 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2668 return self.url_result(dmcloud_url, 'DailymotionCloud')
2670 # Look for OnionStudios embeds
2671 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2672 if onionstudios_url:
2673 return self.url_result(onionstudios_url)
2675 # Look for ViewLift embeds
2676 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2678 return self.url_result(viewlift_url)
2680 # Look for JWPlatform embeds
2681 jwplatform_url = JWPlatformIE._extract_url(webpage)
2683 return self.url_result(jwplatform_url, 'JWPlatform')
2685 # Look for Digiteka embeds
2686 digiteka_url = DigitekaIE._extract_url(webpage)
2688 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2690 # Look for Arkena embeds
2691 arkena_url = ArkenaIE._extract_url(webpage)
2693 return self.url_result(arkena_url, ArkenaIE.ie_key())
2695 # Look for Piksel embeds
2696 piksel_url = PikselIE._extract_url(webpage)
2698 return self.url_result(piksel_url, PikselIE.ie_key())
2700 # Look for Limelight embeds
2701 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2703 return self.playlist_result(
2704 limelight_urls, video_id, video_title, video_description)
2706 # Look for Anvato embeds
2707 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2709 return self.playlist_result(
2710 anvato_urls, video_id, video_title, video_description)
2712 # Look for AdobeTVVideo embeds
2714 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2716 if mobj is not None:
2717 return self.url_result(
2718 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2721 # Look for Vine embeds
2723 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2725 if mobj is not None:
2726 return self.url_result(
2727 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2729 # Look for VODPlatform embeds
2731 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2733 if mobj is not None:
2734 return self.url_result(
2735 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2737 # Look for Mangomolo embeds
2739 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2741 video\?.*?\bid=(?P<video_id>\d+)|
2742 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2743 ).+?)\1''', webpage)
2744 if mobj is not None:
2746 '_type': 'url_transparent',
2747 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2748 'title': video_title,
2749 'description': video_description,
2750 'thumbnail': video_thumbnail,
2751 'uploader': video_uploader,
2753 video_id = mobj.group('video_id')
2756 'ie_key': 'MangomoloVideo',
2761 'ie_key': 'MangomoloLive',
2762 'id': mobj.group('channel_id'),
2766 # Look for Instagram embeds
2767 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2768 if instagram_embed_url is not None:
2769 return self.url_result(
2770 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2772 # Look for LiveLeak embeds
2773 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2775 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2777 # Look for 3Q SDN embeds
2778 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2781 '_type': 'url_transparent',
2782 'ie_key': ThreeQSDNIE.ie_key(),
2783 'url': self._proto_relative_url(threeqsdn_url),
2784 'title': video_title,
2785 'description': video_description,
2786 'thumbnail': video_thumbnail,
2787 'uploader': video_uploader,
2790 # Look for VBOX7 embeds
2791 vbox7_url = Vbox7IE._extract_url(webpage)
2793 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2795 # Look for DBTV embeds
2796 dbtv_urls = DBTVIE._extract_urls(webpage)
2798 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2800 # Look for Videa embeds
2801 videa_urls = VideaIE._extract_urls(webpage)
2803 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2805 # Look for 20 minuten embeds
2806 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2808 return self.playlist_from_matches(
2809 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2811 # Look for Openload embeds
2812 openload_urls = OpenloadIE._extract_urls(webpage)
2814 return self.playlist_from_matches(
2815 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2817 # Look for VideoPress embeds
2818 videopress_urls = VideoPressIE._extract_urls(webpage)
2820 return self.playlist_from_matches(
2821 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2823 # Look for Rutube embeds
2824 rutube_urls = RutubeIE._extract_urls(webpage)
2826 return self.playlist_from_matches(
2827 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2829 # Look for WashingtonPost embeds
2830 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2832 return self.playlist_from_matches(
2833 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2835 # Look for Mediaset embeds
2836 mediaset_urls = MediasetIE._extract_urls(webpage)
2838 return self.playlist_from_matches(
2839 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2841 # Look for JOJ.sk embeds
2842 joj_urls = JojIE._extract_urls(webpage)
2844 return self.playlist_from_matches(
2845 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2847 # Look for megaphone.fm embeds
2848 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2850 return self.playlist_from_matches(
2851 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2853 # Look for vzaar embeds
2854 vzaar_urls = VzaarIE._extract_urls(webpage)
2856 return self.playlist_from_matches(
2857 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
2859 channel9_urls = Channel9IE._extract_urls(webpage)
2861 return self.playlist_from_matches(
2862 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
2864 def merge_dicts(dict1, dict2):
2866 for k, v in dict1.items():
2869 for k, v in dict2.items():
2872 if (k not in merged or
2873 (isinstance(v, compat_str) and v and
2874 isinstance(merged[k], compat_str) and
2879 # Look for HTML5 media
2880 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2882 if len(entries) == 1:
2885 'title': video_title,
2888 for num, entry in enumerate(entries, start=1):
2890 'id': '%s-%s' % (video_id, num),
2891 'title': '%s (%d)' % (video_title, num),
2893 for entry in entries:
2894 self._sort_formats(entry['formats'])
2895 return self.playlist_result(entries, video_id, video_title)
2897 jwplayer_data = self._find_jwplayer_data(
2898 webpage, video_id, transform_source=js_to_json)
2900 info = self._parse_jwplayer_data(
2901 jwplayer_data, video_id, require_title=False, base_url=url)
2902 return merge_dicts(info, info_dict)
2906 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
2908 if mobj is not None:
2909 sources = self._parse_json(
2910 mobj.group(1), video_id, transform_source=js_to_json,
2912 if not isinstance(sources, list):
2915 for source in sources:
2916 src = source.get('src')
2917 if not src or not isinstance(src, compat_str):
2919 src = compat_urlparse.urljoin(url, src)
2920 src_type = source.get('type')
2921 if isinstance(src_type, compat_str):
2922 src_type = src_type.lower()
2923 ext = determine_ext(src).lower()
2924 if src_type == 'video/youtube':
2925 return self.url_result(src, YoutubeIE.ie_key())
2926 if src_type == 'application/dash+xml' or ext == 'mpd':
2927 formats.extend(self._extract_mpd_formats(
2928 src, video_id, mpd_id='dash', fatal=False))
2929 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
2930 formats.extend(self._extract_m3u8_formats(
2931 src, video_id, 'mp4', entry_protocol='m3u8_native',
2932 m3u8_id='hls', fatal=False))
2936 'ext': (mimetype2ext(src_type) or
2937 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
2940 self._sort_formats(formats)
2941 info_dict['formats'] = formats
2944 # Looking for http://schema.org/VideoObject
2945 json_ld = self._search_json_ld(
2946 webpage, video_id, default={}, expected_type='VideoObject')
2947 if json_ld.get('url'):
2948 return merge_dicts(json_ld, info_dict)
2950 def check_video(vurl):
2951 if YoutubeIE.suitable(vurl):
2953 if RtmpIE.suitable(vurl):
2955 vpath = compat_urlparse.urlparse(vurl).path
2956 vext = determine_ext(vpath)
2957 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2959 def filter_video(urls):
2960 return list(filter(check_video, urls))
2962 # Start with something easy: JW Player in SWFObject
2963 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2965 # Look for gorilla-vid style embedding
2966 found = filter_video(re.findall(r'''(?sx)
2970 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2973 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2975 # Broaden the search a little bit
2976 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2978 # Broaden the findall a little bit: JWPlayer JS loader
2979 found = filter_video(re.findall(
2980 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2983 found = filter_video(re.findall(r'''(?xs)
2984 flowplayer\("[^"]+",\s*
2986 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2987 ["']?url["']?\s*:\s*["']([^"']+)["']
2992 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2994 # Try to find twitter cards info
2995 # twitter:player:stream should be checked before twitter:player since
2996 # it is expected to contain a raw stream (see
2997 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2998 found = filter_video(re.findall(
2999 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3001 # We look for Open Graph info:
3002 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3003 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3004 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3005 if m_video_type is not None:
3006 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3008 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3010 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3011 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3014 # Look also in Refresh HTTP header
3015 refresh_header = head_response.headers.get('Refresh')
3017 # In python 2 response HTTP headers are bytestrings
3018 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3019 refresh_header = refresh_header.decode('iso-8859-1')
3020 found = re.search(REDIRECT_REGEX, refresh_header)
3022 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3024 self.report_following_redirect(new_url)
3033 # twitter:player is a https URL to iframe player that may or may not
3034 # be supported by youtube-dl thus this is checked the very last (see
3035 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3036 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3037 if embed_url and embed_url != url:
3038 return self.url_result(embed_url)
3041 raise UnsupportedError(url)
3044 for video_url in orderedSet(found):
3045 video_url = unescapeHTML(video_url)
3046 video_url = video_url.replace('\\/', '/')
3047 video_url = compat_urlparse.urljoin(url, video_url)
3048 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3050 # Sometimes, jwplayer extraction will result in a YouTube URL
3051 if YoutubeIE.suitable(video_url):
3052 entries.append(self.url_result(video_url, 'Youtube'))
3055 # here's a fun little line of code for you:
3056 video_id = os.path.splitext(video_id)[0]
3060 'uploader': video_uploader,
3061 'title': video_title,
3062 'age_limit': age_limit,
3065 if RtmpIE.suitable(video_url):
3066 entry_info_dict.update({
3067 '_type': 'url_transparent',
3068 'ie_key': RtmpIE.ie_key(),
3071 entries.append(entry_info_dict)
3074 ext = determine_ext(video_url)
3076 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3078 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3080 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3082 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3084 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3085 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3086 # Just matching .ism/manifest is not enough to be reliably sure
3087 # whether it's actually an ISM manifest or some other streaming
3088 # manifest since there are various streaming URL formats
3089 # possible (see [1]) as well as some other shenanigans like
3090 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3092 # Thus the most reasonable way to solve this is to delegate
3093 # to generic extractor in order to look into the contents of
3094 # the manifest itself.
3095 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3096 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3097 entry_info_dict = self.url_result(
3098 smuggle_url(video_url, {'to_generic': True}),
3101 entry_info_dict['url'] = video_url
3103 if entry_info_dict.get('formats'):
3104 self._sort_formats(entry_info_dict['formats'])
3106 entries.append(entry_info_dict)
3108 if len(entries) == 1:
3111 for num, e in enumerate(entries, start=1):
3112 # 'url' results don't have a title
3113 if e.get('title') is not None:
3114 e['title'] = '%s (%d)' % (e['title'], num)
3116 '_type': 'playlist',