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,
37 from .commonprotocols import RtmpIE
38 from .brightcove import (
46 from .nbc import NBCSportsVPlayerIE
47 from .ooyala import OoyalaIE
48 from .rutv import RUTVIE
49 from .tvc import TVCIE
50 from .sportbox import SportBoxIE
51 from .smotri import SmotriIE
52 from .myvi import MyviIE
53 from .condenast import CondeNastIE
54 from .udn import UDNEmbedIE
55 from .senateisvp import SenateISVPIE
56 from .svt import SVTIE
57 from .pornhub import PornHubIE
58 from .xhamster import XHamsterEmbedIE
59 from .tnaflix import TNAFlixNetworkEmbedIE
60 from .drtuber import DrTuberIE
61 from .redtube import RedTubeIE
62 from .tube8 import Tube8IE
63 from .vimeo import VimeoIE
64 from .dailymotion import DailymotionIE
65 from .dailymail import DailyMailIE
66 from .onionstudios import OnionStudiosIE
67 from .viewlift import ViewLiftEmbedIE
68 from .mtv import MTVServicesEmbeddedIE
69 from .pladform import PladformIE
70 from .videomore import VideomoreIE
71 from .webcaster import WebcasterFeedIE
72 from .googledrive import GoogleDriveIE
73 from .jwplatform import JWPlatformIE
74 from .digiteka import DigitekaIE
75 from .arkena import ArkenaIE
76 from .instagram import InstagramIE
77 from .liveleak import LiveLeakIE
78 from .threeqsdn import ThreeQSDNIE
79 from .theplatform import ThePlatformIE
80 from .vessel import VesselIE
81 from .kaltura import KalturaIE
82 from .eagleplatform import EaglePlatformIE
83 from .facebook import FacebookIE
84 from .soundcloud import SoundcloudIE
85 from .tunein import TuneInBaseIE
86 from .vbox7 import Vbox7IE
87 from .dbtv import DBTVIE
88 from .piksel import PikselIE
89 from .videa import VideaIE
90 from .twentymin import TwentyMinutenIE
91 from .ustream import UstreamIE
92 from .openload import (
96 from .videopress import VideoPressIE
97 from .rutube import RutubeIE
98 from .limelight import LimelightBaseIE
99 from .anvato import AnvatoIE
100 from .washingtonpost import WashingtonPostIE
101 from .wistia import WistiaIE
102 from .mediaset import MediasetIE
103 from .joj import JojIE
104 from .megaphone import MegaphoneIE
105 from .vzaar import VzaarIE
106 from .channel9 import Channel9IE
107 from .vshare import VShareIE
108 from .mediasite import MediasiteIE
109 from .springboardplatform import SpringboardPlatformIE
110 from .yapfiles import YapFilesIE
111 from .vice import ViceIE
112 from .xfileshare import XFileShareIE
113 from .cloudflarestream import CloudflareStreamIE
114 from .peertube import PeerTubeIE
115 from .teachable import TeachableIE
116 from .indavideo import IndavideoEmbedIE
117 from .apa import APAIE
118 from .foxnews import FoxNewsIE
119 from .viqeo import ViqeoIE
120 from .expressen import ExpressenIE
121 from .zype import ZypeIE
124 class GenericIE(InfoExtractor):
125 IE_DESC = 'Generic downloader that works on some sites'
129 # Direct link to a video
131 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
132 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
137 'upload_date': '20100513',
140 # Direct link to media delivered compressed (until Accept-Encoding is *)
142 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
143 'md5': '128c42e68b13950268b648275386fc74',
145 'id': 'FictionJunction-Parallel_Hearts',
147 'title': 'FictionJunction-Parallel_Hearts',
148 'upload_date': '20140522',
150 'expected_warnings': [
151 'URL could be a direct video link, returning it as such.'
153 'skip': 'URL invalid',
155 # Direct download with broken HEAD
157 'url': 'http://ai-radio.org:8000/radio.opus',
164 'skip_download': True, # infinite live stream
166 'expected_warnings': [
167 r'501.*Not Implemented',
171 # Direct link with incorrect MIME type
173 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
174 'md5': '4ccbebe5f36706d85221f204d7eb5913',
176 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
177 'id': '5_Lennart_Poettering_-_Systemd',
179 'title': '5_Lennart_Poettering_-_Systemd',
180 'upload_date': '20141120',
182 'expected_warnings': [
183 'URL could be a direct video link, returning it as such.'
188 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
190 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
191 'title': 'Zero Punctuation',
192 'description': 're:.*groundbreaking video review series.*'
194 'playlist_mincount': 11,
196 # RSS feed with enclosure
198 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
200 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
202 'upload_date': '20150228',
203 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
206 # RSS feed with enclosures and unsupported link URLs
208 'url': 'http://www.hellointernet.fm/podcast?format=rss',
210 'id': 'http://www.hellointernet.fm/podcast?format=rss',
211 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
212 'title': 'Hello Internet',
214 'playlist_mincount': 100,
216 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
218 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
222 'title': 'Automatics, robotics and biocybernetics',
223 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
224 'upload_date': '20130627',
225 'formats': 'mincount:16',
226 'subtitles': 'mincount:1',
229 'force_generic_extractor': True,
230 'skip_download': True,
233 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
235 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
240 'formats': 'mincount:1',
243 'skip_download': True,
246 # SMIL from https://www.restudy.dk/video/play/id/1637
248 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
252 'title': 'video_1637',
253 'formats': 'mincount:3',
256 'skip_download': True,
259 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
261 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
263 'id': 'smil-service',
265 'title': 'smil-service',
266 'formats': 'mincount:1',
269 'skip_download': True,
272 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
274 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
278 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
279 'formats': 'mincount:3',
282 'skip_download': True,
285 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
287 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
289 'id': 'mZlp2ctYIUEB',
291 'title': 'Tikibad ontruimd wegens brand',
292 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
293 'thumbnail': r're:^https?://.*\.jpg$',
297 'skip_download': True,
300 # MPD from http://dash-mse-test.appspot.com/media.html
302 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
303 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
305 'id': 'car-20120827-manifest',
307 'title': 'car-20120827-manifest',
308 'formats': 'mincount:9',
309 'upload_date': '20130904',
312 'format': 'bestvideo',
315 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
317 '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',
322 'formats': 'mincount:8',
326 'skip_download': True,
328 'skip': 'video gone',
330 # m3u8 served with Content-Type: text/plain
332 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
337 'upload_date': '20140720',
338 'formats': 'mincount:11',
342 'skip_download': True,
344 'skip': 'video gone',
348 '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',
352 'upload_date': '20130224',
353 'uploader_id': 'TheVerge',
354 'description': r're:^Chris Ziegler takes a look at the\.*',
355 'uploader': 'The Verge',
356 'title': 'First Firefox OS phones side-by-side',
359 'skip_download': False,
363 # redirect in Refresh HTTP header
364 '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',
368 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
369 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
370 'upload_date': '20150917',
371 'uploader_id': 'brtvofficial',
372 'uploader': 'Boiler Room',
375 'skip_download': False,
379 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
380 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
382 'id': '13601338388002',
384 'uploader': 'www.hodiho.fr',
385 'title': 'R\u00e9gis plante sa Jeep',
388 # bandcamp page with custom domain
390 'add_ie': ['Bandcamp'],
391 'url': 'http://bronyrock.com/track/the-pony-mash',
395 'title': 'The Pony Mash',
396 'uploader': 'M_Pallante',
398 'skip': 'There is a limit of 200 free downloads / month for the test song',
401 # embedded brightcove video
402 # it also tests brightcove videos that need to set the 'Referer'
403 # in the http requests
404 'add_ie': ['BrightcoveLegacy'],
405 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
407 'id': '2765128793001',
409 'title': 'Le cours de bourse : l’analyse technique',
410 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
411 'uploader': 'BFM BUSINESS',
414 'skip_download': True,
418 # embedded with itemprop embedURL and video id spelled as `idVideo`
419 'add_id': ['BrightcoveLegacy'],
420 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
422 'id': '5255628253001',
424 'title': 'md5:37c519b1128915607601e75a87995fc0',
425 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
426 'uploader': 'BFM BUSINESS',
427 'uploader_id': '876450612001',
428 'timestamp': 1482255315,
429 'upload_date': '20161220',
432 'skip_download': True,
436 # https://github.com/ytdl-org/youtube-dl/issues/2253
437 'url': 'http://bcove.me/i6nfkrc3',
438 'md5': '0ba9446db037002366bab3b3eb30c88c',
440 'id': '3101154703001',
442 'title': 'Still no power',
443 'uploader': 'thestar.com',
444 '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.',
446 'add_ie': ['BrightcoveLegacy'],
447 'skip': 'video gone',
450 'url': 'http://www.championat.com/video/football/v/87/87499.html',
451 'md5': 'fb973ecf6e4a78a67453647444222983',
453 'id': '3414141473001',
455 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
456 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
457 'uploader': 'Championat',
461 # https://github.com/ytdl-org/youtube-dl/issues/3541
462 'add_ie': ['BrightcoveLegacy'],
463 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
465 'id': '3866516442001',
467 'title': 'Leer mij vrouwen kennen: Aflevering 1',
468 'description': 'Leer mij vrouwen kennen: Aflevering 1',
469 'uploader': 'SBS Broadcasting',
471 'skip': 'Restricted to Netherlands',
473 'skip_download': True, # m3u8 download
477 # Brightcove video in <iframe>
478 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
479 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
481 'id': '5360463607001',
483 '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',
484 '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。',
485 'uploader': 'United Nations',
486 'uploader_id': '1362235914001',
487 'timestamp': 1489593889,
488 'upload_date': '20170315',
490 'add_ie': ['BrightcoveLegacy'],
493 # Brightcove with alternative playerID key
494 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
496 'id': 'nmeth.2062_SV1',
497 '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',
501 'id': '2228375078001',
503 'title': 'nmeth.2062-sv1',
504 'description': 'nmeth.2062-sv1',
505 'timestamp': 1363357591,
506 'upload_date': '20130315',
507 'uploader': 'Nature Publishing Group',
508 'uploader_id': '1964492299001',
513 # Brightcove with UUID in videoPlayer
514 'url': 'http://www8.hp.com/cn/zh/home.html',
516 'id': '5255815316001',
518 'title': 'Sprocket Video - China',
519 'description': 'Sprocket Video - China',
520 'uploader': 'HP-Video Gallery',
521 'timestamp': 1482263210,
522 'upload_date': '20161220',
523 'uploader_id': '1107601872001',
526 'skip_download': True, # m3u8 download
528 'skip': 'video rotates...weekly?',
531 # Brightcove:new type [2].
532 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
533 'md5': '2b35148fcf48da41c9fb4591650784f3',
535 'id': '5348741021001',
537 'upload_date': '20170306',
538 'uploader_id': '4191638492001',
539 'timestamp': 1488769918,
540 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
545 # Alternative brightcove <video> attributes
546 '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/',
548 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
549 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
552 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
554 'id': '5311302538001',
556 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
557 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
558 'timestamp': 1486321708,
559 'upload_date': '20170205',
560 'uploader_id': '800000640001',
562 'only_matching': True,
566 # Brightcove with UUID in videoPlayer
567 'url': 'http://www8.hp.com/cn/zh/home.html',
569 'id': '5255815316001',
571 'title': 'Sprocket Video - China',
572 'description': 'Sprocket Video - China',
573 'uploader': 'HP-Video Gallery',
574 'timestamp': 1482263210,
575 'upload_date': '20161220',
576 'uploader_id': '1107601872001',
579 'skip_download': True, # m3u8 download
584 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
585 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
587 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
589 'title': '2cc213299525360.mov', # that's what we get
592 'add_ie': ['Ooyala'],
595 # ooyala video embedded with http://player.ooyala.com/iframe.js
596 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
598 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
600 'title': '"Steve Jobs: Man in the Machine" trailer',
601 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
605 'skip_download': True,
607 'skip': 'movie expired',
609 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
611 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
613 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
615 'title': 'Steampunk Fest Comes to Honesdale',
619 'skip_download': True,
624 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
628 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
629 'upload_date': '20140225',
630 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
631 'uploader': 'Tested',
632 'uploader_id': 'testedcom',
634 # No need to test YoutubeIE here
636 'skip_download': True,
641 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
645 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
646 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
648 # HEAD requests lead to endless 301, while GET is OK
649 'expected_warnings': ['301'],
653 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
657 'title': 'Охотское море стало целиком российским',
658 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
662 'skip_download': True,
667 '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/',
671 'title': 'Дошкольное воспитание',
676 'url': 'http://www.vestifinance.ru/articles/25753',
679 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
684 'title': 'Госзаказ. День 3',
690 'title': 'Госзаказ. День 2',
696 'title': 'Госзаказ. День 1',
702 'skip_download': True,
707 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
709 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
711 'title': 'Ужастики, русский трейлер (2015)',
712 'thumbnail': r're:^https?://.*\.jpg$',
718 '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',
721 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
723 'playlist_mincount': 7,
724 # This forum does not allow <iframe> syntaxes anymore
725 # Now HTML tags are displayed as-is
726 'skip': 'No videos on this page',
730 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
731 'md5': '65fdff94098e4a607385a60c5177c638',
735 'title': 'Hidden miracles of the natural world',
736 'uploader': 'Louie Schwartzberg',
737 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
740 # nowvideo embed hidden behind percent encoding
742 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
743 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
745 'id': '06e53103ca9aa',
747 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
748 'description': 'No description',
753 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
754 'md5': '7653032cbb25bf6c80d80f217055fa43',
756 'id': '048195-004_PLUS7-F',
759 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
760 'upload_date': '20140320',
763 'skip_download': 'Requires rtmpdump'
765 'skip': 'video gone',
769 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
773 'title': 'Alcaline, le concert avec Calogero',
774 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
775 'upload_date': '20150226',
776 'timestamp': 1424989860,
781 'skip_download': True,
783 'expected_warnings': [
789 'url': 'http://www.wired.com/2014/04/honda-asimo/',
790 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
792 'id': '53501be369702d3275860000',
794 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
799 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
800 'md5': '441aeeb82eb72c422c7f14ec533999cd',
802 'id': 'k2mm4bCdJ6CQ2i7c8o2',
804 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
805 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
807 'uploader_id': 'xgditw',
808 'upload_date': '20140425',
809 'timestamp': 1398441542,
811 'add_ie': ['Dailymotion'],
815 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
819 'title': 'Care worker punches elderly dementia patient in head 11 times',
820 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
822 'add_ie': ['DailyMail'],
824 'skip_download': True,
829 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
833 'title': 'The NBL Auction 2014',
834 'uploader': 'BADMINTON England',
835 'uploader_id': 'BADMINTONEvents',
836 'upload_date': '20140603',
837 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
839 'add_ie': ['Youtube'],
841 'skip_download': True,
846 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
847 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
849 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
851 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
852 'description': 'Two valets share their love for movie star Liam Neesons.',
853 'timestamp': 1349922600,
854 'upload_date': '20121011',
857 # YouTube embed via <data-embed-url="">
859 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
863 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
864 'uploader': 'Gameloft',
865 'uploader_id': 'gameloft',
866 'upload_date': '20140828',
867 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
870 'skip_download': True,
873 # YouTube <object> embed
875 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
876 'md5': '516718101ec834f74318df76259fb3cc',
880 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
881 'upload_date': '20080526',
882 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
883 'uploader': 'Christopher Sykes',
884 'uploader_id': 'ChristopherJSykes',
886 'add_ie': ['Youtube'],
890 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
892 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
894 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
895 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
900 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
902 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
903 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
909 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
914 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
915 'md5': '9d65602bf31c6e20014319c7d07fba27',
917 'id': '5123ea6d5e5a7',
920 'uploader': 'www.handjobhub.com',
921 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
924 # Multiple brightcove videos
925 # https://github.com/ytdl-org/youtube-dl/issues/2283
927 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
929 'id': 'always-never',
930 'title': 'Always / Never - The New Yorker',
934 'extract_flat': False,
935 'skip_download': True,
940 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
941 'md5': '96f09a37e44da40dd083e12d9a683327',
945 'title': 'Ump changes call to ball',
946 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
948 'timestamp': 1401537900,
949 'upload_date': '20140531',
950 'thumbnail': r're:^https?://.*\.jpg$',
955 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
956 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
960 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
961 'description': 'a Paywall Videos video from Remilon',
963 'uploader': 'study.com',
964 'timestamp': 1459678540,
965 'upload_date': '20160403',
966 'filesize': 24687186,
970 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
971 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
975 'title': 'Conversation about Hexagonal Rails Part 1',
976 'description': 'a Martin Fowler video from ThoughtWorks',
978 'uploader': 'thoughtworks.wistia.com',
979 'timestamp': 1401832161,
980 'upload_date': '20140603',
983 # Wistia standard embed (async)
985 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
989 'title': 'Drip Brennan Dunn Workshop',
990 'description': 'a JV Webinars video from getdrip-1',
992 'timestamp': 1463607249,
993 'upload_date': '20160518',
996 'skip_download': True,
1001 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1005 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1006 'uploader': 'Sophos Security',
1007 'title': 'Chet Chat 171 - Oct 29, 2014',
1008 'upload_date': '20141029',
1011 # Soundcloud multiple embeds
1013 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1016 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1018 'playlist_mincount': 7,
1020 # TuneIn station embed
1022 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1027 'location': 'Paris, France',
1032 'skip_download': True,
1037 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1041 'upload_date': '20141112',
1042 'title': 'Rosetta #CometLanding webcast HL 10',
1045 # Another Livestream embed, without 'new.' in URL
1047 'url': 'https://www.freespeech.org/',
1051 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1055 'skip_download': True,
1060 'url': 'https://skiplagged.com/',
1063 'title': 'Skiplagged: The smart way to find cheap flights',
1065 'playlist_mincount': 1,
1066 'add_ie': ['Youtube'],
1070 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1074 'upload_date': '20141126',
1075 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1080 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1082 'id': '730m_DandD_1901_512k',
1084 'uploader': 'www.abc.net.au',
1085 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1088 # embedded viddler video
1090 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1094 'uploader': 'deadspin',
1095 'title': 'WALL-TO-GORTAT',
1096 'timestamp': 1422285291,
1097 'upload_date': '20150126',
1099 'add_ie': ['Viddler'],
1103 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1107 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1108 'description': 'md5:601cb790edd05908957dae8aaa866465',
1109 'upload_date': '20150220',
1111 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1115 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1117 'id': 'Mrj4DVp2zeA',
1119 'upload_date': '20150212',
1120 'uploader': 'The National Archives UK',
1121 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1122 'uploader_id': 'NationalArchives08',
1123 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1128 'url': 'http://www.suffolk.edu/sjc/live.php',
1132 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1133 'uploader': 'www.suffolk.edu',
1136 'skip_download': True,
1138 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1142 'url': 'http://www.indiedb.com/games/king-machine/videos',
1146 'title': 'king machine trailer 1',
1147 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1148 'thumbnail': r're:^https?://.*\.jpg$',
1152 # JWPlayer config passed as variable
1153 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1157 'title': 'ARIELE | Tube Cup',
1158 'uploader': 'www.txxx.com',
1162 'skip_download': True,
1167 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1168 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1172 'upload_date': '20171122',
1173 'timestamp': 1511366290,
1174 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1176 'add_ie': [JWPlatformIE.ie_key()],
1179 # Video.js embed, multiple formats
1180 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1182 'id': 'yygqldloqIk',
1184 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1185 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1186 'upload_date': '20130314',
1187 'uploader': 'PROстое3D',
1188 'uploader_id': 'PROstoe3D',
1191 'skip_download': True,
1195 # Video.js embed, single format
1196 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1200 'title': 'Step 1 - Good Foundation',
1201 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1204 'skip_download': True,
1209 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1210 'playlist_mincount': 5,
1212 'id': 'aanslagen-kopenhagen',
1213 'title': 'Aanslagen Kopenhagen',
1218 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1222 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1225 # Kaltura embed (different embed code)
1227 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1231 'upload_date': '20150127',
1232 'uploader_id': 'PremierMedia',
1234 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1237 # Kaltura embed with single quotes
1239 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1244 'timestamp': 1355743100,
1245 'upload_date': '20121217',
1246 'uploader_id': 'cplapp@learn360.com',
1248 'add_ie': ['Kaltura'],
1251 # Kaltura embedded via quoted entry_id
1252 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1256 'title': '06_matthew_brender_raj_dutt',
1257 'timestamp': 1466638791,
1258 'upload_date': '20160622',
1260 'add_ie': ['Kaltura'],
1261 'expected_warnings': [
1262 'Could not send HEAD request'
1265 'skip_download': True,
1269 # Kaltura embedded, some fileExt broken (#11480)
1270 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1274 'title': 'Our "Standard Models" of particle physics and cosmology',
1275 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1276 'timestamp': 1321158993,
1277 'upload_date': '20111113',
1278 'uploader_id': 'kps1',
1280 'add_ie': ['Kaltura'],
1283 # Kaltura iframe embed
1284 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1285 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1289 'title': 'I. M. Pei: A Centennial Celebration',
1290 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1291 'upload_date': '20170403',
1292 'uploader_id': 'batchUser',
1293 'timestamp': 1491232186,
1295 'add_ie': ['Kaltura'],
1298 # Kaltura iframe embed, more sophisticated
1299 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1303 'title': 'lecture-05sep2017',
1304 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1305 'upload_date': '20170913',
1306 'uploader_id': 'eps2',
1307 'timestamp': 1505340777,
1310 'skip_download': True,
1312 'add_ie': ['Kaltura'],
1315 # meta twitter:player
1316 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1320 'title': 'Main Twerk (Video)',
1321 'upload_date': '20171208',
1322 'uploader_id': 'sebastian.salinas@thechive.com',
1323 'timestamp': 1512713057,
1326 'skip_download': True,
1328 'add_ie': ['Kaltura'],
1330 # referrer protected EaglePlatform embed
1332 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1336 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1337 'thumbnail': r're:^https?://.*\.jpg$',
1342 'skip_download': True,
1345 # ClipYou (EaglePlatform) embed (custom URL)
1347 'url': 'http://muz-tv.ru/play/7129/',
1348 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1352 'title': "'O Sole Mio",
1353 'thumbnail': r're:^https?://.*\.jpg$',
1358 'skip_download': True,
1360 'skip': 'This video is unavailable.',
1364 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1368 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1369 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1370 'thumbnail': r're:^https?://.*\.jpg$',
1374 'skip': 'HTTP Error 404: Not Found',
1378 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1382 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1383 'thumbnail': r're:^https?://.*\.png$',
1389 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1390 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1394 'title': 'Facebook Creates "On This Day" | Crunch Report',
1395 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1396 'timestamp': 1427237531,
1397 'uploader': 'Crunch Report',
1398 'upload_date': '20150324',
1402 'skip_download': True,
1405 # Crooks and Liars embed
1407 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1411 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1412 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1413 'timestamp': 1428207000,
1414 'upload_date': '20150405',
1415 'uploader': 'Heather',
1418 # Crooks and Liars external embed
1420 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1422 'id': 'MTE3MjUtMzQ2MzA',
1424 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1425 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1426 'timestamp': 1265032391,
1427 'upload_date': '20100201',
1428 'uploader': 'Heather',
1431 # NBC Sports vplayer embed
1433 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1435 'id': 'ln7x1qSThw4k',
1437 'title': "PFT Live: New leader in the 'new-look' defense",
1438 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1439 'uploader': 'NBCU-SPORTS',
1440 'upload_date': '20140107',
1441 'timestamp': 1389118457,
1443 'skip': 'Invalid Page URL',
1447 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1448 'md5': '1aa589c675898ae6d37a17913cf68d66',
1450 'id': 'x_dtl_oa_LettermanliftPR_160608',
1452 'title': 'David Letterman: A Preview',
1453 '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.',
1454 'upload_date': '20160609',
1455 'timestamp': 1465431544,
1456 'uploader': 'NBCU-NEWS',
1461 'url': 'https://video.udn.com/news/300346',
1462 'md5': 'fd2060e988c326991037b9aff9df21a6',
1466 'title': '中一中男師變性 全校師生力挺',
1467 'thumbnail': r're:^https?://.*\.jpg$',
1471 'skip_download': True,
1473 'expected_warnings': ['Failed to parse JSON Expecting value'],
1475 # Brightcove URL in single quotes
1477 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1478 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1480 'id': '4255764656001',
1482 'title': 'SN Presents: Russell Martin, World Citizen',
1483 '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.',
1484 'uploader': 'Rogers Sportsnet',
1485 'uploader_id': '1704050871',
1486 'upload_date': '20150525',
1487 'timestamp': 1432570283,
1490 # OnionStudios embed
1492 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1496 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1497 'thumbnail': r're:^https?://.*\.jpe?g$',
1498 'uploader': 'ClickHole',
1499 'uploader_id': 'clickhole',
1504 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1506 'id': '74849a00-85a9-11e1-9660-123139220831',
1508 'title': '#whilewewatch',
1511 # AdobeTVVideo embed
1513 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1514 'md5': '43662b577c018ad707a63766462b1e87',
1518 'title': 'New experience with Acrobat DC',
1519 'description': 'New experience with Acrobat DC',
1520 'duration': 248.667,
1523 # BrightcoveInPageEmbed embed
1525 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1527 'id': '4238694884001',
1529 'title': 'Tabletop: Dread, Last Thoughts',
1530 'description': 'Tabletop: Dread, Last Thoughts',
1534 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1535 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1537 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1539 'id': '4785848093001',
1541 'title': 'The Cardinal Pell Interview',
1542 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1543 'uploader': 'GlobeCast Australia - GlobeStream',
1544 'uploader_id': '2733773828001',
1545 'upload_date': '20160304',
1546 'timestamp': 1457083087,
1550 'skip_download': True,
1554 # Brightcove embed with whitespace around attribute names
1555 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1557 'id': '3167554373001',
1559 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1560 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1561 'uploader_id': '1079349493',
1562 'upload_date': '20140207',
1563 'timestamp': 1391810548,
1566 'skip_download': True,
1569 # Another form of arte.tv embed
1571 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1572 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1574 'id': '030273-562_PLUS7-F',
1576 'title': 'ARTE Reportage - Nulle part, en France',
1577 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1578 'upload_date': '20160409',
1583 'url': 'http://www.wykop.pl/link/3088787/',
1584 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1586 'id': '874_1459135191',
1588 'title': 'Man shows poor quality of new apartment building',
1589 'description': 'The wall is like a sand pile.',
1590 'uploader': 'Lake8737',
1592 'add_ie': [LiveLeakIE.ie_key()],
1594 # Another LiveLeak embed pattern (#13336)
1596 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1598 'id': '2eb_1496309988',
1600 'title': 'Thief robs place where everyone was armed',
1601 'description': 'md5:694d73ee79e535953cf2488562288eee',
1602 'uploader': 'brazilwtf',
1604 'add_ie': [LiveLeakIE.ie_key()],
1606 # Duplicated embedded video URLs
1608 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1610 'id': '149298443_480_16c25b74_2',
1612 'title': 'vs. Blue Orange Spring Game',
1613 'uploader': 'www.hudl.com',
1616 # twitter:player:stream embed
1618 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1622 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1623 'uploader': 'www.rtl.be',
1627 'skip_download': True,
1630 # twitter:player embed
1632 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1633 'md5': 'a3e0df96369831de324f0778e126653c',
1635 'id': '4909620399001',
1637 'title': 'What Do Black Holes Sound Like?',
1638 'description': 'what do black holes sound like',
1639 'upload_date': '20160524',
1640 'uploader_id': '29913724001',
1641 'timestamp': 1464107587,
1642 'uploader': 'TheAtlantic',
1644 'add_ie': ['BrightcoveLegacy'],
1646 # Facebook <iframe> embed
1648 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1649 'md5': 'fbcde74f534176ecb015849146dd3aee',
1651 'id': '599637780109885',
1653 'title': 'Facebook video #599637780109885',
1656 # Facebook <iframe> embed, plugin video
1658 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1660 'id': '1754168231264132',
1662 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1663 'uploader': 'Tariq Ramadan (official)',
1664 'timestamp': 1496758379,
1665 'upload_date': '20170606',
1668 'skip_download': True,
1671 # Facebook API embed
1673 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1674 'md5': 'a47372ee61b39a7b90287094d447d94e',
1676 'id': '10153467542406923',
1678 'title': 'Facebook video #10153467542406923',
1681 # Wordpress "YouTube Video Importer" plugin
1683 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1684 'md5': 'd16797741b560b485194eddda8121b48',
1686 'id': 'HNTXWDXV9Is',
1688 'title': 'Blue Devils Drumline Stanford lot 2016',
1689 'upload_date': '20160627',
1690 'uploader_id': 'GENOCIDE8GENERAL10',
1691 'uploader': 'cylus cyrus',
1695 # video stored on custom kaltura server
1696 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1697 'md5': '537617d06e64dfed891fa1593c4b30cc',
1701 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1702 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1703 'uploader_id': 'videos.expansion@el-mundo.net',
1704 'upload_date': '20150429',
1705 'timestamp': 1430303472,
1707 'add_ie': ['Kaltura'],
1710 # Non-standard Vimeo embed
1711 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1712 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1716 'title': 'Understanding the web - Teaser',
1717 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1718 'upload_date': '20151214',
1719 'uploader': 'OpenClassrooms',
1720 'uploader_id': 'openclassrooms',
1722 'add_ie': ['Vimeo'],
1725 # generic vimeo embed that requires original URL passed as Referer
1726 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1727 'only_matching': True,
1730 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1731 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1733 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1735 'title': 'Big Buck Bunny',
1736 'description': 'Royalty free test video',
1737 'timestamp': 1432816365,
1738 'upload_date': '20150528',
1742 'skip_download': True,
1744 'add_ie': [ArkenaIE.ie_key()],
1747 '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/',
1751 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1754 'skip_download': True,
1756 'add_ie': [Vbox7IE.ie_key()],
1760 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1763 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1765 'playlist_mincount': 3,
1769 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1771 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1772 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1774 'playlist_mincount': 2,
1778 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1782 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1783 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1786 'skip_download': True,
1788 'add_ie': [TwentyMinutenIE.ie_key()],
1792 'url': 'https://en.support.wordpress.com/videopress/',
1796 'title': 'IMG_5786',
1797 'timestamp': 1435711927,
1798 'upload_date': '20150701',
1801 'skip_download': True,
1803 'add_ie': [VideoPressIE.ie_key()],
1807 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1809 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1811 'title': 'Магаззино: Казань 2',
1812 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1813 'uploader': 'Магаззино',
1814 'upload_date': '20170228',
1815 'uploader_id': '996642',
1818 'skip_download': True,
1820 'add_ie': [RutubeIE.ie_key()],
1823 # ThePlatform embedded with whitespaces in URLs
1824 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1825 'only_matching': True,
1828 # Senate ISVP iframe https
1829 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1830 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1832 'id': 'govtaff020316',
1834 'title': 'Integrated Senate Video Player',
1836 'add_ie': [SenateISVPIE.ie_key()],
1839 # Limelight embeds (1 channel embed + 4 media embeds)
1840 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1842 'id': 'FacilitatorTraining2017',
1843 'title': 'Facilitator Training 2017',
1845 'playlist_mincount': 5,
1848 # Limelight embed (LimelightPlayerUtil.embed)
1849 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1851 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1853 'title': '07448641',
1854 'timestamp': 1499890639,
1855 'upload_date': '20170712',
1858 'skip_download': True,
1860 'add_ie': ['LimelightMedia'],
1863 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1865 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1866 'title': 'Standoff with Walnut Creek murder suspect ends',
1867 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1869 'playlist_mincount': 4,
1872 # WashingtonPost embed
1873 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1875 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1877 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1878 '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.',
1879 'timestamp': 1455216756,
1880 'uploader': 'The Washington Post',
1881 'upload_date': '20160211',
1883 'add_ie': [WashingtonPostIE.ie_key()],
1887 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1891 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1894 'skip_download': True,
1896 'add_ie': [MediasetIE.ie_key()],
1900 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1902 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1903 'title': 'Slovenskom sa prehnala vlna silných búrok',
1905 'playlist_mincount': 5,
1906 'add_ie': [JojIE.ie_key()],
1909 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1910 'url': 'https://tvrain.ru/amp/418921/',
1911 'md5': 'cc00413936695987e8de148b67d14f1d',
1915 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1920 'url': 'http://help.vzaar.com/article/165-embedding-video',
1921 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1925 'title': 'Building A Business Online: Principal Chairs Q & A',
1929 # multiple HTML5 videos on one page
1930 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1932 'id': 'keyscenarios',
1933 'title': 'Rescue Kit 14 Free Edition - Getting started',
1935 'playlist_count': 4,
1939 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1940 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1943 'title': 'vl14062007715967',
1948 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1949 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1951 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1953 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1954 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1955 'timestamp': 1474354800,
1956 'upload_date': '20160920',
1960 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1964 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1965 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1966 'timestamp': 1516100691,
1967 'upload_date': '20180116',
1970 'skip_download': True,
1972 'add_ie': [SpringboardPlatformIE.ie_key()],
1975 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1977 'id': 'uPDB5I9wfp8',
1979 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1980 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1981 'upload_date': '20160219',
1982 'uploader': 'Pocoyo - Português (BR)',
1983 'uploader_id': 'PocoyoBrazil',
1985 'add_ie': [YoutubeIE.ie_key()],
1987 'skip_download': True,
1991 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1993 'id': 'vMDE4NzI1Mjgt690b',
1997 'add_ie': [YapFilesIE.ie_key()],
1999 'skip_download': True,
2003 # CloudflareStream embed
2004 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2006 'id': '31c9291ab41fac05471db4e73aa11717',
2008 'title': '31c9291ab41fac05471db4e73aa11717',
2010 'add_ie': [CloudflareStreamIE.ie_key()],
2012 'skip_download': True,
2017 'url': 'https://joinpeertube.org/fr/home/',
2020 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2022 'playlist_count': 2,
2026 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2030 'title': 'Így kell otthon hamburgert sütni',
2031 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2032 'timestamp': 1426330212,
2033 'upload_date': '20150314',
2034 'uploader': 'StreetKitchen',
2035 'uploader_id': '546363',
2037 'add_ie': [IndavideoEmbedIE.ie_key()],
2039 'skip_download': True,
2043 # APA embed via JWPlatform embed
2044 'url': 'http://www.vol.at/blue-man-group/5593454',
2048 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2049 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2050 'thumbnail': r're:^https?://.*\.jpg$',
2052 'timestamp': 1519211149,
2053 'upload_date': '20180221',
2056 'skip_download': True,
2060 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2061 'md5': 'b68d276de422ab07ee1d49388103f457',
2064 'title': 'Lock up and get excited',
2067 'skip': 'TODO: fix nested playlists processing in tests',
2071 'url': 'https://viqeo.tv/',
2074 'title': 'All-new video platform',
2076 'playlist_count': 6,
2080 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2082 'id': '5b400b834b32992a310622b9',
2084 'title': 'Smoky Barbecue Favorites',
2085 'thumbnail': r're:^https?://.*\.jpe?g',
2087 'add_ie': [ZypeIE.ie_key()],
2089 'skip_download': True,
2094 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2098 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2099 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2100 'thumbnail': r're:^https?://.*\.jpg$',
2103 'skip_download': True,
2105 'expected_warnings': ['Failed to download MPD manifest'],
2108 # # TODO: find another test
2109 # # http://schema.org/VideoObject
2110 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2111 # 'md5': '888dcf08b7ea671381f00fab74692755',
2113 # 'id': 'nyvTSJMKId',
2115 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2116 # 'description': '#love for cats.',
2117 # 'timestamp': 1461244995,
2118 # 'upload_date': '20160421',
2121 # 'force_generic_extractor': True,
2126 def report_following_redirect(self, new_url):
2127 """Report information extraction."""
2128 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2130 def _extract_rss(self, url, video_id, doc):
2131 playlist_title = doc.find('./channel/title').text
2132 playlist_desc_el = doc.find('./channel/description')
2133 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2136 for it in doc.findall('./channel/item'):
2138 enclosure_nodes = it.findall('./enclosure')
2139 for e in enclosure_nodes:
2140 next_url = e.attrib.get('url')
2145 next_url = xpath_text(it, 'link', fatal=False)
2151 '_type': 'url_transparent',
2153 'title': it.find('title').text,
2157 '_type': 'playlist',
2159 'title': playlist_title,
2160 'description': playlist_desc,
2164 def _extract_camtasia(self, url, video_id, webpage):
2165 """ Returns None if no camtasia video can be found. """
2167 camtasia_cfg = self._search_regex(
2168 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2169 webpage, 'camtasia configuration file', default=None)
2170 if camtasia_cfg is None:
2173 title = self._html_search_meta('DC.title', webpage, fatal=True)
2175 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2176 camtasia_cfg = self._download_xml(
2177 camtasia_url, video_id,
2178 note='Downloading camtasia configuration',
2179 errnote='Failed to download camtasia configuration')
2180 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2183 for n in fileset_node.getchildren():
2184 url_n = n.find('./uri')
2189 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2190 'title': '%s - %s' % (title, n.tag),
2191 'url': compat_urlparse.urljoin(url, url_n.text),
2192 'duration': float_or_none(n.find('./duration').text),
2196 '_type': 'playlist',
2201 def _real_extract(self, url):
2202 if url.startswith('//'):
2203 return self.url_result(self.http_scheme() + url)
2205 parsed_url = compat_urlparse.urlparse(url)
2206 if not parsed_url.scheme:
2207 default_search = self._downloader.params.get('default_search')
2208 if default_search is None:
2209 default_search = 'fixup_error'
2211 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2213 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2214 return self.url_result('http://' + url)
2215 elif default_search != 'fixup_error':
2216 if default_search == 'auto_warning':
2217 if re.match(r'^(?:url|URL)$', url):
2218 raise ExtractorError(
2219 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2222 self._downloader.report_warning(
2223 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2224 return self.url_result('ytsearch:' + url)
2226 if default_search in ('error', 'fixup_error'):
2227 raise ExtractorError(
2228 '%r is not a valid URL. '
2229 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2230 % (url, url), expected=True)
2232 if ':' not in default_search:
2233 default_search += ':'
2234 return self.url_result(default_search + url)
2236 url, smuggled_data = unsmuggle_url(url)
2237 force_videoid = None
2238 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2239 if smuggled_data and 'force_videoid' in smuggled_data:
2240 force_videoid = smuggled_data['force_videoid']
2241 video_id = force_videoid
2243 video_id = self._generic_id(url)
2245 self.to_screen('%s: Requesting header' % video_id)
2247 head_req = HEADRequest(url)
2248 head_response = self._request_webpage(
2250 note=False, errnote='Could not send HEAD request to %s' % url,
2253 if head_response is not False:
2254 # Check for redirect
2255 new_url = compat_str(head_response.geturl())
2257 self.report_following_redirect(new_url)
2259 new_url = smuggle_url(
2260 new_url, {'force_videoid': force_videoid})
2261 return self.url_result(new_url)
2263 full_response = None
2264 if head_response is False:
2265 request = sanitized_Request(url)
2266 request.add_header('Accept-Encoding', '*')
2267 full_response = self._request_webpage(request, video_id)
2268 head_response = full_response
2272 'title': self._generic_title(url),
2273 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2276 # Check for direct link to a video
2277 content_type = head_response.headers.get('Content-Type', '').lower()
2278 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2280 format_id = compat_str(m.group('format_id'))
2281 if format_id.endswith('mpegurl'):
2282 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2283 elif format_id == 'f4m':
2284 formats = self._extract_f4m_formats(url, video_id)
2287 'format_id': format_id,
2289 'vcodec': 'none' if m.group('type') == 'audio' else None
2291 info_dict['direct'] = True
2292 self._sort_formats(formats)
2293 info_dict['formats'] = formats
2296 if not self._downloader.params.get('test', False) and not is_intentional:
2297 force = self._downloader.params.get('force_generic_extractor', False)
2298 self._downloader.report_warning(
2299 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2301 if not full_response:
2302 request = sanitized_Request(url)
2303 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2304 # making it impossible to download only chunk of the file (yet we need only 512kB to
2305 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2306 # that will always result in downloading the whole file that is not desirable.
2307 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2308 # to accept raw bytes and being able to download only a chunk.
2309 # It may probably better to solve this by checking Content-Type for application/octet-stream
2310 # after HEAD request finishes, but not sure if we can rely on this.
2311 request.add_header('Accept-Encoding', '*')
2312 full_response = self._request_webpage(request, video_id)
2314 first_bytes = full_response.read(512)
2316 # Is it an M3U playlist?
2317 if first_bytes.startswith(b'#EXTM3U'):
2318 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2319 self._sort_formats(info_dict['formats'])
2322 # Maybe it's a direct link to a video?
2323 # Be careful not to download the whole thing!
2324 if not is_html(first_bytes):
2325 self._downloader.report_warning(
2326 'URL could be a direct video link, returning it as such.')
2333 webpage = self._webpage_read_content(
2334 full_response, url, video_id, prefix=first_bytes)
2336 self.report_extraction(video_id)
2338 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2340 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2341 if doc.tag == 'rss':
2342 return self._extract_rss(url, video_id, doc)
2343 elif doc.tag == 'SmoothStreamingMedia':
2344 info_dict['formats'] = self._parse_ism_formats(doc, url)
2345 self._sort_formats(info_dict['formats'])
2347 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2348 smil = self._parse_smil(doc, url, video_id)
2349 self._sort_formats(smil['formats'])
2351 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2352 return self.playlist_result(
2354 doc, video_id, xspf_url=url,
2355 xspf_base_url=compat_str(full_response.geturl())),
2357 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2358 info_dict['formats'] = self._parse_mpd_formats(
2360 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2362 self._sort_formats(info_dict['formats'])
2364 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2365 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2366 self._sort_formats(info_dict['formats'])
2368 except compat_xml_parse_error:
2371 # Is it a Camtasia project?
2372 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2373 if camtasia_res is not None:
2376 # Sometimes embedded video player is hidden behind percent encoding
2377 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
2378 # Unescaping the whole page allows to handle those cases in a generic way
2379 webpage = compat_urllib_parse_unquote(webpage)
2381 # it's tempting to parse this further, but you would
2382 # have to take into account all the variations like
2383 # Video Title - Site Name
2384 # Site Name | Video Title
2385 # Video Title - Tagline | Site Name
2386 # and so on and so forth; it's just not practical
2387 video_title = self._og_search_title(
2388 webpage, default=None) or self._html_search_regex(
2389 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2392 # Try to detect age limit automatically
2393 age_limit = self._rta_search(webpage)
2394 # And then there are the jokers who advertise that they use RTA,
2395 # but actually don't.
2396 AGE_LIMIT_MARKERS = [
2397 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2399 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2402 # video uploader is domain name
2403 video_uploader = self._search_regex(
2404 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2406 video_description = self._og_search_description(webpage, default=None)
2407 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2410 'title': video_title,
2411 'description': video_description,
2412 'thumbnail': video_thumbnail,
2413 'age_limit': age_limit,
2416 # Look for Brightcove Legacy Studio embeds
2417 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2421 'url': smuggle_url(bc_url, {'Referer': url}),
2422 'ie_key': 'BrightcoveLegacy'
2423 } for bc_url in bc_urls]
2426 '_type': 'playlist',
2427 'title': video_title,
2432 # Look for Brightcove New Studio embeds
2433 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2435 return self.playlist_from_matches(
2436 bc_urls, video_id, video_title,
2437 getter=lambda x: smuggle_url(x, {'referrer': url}),
2440 # Look for Nexx embeds
2441 nexx_urls = NexxIE._extract_urls(webpage)
2443 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2445 # Look for Nexx iFrame embeds
2446 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2448 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2450 # Look for ThePlatform embeds
2451 tp_urls = ThePlatformIE._extract_urls(webpage)
2453 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2455 # Look for Vessel embeds
2456 vessel_urls = VesselIE._extract_urls(webpage)
2458 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2460 # Look for embedded rtl.nl player
2461 matches = re.findall(
2462 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2465 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2467 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2469 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2471 vid_me_embed_url = self._search_regex(
2472 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2473 webpage, 'vid.me embed', default=None)
2474 if vid_me_embed_url is not None:
2475 return self.url_result(vid_me_embed_url, 'Vidme')
2477 # Look for YouTube embeds
2478 youtube_urls = YoutubeIE._extract_urls(webpage)
2480 return self.playlist_from_matches(
2481 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2483 matches = DailymotionIE._extract_urls(webpage)
2485 return self.playlist_from_matches(matches, video_id, video_title)
2487 # Look for embedded Dailymotion playlist player (#3822)
2489 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2491 playlists = re.findall(
2492 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2494 return self.playlist_from_matches(
2495 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2497 # Look for DailyMail embeds
2498 dailymail_urls = DailyMailIE._extract_urls(webpage)
2500 return self.playlist_from_matches(
2501 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2503 # Look for embedded Wistia player
2504 wistia_url = WistiaIE._extract_url(webpage)
2507 '_type': 'url_transparent',
2508 'url': self._proto_relative_url(wistia_url),
2509 'ie_key': WistiaIE.ie_key(),
2510 'uploader': video_uploader,
2513 # Look for SVT player
2514 svt_url = SVTIE._extract_url(webpage)
2516 return self.url_result(svt_url, 'SVT')
2518 # Look for Bandcamp pages with custom domain
2519 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2520 if mobj is not None:
2521 burl = unescapeHTML(mobj.group(1))
2522 # Don't set the extractor because it can be a track url or an album
2523 return self.url_result(burl)
2525 # Look for embedded Vevo player
2527 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2528 if mobj is not None:
2529 return self.url_result(mobj.group('url'))
2531 # Look for embedded Viddler player
2533 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2535 if mobj is not None:
2536 return self.url_result(mobj.group('url'))
2538 # Look for NYTimes player
2540 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2542 if mobj is not None:
2543 return self.url_result(mobj.group('url'))
2545 # Look for Libsyn player
2547 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2548 if mobj is not None:
2549 return self.url_result(mobj.group('url'))
2551 # Look for Ooyala videos
2552 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
2553 or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2554 or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2555 or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
2556 or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2557 if mobj is not None:
2558 embed_token = self._search_regex(
2559 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2560 webpage, 'ooyala embed token', default=None)
2561 return OoyalaIE._build_url_result(smuggle_url(
2564 'embed_token': embed_token,
2567 # Look for multiple Ooyala embeds on SBN network websites
2568 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2569 if mobj is not None:
2570 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2572 return self.playlist_from_matches(
2573 embeds, video_id, video_title,
2574 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2576 # Look for Aparat videos
2577 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2578 if mobj is not None:
2579 return self.url_result(mobj.group(1), 'Aparat')
2581 # Look for MPORA videos
2582 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2583 if mobj is not None:
2584 return self.url_result(mobj.group(1), 'Mpora')
2586 # Look for embedded Facebook player
2587 facebook_urls = FacebookIE._extract_urls(webpage)
2589 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2591 # Look for embedded VK player
2592 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2593 if mobj is not None:
2594 return self.url_result(mobj.group('url'), 'VK')
2596 # Look for embedded Odnoklassniki player
2597 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2598 if mobj is not None:
2599 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2601 # Look for embedded ivi player
2602 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2603 if mobj is not None:
2604 return self.url_result(mobj.group('url'), 'Ivi')
2606 # Look for embedded Huffington Post player
2608 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2609 if mobj is not None:
2610 return self.url_result(mobj.group('url'), 'HuffPost')
2613 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2614 if mobj is not None:
2615 return self.url_result(mobj.group('url'))
2616 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2617 if mobj is not None:
2618 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2620 # Look for funnyordie embed
2621 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2623 return self.playlist_from_matches(
2624 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2626 # Look for BBC iPlayer embed
2627 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2629 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2631 # Look for embedded RUTV player
2632 rutv_url = RUTVIE._extract_url(webpage)
2634 return self.url_result(rutv_url, 'RUTV')
2636 # Look for embedded TVC player
2637 tvc_url = TVCIE._extract_url(webpage)
2639 return self.url_result(tvc_url, 'TVC')
2641 # Look for embedded SportBox player
2642 sportbox_urls = SportBoxIE._extract_urls(webpage)
2644 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
2646 # Look for embedded XHamster player
2647 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2649 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2651 # Look for embedded TNAFlixNetwork player
2652 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2654 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2656 # Look for embedded PornHub player
2657 pornhub_urls = PornHubIE._extract_urls(webpage)
2659 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2661 # Look for embedded DrTuber player
2662 drtuber_urls = DrTuberIE._extract_urls(webpage)
2664 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2666 # Look for embedded RedTube player
2667 redtube_urls = RedTubeIE._extract_urls(webpage)
2669 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2671 # Look for embedded Tube8 player
2672 tube8_urls = Tube8IE._extract_urls(webpage)
2674 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2676 # Look for embedded Tvigle player
2678 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2679 if mobj is not None:
2680 return self.url_result(mobj.group('url'), 'Tvigle')
2682 # Look for embedded TED player
2684 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2685 if mobj is not None:
2686 return self.url_result(mobj.group('url'), 'TED')
2688 # Look for embedded Ustream videos
2689 ustream_url = UstreamIE._extract_url(webpage)
2691 return self.url_result(ustream_url, UstreamIE.ie_key())
2693 # Look for embedded arte.tv player
2695 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2697 if mobj is not None:
2698 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2700 # Look for embedded francetv player
2702 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2704 if mobj is not None:
2705 return self.url_result(mobj.group('url'))
2707 # Look for embedded smotri.com player
2708 smotri_url = SmotriIE._extract_url(webpage)
2710 return self.url_result(smotri_url, 'Smotri')
2712 # Look for embedded Myvi.ru player
2713 myvi_url = MyviIE._extract_url(webpage)
2715 return self.url_result(myvi_url)
2717 # Look for embedded soundcloud player
2718 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2720 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2722 # Look for tunein player
2723 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2725 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2727 # Look for embedded mtvservices player
2728 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2730 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2732 # Look for embedded yahoo player
2734 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2736 if mobj is not None:
2737 return self.url_result(mobj.group('url'), 'Yahoo')
2739 # Look for embedded sbs.com.au player
2743 <meta\s+property="og:video"\s+content=|
2746 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2748 if mobj is not None:
2749 return self.url_result(mobj.group('url'), 'SBS')
2751 # Look for embedded Cinchcast player
2753 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2755 if mobj is not None:
2756 return self.url_result(mobj.group('url'), 'Cinchcast')
2759 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2763 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2765 if mobj is not None:
2766 return self.url_result(mobj.group('url'), 'MLB')
2769 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2771 if mobj is not None:
2772 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2775 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2777 if mobj is not None:
2778 return self.url_result(mobj.group('url'), 'Livestream')
2780 # Look for Zapiks embed
2782 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2783 if mobj is not None:
2784 return self.url_result(mobj.group('url'), 'Zapiks')
2786 # Look for Kaltura embeds
2787 kaltura_url = KalturaIE._extract_url(webpage)
2789 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2791 # Look for EaglePlatform embeds
2792 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2793 if eagleplatform_url:
2794 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2796 # Look for ClipYou (uses EaglePlatform) embeds
2798 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2799 if mobj is not None:
2800 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2802 # Look for Pladform embeds
2803 pladform_url = PladformIE._extract_url(webpage)
2805 return self.url_result(pladform_url)
2807 # Look for Videomore embeds
2808 videomore_url = VideomoreIE._extract_url(webpage)
2810 return self.url_result(videomore_url)
2812 # Look for Webcaster embeds
2813 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2815 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2817 # Look for Playwire embeds
2819 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2820 if mobj is not None:
2821 return self.url_result(mobj.group('url'))
2823 # Look for 5min embeds
2825 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2826 if mobj is not None:
2827 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2829 # Look for Crooks and Liars embeds
2831 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2832 if mobj is not None:
2833 return self.url_result(mobj.group('url'))
2835 # Look for NBC Sports VPlayer embeds
2836 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2838 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2840 # Look for NBC News embeds
2841 nbc_news_embed_url = re.search(
2842 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2843 if nbc_news_embed_url:
2844 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2846 # Look for Google Drive embeds
2847 google_drive_url = GoogleDriveIE._extract_url(webpage)
2848 if google_drive_url:
2849 return self.url_result(google_drive_url, 'GoogleDrive')
2851 # Look for UDN embeds
2853 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2854 if mobj is not None:
2855 return self.url_result(
2856 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2858 # Look for Senate ISVP iframe
2859 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2861 return self.url_result(senate_isvp_url, 'SenateISVP')
2863 # Look for OnionStudios embeds
2864 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2865 if onionstudios_url:
2866 return self.url_result(onionstudios_url)
2868 # Look for ViewLift embeds
2869 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2871 return self.url_result(viewlift_url)
2873 # Look for JWPlatform embeds
2874 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2876 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2878 # Look for Digiteka embeds
2879 digiteka_url = DigitekaIE._extract_url(webpage)
2881 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2883 # Look for Arkena embeds
2884 arkena_url = ArkenaIE._extract_url(webpage)
2886 return self.url_result(arkena_url, ArkenaIE.ie_key())
2888 # Look for Piksel embeds
2889 piksel_url = PikselIE._extract_url(webpage)
2891 return self.url_result(piksel_url, PikselIE.ie_key())
2893 # Look for Limelight embeds
2894 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2896 return self.playlist_result(
2897 limelight_urls, video_id, video_title, video_description)
2899 # Look for Anvato embeds
2900 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2902 return self.playlist_result(
2903 anvato_urls, video_id, video_title, video_description)
2905 # Look for AdobeTVVideo embeds
2907 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2909 if mobj is not None:
2910 return self.url_result(
2911 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2914 # Look for Vine embeds
2916 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2918 if mobj is not None:
2919 return self.url_result(
2920 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2922 # Look for VODPlatform embeds
2924 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2926 if mobj is not None:
2927 return self.url_result(
2928 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2930 # Look for Mangomolo embeds
2932 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2934 video\?.*?\bid=(?P<video_id>\d+)|
2935 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2936 ).+?)\1''', webpage)
2937 if mobj is not None:
2939 '_type': 'url_transparent',
2940 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2941 'title': video_title,
2942 'description': video_description,
2943 'thumbnail': video_thumbnail,
2944 'uploader': video_uploader,
2946 video_id = mobj.group('video_id')
2949 'ie_key': 'MangomoloVideo',
2954 'ie_key': 'MangomoloLive',
2955 'id': mobj.group('channel_id'),
2959 # Look for Instagram embeds
2960 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2961 if instagram_embed_url is not None:
2962 return self.url_result(
2963 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2965 # Look for LiveLeak embeds
2966 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2968 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2970 # Look for 3Q SDN embeds
2971 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2974 '_type': 'url_transparent',
2975 'ie_key': ThreeQSDNIE.ie_key(),
2976 'url': self._proto_relative_url(threeqsdn_url),
2977 'title': video_title,
2978 'description': video_description,
2979 'thumbnail': video_thumbnail,
2980 'uploader': video_uploader,
2983 # Look for VBOX7 embeds
2984 vbox7_url = Vbox7IE._extract_url(webpage)
2986 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2988 # Look for DBTV embeds
2989 dbtv_urls = DBTVIE._extract_urls(webpage)
2991 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2993 # Look for Videa embeds
2994 videa_urls = VideaIE._extract_urls(webpage)
2996 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2998 # Look for 20 minuten embeds
2999 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3001 return self.playlist_from_matches(
3002 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3004 # Look for Openload embeds
3005 openload_urls = OpenloadIE._extract_urls(webpage)
3007 return self.playlist_from_matches(
3008 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
3010 # Look for Verystream embeds
3011 verystream_urls = VerystreamIE._extract_urls(webpage)
3013 return self.playlist_from_matches(
3014 verystream_urls, video_id, video_title, ie=VerystreamIE.ie_key())
3016 # Look for VideoPress embeds
3017 videopress_urls = VideoPressIE._extract_urls(webpage)
3019 return self.playlist_from_matches(
3020 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3022 # Look for Rutube embeds
3023 rutube_urls = RutubeIE._extract_urls(webpage)
3025 return self.playlist_from_matches(
3026 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3028 # Look for WashingtonPost embeds
3029 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3031 return self.playlist_from_matches(
3032 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3034 # Look for Mediaset embeds
3035 mediaset_urls = MediasetIE._extract_urls(self, webpage)
3037 return self.playlist_from_matches(
3038 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3040 # Look for JOJ.sk embeds
3041 joj_urls = JojIE._extract_urls(webpage)
3043 return self.playlist_from_matches(
3044 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3046 # Look for megaphone.fm embeds
3047 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3049 return self.playlist_from_matches(
3050 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3052 # Look for vzaar embeds
3053 vzaar_urls = VzaarIE._extract_urls(webpage)
3055 return self.playlist_from_matches(
3056 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3058 channel9_urls = Channel9IE._extract_urls(webpage)
3060 return self.playlist_from_matches(
3061 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3063 vshare_urls = VShareIE._extract_urls(webpage)
3065 return self.playlist_from_matches(
3066 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3068 # Look for Mediasite embeds
3069 mediasite_urls = MediasiteIE._extract_urls(webpage)
3072 self.url_result(smuggle_url(
3073 compat_urlparse.urljoin(url, mediasite_url),
3074 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3075 for mediasite_url in mediasite_urls]
3076 return self.playlist_result(entries, video_id, video_title)
3078 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3079 if springboardplatform_urls:
3080 return self.playlist_from_matches(
3081 springboardplatform_urls, video_id, video_title,
3082 ie=SpringboardPlatformIE.ie_key())
3084 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3086 return self.playlist_from_matches(
3087 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3089 vice_urls = ViceIE._extract_urls(webpage)
3091 return self.playlist_from_matches(
3092 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3094 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3096 return self.playlist_from_matches(
3097 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3099 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3100 if cloudflarestream_urls:
3101 return self.playlist_from_matches(
3102 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3104 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3106 return self.playlist_from_matches(
3107 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3109 teachable_url = TeachableIE._extract_url(webpage, url)
3111 return self.url_result(teachable_url)
3113 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3115 return self.playlist_from_matches(
3116 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3118 apa_urls = APAIE._extract_urls(webpage)
3120 return self.playlist_from_matches(
3121 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3123 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3125 return self.playlist_from_matches(
3126 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3128 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3129 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3131 if sharevideos_urls:
3132 return self.playlist_from_matches(
3133 sharevideos_urls, video_id, video_title)
3135 viqeo_urls = ViqeoIE._extract_urls(webpage)
3137 return self.playlist_from_matches(
3138 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3140 expressen_urls = ExpressenIE._extract_urls(webpage)
3142 return self.playlist_from_matches(
3143 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3145 zype_urls = ZypeIE._extract_urls(webpage)
3147 return self.playlist_from_matches(
3148 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3150 # Look for HTML5 media
3151 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3153 if len(entries) == 1:
3156 'title': video_title,
3159 for num, entry in enumerate(entries, start=1):
3161 'id': '%s-%s' % (video_id, num),
3162 'title': '%s (%d)' % (video_title, num),
3164 for entry in entries:
3165 self._sort_formats(entry['formats'])
3166 return self.playlist_result(entries, video_id, video_title)
3168 jwplayer_data = self._find_jwplayer_data(
3169 webpage, video_id, transform_source=js_to_json)
3172 info = self._parse_jwplayer_data(
3173 jwplayer_data, video_id, require_title=False, base_url=url)
3174 return merge_dicts(info, info_dict)
3175 except ExtractorError:
3176 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3181 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3183 if mobj is not None:
3184 sources = self._parse_json(
3185 mobj.group(1), video_id, transform_source=js_to_json,
3187 if not isinstance(sources, list):
3190 for source in sources:
3191 src = source.get('src')
3192 if not src or not isinstance(src, compat_str):
3194 src = compat_urlparse.urljoin(url, src)
3195 src_type = source.get('type')
3196 if isinstance(src_type, compat_str):
3197 src_type = src_type.lower()
3198 ext = determine_ext(src).lower()
3199 if src_type == 'video/youtube':
3200 return self.url_result(src, YoutubeIE.ie_key())
3201 if src_type == 'application/dash+xml' or ext == 'mpd':
3202 formats.extend(self._extract_mpd_formats(
3203 src, video_id, mpd_id='dash', fatal=False))
3204 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3205 formats.extend(self._extract_m3u8_formats(
3206 src, video_id, 'mp4', entry_protocol='m3u8_native',
3207 m3u8_id='hls', fatal=False))
3211 'ext': (mimetype2ext(src_type)
3212 or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3215 self._sort_formats(formats)
3216 info_dict['formats'] = formats
3219 # Looking for http://schema.org/VideoObject
3220 json_ld = self._search_json_ld(
3221 webpage, video_id, default={}, expected_type='VideoObject')
3222 if json_ld.get('url'):
3223 return merge_dicts(json_ld, info_dict)
3225 def check_video(vurl):
3226 if YoutubeIE.suitable(vurl):
3228 if RtmpIE.suitable(vurl):
3230 vpath = compat_urlparse.urlparse(vurl).path
3231 vext = determine_ext(vpath)
3232 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3234 def filter_video(urls):
3235 return list(filter(check_video, urls))
3237 # Start with something easy: JW Player in SWFObject
3238 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3240 # Look for gorilla-vid style embedding
3241 found = filter_video(re.findall(r'''(?sx)
3245 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3248 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3250 # Broaden the search a little bit
3251 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3253 # Broaden the findall a little bit: JWPlayer JS loader
3254 found = filter_video(re.findall(
3255 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3258 found = filter_video(re.findall(r'''(?xs)
3259 flowplayer\("[^"]+",\s*
3261 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3262 ["']?url["']?\s*:\s*["']([^"']+)["']
3267 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3269 # Try to find twitter cards info
3270 # twitter:player:stream should be checked before twitter:player since
3271 # it is expected to contain a raw stream (see
3272 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3273 found = filter_video(re.findall(
3274 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3276 # We look for Open Graph info:
3277 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3278 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3279 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3280 if m_video_type is not None:
3281 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3283 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3285 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3286 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3289 # Look also in Refresh HTTP header
3290 refresh_header = head_response.headers.get('Refresh')
3292 # In python 2 response HTTP headers are bytestrings
3293 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3294 refresh_header = refresh_header.decode('iso-8859-1')
3295 found = re.search(REDIRECT_REGEX, refresh_header)
3297 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3299 self.report_following_redirect(new_url)
3308 # twitter:player is a https URL to iframe player that may or may not
3309 # be supported by youtube-dl thus this is checked the very last (see
3310 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3311 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3312 if embed_url and embed_url != url:
3313 return self.url_result(embed_url)
3316 raise UnsupportedError(url)
3319 for video_url in orderedSet(found):
3320 video_url = unescapeHTML(video_url)
3321 video_url = video_url.replace('\\/', '/')
3322 video_url = compat_urlparse.urljoin(url, video_url)
3323 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3325 # Sometimes, jwplayer extraction will result in a YouTube URL
3326 if YoutubeIE.suitable(video_url):
3327 entries.append(self.url_result(video_url, 'Youtube'))
3330 # here's a fun little line of code for you:
3331 video_id = os.path.splitext(video_id)[0]
3335 'uploader': video_uploader,
3336 'title': video_title,
3337 'age_limit': age_limit,
3340 if RtmpIE.suitable(video_url):
3341 entry_info_dict.update({
3342 '_type': 'url_transparent',
3343 'ie_key': RtmpIE.ie_key(),
3346 entries.append(entry_info_dict)
3349 ext = determine_ext(video_url)
3351 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3353 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3355 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3357 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3359 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3360 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3361 # Just matching .ism/manifest is not enough to be reliably sure
3362 # whether it's actually an ISM manifest or some other streaming
3363 # manifest since there are various streaming URL formats
3364 # possible (see [1]) as well as some other shenanigans like
3365 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3367 # Thus the most reasonable way to solve this is to delegate
3368 # to generic extractor in order to look into the contents of
3369 # the manifest itself.
3370 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3371 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3372 entry_info_dict = self.url_result(
3373 smuggle_url(video_url, {'to_generic': True}),
3376 entry_info_dict['url'] = video_url
3378 if entry_info_dict.get('formats'):
3379 self._sort_formats(entry_info_dict['formats'])
3381 entries.append(entry_info_dict)
3383 if len(entries) == 1:
3386 for num, e in enumerate(entries, start=1):
3387 # 'url' results don't have a title
3388 if e.get('title') is not None:
3389 e['title'] = '%s (%d)' % (e['title'], num)
3391 '_type': 'playlist',