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 .mofosex
import MofosexEmbedIE
64 from .spankwire
import SpankwireIE
65 from .youporn
import YouPornIE
66 from .vimeo
import VimeoIE
67 from .dailymotion
import DailymotionIE
68 from .dailymail
import DailyMailIE
69 from .onionstudios
import OnionStudiosIE
70 from .viewlift
import ViewLiftEmbedIE
71 from .mtv
import MTVServicesEmbeddedIE
72 from .pladform
import PladformIE
73 from .videomore
import VideomoreIE
74 from .webcaster
import WebcasterFeedIE
75 from .googledrive
import GoogleDriveIE
76 from .jwplatform
import JWPlatformIE
77 from .digiteka
import DigitekaIE
78 from .arkena
import ArkenaIE
79 from .instagram
import InstagramIE
80 from .liveleak
import LiveLeakIE
81 from .threeqsdn
import ThreeQSDNIE
82 from .theplatform
import ThePlatformIE
83 from .kaltura
import KalturaIE
84 from .eagleplatform
import EaglePlatformIE
85 from .facebook
import FacebookIE
86 from .soundcloud
import SoundcloudEmbedIE
87 from .tunein
import TuneInBaseIE
88 from .vbox7
import Vbox7IE
89 from .dbtv
import DBTVIE
90 from .piksel
import PikselIE
91 from .videa
import VideaIE
92 from .twentymin
import TwentyMinutenIE
93 from .ustream
import UstreamIE
94 from .videopress
import VideoPressIE
95 from .rutube
import RutubeIE
96 from .limelight
import LimelightBaseIE
97 from .anvato
import AnvatoIE
98 from .washingtonpost
import WashingtonPostIE
99 from .wistia
import WistiaIE
100 from .mediaset
import MediasetIE
101 from .joj
import JojIE
102 from .megaphone
import MegaphoneIE
103 from .vzaar
import VzaarIE
104 from .channel9
import Channel9IE
105 from .vshare
import VShareIE
106 from .mediasite
import MediasiteIE
107 from .springboardplatform
import SpringboardPlatformIE
108 from .yapfiles
import YapFilesIE
109 from .vice
import ViceIE
110 from .xfileshare
import XFileShareIE
111 from .cloudflarestream
import CloudflareStreamIE
112 from .peertube
import PeerTubeIE
113 from .teachable
import TeachableIE
114 from .indavideo
import IndavideoEmbedIE
115 from .apa
import APAIE
116 from .foxnews
import FoxNewsIE
117 from .viqeo
import ViqeoIE
118 from .expressen
import ExpressenIE
119 from .zype
import ZypeIE
120 from .odnoklassniki
import OdnoklassnikiIE
121 from .kinja
import KinjaEmbedIE
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,
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 'description': 'Migrated from OnionStudios',
1498 'thumbnail': r
're:^https?://.*\.jpe?g$',
1499 'uploader': 'clickhole',
1500 'upload_date': '20150527',
1501 'timestamp': 1432744860,
1506 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1508 'id': '74849a00-85a9-11e1-9660-123139220831',
1510 'title': '#whilewewatch',
1513 # AdobeTVVideo embed
1515 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1516 'md5': '43662b577c018ad707a63766462b1e87',
1520 'title': 'New experience with Acrobat DC',
1521 'description': 'New experience with Acrobat DC',
1522 'duration': 248.667,
1525 # BrightcoveInPageEmbed embed
1527 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1529 'id': '4238694884001',
1531 'title': 'Tabletop: Dread, Last Thoughts',
1532 'description': 'Tabletop: Dread, Last Thoughts',
1536 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1537 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1539 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1541 'id': '4785848093001',
1543 'title': 'The Cardinal Pell Interview',
1544 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1545 'uploader': 'GlobeCast Australia - GlobeStream',
1546 'uploader_id': '2733773828001',
1547 'upload_date': '20160304',
1548 'timestamp': 1457083087,
1552 'skip_download': True,
1556 # Brightcove embed with whitespace around attribute names
1557 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1559 'id': '3167554373001',
1561 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1562 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1563 'uploader_id': '1079349493',
1564 'upload_date': '20140207',
1565 'timestamp': 1391810548,
1568 'skip_download': True,
1571 # Another form of arte.tv embed
1573 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1574 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1576 'id': '030273-562_PLUS7-F',
1578 'title': 'ARTE Reportage - Nulle part, en France',
1579 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1580 'upload_date': '20160409',
1585 'url': 'http://www.wykop.pl/link/3088787/',
1586 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1588 'id': '874_1459135191',
1590 'title': 'Man shows poor quality of new apartment building',
1591 'description': 'The wall is like a sand pile.',
1592 'uploader': 'Lake8737',
1594 'add_ie': [LiveLeakIE
.ie_key()],
1596 # Another LiveLeak embed pattern (#13336)
1598 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1600 'id': '2eb_1496309988',
1602 'title': 'Thief robs place where everyone was armed',
1603 'description': 'md5:694d73ee79e535953cf2488562288eee',
1604 'uploader': 'brazilwtf',
1606 'add_ie': [LiveLeakIE
.ie_key()],
1608 # Duplicated embedded video URLs
1610 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1612 'id': '149298443_480_16c25b74_2',
1614 'title': 'vs. Blue Orange Spring Game',
1615 'uploader': 'www.hudl.com',
1618 # twitter:player:stream embed
1620 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1624 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1625 'uploader': 'www.rtl.be',
1629 'skip_download': True,
1632 # twitter:player embed
1634 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1635 'md5': 'a3e0df96369831de324f0778e126653c',
1637 'id': '4909620399001',
1639 'title': 'What Do Black Holes Sound Like?',
1640 'description': 'what do black holes sound like',
1641 'upload_date': '20160524',
1642 'uploader_id': '29913724001',
1643 'timestamp': 1464107587,
1644 'uploader': 'TheAtlantic',
1646 'add_ie': ['BrightcoveLegacy'],
1648 # Facebook <iframe> embed
1650 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1651 'md5': 'fbcde74f534176ecb015849146dd3aee',
1653 'id': '599637780109885',
1655 'title': 'Facebook video #599637780109885',
1658 # Facebook <iframe> embed, plugin video
1660 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1662 'id': '1754168231264132',
1664 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1665 'uploader': 'Tariq Ramadan (official)',
1666 'timestamp': 1496758379,
1667 'upload_date': '20170606',
1670 'skip_download': True,
1673 # Facebook API embed
1675 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1676 'md5': 'a47372ee61b39a7b90287094d447d94e',
1678 'id': '10153467542406923',
1680 'title': 'Facebook video #10153467542406923',
1683 # Wordpress "YouTube Video Importer" plugin
1685 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1686 'md5': 'd16797741b560b485194eddda8121b48',
1688 'id': 'HNTXWDXV9Is',
1690 'title': 'Blue Devils Drumline Stanford lot 2016',
1691 'upload_date': '20160627',
1692 'uploader_id': 'GENOCIDE8GENERAL10',
1693 'uploader': 'cylus cyrus',
1697 # video stored on custom kaltura server
1698 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1699 'md5': '537617d06e64dfed891fa1593c4b30cc',
1703 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1704 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1705 'uploader_id': 'videos.expansion@el-mundo.net',
1706 'upload_date': '20150429',
1707 'timestamp': 1430303472,
1709 'add_ie': ['Kaltura'],
1712 # Non-standard Vimeo embed
1713 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1714 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1718 'title': 'Understanding the web - Teaser',
1719 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1720 'upload_date': '20151214',
1721 'uploader': 'OpenClassrooms',
1722 'uploader_id': 'openclassrooms',
1724 'add_ie': ['Vimeo'],
1727 # generic vimeo embed that requires original URL passed as Referer
1728 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1729 'only_matching': True,
1732 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1733 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1735 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1737 'title': 'Big Buck Bunny',
1738 'description': 'Royalty free test video',
1739 'timestamp': 1432816365,
1740 'upload_date': '20150528',
1744 'skip_download': True,
1746 'add_ie': [ArkenaIE
.ie_key()],
1749 '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/',
1753 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1756 'skip_download': True,
1758 'add_ie': [Vbox7IE
.ie_key()],
1762 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1765 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1767 'playlist_mincount': 3,
1771 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1773 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1774 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1776 'playlist_mincount': 2,
1780 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1784 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1785 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1788 'skip_download': True,
1790 'add_ie': [TwentyMinutenIE
.ie_key()],
1794 'url': 'https://en.support.wordpress.com/videopress/',
1798 'title': 'IMG_5786',
1799 'timestamp': 1435711927,
1800 'upload_date': '20150701',
1803 'skip_download': True,
1805 'add_ie': [VideoPressIE
.ie_key()],
1809 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1811 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1813 'title': 'Магаззино: Казань 2',
1814 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1815 'uploader': 'Магаззино',
1816 'upload_date': '20170228',
1817 'uploader_id': '996642',
1820 'skip_download': True,
1822 'add_ie': [RutubeIE
.ie_key()],
1825 # ThePlatform embedded with whitespaces in URLs
1826 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1827 'only_matching': True,
1830 # Senate ISVP iframe https
1831 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1832 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1834 'id': 'govtaff020316',
1836 'title': 'Integrated Senate Video Player',
1838 'add_ie': [SenateISVPIE
.ie_key()],
1841 # Limelight embeds (1 channel embed + 4 media embeds)
1842 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1844 'id': 'FacilitatorTraining2017',
1845 'title': 'Facilitator Training 2017',
1847 'playlist_mincount': 5,
1850 # Limelight embed (LimelightPlayerUtil.embed)
1851 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1853 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1855 'title': '07448641',
1856 'timestamp': 1499890639,
1857 'upload_date': '20170712',
1860 'skip_download': True,
1862 'add_ie': ['LimelightMedia'],
1865 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1867 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1868 'title': 'Standoff with Walnut Creek murder suspect ends',
1869 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1871 'playlist_mincount': 4,
1874 # WashingtonPost embed
1875 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1877 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1879 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1880 '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.',
1881 'timestamp': 1455216756,
1882 'uploader': 'The Washington Post',
1883 'upload_date': '20160211',
1885 'add_ie': [WashingtonPostIE
.ie_key()],
1889 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1893 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1896 'skip_download': True,
1898 'add_ie': [MediasetIE
.ie_key()],
1902 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1904 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1905 'title': 'Slovenskom sa prehnala vlna silných búrok',
1907 'playlist_mincount': 5,
1908 'add_ie': [JojIE
.ie_key()],
1911 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1912 'url': 'https://tvrain.ru/amp/418921/',
1913 'md5': 'cc00413936695987e8de148b67d14f1d',
1917 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1922 'url': 'http://help.vzaar.com/article/165-embedding-video',
1923 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1927 'title': 'Building A Business Online: Principal Chairs Q & A',
1931 # multiple HTML5 videos on one page
1932 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1934 'id': 'keyscenarios',
1935 'title': 'Rescue Kit 14 Free Edition - Getting started',
1937 'playlist_count': 4,
1941 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1942 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1945 'title': 'vl14062007715967',
1950 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1951 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1953 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1955 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1956 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1957 'timestamp': 1474354800,
1958 'upload_date': '20160920',
1962 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1966 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1967 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1968 'timestamp': 1516100691,
1969 'upload_date': '20180116',
1972 'skip_download': True,
1974 'add_ie': [SpringboardPlatformIE
.ie_key()],
1977 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1979 'id': 'uPDB5I9wfp8',
1981 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1982 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1983 'upload_date': '20160219',
1984 'uploader': 'Pocoyo - Português (BR)',
1985 'uploader_id': 'PocoyoBrazil',
1987 'add_ie': [YoutubeIE
.ie_key()],
1989 'skip_download': True,
1993 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1995 'id': 'vMDE4NzI1Mjgt690b',
1999 'add_ie': [YapFilesIE
.ie_key()],
2001 'skip_download': True,
2005 # CloudflareStream embed
2006 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2008 'id': '31c9291ab41fac05471db4e73aa11717',
2010 'title': '31c9291ab41fac05471db4e73aa11717',
2012 'add_ie': [CloudflareStreamIE
.ie_key()],
2014 'skip_download': True,
2019 'url': 'https://joinpeertube.org/fr/home/',
2022 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2024 'playlist_count': 2,
2028 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2032 'title': 'Így kell otthon hamburgert sütni',
2033 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2034 'timestamp': 1426330212,
2035 'upload_date': '20150314',
2036 'uploader': 'StreetKitchen',
2037 'uploader_id': '546363',
2039 'add_ie': [IndavideoEmbedIE
.ie_key()],
2041 'skip_download': True,
2045 # APA embed via JWPlatform embed
2046 'url': 'http://www.vol.at/blue-man-group/5593454',
2050 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2051 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2052 'thumbnail': r
're:^https?://.*\.jpg$',
2054 'timestamp': 1519211149,
2055 'upload_date': '20180221',
2058 'skip_download': True,
2062 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2063 'md5': 'b68d276de422ab07ee1d49388103f457',
2066 'title': 'Lock up and get excited',
2069 'skip': 'TODO: fix nested playlists processing in tests',
2073 'url': 'https://viqeo.tv/',
2076 'title': 'All-new video platform',
2078 'playlist_count': 6,
2081 # Squarespace video embed, 2019-08-28
2082 'url': 'http://ootboxford.com',
2084 'id': 'Tc7b_JGdZfw',
2085 'title': 'Out of the Blue, at Childish Things 10',
2087 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
2088 'uploader_id': 'helendouglashouse',
2089 'uploader': 'Helen & Douglas House',
2090 'upload_date': '20140328',
2093 'skip_download': True,
2098 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2100 'id': '5b400b834b32992a310622b9',
2102 'title': 'Smoky Barbecue Favorites',
2103 'thumbnail': r
're:^https?://.*\.jpe?g',
2104 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
2105 'upload_date': '20170909',
2106 'timestamp': 1504915200,
2108 'add_ie': [ZypeIE
.ie_key()],
2110 'skip_download': True,
2115 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2119 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2120 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2121 'thumbnail': r
're:^https?://.*\.jpg$',
2124 'skip_download': True,
2126 'expected_warnings': ['Failed to download MPD manifest'],
2129 # DailyMotion embed with DM.player
2130 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
2132 'id': 'k6aKkGHd9FJs4mtJN39',
2134 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
2135 'description': 'This video is private.',
2136 'uploader_id': 'x1jf30l',
2137 'uploader': 'beIN SPORTS USA',
2138 'upload_date': '20190528',
2139 'timestamp': 1559062971,
2142 'skip_download': True,
2146 # # TODO: find another test
2147 # # http://schema.org/VideoObject
2148 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2149 # 'md5': '888dcf08b7ea671381f00fab74692755',
2151 # 'id': 'nyvTSJMKId',
2153 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2154 # 'description': '#love for cats.',
2155 # 'timestamp': 1461244995,
2156 # 'upload_date': '20160421',
2159 # 'force_generic_extractor': True,
2164 def report_following_redirect(self
, new_url
):
2165 """Report information extraction."""
2166 self
._downloader
.to_screen('[redirect] Following redirect to %s' % new_url
)
2168 def _extract_rss(self
, url
, video_id
, doc
):
2169 playlist_title
= doc
.find('./channel/title').text
2170 playlist_desc_el
= doc
.find('./channel/description')
2171 playlist_desc
= None if playlist_desc_el
is None else playlist_desc_el
.text
2174 for it
in doc
.findall('./channel/item'):
2176 enclosure_nodes
= it
.findall('./enclosure')
2177 for e
in enclosure_nodes
:
2178 next_url
= e
.attrib
.get('url')
2183 next_url
= xpath_text(it
, 'link', fatal
=False)
2189 '_type': 'url_transparent',
2191 'title': it
.find('title').text
,
2195 '_type': 'playlist',
2197 'title': playlist_title
,
2198 'description': playlist_desc
,
2202 def _extract_camtasia(self
, url
, video_id
, webpage
):
2203 """ Returns None if no camtasia video can be found. """
2205 camtasia_cfg
= self
._search
_regex
(
2206 r
'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2207 webpage
, 'camtasia configuration file', default
=None)
2208 if camtasia_cfg
is None:
2211 title
= self
._html
_search
_meta
('DC.title', webpage
, fatal
=True)
2213 camtasia_url
= compat_urlparse
.urljoin(url
, camtasia_cfg
)
2214 camtasia_cfg
= self
._download
_xml
(
2215 camtasia_url
, video_id
,
2216 note
='Downloading camtasia configuration',
2217 errnote
='Failed to download camtasia configuration')
2218 fileset_node
= camtasia_cfg
.find('./playlist/array/fileset')
2221 for n
in fileset_node
.getchildren():
2222 url_n
= n
.find('./uri')
2227 'id': os
.path
.splitext(url_n
.text
.rpartition('/')[2])[0],
2228 'title': '%s - %s' % (title
, n
.tag
),
2229 'url': compat_urlparse
.urljoin(url
, url_n
.text
),
2230 'duration': float_or_none(n
.find('./duration').text
),
2234 '_type': 'playlist',
2239 def _real_extract(self
, url
):
2240 if url
.startswith('//'):
2241 return self
.url_result(self
.http_scheme() + url
)
2243 parsed_url
= compat_urlparse
.urlparse(url
)
2244 if not parsed_url
.scheme
:
2245 default_search
= self
._downloader
.params
.get('default_search')
2246 if default_search
is None:
2247 default_search
= 'fixup_error'
2249 if default_search
in ('auto', 'auto_warning', 'fixup_error'):
2250 if re
.match(r
'^[^\s/]+\.[^\s/]+/', url
):
2251 self
._downloader
.report_warning('The url doesn\'t specify the protocol, trying with http')
2252 return self
.url_result('http://' + url
)
2253 elif default_search
!= 'fixup_error':
2254 if default_search
== 'auto_warning':
2255 if re
.match(r
'^(?:url|URL)$', url
):
2256 raise ExtractorError(
2257 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url
,
2260 self
._downloader
.report_warning(
2261 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url
)
2262 return self
.url_result('ytsearch:' + url
)
2264 if default_search
in ('error', 'fixup_error'):
2265 raise ExtractorError(
2266 '%r is not a valid URL. '
2267 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2268 % (url
, url
), expected
=True)
2270 if ':' not in default_search
:
2271 default_search
+= ':'
2272 return self
.url_result(default_search
+ url
)
2274 url
, smuggled_data
= unsmuggle_url(url
)
2275 force_videoid
= None
2276 is_intentional
= smuggled_data
and smuggled_data
.get('to_generic')
2277 if smuggled_data
and 'force_videoid' in smuggled_data
:
2278 force_videoid
= smuggled_data
['force_videoid']
2279 video_id
= force_videoid
2281 video_id
= self
._generic
_id
(url
)
2283 self
.to_screen('%s: Requesting header' % video_id
)
2285 head_req
= HEADRequest(url
)
2286 head_response
= self
._request
_webpage
(
2288 note
=False, errnote
='Could not send HEAD request to %s' % url
,
2291 if head_response
is not False:
2292 # Check for redirect
2293 new_url
= head_response
.geturl()
2295 self
.report_following_redirect(new_url
)
2297 new_url
= smuggle_url(
2298 new_url
, {'force_videoid': force_videoid}
)
2299 return self
.url_result(new_url
)
2301 full_response
= None
2302 if head_response
is False:
2303 request
= sanitized_Request(url
)
2304 request
.add_header('Accept-Encoding', '*')
2305 full_response
= self
._request
_webpage
(request
, video_id
)
2306 head_response
= full_response
2310 'title': self
._generic
_title
(url
),
2311 'upload_date': unified_strdate(head_response
.headers
.get('Last-Modified'))
2314 # Check for direct link to a video
2315 content_type
= head_response
.headers
.get('Content-Type', '').lower()
2316 m
= re
.match(r
'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type
)
2318 format_id
= compat_str(m
.group('format_id'))
2319 if format_id
.endswith('mpegurl'):
2320 formats
= self
._extract
_m
3u8_formats
(url
, video_id
, 'mp4')
2321 elif format_id
== 'f4m':
2322 formats
= self
._extract
_f
4m
_formats
(url
, video_id
)
2325 'format_id': format_id
,
2327 'vcodec': 'none' if m
.group('type') == 'audio' else None
2329 info_dict
['direct'] = True
2330 self
._sort
_formats
(formats
)
2331 info_dict
['formats'] = formats
2334 if not self
._downloader
.params
.get('test', False) and not is_intentional
:
2335 force
= self
._downloader
.params
.get('force_generic_extractor', False)
2336 self
._downloader
.report_warning(
2337 '%s on generic information extractor.' % ('Forcing' if force
else 'Falling back'))
2339 if not full_response
:
2340 request
= sanitized_Request(url
)
2341 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2342 # making it impossible to download only chunk of the file (yet we need only 512kB to
2343 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2344 # that will always result in downloading the whole file that is not desirable.
2345 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2346 # to accept raw bytes and being able to download only a chunk.
2347 # It may probably better to solve this by checking Content-Type for application/octet-stream
2348 # after HEAD request finishes, but not sure if we can rely on this.
2349 request
.add_header('Accept-Encoding', '*')
2350 full_response
= self
._request
_webpage
(request
, video_id
)
2352 first_bytes
= full_response
.read(512)
2354 # Is it an M3U playlist?
2355 if first_bytes
.startswith(b
'#EXTM3U'):
2356 info_dict
['formats'] = self
._extract
_m
3u8_formats
(url
, video_id
, 'mp4')
2357 self
._sort
_formats
(info_dict
['formats'])
2360 # Maybe it's a direct link to a video?
2361 # Be careful not to download the whole thing!
2362 if not is_html(first_bytes
):
2363 self
._downloader
.report_warning(
2364 'URL could be a direct video link, returning it as such.')
2371 webpage
= self
._webpage
_read
_content
(
2372 full_response
, url
, video_id
, prefix
=first_bytes
)
2374 self
.report_extraction(video_id
)
2376 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2378 doc
= compat_etree_fromstring(webpage
.encode('utf-8'))
2379 if doc
.tag
== 'rss':
2380 return self
._extract
_rss
(url
, video_id
, doc
)
2381 elif doc
.tag
== 'SmoothStreamingMedia':
2382 info_dict
['formats'] = self
._parse
_ism
_formats
(doc
, url
)
2383 self
._sort
_formats
(info_dict
['formats'])
2385 elif re
.match(r
'^(?:{[^}]+})?smil$', doc
.tag
):
2386 smil
= self
._parse
_smil
(doc
, url
, video_id
)
2387 self
._sort
_formats
(smil
['formats'])
2389 elif doc
.tag
== '{http://xspf.org/ns/0/}playlist':
2390 return self
.playlist_result(
2392 doc
, video_id
, xspf_url
=url
,
2393 xspf_base_url
=full_response
.geturl()),
2395 elif re
.match(r
'(?i)^(?:{[^}]+})?MPD$', doc
.tag
):
2396 info_dict
['formats'] = self
._parse
_mpd
_formats
(
2398 mpd_base_url
=full_response
.geturl().rpartition('/')[0],
2400 self
._sort
_formats
(info_dict
['formats'])
2402 elif re
.match(r
'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc
.tag
):
2403 info_dict
['formats'] = self
._parse
_f
4m
_formats
(doc
, url
, video_id
)
2404 self
._sort
_formats
(info_dict
['formats'])
2406 except compat_xml_parse_error
:
2409 # Is it a Camtasia project?
2410 camtasia_res
= self
._extract
_camtasia
(url
, video_id
, webpage
)
2411 if camtasia_res
is not None:
2414 # Sometimes embedded video player is hidden behind percent encoding
2415 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
2416 # Unescaping the whole page allows to handle those cases in a generic way
2417 webpage
= compat_urllib_parse_unquote(webpage
)
2419 # Unescape squarespace embeds to be detected by generic extractor,
2420 # see https://github.com/ytdl-org/youtube-dl/issues/21294
2422 r
'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
2423 lambda x
: unescapeHTML(x
.group(0)), webpage
)
2425 # it's tempting to parse this further, but you would
2426 # have to take into account all the variations like
2427 # Video Title - Site Name
2428 # Site Name | Video Title
2429 # Video Title - Tagline | Site Name
2430 # and so on and so forth; it's just not practical
2431 video_title
= self
._og
_search
_title
(
2432 webpage
, default
=None) or self
._html
_search
_regex
(
2433 r
'(?s)<title>(.*?)</title>', webpage
, 'video title',
2436 # Try to detect age limit automatically
2437 age_limit
= self
._rta
_search
(webpage
)
2438 # And then there are the jokers who advertise that they use RTA,
2439 # but actually don't.
2440 AGE_LIMIT_MARKERS
= [
2441 r
'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2443 if any(re
.search(marker
, webpage
) for marker
in AGE_LIMIT_MARKERS
):
2446 # video uploader is domain name
2447 video_uploader
= self
._search
_regex
(
2448 r
'^(?:https?://)?([^/]*)/.*', url
, 'video uploader')
2450 video_description
= self
._og
_search
_description
(webpage
, default
=None)
2451 video_thumbnail
= self
._og
_search
_thumbnail
(webpage
, default
=None)
2454 'title': video_title
,
2455 'description': video_description
,
2456 'thumbnail': video_thumbnail
,
2457 'age_limit': age_limit
,
2460 # Look for Brightcove Legacy Studio embeds
2461 bc_urls
= BrightcoveLegacyIE
._extract
_brightcove
_urls
(webpage
)
2465 'url': smuggle_url(bc_url
, {'Referer': url}
),
2466 'ie_key': 'BrightcoveLegacy'
2467 } for bc_url
in bc_urls
]
2470 '_type': 'playlist',
2471 'title': video_title
,
2476 # Look for Brightcove New Studio embeds
2477 bc_urls
= BrightcoveNewIE
._extract
_urls
(self
, webpage
)
2479 return self
.playlist_from_matches(
2480 bc_urls
, video_id
, video_title
,
2481 getter
=lambda x
: smuggle_url(x
, {'referrer': url}
),
2484 # Look for Nexx embeds
2485 nexx_urls
= NexxIE
._extract
_urls
(webpage
)
2487 return self
.playlist_from_matches(nexx_urls
, video_id
, video_title
, ie
=NexxIE
.ie_key())
2489 # Look for Nexx iFrame embeds
2490 nexx_embed_urls
= NexxEmbedIE
._extract
_urls
(webpage
)
2492 return self
.playlist_from_matches(nexx_embed_urls
, video_id
, video_title
, ie
=NexxEmbedIE
.ie_key())
2494 # Look for ThePlatform embeds
2495 tp_urls
= ThePlatformIE
._extract
_urls
(webpage
)
2497 return self
.playlist_from_matches(tp_urls
, video_id
, video_title
, ie
='ThePlatform')
2499 # Look for embedded rtl.nl player
2500 matches
= re
.findall(
2501 r
'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2504 return self
.playlist_from_matches(matches
, video_id
, video_title
, ie
='RtlNl')
2506 vimeo_urls
= VimeoIE
._extract
_urls
(url
, webpage
)
2508 return self
.playlist_from_matches(vimeo_urls
, video_id
, video_title
, ie
=VimeoIE
.ie_key())
2510 vid_me_embed_url
= self
._search
_regex
(
2511 r
'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2512 webpage, 'vid.me embed', default=None)
2513 if vid_me_embed_url is not None:
2514 return self.url_result(vid_me_embed_url, 'Vidme')
2516 # Look for YouTube embeds
2517 youtube_urls = YoutubeIE._extract_urls(webpage)
2519 return self.playlist_from_matches(
2520 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2522 matches = DailymotionIE._extract_urls(webpage)
2524 return self.playlist_from_matches(matches, video_id, video_title)
2526 # Look for embedded Dailymotion playlist player (#3822)
2528 r'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:www\
.)?dailymotion\
.[a
-z
]{2,3}
/widget
/jukebox
\?.+?
)\
1', webpage)
2530 playlists = re.findall(
2531 r'list\
[\
]=/playlist
/([^
/]+)/', unescapeHTML(m.group('url
')))
2533 return self.playlist_from_matches(
2534 playlists, video_id, video_title, lambda p: '//dailymotion
.com
/playlist
/%s' % p)
2536 # Look for DailyMail embeds
2537 dailymail_urls = DailyMailIE._extract_urls(webpage)
2539 return self.playlist_from_matches(
2540 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2542 # Look for Teachable embeds, must be before Wistia
2543 teachable_url = TeachableIE._extract_url(webpage, url)
2545 return self.url_result(teachable_url)
2547 # Look for embedded Wistia player
2548 wistia_urls = WistiaIE._extract_urls(webpage)
2550 playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
2551 for entry in playlist['entries
']:
2553 '_type
': 'url_transparent
',
2554 'uploader
': video_uploader,
2558 # Look for SVT player
2559 svt_url = SVTIE._extract_url(webpage)
2561 return self.url_result(svt_url, 'SVT
')
2563 # Look for Bandcamp pages with custom domain
2564 mobj = re.search(r'<meta
property="og:url"[^
>]*?content
="(.*?bandcamp\.com.*?)"', webpage)
2565 if mobj is not None:
2566 burl = unescapeHTML(mobj.group(1))
2567 # Don't
set the extractor because it can be a track url
or an album
2568 return self
.url_result(burl
)
2570 # Look for embedded Vevo player
2572 r
'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:cache\
.)?vevo\
.com
/.+?
)\
1', webpage)
2573 if mobj is not None:
2574 return self.url_result(mobj.group('url
'))
2576 # Look for embedded Viddler player
2578 r'<(?
:iframe
[^
>]+?src|param
[^
>]+?value
)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2580 if mobj is not None:
2581 return self.url_result(mobj.group('url'))
2583 # Look for NYTimes player
2585 r'<iframe[^>]+src=(["\'])(?P
<url
>(?
:https?
:)?
//graphics8\
.nytimes\
.com
/bcvideo
/[^
/]+/iframe
/embed\
.html
.+?
)\
1>',
2587 if mobj is not None:
2588 return self.url_result(mobj.group('url
'))
2590 # Look for Libsyn player
2592 r'<iframe
[^
>]+src
=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2593 if mobj is not None:
2594 return self.url_result(mobj.group('url'))
2596 # Look for Ooyala videos
2597 mobj = (re.search(r'player\.ooyala\.com/[^"?
]+[?
#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
2598 or re
.search(r
'OO\.Player\.create\([\'"].*?[\'"],\s
*[\'"](?P<ec>.{32})[\'"]', webpage)
2599 or re.search(r'OO\
.Player\
.create\
.apply\
(\s
*OO\
.Player\s
*,\s
*op\
(\s
*\
[\s
*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P
<ec
>.{32}
)[\'"]', webpage)
2600 or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P
<ec
>.{32}
)[\'"]\)', webpage)
2601 or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P
<ec
>.{32}
)[\'"]', webpage))
2602 if mobj is not None:
2603 embed_token = self._search_regex(
2604 r'embedToken[\'"]?\s
*:\s
*[\'"]([^\'"]+)',
2605 webpage, 'ooyala embed token
', default=None)
2606 return OoyalaIE._build_url_result(smuggle_url(
2609 'embed_token
': embed_token,
2612 # Look for multiple Ooyala embeds on SBN network websites
2613 mobj = re.search(r'SBN\
.VideoLinkset\
.entryGroup\
((\
[.*?\
])', webpage)
2614 if mobj is not None:
2615 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2617 return self.playlist_from_matches(
2618 embeds, video_id, video_title,
2619 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id
'], {'domain': url})), ie='Ooyala
')
2621 # Look for Aparat videos
2622 mobj = re.search(r'<iframe
.*?src
="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2623 if mobj is not None:
2624 return self.url_result(mobj.group(1), 'Aparat')
2626 # Look for MPORA videos
2627 mobj = re.search(r'<iframe .*?src="(http
://mpora\
.(?
:com|de
)/videos
/[^
"]+)"', webpage)
2628 if mobj is not None:
2629 return self.url_result(mobj.group(1), 'Mpora
')
2631 # Look for embedded Facebook player
2632 facebook_urls = FacebookIE._extract_urls(webpage)
2634 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2636 # Look for embedded VK player
2637 mobj = re.search(r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2638 if mobj is not None:
2639 return self.url_result(mobj.group('url'), 'VK')
2641 # Look for embedded Odnoklassniki player
2642 odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
2643 if odnoklassniki_url:
2644 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
2646 # Look for embedded ivi player
2647 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P
<url
>https?
://(?
:www\
.)?ivi\
.ru
/video
/player
.+?
)\
1', webpage)
2648 if mobj is not None:
2649 return self.url_result(mobj.group('url
'), 'Ivi
')
2651 # Look for embedded Huffington Post player
2653 r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2654 if mobj is not None:
2655 return self.url_result(mobj.group('url'), 'HuffPost')
2658 mobj = re.search(r'class=["\']embedly
-card
["\'][^>]href=["\'](?P
<url
>[^
"\']+)', webpage)
2659 if mobj is not None:
2660 return self.url_result(mobj.group('url'))
2661 mobj = re.search(r'class=["\']embedly
-embed
["\'][^>]src=["\'][^
"\']*url=(?P<url>[^&]+)', webpage)
2662 if mobj is not None:
2663 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2665 # Look for funnyordie embed
2666 matches = re.findall(r'<iframe[^>]+?src="(https?
://(?
:www\
.)?funnyordie\
.com
/embed
/[^
"]+)"', webpage)
2668 return self.playlist_from_matches(
2669 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie
')
2671 # Look for BBC iPlayer embed
2672 matches = re.findall(r'setPlaylist\
("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\
)', webpage)
2674 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk
')
2676 # Look for embedded RUTV player
2677 rutv_url = RUTVIE._extract_url(webpage)
2679 return self.url_result(rutv_url, 'RUTV
')
2681 # Look for embedded TVC player
2682 tvc_url = TVCIE._extract_url(webpage)
2684 return self.url_result(tvc_url, 'TVC
')
2686 # Look for embedded SportBox player
2687 sportbox_urls = SportBoxIE._extract_urls(webpage)
2689 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
2691 # Look for embedded XHamster player
2692 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2694 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed
')
2696 # Look for embedded TNAFlixNetwork player
2697 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2699 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2701 # Look for embedded PornHub player
2702 pornhub_urls = PornHubIE._extract_urls(webpage)
2704 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2706 # Look for embedded DrTuber player
2707 drtuber_urls = DrTuberIE._extract_urls(webpage)
2709 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2711 # Look for embedded RedTube player
2712 redtube_urls = RedTubeIE._extract_urls(webpage)
2714 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2716 # Look for embedded Tube8 player
2717 tube8_urls = Tube8IE._extract_urls(webpage)
2719 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2721 # Look for embedded Mofosex player
2722 mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
2724 return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
2726 # Look for embedded Spankwire player
2727 spankwire_urls = SpankwireIE._extract_urls(webpage)
2729 return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
2731 # Look for embedded YouPorn player
2732 youporn_urls = YouPornIE._extract_urls(webpage)
2734 return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
2736 # Look for embedded Tvigle player
2738 r'<iframe
[^
>]+?src
=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2739 if mobj is not None:
2740 return self.url_result(mobj.group('url'), 'Tvigle')
2742 # Look for embedded TED player
2744 r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://embed(?
:-ssl
)?\
.ted\
.com
/.+?
)\
1', webpage)
2745 if mobj is not None:
2746 return self.url_result(mobj.group('url
'), 'TED
')
2748 # Look for embedded Ustream videos
2749 ustream_url = UstreamIE._extract_url(webpage)
2751 return self.url_result(ustream_url, UstreamIE.ie_key())
2753 # Look for embedded arte.tv player
2755 r'<(?
:script|iframe
) [^
>]*?src
="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2757 if mobj is not None:
2758 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2760 # Look for embedded francetv player
2762 r'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
://)?embed\
.francetv\
.fr
/\?ue
=.+?
)\
1',
2764 if mobj is not None:
2765 return self.url_result(mobj.group('url
'))
2767 # Look for embedded smotri.com player
2768 smotri_url = SmotriIE._extract_url(webpage)
2770 return self.url_result(smotri_url, 'Smotri
')
2772 # Look for embedded Myvi.ru player
2773 myvi_url = MyviIE._extract_url(webpage)
2775 return self.url_result(myvi_url)
2777 # Look for embedded soundcloud player
2778 soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
2780 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
2782 # Look for tunein player
2783 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2785 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2787 # Look for embedded mtvservices player
2788 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2790 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded
')
2792 # Look for embedded yahoo player
2794 r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2796 if mobj is not None:
2797 return self.url_result(mobj.group('url'), 'Yahoo')
2799 # Look for embedded sbs.com.au player
2803 <meta\s+property="og
:video
"\s+content=|
2806 (["\'])(?P
<url
>https?
://(?
:www\
.)?sbs\
.com\
.au
/ondemand
/video
/.+?
)\
1''',
2808 if mobj is not None:
2809 return self.url_result(mobj.group('url'), 'SBS')
2811 # Look for embedded Cinchcast player
2813 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2815 if mobj is not None:
2816 return self.url_result(mobj.group('url'), 'Cinchcast')
2819 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2823 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2825 if mobj is not None:
2826 return self.url_result(mobj.group('url'), 'MLB')
2829 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2831 if mobj is not None:
2832 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2835 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2837 if mobj is not None:
2838 return self.url_result(mobj.group('url'), 'Livestream')
2840 # Look for Zapiks embed
2842 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2843 if mobj is not None:
2844 return self.url_result(mobj.group('url'), 'Zapiks')
2846 # Look for Kaltura embeds
2847 kaltura_url = KalturaIE._extract_url(webpage)
2849 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2851 # Look for EaglePlatform embeds
2852 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2853 if eagleplatform_url:
2854 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2856 # Look for ClipYou (uses EaglePlatform) embeds
2858 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2859 if mobj is not None:
2860 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2862 # Look for Pladform embeds
2863 pladform_url = PladformIE._extract_url(webpage)
2865 return self.url_result(pladform_url)
2867 # Look for Videomore embeds
2868 videomore_url = VideomoreIE._extract_url(webpage)
2870 return self.url_result(videomore_url)
2872 # Look for Webcaster embeds
2873 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2875 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2877 # Look for Playwire embeds
2879 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2880 if mobj is not None:
2881 return self.url_result(mobj.group('url'))
2883 # Look for 5min embeds
2885 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2886 if mobj is not None:
2887 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2889 # Look for Crooks and Liars embeds
2891 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2892 if mobj is not None:
2893 return self.url_result(mobj.group('url'))
2895 # Look for NBC Sports VPlayer embeds
2896 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2898 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2900 # Look for NBC News embeds
2901 nbc_news_embed_url = re.search(
2902 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2903 if nbc_news_embed_url:
2904 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2906 # Look for Google Drive embeds
2907 google_drive_url = GoogleDriveIE._extract_url(webpage)
2908 if google_drive_url:
2909 return self.url_result(google_drive_url, 'GoogleDrive')
2911 # Look for UDN embeds
2913 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2914 if mobj is not None:
2915 return self.url_result(
2916 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2918 # Look for Senate ISVP iframe
2919 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2921 return self.url_result(senate_isvp_url, 'SenateISVP')
2923 # Look for Kinja embeds
2924 kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
2925 if kinja_embed_urls:
2926 return self.playlist_from_matches(
2927 kinja_embed_urls, video_id, video_title)
2929 # Look for OnionStudios embeds
2930 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2931 if onionstudios_url:
2932 return self.url_result(onionstudios_url)
2934 # Look for ViewLift embeds
2935 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2937 return self.url_result(viewlift_url)
2939 # Look for JWPlatform embeds
2940 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2942 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2944 # Look for Digiteka embeds
2945 digiteka_url = DigitekaIE._extract_url(webpage)
2947 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2949 # Look for Arkena embeds
2950 arkena_url = ArkenaIE._extract_url(webpage)
2952 return self.url_result(arkena_url, ArkenaIE.ie_key())
2954 # Look for Piksel embeds
2955 piksel_url = PikselIE._extract_url(webpage)
2957 return self.url_result(piksel_url, PikselIE.ie_key())
2959 # Look for Limelight embeds
2960 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2962 return self.playlist_result(
2963 limelight_urls, video_id, video_title, video_description)
2965 # Look for Anvato embeds
2966 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2968 return self.playlist_result(
2969 anvato_urls, video_id, video_title, video_description)
2971 # Look for AdobeTVVideo embeds
2973 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2975 if mobj is not None:
2976 return self.url_result(
2977 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2980 # Look for Vine embeds
2982 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2984 if mobj is not None:
2985 return self.url_result(
2986 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2988 # Look for VODPlatform embeds
2990 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
2992 if mobj is not None:
2993 return self.url_result(
2994 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2996 # Look for Mangomolo embeds
2998 r'''(?x
)<iframe
[^
>]+src
=(["\'])(?P<url>(?:https?:)?//
3000 admin\.mangomolo\.com/analytics/index\.php/customers/embed|
3001 player\.mangomolo\.com/v1
3004 video\?.*?\bid=(?P<video_id>\d+)|
3005 (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
3006 ).+?)\1''', webpage)
3007 if mobj is not None:
3009 '_type': 'url_transparent',
3010 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
3011 'title': video_title,
3012 'description': video_description,
3013 'thumbnail': video_thumbnail,
3014 'uploader': video_uploader,
3016 video_id = mobj.group('video_id')
3019 'ie_key': 'MangomoloVideo',
3024 'ie_key': 'MangomoloLive',
3025 'id': mobj.group('channel_id'),
3029 # Look for Instagram embeds
3030 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
3031 if instagram_embed_url is not None:
3032 return self.url_result(
3033 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
3035 # Look for LiveLeak embeds
3036 liveleak_urls = LiveLeakIE._extract_urls(webpage)
3038 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
3040 # Look for 3Q SDN embeds
3041 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
3044 '_type': 'url_transparent',
3045 'ie_key': ThreeQSDNIE.ie_key(),
3046 'url': self._proto_relative_url(threeqsdn_url),
3047 'title': video_title,
3048 'description': video_description,
3049 'thumbnail': video_thumbnail,
3050 'uploader': video_uploader,
3053 # Look for VBOX7 embeds
3054 vbox7_url = Vbox7IE._extract_url(webpage)
3056 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3058 # Look for DBTV embeds
3059 dbtv_urls = DBTVIE._extract_urls(webpage)
3061 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
3063 # Look for Videa embeds
3064 videa_urls = VideaIE._extract_urls(webpage)
3066 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
3068 # Look for 20 minuten embeds
3069 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3071 return self.playlist_from_matches(
3072 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3074 # Look for VideoPress embeds
3075 videopress_urls = VideoPressIE._extract_urls(webpage)
3077 return self.playlist_from_matches(
3078 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3080 # Look for Rutube embeds
3081 rutube_urls = RutubeIE._extract_urls(webpage)
3083 return self.playlist_from_matches(
3084 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3086 # Look for WashingtonPost embeds
3087 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3089 return self.playlist_from_matches(
3090 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3092 # Look for Mediaset embeds
3093 mediaset_urls = MediasetIE._extract_urls(self, webpage)
3095 return self.playlist_from_matches(
3096 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3098 # Look for JOJ.sk embeds
3099 joj_urls = JojIE._extract_urls(webpage)
3101 return self.playlist_from_matches(
3102 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3104 # Look for megaphone.fm embeds
3105 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3107 return self.playlist_from_matches(
3108 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3110 # Look for vzaar embeds
3111 vzaar_urls = VzaarIE._extract_urls(webpage)
3113 return self.playlist_from_matches(
3114 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3116 channel9_urls = Channel9IE._extract_urls(webpage)
3118 return self.playlist_from_matches(
3119 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3121 vshare_urls = VShareIE._extract_urls(webpage)
3123 return self.playlist_from_matches(
3124 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3126 # Look for Mediasite embeds
3127 mediasite_urls = MediasiteIE._extract_urls(webpage)
3130 self.url_result(smuggle_url(
3131 compat_urlparse.urljoin(url, mediasite_url),
3132 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3133 for mediasite_url in mediasite_urls]
3134 return self.playlist_result(entries, video_id, video_title)
3136 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3137 if springboardplatform_urls:
3138 return self.playlist_from_matches(
3139 springboardplatform_urls, video_id, video_title,
3140 ie=SpringboardPlatformIE.ie_key())
3142 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3144 return self.playlist_from_matches(
3145 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3147 vice_urls = ViceIE._extract_urls(webpage)
3149 return self.playlist_from_matches(
3150 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3152 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3154 return self.playlist_from_matches(
3155 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3157 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3158 if cloudflarestream_urls:
3159 return self.playlist_from_matches(
3160 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3162 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3164 return self.playlist_from_matches(
3165 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3167 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3169 return self.playlist_from_matches(
3170 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3172 apa_urls = APAIE._extract_urls(webpage)
3174 return self.playlist_from_matches(
3175 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3177 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3179 return self.playlist_from_matches(
3180 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3182 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3183 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P
<url
>(?
:https?
:)?
//embed\
.share
-videos\
.se
/auto
/embed
/\d
+\?.*?
\buid
=\d
+.*?
)\
1',
3185 if sharevideos_urls:
3186 return self.playlist_from_matches(
3187 sharevideos_urls, video_id, video_title)
3189 viqeo_urls = ViqeoIE._extract_urls(webpage)
3191 return self.playlist_from_matches(
3192 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3194 expressen_urls = ExpressenIE._extract_urls(webpage)
3196 return self.playlist_from_matches(
3197 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3199 zype_urls = ZypeIE._extract_urls(webpage)
3201 return self.playlist_from_matches(
3202 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3204 # Look for HTML5 media
3205 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls
')
3207 if len(entries) == 1:
3210 'title
': video_title,
3213 for num, entry in enumerate(entries, start=1):
3215 'id': '%s-%s' % (video_id, num),
3216 'title
': '%s (%d)' % (video_title, num),
3218 for entry in entries:
3219 self._sort_formats(entry['formats
'])
3220 return self.playlist_result(entries, video_id, video_title)
3222 jwplayer_data = self._find_jwplayer_data(
3223 webpage, video_id, transform_source=js_to_json)
3226 info = self._parse_jwplayer_data(
3227 jwplayer_data, video_id, require_title=False, base_url=url)
3228 return merge_dicts(info, info_dict)
3229 except ExtractorError:
3230 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3235 r'(?s
)\bvideojs\s
*\
(.+?\
.src\s
*\
(\s
*((?
:\
[.+?\
]|{.+?}
))\s
*\
)\s
*;',
3237 if mobj is not None:
3238 sources = self._parse_json(
3239 mobj.group(1), video_id, transform_source=js_to_json,
3241 if not isinstance(sources, list):
3244 for source in sources:
3245 src = source.get('src
')
3246 if not src or not isinstance(src, compat_str):
3248 src = compat_urlparse.urljoin(url, src)
3249 src_type = source.get('type')
3250 if isinstance(src_type, compat_str):
3251 src_type = src_type.lower()
3252 ext = determine_ext(src).lower()
3253 if src_type == 'video
/youtube
':
3254 return self.url_result(src, YoutubeIE.ie_key())
3255 if src_type == 'application
/dash
+xml
' or ext == 'mpd
':
3256 formats.extend(self._extract_mpd_formats(
3257 src, video_id, mpd_id='dash
', fatal=False))
3258 elif src_type == 'application
/x
-mpegurl
' or ext == 'm3u8
':
3259 formats.extend(self._extract_m3u8_formats(
3260 src, video_id, 'mp4
', entry_protocol='m3u8_native
',
3261 m3u8_id='hls
', fatal=False))
3265 'ext
': (mimetype2ext(src_type)
3266 or ext if ext in KNOWN_EXTENSIONS else 'mp4
'),
3269 self._sort_formats(formats)
3270 info_dict['formats
'] = formats
3273 # Looking for http://schema.org/VideoObject
3274 json_ld = self._search_json_ld(
3275 webpage, video_id, default={}, expected_type='VideoObject
')
3276 if json_ld.get('url
'):
3277 return merge_dicts(json_ld, info_dict)
3279 def check_video(vurl):
3280 if YoutubeIE.suitable(vurl):
3282 if RtmpIE.suitable(vurl):
3284 vpath = compat_urlparse.urlparse(vurl).path
3285 vext = determine_ext(vpath)
3286 return '.' in vpath and vext not in ('swf
', 'png
', 'jpg
', 'srt
', 'sbv
', 'sub
', 'vtt
', 'ttml
', 'js
', 'xml
')
3288 def filter_video(urls):
3289 return list(filter(check_video, urls))
3291 # Start with something easy: JW Player in SWFObject
3292 found = filter_video(re.findall(r'flashvars
: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3294 # Look for gorilla-vid style embedding
3295 found = filter_video(re.findall(r'''(?sx)
3299 jwplayer\s*\(\s*["'][^
'"]+["']\s
*\
)\s
*\
.setup
3302 ['"]?file['"]?\s*:\s*["\'](.*?
)["\']''', webpage))
3304 # Broaden the search a little bit
3305 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3307 # Broaden the findall a little bit: JWPlayer JS loader
3308 found = filter_video(re.findall(
3309 r'[^A
-Za
-z0
-9]?
(?
:file|video_url
)["\']?:\s*["\'](http(?
![^
\'"]+\.[0-9]+[\'"])[^
\'"]+)["\']', webpage))
3312 found = filter_video(re.findall(r'''(?xs)
3313 flowplayer\("[^"]+",\s*
3315 \s*\{[^}]+? ["']?clip
["']?\s*:\s*\{\s*
3316 ["']?url["']?\s
*:\s
*["']([^"']+)["']
3321 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3323 # Try to find twitter cards info
3324 # twitter:player:stream should be checked before twitter:player since
3325 # it is expected to contain a raw stream (see
3326 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3327 found = filter_video(re.findall(
3328 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3330 # We look for Open Graph info:
3331 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3332 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3333 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3334 if m_video_type is not None:
3335 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3337 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3339 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3340 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3343 # Look also in Refresh HTTP header
3344 refresh_header = head_response.headers.get('Refresh')
3346 # In python 2 response HTTP headers are bytestrings
3347 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3348 refresh_header = refresh_header.decode('iso-8859-1')
3349 found = re.search(REDIRECT_REGEX, refresh_header)
3351 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3353 self.report_following_redirect(new_url)
3362 # twitter:player is a https URL to iframe player that may or may not
3363 # be supported by youtube-dl thus this is checked the very last (see
3364 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3365 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3366 if embed_url and embed_url != url:
3367 return self.url_result(embed_url)
3370 raise UnsupportedError(url)
3373 for video_url in orderedSet(found):
3374 video_url = unescapeHTML(video_url)
3375 video_url = video_url.replace('\\/', '/')
3376 video_url = compat_urlparse.urljoin(url, video_url)
3377 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3379 # Sometimes, jwplayer extraction will result in a YouTube URL
3380 if YoutubeIE.suitable(video_url):
3381 entries.append(self.url_result(video_url, 'Youtube'))
3384 # here's a fun little line of code for you:
3385 video_id = os.path.splitext(video_id)[0]
3389 'uploader': video_uploader,
3390 'title': video_title,
3391 'age_limit': age_limit,
3394 if RtmpIE.suitable(video_url):
3395 entry_info_dict.update({
3396 '_type': 'url_transparent',
3397 'ie_key': RtmpIE.ie_key(),
3400 entries.append(entry_info_dict)
3403 ext = determine_ext(video_url)
3405 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3407 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3409 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3411 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3413 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3414 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3415 # Just matching .ism/manifest is not enough to be reliably sure
3416 # whether it's actually an ISM manifest or some other streaming
3417 # manifest since there are various streaming URL formats
3418 # possible (see [1]) as well as some other shenanigans like
3419 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3421 # Thus the most reasonable way to solve this is to delegate
3422 # to generic extractor in order to look into the contents of
3423 # the manifest itself.
3424 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3425 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3426 entry_info_dict = self.url_result(
3427 smuggle_url(video_url, {'to_generic': True}),
3430 entry_info_dict['url'] = video_url
3432 if entry_info_dict.get('formats'):
3433 self._sort_formats(entry_info_dict['formats'])
3435 entries.append(entry_info_dict)
3437 if len(entries) == 1:
3440 for num, e in enumerate(entries, start=1):
3441 # 'url' results don't have a title
3442 if e.get('title') is not None:
3443 e['title'] = '%s (%d)' % (e['title'], num)
3445 '_type': 'playlist',