3 from __future__
import unicode_literals
9 from .common
import InfoExtractor
10 from .youtube
import YoutubeIE
11 from ..compat
import (
12 compat_etree_fromstring
,
14 compat_urllib_parse_unquote
,
16 compat_xml_parse_error
,
37 from .commonprotocols
import RtmpIE
38 from .brightcove
import (
46 from .nbc
import NBCSportsVPlayerIE
47 from .ooyala
import OoyalaIE
48 from .rutv
import RUTVIE
49 from .tvc
import TVCIE
50 from .sportbox
import SportBoxIE
51 from .smotri
import SmotriIE
52 from .myvi
import MyviIE
53 from .condenast
import CondeNastIE
54 from .udn
import UDNEmbedIE
55 from .senateisvp
import SenateISVPIE
56 from .svt
import SVTIE
57 from .pornhub
import PornHubIE
58 from .xhamster
import XHamsterEmbedIE
59 from .tnaflix
import TNAFlixNetworkEmbedIE
60 from .drtuber
import DrTuberIE
61 from .redtube
import RedTubeIE
62 from .tube8
import Tube8IE
63 from .vimeo
import VimeoIE
64 from .dailymotion
import DailymotionIE
65 from .dailymail
import DailyMailIE
66 from .onionstudios
import OnionStudiosIE
67 from .viewlift
import ViewLiftEmbedIE
68 from .mtv
import MTVServicesEmbeddedIE
69 from .pladform
import PladformIE
70 from .videomore
import VideomoreIE
71 from .webcaster
import WebcasterFeedIE
72 from .googledrive
import GoogleDriveIE
73 from .jwplatform
import JWPlatformIE
74 from .digiteka
import DigitekaIE
75 from .arkena
import ArkenaIE
76 from .instagram
import InstagramIE
77 from .liveleak
import LiveLeakIE
78 from .threeqsdn
import ThreeQSDNIE
79 from .theplatform
import ThePlatformIE
80 from .vessel
import VesselIE
81 from .kaltura
import KalturaIE
82 from .eagleplatform
import EaglePlatformIE
83 from .facebook
import FacebookIE
84 from .soundcloud
import SoundcloudIE
85 from .tunein
import TuneInBaseIE
86 from .vbox7
import Vbox7IE
87 from .dbtv
import DBTVIE
88 from .piksel
import PikselIE
89 from .videa
import VideaIE
90 from .twentymin
import TwentyMinutenIE
91 from .ustream
import UstreamIE
92 from .openload
import OpenloadIE
93 from .videopress
import VideoPressIE
94 from .rutube
import RutubeIE
95 from .limelight
import LimelightBaseIE
96 from .anvato
import AnvatoIE
97 from .washingtonpost
import WashingtonPostIE
98 from .wistia
import WistiaIE
99 from .mediaset
import MediasetIE
100 from .joj
import JojIE
101 from .megaphone
import MegaphoneIE
102 from .vzaar
import VzaarIE
103 from .channel9
import Channel9IE
104 from .vshare
import VShareIE
105 from .mediasite
import MediasiteIE
106 from .springboardplatform
import SpringboardPlatformIE
107 from .yapfiles
import YapFilesIE
108 from .vice
import ViceIE
109 from .xfileshare
import XFileShareIE
110 from .cloudflarestream
import CloudflareStreamIE
111 from .peertube
import PeerTubeIE
112 from .teachable
import TeachableIE
113 from .indavideo
import IndavideoEmbedIE
114 from .apa
import APAIE
115 from .foxnews
import FoxNewsIE
116 from .viqeo
import ViqeoIE
117 from .expressen
import ExpressenIE
118 from .zype
import ZypeIE
121 class GenericIE(InfoExtractor
):
122 IE_DESC
= 'Generic downloader that works on some sites'
126 # Direct link to a video
128 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
129 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
134 'upload_date': '20100513',
137 # Direct link to media delivered compressed (until Accept-Encoding is *)
139 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
140 'md5': '128c42e68b13950268b648275386fc74',
142 'id': 'FictionJunction-Parallel_Hearts',
144 'title': 'FictionJunction-Parallel_Hearts',
145 'upload_date': '20140522',
147 'expected_warnings': [
148 'URL could be a direct video link, returning it as such.'
150 'skip': 'URL invalid',
152 # Direct download with broken HEAD
154 'url': 'http://ai-radio.org:8000/radio.opus',
161 'skip_download': True, # infinite live stream
163 'expected_warnings': [
164 r
'501.*Not Implemented',
168 # Direct link with incorrect MIME type
170 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
171 'md5': '4ccbebe5f36706d85221f204d7eb5913',
173 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
174 'id': '5_Lennart_Poettering_-_Systemd',
176 'title': '5_Lennart_Poettering_-_Systemd',
177 'upload_date': '20141120',
179 'expected_warnings': [
180 'URL could be a direct video link, returning it as such.'
185 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
187 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
188 'title': 'Zero Punctuation',
189 'description': 're:.*groundbreaking video review series.*'
191 'playlist_mincount': 11,
193 # RSS feed with enclosure
195 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
197 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
199 'upload_date': '20150228',
200 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
203 # RSS feed with enclosures and unsupported link URLs
205 'url': 'http://www.hellointernet.fm/podcast?format=rss',
207 'id': 'http://www.hellointernet.fm/podcast?format=rss',
208 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
209 'title': 'Hello Internet',
211 'playlist_mincount': 100,
213 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
215 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
219 'title': 'Automatics, robotics and biocybernetics',
220 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
221 'upload_date': '20130627',
222 'formats': 'mincount:16',
223 'subtitles': 'mincount:1',
226 'force_generic_extractor': True,
227 'skip_download': True,
230 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
232 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
237 'formats': 'mincount:1',
240 'skip_download': True,
243 # SMIL from https://www.restudy.dk/video/play/id/1637
245 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
249 'title': 'video_1637',
250 'formats': 'mincount:3',
253 'skip_download': True,
256 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
258 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
260 'id': 'smil-service',
262 'title': 'smil-service',
263 'formats': 'mincount:1',
266 'skip_download': True,
269 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
271 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
275 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
276 'formats': 'mincount:3',
279 'skip_download': True,
282 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
284 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
286 'id': 'mZlp2ctYIUEB',
288 'title': 'Tikibad ontruimd wegens brand',
289 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
290 'thumbnail': r
're:^https?://.*\.jpg$',
294 'skip_download': True,
297 # MPD from http://dash-mse-test.appspot.com/media.html
299 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
300 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
302 'id': 'car-20120827-manifest',
304 'title': 'car-20120827-manifest',
305 'formats': 'mincount:9',
306 'upload_date': '20130904',
309 'format': 'bestvideo',
312 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
314 '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',
319 'formats': 'mincount:8',
323 'skip_download': True,
325 'skip': 'video gone',
327 # m3u8 served with Content-Type: text/plain
329 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
334 'upload_date': '20140720',
335 'formats': 'mincount:11',
339 'skip_download': True,
341 'skip': 'video gone',
345 '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',
349 'upload_date': '20130224',
350 'uploader_id': 'TheVerge',
351 'description': r
're:^Chris Ziegler takes a look at the\.*',
352 'uploader': 'The Verge',
353 'title': 'First Firefox OS phones side-by-side',
356 'skip_download': False,
360 # redirect in Refresh HTTP header
361 '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',
365 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
366 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
367 'upload_date': '20150917',
368 'uploader_id': 'brtvofficial',
369 'uploader': 'Boiler Room',
372 'skip_download': False,
376 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
377 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
379 'id': '13601338388002',
381 'uploader': 'www.hodiho.fr',
382 'title': 'R\u00e9gis plante sa Jeep',
385 # bandcamp page with custom domain
387 'add_ie': ['Bandcamp'],
388 'url': 'http://bronyrock.com/track/the-pony-mash',
392 'title': 'The Pony Mash',
393 'uploader': 'M_Pallante',
395 'skip': 'There is a limit of 200 free downloads / month for the test song',
398 # embedded brightcove video
399 # it also tests brightcove videos that need to set the 'Referer'
400 # in the http requests
401 'add_ie': ['BrightcoveLegacy'],
402 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
404 'id': '2765128793001',
406 'title': 'Le cours de bourse : lāanalyse technique',
407 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
408 'uploader': 'BFM BUSINESS',
411 'skip_download': True,
415 # embedded with itemprop embedURL and video id spelled as `idVideo`
416 'add_id': ['BrightcoveLegacy'],
417 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
419 'id': '5255628253001',
421 'title': 'md5:37c519b1128915607601e75a87995fc0',
422 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
423 'uploader': 'BFM BUSINESS',
424 'uploader_id': '876450612001',
425 'timestamp': 1482255315,
426 'upload_date': '20161220',
429 'skip_download': True,
433 # https://github.com/rg3/youtube-dl/issues/2253
434 'url': 'http://bcove.me/i6nfkrc3',
435 'md5': '0ba9446db037002366bab3b3eb30c88c',
437 'id': '3101154703001',
439 'title': 'Still no power',
440 'uploader': 'thestar.com',
441 '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.',
443 'add_ie': ['BrightcoveLegacy'],
444 'skip': 'video gone',
447 'url': 'http://www.championat.com/video/football/v/87/87499.html',
448 'md5': 'fb973ecf6e4a78a67453647444222983',
450 'id': '3414141473001',
452 'title': 'ŠŠøŠ“ŠµŠ¾. Š£Š“Š°Š»ŠµŠ½ŠøŠµ ŠŠ·Š°Š³Š¾ŠµŠ²Š° (Š¦Š”ŠŠ)',
453 'description': 'ŠŠ½Š»Š°Š¹Š½-ŃŃŠ°Š½ŃŠ»ŃŃŠøŃ Š¼Š°ŃŃŠ° Š¦Š”ŠŠ - "ŠŠ¾Š»Š³Š°"',
454 'uploader': 'Championat',
458 # https://github.com/rg3/youtube-dl/issues/3541
459 'add_ie': ['BrightcoveLegacy'],
460 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
462 'id': '3866516442001',
464 'title': 'Leer mij vrouwen kennen: Aflevering 1',
465 'description': 'Leer mij vrouwen kennen: Aflevering 1',
466 'uploader': 'SBS Broadcasting',
468 'skip': 'Restricted to Netherlands',
470 'skip_download': True, # m3u8 download
474 # Brightcove video in <iframe>
475 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
476 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
478 'id': '5360463607001',
480 'title': 'åå©äŗ失ęåæē«„åØåŗå¢äøę¼å±ćåæč·³ć å¼åč·å¾ę£åøøē«„幓ēę“»',
481 'description': 'čåå½åæē«„åŗéä¼äøäøååéåŗå大ä½æćä½ę²å®¶ęå¾·Ā·čæŖęå°¼ļ¼Zade Diraniļ¼åØ3ę15ę„åå©äŗå²ēŖēå7åØ幓ēŗŖåæµę„ä¹é
ååøäŗäøŗåå©äŗč°±åēęę²ćåæč·³ćļ¼HEARTBEATļ¼ļ¼äøŗåå°å
幓å²ēŖå½±åēåå©äŗåæē«„ååŗå¼ŗēååļ¼å¼åäøēååŗå
±ååŖåļ¼ä½æåå©äŗåæē«„éę°č·å¾äŗ«ęę£åøøē«„幓ēę“»ēęå©ć',
482 'uploader': 'United Nations',
483 'uploader_id': '1362235914001',
484 'timestamp': 1489593889,
485 'upload_date': '20170315',
487 'add_ie': ['BrightcoveLegacy'],
490 # Brightcove with alternative playerID key
491 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
493 'id': 'nmeth.2062_SV1',
494 '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',
498 'id': '2228375078001',
500 'title': 'nmeth.2062-sv1',
501 'description': 'nmeth.2062-sv1',
502 'timestamp': 1363357591,
503 'upload_date': '20130315',
504 'uploader': 'Nature Publishing Group',
505 'uploader_id': '1964492299001',
510 # Brightcove with UUID in videoPlayer
511 'url': 'http://www8.hp.com/cn/zh/home.html',
513 'id': '5255815316001',
515 'title': 'Sprocket Video - China',
516 'description': 'Sprocket Video - China',
517 'uploader': 'HP-Video Gallery',
518 'timestamp': 1482263210,
519 'upload_date': '20161220',
520 'uploader_id': '1107601872001',
523 'skip_download': True, # m3u8 download
525 'skip': 'video rotates...weekly?',
528 # Brightcove:new type [2].
529 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
530 'md5': '2b35148fcf48da41c9fb4591650784f3',
532 'id': '5348741021001',
534 'upload_date': '20170306',
535 'uploader_id': '4191638492001',
536 'timestamp': 1488769918,
537 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
542 # Alternative brightcove <video> attributes
543 '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/',
545 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
546 'title': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidĆ©os avec TĆ©lĆ©-Loisirs",
549 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
551 'id': '5311302538001',
553 'title': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
554 'description': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 fĆ©vrier 2017)",
555 'timestamp': 1486321708,
556 'upload_date': '20170205',
557 'uploader_id': '800000640001',
559 'only_matching': True,
563 # Brightcove with UUID in videoPlayer
564 'url': 'http://www8.hp.com/cn/zh/home.html',
566 'id': '5255815316001',
568 'title': 'Sprocket Video - China',
569 'description': 'Sprocket Video - China',
570 'uploader': 'HP-Video Gallery',
571 'timestamp': 1482263210,
572 'upload_date': '20161220',
573 'uploader_id': '1107601872001',
576 'skip_download': True, # m3u8 download
581 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
582 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
584 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
586 'title': '2cc213299525360.mov', # that's what we get
589 'add_ie': ['Ooyala'],
592 # ooyala video embedded with http://player.ooyala.com/iframe.js
593 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
595 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
597 'title': '"Steve Jobs: Man in the Machine" trailer',
598 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
602 'skip_download': True,
604 'skip': 'movie expired',
606 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
608 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
610 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
612 'title': 'Steampunk Fest Comes to Honesdale',
616 'skip_download': True,
621 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
625 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
626 'upload_date': '20140225',
627 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
628 'uploader': 'Tested',
629 'uploader_id': 'testedcom',
631 # No need to test YoutubeIE here
633 'skip_download': True,
638 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
642 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
643 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
645 # HEAD requests lead to endless 301, while GET is OK
646 'expected_warnings': ['301'],
650 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
654 'title': 'ŠŃ
Š¾ŃŃŠŗŠ¾Šµ Š¼Š¾ŃŠµ ŃŃŠ°Š»Š¾ ŃŠµŠ»ŠøŠŗŠ¾Š¼ ŃŠ¾ŃŃŠøŠ¹ŃŠŗŠøŠ¼',
655 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
659 'skip_download': True,
664 '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/',
668 'title': 'ŠŠ¾ŃŠŗŠ¾Š»ŃŠ½Š¾Šµ Š²Š¾ŃŠæŠøŃŠ°Š½ŠøŠµ',
673 'url': 'http://www.vestifinance.ru/articles/25753',
676 'title': 'ŠŃŃŠ¼ŃŠµ ŃŃŠ°Š½ŃŠ»ŃŃŠøŠø Ń Š¤Š¾ŃŃŠ¼Š°-Š²ŃŃŃŠ°Š²ŠŗŠø "ŠŠ¾ŃŠ·Š°ŠŗŠ°Š·-2013"',
681 'title': 'ŠŠ¾ŃŠ·Š°ŠŗŠ°Š·. ŠŠµŠ½Ń 3',
687 'title': 'ŠŠ¾ŃŠ·Š°ŠŗŠ°Š·. ŠŠµŠ½Ń 2',
693 'title': 'ŠŠ¾ŃŠ·Š°ŠŗŠ°Š·. ŠŠµŠ½Ń 1',
699 'skip_download': True,
704 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
706 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
708 'title': 'Š£Š¶Š°ŃŃŠøŠŗŠø, ŃŃŃŃŠŗŠøŠ¹ ŃŃŠµŠ¹Š»ŠµŃ (2015)',
709 'thumbnail': r
're:^https?://.*\.jpg$',
715 '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',
718 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
720 'playlist_mincount': 7,
721 # This forum does not allow <iframe> syntaxes anymore
722 # Now HTML tags are displayed as-is
723 'skip': 'No videos on this page',
727 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
728 'md5': '65fdff94098e4a607385a60c5177c638',
732 'title': 'Hidden miracles of the natural world',
733 'uploader': 'Louie Schwartzberg',
734 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
737 # nowvideo embed hidden behind percent encoding
739 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
740 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
742 'id': '06e53103ca9aa',
744 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
745 'description': 'No description',
750 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
751 'md5': '7653032cbb25bf6c80d80f217055fa43',
753 'id': '048195-004_PLUS7-F',
756 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
757 'upload_date': '20140320',
760 'skip_download': 'Requires rtmpdump'
762 'skip': 'video gone',
766 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
770 'title': 'Alcaline, le concert avec Calogero',
771 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
772 'upload_date': '20150226',
773 'timestamp': 1424989860,
778 'skip_download': True,
780 'expected_warnings': [
786 'url': 'http://www.wired.com/2014/04/honda-asimo/',
787 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
789 'id': '53501be369702d3275860000',
791 'title': 'Hondaās New Asimo Robot Is More Human Than Ever',
796 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
797 'md5': '441aeeb82eb72c422c7f14ec533999cd',
799 'id': 'k2mm4bCdJ6CQ2i7c8o2',
801 'title': 'Le Zap de Spi0n nĀ°216 - Zapping du Web',
802 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
804 'uploader_id': 'xgditw',
805 'upload_date': '20140425',
806 'timestamp': 1398441542,
808 'add_ie': ['Dailymotion'],
812 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
816 'title': 'Care worker punches elderly dementia patient in head 11 times',
817 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
819 'add_ie': ['DailyMail'],
821 'skip_download': True,
826 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
830 'title': 'The NBL Auction 2014',
831 'uploader': 'BADMINTON England',
832 'uploader_id': 'BADMINTONEvents',
833 'upload_date': '20140603',
834 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
836 'add_ie': ['Youtube'],
838 'skip_download': True,
843 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
844 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
846 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
848 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
849 'description': 'Two valets share their love for movie star Liam Neesons.',
850 'timestamp': 1349922600,
851 'upload_date': '20121011',
854 # YouTube embed via <data-embed-url="">
856 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
860 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
861 'uploader': 'Gameloft',
862 'uploader_id': 'gameloft',
863 'upload_date': '20140828',
864 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
867 'skip_download': True,
870 # YouTube <object> embed
872 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
873 'md5': '516718101ec834f74318df76259fb3cc',
877 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
878 'upload_date': '20080526',
879 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
880 'uploader': 'Christopher Sykes',
881 'uploader_id': 'ChristopherJSykes',
883 'add_ie': ['Youtube'],
887 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
889 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
891 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
892 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
897 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
899 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
900 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
906 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
911 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
912 'md5': '9d65602bf31c6e20014319c7d07fba27',
914 'id': '5123ea6d5e5a7',
917 'uploader': 'www.handjobhub.com',
918 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
921 # Multiple brightcove videos
922 # https://github.com/rg3/youtube-dl/issues/2283
924 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
926 'id': 'always-never',
927 'title': 'Always / Never - The New Yorker',
931 'extract_flat': False,
932 'skip_download': True,
937 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
938 'md5': '96f09a37e44da40dd083e12d9a683327',
942 'title': 'Ump changes call to ball',
943 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
945 'timestamp': 1401537900,
946 'upload_date': '20140531',
947 'thumbnail': r
're:^https?://.*\.jpg$',
952 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
953 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
957 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
958 'description': 'a Paywall Videos video from Remilon',
960 'uploader': 'study.com',
961 'timestamp': 1459678540,
962 'upload_date': '20160403',
963 'filesize': 24687186,
967 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
968 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
972 'title': 'Conversation about Hexagonal Rails Part 1',
973 'description': 'a Martin Fowler video from ThoughtWorks',
975 'uploader': 'thoughtworks.wistia.com',
976 'timestamp': 1401832161,
977 'upload_date': '20140603',
980 # Wistia standard embed (async)
982 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
986 'title': 'Drip Brennan Dunn Workshop',
987 'description': 'a JV Webinars video from getdrip-1',
989 'timestamp': 1463607249,
990 'upload_date': '20160518',
993 'skip_download': True,
998 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1002 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1003 'uploader': 'Sophos Security',
1004 'title': 'Chet Chat 171 - Oct 29, 2014',
1005 'upload_date': '20141029',
1008 # Soundcloud multiple embeds
1010 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1013 'title': 'Guitar Essentials: Legato WorkoutāOne-Hour to Fluid Performance | TAB + AUDIO',
1015 'playlist_mincount': 7,
1017 # TuneIn station embed
1019 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1024 'location': 'Paris, France',
1029 'skip_download': True,
1034 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1038 'upload_date': '20141112',
1039 'title': 'Rosetta #CometLanding webcast HL 10',
1042 # Another Livestream embed, without 'new.' in URL
1044 'url': 'https://www.freespeech.org/',
1048 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1052 'skip_download': True,
1057 'url': 'https://skiplagged.com/',
1060 'title': 'Skiplagged: The smart way to find cheap flights',
1062 'playlist_mincount': 1,
1063 'add_ie': ['Youtube'],
1067 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1071 'upload_date': '20141126',
1072 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1077 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1079 'id': '730m_DandD_1901_512k',
1081 'uploader': 'www.abc.net.au',
1082 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1085 # embedded viddler video
1087 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1091 'uploader': 'deadspin',
1092 'title': 'WALL-TO-GORTAT',
1093 'timestamp': 1422285291,
1094 'upload_date': '20150126',
1096 'add_ie': ['Viddler'],
1100 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1104 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1105 'description': 'md5:601cb790edd05908957dae8aaa866465',
1106 'upload_date': '20150220',
1108 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1112 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1114 'id': 'Mrj4DVp2zeA',
1116 'upload_date': '20150212',
1117 'uploader': 'The National Archives UK',
1118 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1119 'uploader_id': 'NationalArchives08',
1120 'title': 'Webinar: Using Discovery, The National Archivesā online catalogue',
1125 'url': 'http://www.suffolk.edu/sjc/live.php',
1129 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1130 'uploader': 'www.suffolk.edu',
1133 'skip_download': True,
1135 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1139 'url': 'http://www.indiedb.com/games/king-machine/videos',
1143 'title': 'king machine trailer 1',
1144 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1145 'thumbnail': r
're:^https?://.*\.jpg$',
1149 # JWPlayer config passed as variable
1150 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1154 'title': 'ARIELE | Tube Cup',
1155 'uploader': 'www.txxx.com',
1159 'skip_download': True,
1164 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1165 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1169 'upload_date': '20171122',
1170 'timestamp': 1511366290,
1171 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1173 'add_ie': [JWPlatformIE
.ie_key()],
1176 # Video.js embed, multiple formats
1177 'url': 'http://ortcam.com/solidworks-ŃŃŠ¾Šŗ-6-Š½Š°ŃŃŃŠ¾Š¹ŠŗŠ°-ŃŠµŃŃŠµŠ¶Š°_33f9b7351.html',
1179 'id': 'yygqldloqIk',
1181 'title': 'SolidWorks. Š£ŃŠ¾Šŗ 6 ŠŠ°ŃŃŃŠ¾Š¹ŠŗŠ° ŃŠµŃŃŠµŠ¶Š°',
1182 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1183 'upload_date': '20130314',
1184 'uploader': 'PROŃŃŠ¾Šµ3D',
1185 'uploader_id': 'PROstoe3D',
1188 'skip_download': True,
1192 # Video.js embed, single format
1193 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1197 'title': 'Step 1 - Good Foundation',
1198 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1201 'skip_download': True,
1206 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1207 'playlist_mincount': 5,
1209 'id': 'aanslagen-kopenhagen',
1210 'title': 'Aanslagen Kopenhagen',
1215 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1219 'title': 'EP3S5 - Bon AppƩtit - Baqueira Mi Corazon !',
1222 # Kaltura embed (different embed code)
1224 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1228 'upload_date': '20150127',
1229 'uploader_id': 'PremierMedia',
1231 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1234 # Kaltura embed with single quotes
1236 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1241 'timestamp': 1355743100,
1242 'upload_date': '20121217',
1243 'uploader_id': 'cplapp@learn360.com',
1245 'add_ie': ['Kaltura'],
1248 # Kaltura embedded via quoted entry_id
1249 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1253 'title': '06_matthew_brender_raj_dutt',
1254 'timestamp': 1466638791,
1255 'upload_date': '20160622',
1257 'add_ie': ['Kaltura'],
1258 'expected_warnings': [
1259 'Could not send HEAD request'
1262 'skip_download': True,
1266 # Kaltura embedded, some fileExt broken (#11480)
1267 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1271 'title': 'Our "Standard Models" of particle physics and cosmology',
1272 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1273 'timestamp': 1321158993,
1274 'upload_date': '20111113',
1275 'uploader_id': 'kps1',
1277 'add_ie': ['Kaltura'],
1280 # Kaltura iframe embed
1281 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1282 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1286 'title': 'I. M. Pei: A Centennial Celebration',
1287 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1288 'upload_date': '20170403',
1289 'uploader_id': 'batchUser',
1290 'timestamp': 1491232186,
1292 'add_ie': ['Kaltura'],
1295 # Kaltura iframe embed, more sophisticated
1296 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1300 'title': 'lecture-05sep2017',
1301 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1302 'upload_date': '20170913',
1303 'uploader_id': 'eps2',
1304 'timestamp': 1505340777,
1307 'skip_download': True,
1309 'add_ie': ['Kaltura'],
1312 # meta twitter:player
1313 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1317 'title': 'Main Twerk (Video)',
1318 'upload_date': '20171208',
1319 'uploader_id': 'sebastian.salinas@thechive.com',
1320 'timestamp': 1512713057,
1323 'skip_download': True,
1325 'add_ie': ['Kaltura'],
1327 # referrer protected EaglePlatform embed
1329 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1333 'title': 'Š”ŃŠ°Ń ŠŠ°Š¼ŠøŠ½: Ā«ŠŃ Š½Š°ŃŃŃŠøŠ»Šø Š“ŠµŠ²ŃŃŠ²ŠµŠ½Š½Š¾ŃŃŃ ŠŃŠµŠ¼Š»ŃĀ»',
1334 'thumbnail': r
're:^https?://.*\.jpg$',
1339 'skip_download': True,
1342 # ClipYou (EaglePlatform) embed (custom URL)
1344 'url': 'http://muz-tv.ru/play/7129/',
1345 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1349 'title': "'O Sole Mio",
1350 'thumbnail': r
're:^https?://.*\.jpg$',
1355 'skip_download': True,
1357 'skip': 'This video is unavailable.',
1361 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1365 'title': 'Š¢Š°Š¹Š½Ń ŠæŠµŃŠµŠ²Š°Š»Š° ŠŃŃŠ»Š¾Š²Š° ā¢ 1 ŃŠµŃŠøŃ 2 ŃŠ°ŃŃŃ',
1366 'description': 'ŠŠ¾ŠŗŃŠ¼ŠµŠ½ŃŠ°Š»ŃŠ½ŃŠ¹ ŃŠµŃŠøŠ°Š»-ŃŠ°ŃŃŠ»ŠµŠ“Š¾Š²Š°Š½ŠøŠµ Š¾Š“Š½Š¾Š¹ ŠøŠ· ŃŠ°Š¼ŃŃ
Š¶ŃŃŠŗŠøŃ
ŃŠ°Š¹Š½ Š„Š„ Š²ŠµŠŗŠ°',
1367 'thumbnail': r
're:^https?://.*\.jpg$',
1371 'skip': 'HTTP Error 404: Not Found',
1375 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1379 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1380 'thumbnail': r
're:^https?://.*\.png$',
1386 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1387 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1391 'title': 'Facebook Creates "On This Day" | Crunch Report',
1392 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1393 'timestamp': 1427237531,
1394 'uploader': 'Crunch Report',
1395 'upload_date': '20150324',
1399 'skip_download': True,
1402 # Crooks and Liars embed
1404 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1408 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1409 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1410 'timestamp': 1428207000,
1411 'upload_date': '20150405',
1412 'uploader': 'Heather',
1415 # Crooks and Liars external embed
1417 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1419 'id': 'MTE3MjUtMzQ2MzA',
1421 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1422 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1423 'timestamp': 1265032391,
1424 'upload_date': '20100201',
1425 'uploader': 'Heather',
1428 # NBC Sports vplayer embed
1430 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1432 'id': 'ln7x1qSThw4k',
1434 'title': "PFT Live: New leader in the 'new-look' defense",
1435 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1436 'uploader': 'NBCU-SPORTS',
1437 'upload_date': '20140107',
1438 'timestamp': 1389118457,
1440 'skip': 'Invalid Page URL',
1444 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1445 'md5': '1aa589c675898ae6d37a17913cf68d66',
1447 'id': 'x_dtl_oa_LettermanliftPR_160608',
1449 'title': 'David Letterman: A Preview',
1450 '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.',
1451 'upload_date': '20160609',
1452 'timestamp': 1465431544,
1453 'uploader': 'NBCU-NEWS',
1458 'url': 'https://video.udn.com/news/300346',
1459 'md5': 'fd2060e988c326991037b9aff9df21a6',
1463 'title': 'äøäøäøē·åø«č®ę§ å
Øę ”åø«ēåęŗ',
1464 'thumbnail': r
're:^https?://.*\.jpg$',
1468 'skip_download': True,
1470 'expected_warnings': ['Failed to parse JSON Expecting value'],
1472 # Brightcove URL in single quotes
1474 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1475 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1477 'id': '4255764656001',
1479 'title': 'SN Presents: Russell Martin, World Citizen',
1480 'description': 'To understand why he was the Toronto Blue Jaysā 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.',
1481 'uploader': 'Rogers Sportsnet',
1482 'uploader_id': '1704050871',
1483 'upload_date': '20150525',
1484 'timestamp': 1432570283,
1487 # OnionStudios embed
1489 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1493 'title': 'Donāt Understand Bitcoin? This Man Will Mumble An Explanation At You',
1494 'thumbnail': r
're:^https?://.*\.jpe?g$',
1495 'uploader': 'ClickHole',
1496 'uploader_id': 'clickhole',
1501 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1503 'id': '74849a00-85a9-11e1-9660-123139220831',
1505 'title': '#whilewewatch',
1508 # AdobeTVVideo embed
1510 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1511 'md5': '43662b577c018ad707a63766462b1e87',
1515 'title': 'New experience with Acrobat DC',
1516 'description': 'New experience with Acrobat DC',
1517 'duration': 248.667,
1520 # BrightcoveInPageEmbed embed
1522 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1524 'id': '4238694884001',
1526 'title': 'Tabletop: Dread, Last Thoughts',
1527 'description': 'Tabletop: Dread, Last Thoughts',
1531 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1532 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1534 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1536 'id': '4785848093001',
1538 'title': 'The Cardinal Pell Interview',
1539 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1540 'uploader': 'GlobeCast Australia - GlobeStream',
1541 'uploader_id': '2733773828001',
1542 'upload_date': '20160304',
1543 'timestamp': 1457083087,
1547 'skip_download': True,
1551 # Brightcove embed with whitespace around attribute names
1552 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1554 'id': '3167554373001',
1556 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1557 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1558 'uploader_id': '1079349493',
1559 'upload_date': '20140207',
1560 'timestamp': 1391810548,
1563 'skip_download': True,
1566 # Another form of arte.tv embed
1568 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1569 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1571 'id': '030273-562_PLUS7-F',
1573 'title': 'ARTE Reportage - Nulle part, en France',
1574 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1575 'upload_date': '20160409',
1580 'url': 'http://www.wykop.pl/link/3088787/',
1581 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1583 'id': '874_1459135191',
1585 'title': 'Man shows poor quality of new apartment building',
1586 'description': 'The wall is like a sand pile.',
1587 'uploader': 'Lake8737',
1589 'add_ie': [LiveLeakIE
.ie_key()],
1591 # Another LiveLeak embed pattern (#13336)
1593 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1595 'id': '2eb_1496309988',
1597 'title': 'Thief robs place where everyone was armed',
1598 'description': 'md5:694d73ee79e535953cf2488562288eee',
1599 'uploader': 'brazilwtf',
1601 'add_ie': [LiveLeakIE
.ie_key()],
1603 # Duplicated embedded video URLs
1605 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1607 'id': '149298443_480_16c25b74_2',
1609 'title': 'vs. Blue Orange Spring Game',
1610 'uploader': 'www.hudl.com',
1613 # twitter:player:stream embed
1615 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1619 'title': 'Une nouvelle espĆØce de dinosaure dĆ©couverte en Argentine',
1620 'uploader': 'www.rtl.be',
1624 'skip_download': True,
1627 # twitter:player embed
1629 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1630 'md5': 'a3e0df96369831de324f0778e126653c',
1632 'id': '4909620399001',
1634 'title': 'What Do Black Holes Sound Like?',
1635 'description': 'what do black holes sound like',
1636 'upload_date': '20160524',
1637 'uploader_id': '29913724001',
1638 'timestamp': 1464107587,
1639 'uploader': 'TheAtlantic',
1641 'add_ie': ['BrightcoveLegacy'],
1643 # Facebook <iframe> embed
1645 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1646 'md5': 'fbcde74f534176ecb015849146dd3aee',
1648 'id': '599637780109885',
1650 'title': 'Facebook video #599637780109885',
1653 # Facebook <iframe> embed, plugin video
1655 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1657 'id': '1754168231264132',
1659 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1660 'uploader': 'Tariq Ramadan (official)',
1661 'timestamp': 1496758379,
1662 'upload_date': '20170606',
1665 'skip_download': True,
1668 # Facebook API embed
1670 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1671 'md5': 'a47372ee61b39a7b90287094d447d94e',
1673 'id': '10153467542406923',
1675 'title': 'Facebook video #10153467542406923',
1678 # Wordpress "YouTube Video Importer" plugin
1680 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1681 'md5': 'd16797741b560b485194eddda8121b48',
1683 'id': 'HNTXWDXV9Is',
1685 'title': 'Blue Devils Drumline Stanford lot 2016',
1686 'upload_date': '20160627',
1687 'uploader_id': 'GENOCIDE8GENERAL10',
1688 'uploader': 'cylus cyrus',
1692 # video stored on custom kaltura server
1693 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1694 'md5': '537617d06e64dfed891fa1593c4b30cc',
1698 'title': 'Elecciones britƔnicas: 5 lecciones para Rajoy',
1699 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1700 'uploader_id': 'videos.expansion@el-mundo.net',
1701 'upload_date': '20150429',
1702 'timestamp': 1430303472,
1704 'add_ie': ['Kaltura'],
1707 # Non-standard Vimeo embed
1708 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1709 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1713 'title': 'Understanding the web - Teaser',
1714 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1715 'upload_date': '20151214',
1716 'uploader': 'OpenClassrooms',
1717 'uploader_id': 'openclassrooms',
1719 'add_ie': ['Vimeo'],
1722 # generic vimeo embed that requires original URL passed as Referer
1723 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1724 'only_matching': True,
1727 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1728 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1730 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1732 'title': 'Big Buck Bunny',
1733 'description': 'Royalty free test video',
1734 'timestamp': 1432816365,
1735 'upload_date': '20150528',
1739 'skip_download': True,
1741 'add_ie': [ArkenaIE
.ie_key()],
1744 '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/',
1748 'title': 'ŠŠ ŠŠŠ”ŠŖŠ ŠŠ¢ ŠŠŠ ŠŠ: ŠŠ·ŃŠøŃŠ°Š½Šµ Š½Š° Š³Š°Š· Š½Š° Š±ŠµŠ½Š·ŠøŠ½Š¾ŃŃŠ°Š½ŃŠøŃ Š² ŠŠ»Š¾Š²Š“ŠøŠ²',
1751 'skip_download': True,
1753 'add_ie': [Vbox7IE
.ie_key()],
1757 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1760 'title': 'Etter ett Ƅrs planlegging, klaffet endelig alt: - Jeg mƄtte ta en liten dans',
1762 'playlist_mincount': 3,
1766 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1768 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1769 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1771 'playlist_mincount': 2,
1775 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1779 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1780 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1783 'skip_download': True,
1785 'add_ie': [TwentyMinutenIE
.ie_key()],
1789 'url': 'https://en.support.wordpress.com/videopress/',
1793 'title': 'IMG_5786',
1794 'timestamp': 1435711927,
1795 'upload_date': '20150701',
1798 'skip_download': True,
1800 'add_ie': [VideoPressIE
.ie_key()],
1804 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1806 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1808 'title': 'ŠŠ°Š³Š°Š·Š·ŠøŠ½Š¾: ŠŠ°Š·Š°Š½Ń 2',
1809 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1810 'uploader': 'ŠŠ°Š³Š°Š·Š·ŠøŠ½Š¾',
1811 'upload_date': '20170228',
1812 'uploader_id': '996642',
1815 'skip_download': True,
1817 'add_ie': [RutubeIE
.ie_key()],
1820 # ThePlatform embedded with whitespaces in URLs
1821 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1822 'only_matching': True,
1825 # Senate ISVP iframe https
1826 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1827 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1829 'id': 'govtaff020316',
1831 'title': 'Integrated Senate Video Player',
1833 'add_ie': [SenateISVPIE
.ie_key()],
1836 # Limelight embeds (1 channel embed + 4 media embeds)
1837 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1839 'id': 'FacilitatorTraining2017',
1840 'title': 'Facilitator Training 2017',
1842 'playlist_mincount': 5,
1845 # Limelight embed (LimelightPlayerUtil.embed)
1846 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1848 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1850 'title': '07448641',
1851 'timestamp': 1499890639,
1852 'upload_date': '20170712',
1855 'skip_download': True,
1857 'add_ie': ['LimelightMedia'],
1860 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1862 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1863 'title': 'Standoff with Walnut Creek murder suspect ends',
1864 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1866 'playlist_mincount': 4,
1869 # WashingtonPost embed
1870 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1872 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1874 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1875 '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 ā and enlisted actors.',
1876 'timestamp': 1455216756,
1877 'uploader': 'The Washington Post',
1878 'upload_date': '20160211',
1880 'add_ie': [WashingtonPostIE
.ie_key()],
1884 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1888 'title': 'Serracchiani: "Voglio vivere in una societĆ aperta, con tutela del patto di fiducia"',
1891 'skip_download': True,
1893 'add_ie': [MediasetIE
.ie_key()],
1897 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1899 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1900 'title': 'Slovenskom sa prehnala vlna silnĆ½ch bĆŗrok',
1902 'playlist_mincount': 5,
1903 'add_ie': [JojIE
.ie_key()],
1906 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1907 'url': 'https://tvrain.ru/amp/418921/',
1908 'md5': 'cc00413936695987e8de148b67d14f1d',
1912 'title': 'Š”ŃŠ°Ń ŠŠ°Š¼ŠøŠ½: Ā«ŠŃ Š½Š°ŃŃŃŠøŠ»Šø Š“ŠµŠ²ŃŃŠ²ŠµŠ½Š½Š¾ŃŃŃ ŠŃŠµŠ¼Š»ŃĀ»',
1917 'url': 'http://help.vzaar.com/article/165-embedding-video',
1918 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1922 'title': 'Building A Business Online: Principal Chairs Q & A',
1926 # multiple HTML5 videos on one page
1927 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1929 'id': 'keyscenarios',
1930 'title': 'Rescue Kit 14 Free Edition - Getting started',
1932 'playlist_count': 4,
1936 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1937 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1940 'title': 'vl14062007715967',
1945 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1946 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1948 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1950 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1951 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1952 'timestamp': 1474354800,
1953 'upload_date': '20160920',
1957 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1961 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1962 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1963 'timestamp': 1516100691,
1964 'upload_date': '20180116',
1967 'skip_download': True,
1969 'add_ie': [SpringboardPlatformIE
.ie_key()],
1972 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1974 'id': 'uPDB5I9wfp8',
1976 'title': 'Pocoyo: 90 minutos de episĆ³dios completos PortuguĆŖs para crianƧas - PARTE 3',
1977 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1978 'upload_date': '20160219',
1979 'uploader': 'Pocoyo - PortuguĆŖs (BR)',
1980 'uploader_id': 'PocoyoBrazil',
1982 'add_ie': [YoutubeIE
.ie_key()],
1984 'skip_download': True,
1988 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1990 'id': 'vMDE4NzI1Mjgt690b',
1992 'title': 'ŠŠ¾ŃŃŃŠ°',
1994 'add_ie': [YapFilesIE
.ie_key()],
1996 'skip_download': True,
2000 # CloudflareStream embed
2001 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2003 'id': '31c9291ab41fac05471db4e73aa11717',
2005 'title': '31c9291ab41fac05471db4e73aa11717',
2007 'add_ie': [CloudflareStreamIE
.ie_key()],
2009 'skip_download': True,
2014 'url': 'https://joinpeertube.org/fr/home/',
2017 'title': 'Reprenez le contrƓle de vos vidƩos ! #JoinPeertube',
2019 'playlist_count': 2,
2023 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2027 'title': 'Ćgy kell otthon hamburgert sĆ¼tni',
2028 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2029 'timestamp': 1426330212,
2030 'upload_date': '20150314',
2031 'uploader': 'StreetKitchen',
2032 'uploader_id': '546363',
2034 'add_ie': [IndavideoEmbedIE
.ie_key()],
2036 'skip_download': True,
2040 # APA embed via JWPlatform embed
2041 'url': 'http://www.vol.at/blue-man-group/5593454',
2045 'title': '"Blau ist mysteriƶs": Die Blue Man Group im Interview',
2046 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2047 'thumbnail': r
're:^https?://.*\.jpg$',
2049 'timestamp': 1519211149,
2050 'upload_date': '20180221',
2053 'skip_download': True,
2057 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2058 'md5': 'b68d276de422ab07ee1d49388103f457',
2061 'title': 'Lock up and get excited',
2064 'skip': 'TODO: fix nested playlists processing in tests',
2068 'url': 'https://viqeo.tv/',
2071 'title': 'All-new video platform',
2073 'playlist_count': 6,
2077 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2079 'id': '5b400b834b32992a310622b9',
2081 'title': 'Smoky Barbecue Favorites',
2082 'thumbnail': r
're:^https?://.*\.jpe?g',
2084 'add_ie': [ZypeIE
.ie_key()],
2086 'skip_download': True,
2091 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2095 'title': 'ŠŠ¾ŃŃŠ°Š²ŃŠøŠŗ ŠæŠøŃŃŃ ŃŠæŃŠ¾ŃŠøŠ» ŃŠ°Š·ŃŠµŃŠµŠ½ŠøŃ ŃŃŠ³ŃŠ°ŃŃ Š½Š° ŃŠ¾ŃŃŠµŠæŠøŠ°Š½Š¾',
2096 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2097 'thumbnail': r
're:^https?://.*\.jpg$',
2100 'skip_download': True,
2102 'expected_warnings': ['Failed to download MPD manifest'],
2105 # # TODO: find another test
2106 # # http://schema.org/VideoObject
2107 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2108 # 'md5': '888dcf08b7ea671381f00fab74692755',
2110 # 'id': 'nyvTSJMKId',
2112 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2113 # 'description': '#love for cats.',
2114 # 'timestamp': 1461244995,
2115 # 'upload_date': '20160421',
2118 # 'force_generic_extractor': True,
2123 def report_following_redirect(self
, new_url
):
2124 """Report information extraction."""
2125 self
._downloader
.to_screen('[redirect] Following redirect to %s' % new_url
)
2127 def _extract_rss(self
, url
, video_id
, doc
):
2128 playlist_title
= doc
.find('./channel/title').text
2129 playlist_desc_el
= doc
.find('./channel/description')
2130 playlist_desc
= None if playlist_desc_el
is None else playlist_desc_el
.text
2133 for it
in doc
.findall('./channel/item'):
2135 enclosure_nodes
= it
.findall('./enclosure')
2136 for e
in enclosure_nodes
:
2137 next_url
= e
.attrib
.get('url')
2142 next_url
= xpath_text(it
, 'link', fatal
=False)
2148 '_type': 'url_transparent',
2150 'title': it
.find('title').text
,
2154 '_type': 'playlist',
2156 'title': playlist_title
,
2157 'description': playlist_desc
,
2161 def _extract_camtasia(self
, url
, video_id
, webpage
):
2162 """ Returns None if no camtasia video can be found. """
2164 camtasia_cfg
= self
._search
_regex
(
2165 r
'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2166 webpage
, 'camtasia configuration file', default
=None)
2167 if camtasia_cfg
is None:
2170 title
= self
._html
_search
_meta
('DC.title', webpage
, fatal
=True)
2172 camtasia_url
= compat_urlparse
.urljoin(url
, camtasia_cfg
)
2173 camtasia_cfg
= self
._download
_xml
(
2174 camtasia_url
, video_id
,
2175 note
='Downloading camtasia configuration',
2176 errnote
='Failed to download camtasia configuration')
2177 fileset_node
= camtasia_cfg
.find('./playlist/array/fileset')
2180 for n
in fileset_node
.getchildren():
2181 url_n
= n
.find('./uri')
2186 'id': os
.path
.splitext(url_n
.text
.rpartition('/')[2])[0],
2187 'title': '%s - %s' % (title
, n
.tag
),
2188 'url': compat_urlparse
.urljoin(url
, url_n
.text
),
2189 'duration': float_or_none(n
.find('./duration').text
),
2193 '_type': 'playlist',
2198 def _real_extract(self
, url
):
2199 if url
.startswith('//'):
2200 return self
.url_result(self
.http_scheme() + url
)
2202 parsed_url
= compat_urlparse
.urlparse(url
)
2203 if not parsed_url
.scheme
:
2204 default_search
= self
._downloader
.params
.get('default_search')
2205 if default_search
is None:
2206 default_search
= 'fixup_error'
2208 if default_search
in ('auto', 'auto_warning', 'fixup_error'):
2210 self
._downloader
.report_warning('The url doesn\'t specify the protocol, trying with http')
2211 return self
.url_result('http://' + url
)
2212 elif default_search
!= 'fixup_error':
2213 if default_search
== 'auto_warning':
2214 if re
.match(r
'^(?:url|URL)$', url
):
2215 raise ExtractorError(
2216 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url
,
2219 self
._downloader
.report_warning(
2220 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url
)
2221 return self
.url_result('ytsearch:' + url
)
2223 if default_search
in ('error', 'fixup_error'):
2224 raise ExtractorError(
2225 '%r is not a valid URL. '
2226 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2227 % (url
, url
), expected
=True)
2229 if ':' not in default_search
:
2230 default_search
+= ':'
2231 return self
.url_result(default_search
+ url
)
2233 url
, smuggled_data
= unsmuggle_url(url
)
2234 force_videoid
= None
2235 is_intentional
= smuggled_data
and smuggled_data
.get('to_generic')
2236 if smuggled_data
and 'force_videoid' in smuggled_data
:
2237 force_videoid
= smuggled_data
['force_videoid']
2238 video_id
= force_videoid
2240 video_id
= self
._generic
_id
(url
)
2242 self
.to_screen('%s: Requesting header' % video_id
)
2244 head_req
= HEADRequest(url
)
2245 head_response
= self
._request
_webpage
(
2247 note
=False, errnote
='Could not send HEAD request to %s' % url
,
2250 if head_response
is not False:
2251 # Check for redirect
2252 new_url
= compat_str(head_response
.geturl())
2254 self
.report_following_redirect(new_url
)
2256 new_url
= smuggle_url(
2257 new_url
, {'force_videoid': force_videoid
})
2258 return self
.url_result(new_url
)
2260 full_response
= None
2261 if head_response
is False:
2262 request
= sanitized_Request(url
)
2263 request
.add_header('Accept-Encoding', '*')
2264 full_response
= self
._request
_webpage
(request
, video_id
)
2265 head_response
= full_response
2269 'title': self
._generic
_title
(url
),
2270 'upload_date': unified_strdate(head_response
.headers
.get('Last-Modified'))
2273 # Check for direct link to a video
2274 content_type
= head_response
.headers
.get('Content-Type', '').lower()
2275 m
= re
.match(r
'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type
)
2277 format_id
= compat_str(m
.group('format_id'))
2278 if format_id
.endswith('mpegurl'):
2279 formats
= self
._extract
_m
3u8_formats
(url
, video_id
, 'mp4')
2280 elif format_id
== 'f4m':
2281 formats
= self
._extract
_f
4m
_formats
(url
, video_id
)
2284 'format_id': format_id
,
2286 'vcodec': 'none' if m
.group('type') == 'audio' else None
2288 info_dict
['direct'] = True
2289 self
._sort
_formats
(formats
)
2290 info_dict
['formats'] = formats
2293 if not self
._downloader
.params
.get('test', False) and not is_intentional
:
2294 force
= self
._downloader
.params
.get('force_generic_extractor', False)
2295 self
._downloader
.report_warning(
2296 '%s on generic information extractor.' % ('Forcing' if force
else 'Falling back'))
2298 if not full_response
:
2299 request
= sanitized_Request(url
)
2300 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2301 # making it impossible to download only chunk of the file (yet we need only 512kB to
2302 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2303 # that will always result in downloading the whole file that is not desirable.
2304 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2305 # to accept raw bytes and being able to download only a chunk.
2306 # It may probably better to solve this by checking Content-Type for application/octet-stream
2307 # after HEAD request finishes, but not sure if we can rely on this.
2308 request
.add_header('Accept-Encoding', '*')
2309 full_response
= self
._request
_webpage
(request
, video_id
)
2311 first_bytes
= full_response
.read(512)
2313 # Is it an M3U playlist?
2314 if first_bytes
.startswith(b
'#EXTM3U'):
2315 info_dict
['formats'] = self
._extract
_m
3u8_formats
(url
, video_id
, 'mp4')
2316 self
._sort
_formats
(info_dict
['formats'])
2319 # Maybe it's a direct link to a video?
2320 # Be careful not to download the whole thing!
2321 if not is_html(first_bytes
):
2322 self
._downloader
.report_warning(
2323 'URL could be a direct video link, returning it as such.')
2330 webpage
= self
._webpage
_read
_content
(
2331 full_response
, url
, video_id
, prefix
=first_bytes
)
2333 self
.report_extraction(video_id
)
2335 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2337 doc
= compat_etree_fromstring(webpage
.encode('utf-8'))
2338 if doc
.tag
== 'rss':
2339 return self
._extract
_rss
(url
, video_id
, doc
)
2340 elif doc
.tag
== 'SmoothStreamingMedia':
2341 info_dict
['formats'] = self
._parse
_ism
_formats
(doc
, url
)
2342 self
._sort
_formats
(info_dict
['formats'])
2344 elif re
.match(r
'^(?:{[^}]+})?smil$', doc
.tag
):
2345 smil
= self
._parse
_smil
(doc
, url
, video_id
)
2346 self
._sort
_formats
(smil
['formats'])
2348 elif doc
.tag
== '{http://xspf.org/ns/0/}playlist':
2349 return self
.playlist_result(
2351 doc
, video_id
, xspf_url
=url
,
2352 xspf_base_url
=compat_str(full_response
.geturl())),
2354 elif re
.match(r
'(?i)^(?:{[^}]+})?MPD$', doc
.tag
):
2355 info_dict
['formats'] = self
._parse
_mpd
_formats
(
2357 mpd_base_url
=compat_str(full_response
.geturl()).rpartition('/')[0],
2359 self
._sort
_formats
(info_dict
['formats'])
2361 elif re
.match(r
'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc
.tag
):
2362 info_dict
['formats'] = self
._parse
_f
4m
_formats
(doc
, url
, video_id
)
2363 self
._sort
_formats
(info_dict
['formats'])
2365 except compat_xml_parse_error
:
2368 # Is it a Camtasia project?
2369 camtasia_res
= self
._extract
_camtasia
(url
, video_id
, webpage
)
2370 if camtasia_res
is not None:
2373 # Sometimes embedded video player is hidden behind percent encoding
2374 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2375 # Unescaping the whole page allows to handle those cases in a generic way
2376 webpage
= compat_urllib_parse_unquote(webpage
)
2378 # it's tempting to parse this further, but you would
2379 # have to take into account all the variations like
2380 # Video Title - Site Name
2381 # Site Name | Video Title
2382 # Video Title - Tagline | Site Name
2383 # and so on and so forth; it's just not practical
2384 video_title
= self
._og
_search
_title
(
2385 webpage
, default
=None) or self
._html
_search
_regex
(
2386 r
'(?s)<title>(.*?)</title>', webpage
, 'video title',
2389 # Try to detect age limit automatically
2390 age_limit
= self
._rta
_search
(webpage
)
2391 # And then there are the jokers who advertise that they use RTA,
2392 # but actually don't.
2393 AGE_LIMIT_MARKERS
= [
2394 r
'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2396 if any(re
.search(marker
, webpage
) for marker
in AGE_LIMIT_MARKERS
):
2399 # video uploader is domain name
2400 video_uploader
= self
._search
_regex
(
2401 r
'^(?:https?://)?([^/]*)/.*', url
, 'video uploader')
2403 video_description
= self
._og
_search
_description
(webpage
, default
=None)
2404 video_thumbnail
= self
._og
_search
_thumbnail
(webpage
, default
=None)
2407 'title': video_title
,
2408 'description': video_description
,
2409 'thumbnail': video_thumbnail
,
2410 'age_limit': age_limit
,
2413 # Look for Brightcove Legacy Studio embeds
2414 bc_urls
= BrightcoveLegacyIE
._extract
_brightcove
_urls
(webpage
)
2418 'url': smuggle_url(bc_url
, {'Referer': url
}),
2419 'ie_key': 'BrightcoveLegacy'
2420 } for bc_url
in bc_urls
]
2423 '_type': 'playlist',
2424 'title': video_title
,
2429 # Look for Brightcove New Studio embeds
2430 bc_urls
= BrightcoveNewIE
._extract
_urls
(self
, webpage
)
2432 return self
.playlist_from_matches(
2433 bc_urls
, video_id
, video_title
,
2434 getter
=lambda x
: smuggle_url(x
, {'referrer': url
}),
2437 # Look for Nexx embeds
2438 nexx_urls
= NexxIE
._extract
_urls
(webpage
)
2440 return self
.playlist_from_matches(nexx_urls
, video_id
, video_title
, ie
=NexxIE
.ie_key())
2442 # Look for Nexx iFrame embeds
2443 nexx_embed_urls
= NexxEmbedIE
._extract
_urls
(webpage
)
2445 return self
.playlist_from_matches(nexx_embed_urls
, video_id
, video_title
, ie
=NexxEmbedIE
.ie_key())
2447 # Look for ThePlatform embeds
2448 tp_urls
= ThePlatformIE
._extract
_urls
(webpage
)
2450 return self
.playlist_from_matches(tp_urls
, video_id
, video_title
, ie
='ThePlatform')
2452 # Look for Vessel embeds
2453 vessel_urls
= VesselIE
._extract
_urls
(webpage
)
2455 return self
.playlist_from_matches(vessel_urls
, video_id
, video_title
, ie
=VesselIE
.ie_key())
2457 # Look for embedded rtl.nl player
2458 matches
= re
.findall(
2459 r
'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2462 return self
.playlist_from_matches(matches
, video_id
, video_title
, ie
='RtlNl')
2464 vimeo_urls
= VimeoIE
._extract
_urls
(url
, webpage
)
2466 return self
.playlist_from_matches(vimeo_urls
, video_id
, video_title
, ie
=VimeoIE
.ie_key())
2468 vid_me_embed_url
= self
._search
_regex
(
2469 r
'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2470 webpage, 'vid.me embed', default=None)
2471 if vid_me_embed_url is not None:
2472 return self.url_result(vid_me_embed_url, 'Vidme')
2474 # Look for YouTube embeds
2475 youtube_urls = YoutubeIE._extract_urls(webpage)
2477 return self.playlist_from_matches(
2478 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2480 matches = DailymotionIE._extract_urls(webpage)
2482 return self.playlist_from_matches(matches, video_id, video_title)
2484 # Look for embedded Dailymotion playlist player (#3822)
2486 r'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:www\
.)?dailymotion\
.[a
-z
]{2,3}/widget
/jukebox
\?.+?
)\
1', webpage)
2488 playlists = re.findall(
2489 r'list\
[\
]=/playlist
/([^
/]+)/', unescapeHTML(m.group('url
')))
2491 return self.playlist_from_matches(
2492 playlists, video_id, video_title, lambda p: '//dailymotion
.com
/playlist
/%s' % p)
2494 # Look for DailyMail embeds
2495 dailymail_urls = DailyMailIE._extract_urls(webpage)
2497 return self.playlist_from_matches(
2498 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2500 # Look for embedded Wistia player
2501 wistia_url = WistiaIE._extract_url(webpage)
2504 '_type
': 'url_transparent
',
2505 'url
': self._proto_relative_url(wistia_url),
2506 'ie_key
': WistiaIE.ie_key(),
2507 'uploader
': video_uploader,
2510 # Look for SVT player
2511 svt_url = SVTIE._extract_url(webpage)
2513 return self.url_result(svt_url, 'SVT
')
2515 # Look for Bandcamp pages with custom domain
2516 mobj = re.search(r'<meta
property="og:url"[^
>]*?content
="(.*?bandcamp\.com.*?)"', webpage)
2517 if mobj is not None:
2518 burl = unescapeHTML(mobj.group(1))
2519 # Don't
set the extractor because it can be a track url
or an album
2520 return self
.url_result(burl
)
2522 # Look for embedded Vevo player
2524 r
'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:cache\
.)?vevo\
.com
/.+?
)\
1', webpage)
2525 if mobj is not None:
2526 return self.url_result(mobj.group('url
'))
2528 # Look for embedded Viddler player
2530 r'<(?
:iframe
[^
>]+?src|param
[^
>]+?value
)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2532 if mobj is not None:
2533 return self.url_result(mobj.group('url'))
2535 # Look for NYTimes player
2537 r'<iframe[^>]+src=(["\'])(?P
<url
>(?
:https?
:)?
//graphics8\
.nytimes\
.com
/bcvideo
/[^
/]+/iframe
/embed\
.html
.+?
)\
1>',
2539 if mobj is not None:
2540 return self.url_result(mobj.group('url
'))
2542 # Look for Libsyn player
2544 r'<iframe
[^
>]+src
=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2545 if mobj is not None:
2546 return self.url_result(mobj.group('url'))
2548 # Look for Ooyala videos
2549 mobj = (re.search(r'player\.ooyala\.com/[^"?
]+[?
#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2550 re
.search(r
'OO\.Player\.create\([\'"].*?[\'"],\s
*[\'"](?P<ec>.{32})[\'"]', webpage) or
2551 re.search(r'OO\
.Player\
.create\
.apply\
(\s
*OO\
.Player\s
*,\s
*op\
(\s
*\
[\s
*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P
<ec
>.{32}
)[\'"]', webpage) or
2552 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P
<ec
>.{32}
)[\'"]\)', webpage) or
2553 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P
<ec
>.{32}
)[\'"]', webpage))
2554 if mobj is not None:
2555 embed_token = self._search_regex(
2556 r'embedToken[\'"]?\s
*:\s
*[\'"]([^\'"]+)',
2557 webpage, 'ooyala embed token
', default=None)
2558 return OoyalaIE._build_url_result(smuggle_url(
2561 'embed_token
': embed_token,
2564 # Look for multiple Ooyala embeds on SBN network websites
2565 mobj = re.search(r'SBN\
.VideoLinkset\
.entryGroup\
((\
[.*?\
])', webpage)
2566 if mobj is not None:
2567 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2569 return self.playlist_from_matches(
2570 embeds, video_id, video_title,
2571 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id
'], {'domain
': url})), ie='Ooyala
')
2573 # Look for Aparat videos
2574 mobj = re.search(r'<iframe
.*?src
="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2575 if mobj is not None:
2576 return self.url_result(mobj.group(1), 'Aparat')
2578 # Look for MPORA videos
2579 mobj = re.search(r'<iframe .*?src="(http
://mpora\
.(?
:com|de
)/videos
/[^
"]+)"', webpage)
2580 if mobj is not None:
2581 return self.url_result(mobj.group(1), 'Mpora
')
2583 # Look for embedded NovaMov-based player
2585 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2586 (?P<url>http://(?:(?:embed|www)\.)?
2588 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2589 videoweed\.(?:es|com)|
2590 movshare\.(?:net|sx|ag)|
2591 divxstage\.(?:eu|net|ch|co|at|ag))
2592 /embed\.php.+?)\1''', webpage)
2593 if mobj is not None:
2594 return self.url_result(mobj.group('url
'))
2596 # Look for embedded Facebook player
2597 facebook_urls = FacebookIE._extract_urls(webpage)
2599 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2601 # Look for embedded VK player
2602 mobj = re.search(r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2603 if mobj is not None:
2604 return self.url_result(mobj.group('url'), 'VK')
2606 # Look for embedded Odnoklassniki player
2607 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://(?
:odnoklassniki|ok
)\
.ru
/videoembed
/.+?
)\
1', webpage)
2608 if mobj is not None:
2609 return self.url_result(mobj.group('url
'), 'Odnoklassniki
')
2611 # Look for embedded ivi player
2612 mobj = re.search(r'<embed
[^
>]+?src
=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2613 if mobj is not None:
2614 return self.url_result(mobj.group('url'), 'Ivi')
2616 # Look for embedded Huffington Post player
2618 r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://embed\
.live\
.huffingtonpost\
.com
/.+?
)\
1', webpage)
2619 if mobj is not None:
2620 return self.url_result(mobj.group('url
'), 'HuffPost
')
2623 mobj = re.search(r'class=["\']embedly-card["\'][^
>]href
=["\'](?P<url>[^"\']+)', webpage)
2624 if mobj is not None:
2625 return self.url_result(mobj.group('url
'))
2626 mobj = re.search(r'class=["\']embedly-embed["\'][^
>]src
=["\'][^"\']*url
=(?P
<url
>[^
&]+)', webpage)
2627 if mobj is not None:
2628 return self.url_result(compat_urllib_parse_unquote(mobj.group('url
')))
2630 # Look for funnyordie embed
2631 matches = re.findall(r'<iframe
[^
>]+?src
="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2633 return self.playlist_from_matches(
2634 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2636 # Look for BBC iPlayer embed
2637 matches = re.findall(r'setPlaylist\("(https?
://www\
.bbc\
.co\
.uk
/iplayer
/[^
/]+/[\da
-z
]{8}
)"\)', webpage)
2639 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2641 # Look for embedded RUTV player
2642 rutv_url = RUTVIE._extract_url(webpage)
2644 return self.url_result(rutv_url, 'RUTV')
2646 # Look for embedded TVC player
2647 tvc_url = TVCIE._extract_url(webpage)
2649 return self.url_result(tvc_url, 'TVC')
2651 # Look for embedded SportBox player
2652 sportbox_urls = SportBoxIE._extract_urls(webpage)
2654 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
2656 # Look for embedded XHamster player
2657 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2659 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2661 # Look for embedded TNAFlixNetwork player
2662 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2664 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2666 # Look for embedded PornHub player
2667 pornhub_urls = PornHubIE._extract_urls(webpage)
2669 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2671 # Look for embedded DrTuber player
2672 drtuber_urls = DrTuberIE._extract_urls(webpage)
2674 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2676 # Look for embedded RedTube player
2677 redtube_urls = RedTubeIE._extract_urls(webpage)
2679 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2681 # Look for embedded Tube8 player
2682 tube8_urls = Tube8IE._extract_urls(webpage)
2684 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2686 # Look for embedded Tvigle player
2688 r'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
:)?
//cloud\
.tvigle\
.ru
/video
/.+?
)\
1', webpage)
2689 if mobj is not None:
2690 return self.url_result(mobj.group('url
'), 'Tvigle
')
2692 # Look for embedded TED player
2694 r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2695 if mobj is not None:
2696 return self.url_result(mobj.group('url'), 'TED')
2698 # Look for embedded Ustream videos
2699 ustream_url = UstreamIE._extract_url(webpage)
2701 return self.url_result(ustream_url, UstreamIE.ie_key())
2703 # Look for embedded arte.tv player
2705 r'<(?:script|iframe) [^>]*?src="(?P
<url
>http
://www\
.arte\
.tv
/(?
:playerv2
/embed|arte_vp
/index
)[^
"]+)"',
2707 if mobj is not None:
2708 return self.url_result(mobj.group('url
'), 'ArteTVEmbed
')
2710 # Look for embedded francetv player
2712 r'<iframe
[^
>]+?src
=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2714 if mobj is not None:
2715 return self.url_result(mobj.group('url'))
2717 # Look for embedded smotri.com player
2718 smotri_url = SmotriIE._extract_url(webpage)
2720 return self.url_result(smotri_url, 'Smotri')
2722 # Look for embedded Myvi.ru player
2723 myvi_url = MyviIE._extract_url(webpage)
2725 return self.url_result(myvi_url)
2727 # Look for embedded soundcloud player
2728 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2730 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2732 # Look for tunein player
2733 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2735 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2737 # Look for embedded mtvservices player
2738 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2740 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2742 # Look for embedded yahoo player
2744 r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://(?
:screen|movies
)\
.yahoo\
.com
/.+?\
.html
\?format
=embed
)\
1',
2746 if mobj is not None:
2747 return self.url_result(mobj.group('url
'), 'Yahoo
')
2749 # Look for embedded sbs.com.au player
2753 <meta\s+property="og:video"\s+content=|
2756 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2758 if mobj is not None:
2759 return self.url_result(mobj.group('url
'), 'SBS
')
2761 # Look for embedded Cinchcast player
2763 r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2765 if mobj is not None:
2766 return self.url_result(mobj.group('url'), 'Cinchcast')
2769 r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://m(?
:lb
)?\
.mlb\
.com
/shared
/video
/embed
/embed\
.html
\?.+?
)\
1',
2773 r'data
-video
-link
=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2775 if mobj is not None:
2776 return self.url_result(mobj.group('url
'), 'MLB
')
2779 r'<(?
:iframe|script
)[^
>]+?src
=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2781 if mobj is not None:
2782 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2785 r'<iframe[^>]+src="(?P
<url
>https?
://(?
:new\
.)?livestream\
.com
/[^
"]+/player[^"]+)"',
2787 if mobj is not None:
2788 return self.url_result(mobj.group('url'), 'Livestream')
2790 # Look for Zapiks embed
2792 r'<iframe[^>]+src="(?P
<url
>https?
://(?
:www\
.)?zapiks\
.fr
/index\
.php
\?.+?
)"', webpage)
2793 if mobj is not None:
2794 return self.url_result(mobj.group('url'), 'Zapiks')
2796 # Look for Kaltura embeds
2797 kaltura_url = KalturaIE._extract_url(webpage)
2799 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2801 # Look for EaglePlatform embeds
2802 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2803 if eagleplatform_url:
2804 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2806 # Look for ClipYou (uses EaglePlatform) embeds
2808 r'<iframe[^>]+src="https?
://(?P
<host
>media\
.clipyou\
.ru
)/index
/player
\?.*\brecord
_id
=(?P
<id>\d
+).*"', webpage)
2809 if mobj is not None:
2810 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2812 # Look for Pladform embeds
2813 pladform_url = PladformIE._extract_url(webpage)
2815 return self.url_result(pladform_url)
2817 # Look for Videomore embeds
2818 videomore_url = VideomoreIE._extract_url(webpage)
2820 return self.url_result(videomore_url)
2822 # Look for Webcaster embeds
2823 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2825 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2827 # Look for Playwire embeds
2829 r'<script[^>]+data-config=(["\'])(?P
<url
>(?
:https?
:)?
//config\
.playwire\
.com
/.+?
)\
1', webpage)
2830 if mobj is not None:
2831 return self.url_result(mobj.group('url
'))
2833 # Look for 5min embeds
2835 r'<meta
[^
>]+property="og:video"[^
>]+content
="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2836 if mobj is not None:
2837 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2839 # Look for Crooks and Liars embeds
2841 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P
<url
>(?
:https?
:)?
//embed\
.crooksandliars\
.com
/(?
:embed|v
)/.+?
)\
1', webpage)
2842 if mobj is not None:
2843 return self.url_result(mobj.group('url
'))
2845 # Look for NBC Sports VPlayer embeds
2846 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2848 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer
')
2850 # Look for NBC News embeds
2851 nbc_news_embed_url = re.search(
2852 r'<iframe
[^
>]+src
=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\
1', webpage)
2853 if nbc_news_embed_url:
2854 return self.url_result(nbc_news_embed_url.group('url
'), 'NBCNews
')
2856 # Look for Google Drive embeds
2857 google_drive_url = GoogleDriveIE._extract_url(webpage)
2858 if google_drive_url:
2859 return self.url_result(google_drive_url, 'GoogleDrive
')
2861 # Look for UDN embeds
2863 r'<iframe
[^
>]+src
="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2864 if mobj is not None:
2865 return self.url_result(
2866 compat_urlparse.urljoin(url, mobj.group('url
')), 'UDNEmbed
')
2868 # Look for Senate ISVP iframe
2869 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2871 return self.url_result(senate_isvp_url, 'SenateISVP
')
2873 # Look for OnionStudios embeds
2874 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2875 if onionstudios_url:
2876 return self.url_result(onionstudios_url)
2878 # Look for ViewLift embeds
2879 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2881 return self.url_result(viewlift_url)
2883 # Look for JWPlatform embeds
2884 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2886 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2888 # Look for Digiteka embeds
2889 digiteka_url = DigitekaIE._extract_url(webpage)
2891 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2893 # Look for Arkena embeds
2894 arkena_url = ArkenaIE._extract_url(webpage)
2896 return self.url_result(arkena_url, ArkenaIE.ie_key())
2898 # Look for Piksel embeds
2899 piksel_url = PikselIE._extract_url(webpage)
2901 return self.url_result(piksel_url, PikselIE.ie_key())
2903 # Look for Limelight embeds
2904 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2906 return self.playlist_result(
2907 limelight_urls, video_id, video_title, video_description)
2909 # Look for Anvato embeds
2910 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2912 return self.playlist_result(
2913 anvato_urls, video_id, video_title, video_description)
2915 # Look for AdobeTVVideo embeds
2917 r'<iframe
[^
>]+src
=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2919 if mobj is not None:
2920 return self.url_result(
2921 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2924 # Look for Vine embeds
2926 r'<iframe[^>]+src=[\'"]((?
:https?
:)?
//(?
:www\
.)?vine\
.co
/v
/[^
/]+/embed
/(?
:simple|postcard
))',
2928 if mobj is not None:
2929 return self.url_result(
2930 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine
')
2932 # Look for VODPlatform embeds
2934 r'<iframe
[^
>]+src
=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2936 if mobj is not None:
2937 return self.url_result(
2938 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2940 # Look for Mangomolo embeds
2942 r'''(?x)<iframe[^>]+src=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:www\
.)?admin\
.mangomolo\
.com
/analytics
/index\
.php
/customers
/embed
/
2944 video
\?.*?
\bid
=(?P
<video_id
>\d
+)|
2945 index
\?.*?
\bchannelid
=(?P
<channel_id
>(?
:[A
-Za
-z0
-9+/=]|
%2B|
%2F|
%3D
)+)
2946 ).+?
)\
1''', webpage)
2947 if mobj is not None:
2949 '_type': 'url_transparent',
2950 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2951 'title': video_title,
2952 'description': video_description,
2953 'thumbnail': video_thumbnail,
2954 'uploader': video_uploader,
2956 video_id = mobj.group('video_id')
2959 'ie_key': 'MangomoloVideo',
2964 'ie_key': 'MangomoloLive',
2965 'id': mobj.group('channel_id'),
2969 # Look for Instagram embeds
2970 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2971 if instagram_embed_url is not None:
2972 return self.url_result(
2973 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2975 # Look for LiveLeak embeds
2976 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2978 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2980 # Look for 3Q SDN embeds
2981 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2984 '_type': 'url_transparent',
2985 'ie_key': ThreeQSDNIE.ie_key(),
2986 'url': self._proto_relative_url(threeqsdn_url),
2987 'title': video_title,
2988 'description': video_description,
2989 'thumbnail': video_thumbnail,
2990 'uploader': video_uploader,
2993 # Look for VBOX7 embeds
2994 vbox7_url = Vbox7IE._extract_url(webpage)
2996 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2998 # Look for DBTV embeds
2999 dbtv_urls = DBTVIE._extract_urls(webpage)
3001 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
3003 # Look for Videa embeds
3004 videa_urls = VideaIE._extract_urls(webpage)
3006 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
3008 # Look for 20 minuten embeds
3009 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3011 return self.playlist_from_matches(
3012 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3014 # Look for Openload embeds
3015 openload_urls = OpenloadIE._extract_urls(webpage)
3017 return self.playlist_from_matches(
3018 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
3020 # Look for VideoPress embeds
3021 videopress_urls = VideoPressIE._extract_urls(webpage)
3023 return self.playlist_from_matches(
3024 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3026 # Look for Rutube embeds
3027 rutube_urls = RutubeIE._extract_urls(webpage)
3029 return self.playlist_from_matches(
3030 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3032 # Look for WashingtonPost embeds
3033 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3035 return self.playlist_from_matches(
3036 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3038 # Look for Mediaset embeds
3039 mediaset_urls = MediasetIE._extract_urls(self, webpage)
3041 return self.playlist_from_matches(
3042 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3044 # Look for JOJ.sk embeds
3045 joj_urls = JojIE._extract_urls(webpage)
3047 return self.playlist_from_matches(
3048 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3050 # Look for megaphone.fm embeds
3051 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3053 return self.playlist_from_matches(
3054 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3056 # Look for vzaar embeds
3057 vzaar_urls = VzaarIE._extract_urls(webpage)
3059 return self.playlist_from_matches(
3060 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3062 channel9_urls = Channel9IE._extract_urls(webpage)
3064 return self.playlist_from_matches(
3065 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3067 vshare_urls = VShareIE._extract_urls(webpage)
3069 return self.playlist_from_matches(
3070 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3072 # Look for Mediasite embeds
3073 mediasite_urls = MediasiteIE._extract_urls(webpage)
3076 self.url_result(smuggle_url(
3077 compat_urlparse.urljoin(url, mediasite_url),
3078 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3079 for mediasite_url in mediasite_urls]
3080 return self.playlist_result(entries, video_id, video_title)
3082 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3083 if springboardplatform_urls:
3084 return self.playlist_from_matches(
3085 springboardplatform_urls, video_id, video_title,
3086 ie=SpringboardPlatformIE.ie_key())
3088 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3090 return self.playlist_from_matches(
3091 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3093 vice_urls = ViceIE._extract_urls(webpage)
3095 return self.playlist_from_matches(
3096 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3098 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3100 return self.playlist_from_matches(
3101 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3103 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3104 if cloudflarestream_urls:
3105 return self.playlist_from_matches(
3106 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3108 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3110 return self.playlist_from_matches(
3111 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3113 teachable_url = TeachableIE._extract_url(webpage, url)
3115 return self.url_result(teachable_url)
3117 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3119 return self.playlist_from_matches(
3120 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3122 apa_urls = APAIE._extract_urls(webpage)
3124 return self.playlist_from_matches(
3125 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3127 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3129 return self.playlist_from_matches(
3130 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3132 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3133 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3135 if sharevideos_urls:
3136 return self.playlist_from_matches(
3137 sharevideos_urls, video_id, video_title)
3139 viqeo_urls = ViqeoIE._extract_urls(webpage)
3141 return self.playlist_from_matches(
3142 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3144 expressen_urls = ExpressenIE._extract_urls(webpage)
3146 return self.playlist_from_matches(
3147 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3149 zype_urls = ZypeIE._extract_urls(webpage)
3151 return self.playlist_from_matches(
3152 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3154 # Look for HTML5 media
3155 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3157 if len(entries) == 1:
3160 'title': video_title,
3163 for num, entry in enumerate(entries, start=1):
3165 'id': '%s-%s' % (video_id, num),
3166 'title': '%s (%d)' % (video_title, num),
3168 for entry in entries:
3169 self._sort_formats(entry['formats'])
3170 return self.playlist_result(entries, video_id, video_title)
3172 jwplayer_data = self._find_jwplayer_data(
3173 webpage, video_id, transform_source=js_to_json)
3176 info = self._parse_jwplayer_data(
3177 jwplayer_data, video_id, require_title=False, base_url=url)
3178 return merge_dicts(info, info_dict)
3179 except ExtractorError:
3180 # See https://github.com/rg3/youtube-dl/pull/16735
3185 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3187 if mobj is not None:
3188 sources = self._parse_json(
3189 mobj.group(1), video_id, transform_source=js_to_json,
3191 if not isinstance(sources, list):
3194 for source in sources:
3195 src = source.get('src')
3196 if not src or not isinstance(src, compat_str):
3198 src = compat_urlparse.urljoin(url, src)
3199 src_type = source.get('type')
3200 if isinstance(src_type, compat_str):
3201 src_type = src_type.lower()
3202 ext = determine_ext(src).lower()
3203 if src_type == 'video/youtube':
3204 return self.url_result(src, YoutubeIE.ie_key())
3205 if src_type == 'application/dash+xml' or ext == 'mpd':
3206 formats.extend(self._extract_mpd_formats(
3207 src, video_id, mpd_id='dash', fatal=False))
3208 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3209 formats.extend(self._extract_m3u8_formats(
3210 src, video_id, 'mp4', entry_protocol='m3u8_native',
3211 m3u8_id='hls', fatal=False))
3215 'ext': (mimetype2ext(src_type) or
3216 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3219 self._sort_formats(formats)
3220 info_dict['formats'] = formats
3223 # Looking for http://schema.org/VideoObject
3224 json_ld = self._search_json_ld(
3225 webpage, video_id, default={}, expected_type='VideoObject')
3226 if json_ld.get('url'):
3227 return merge_dicts(json_ld, info_dict)
3229 def check_video(vurl):
3230 if YoutubeIE.suitable(vurl):
3232 if RtmpIE.suitable(vurl):
3234 vpath = compat_urlparse.urlparse(vurl).path
3235 vext = determine_ext(vpath)
3236 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3238 def filter_video(urls):
3239 return list(filter(check_video, urls))
3241 # Start with something easy: JW Player in SWFObject
3242 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3244 # Look for gorilla-vid style embedding
3245 found = filter_video(re.findall(r'''(?sx
)
3249 jwplayer\s
*\
(\s
*["'][^'"]+["']\s*\)\s*\.setup
3252 ['"]?
file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3254 # Broaden the search a little bit
3255 found = filter_video(re.findall(r'[^A
-Za
-z0
-9]?
(?
:file|source
)=(http
[^
\'"&]*)', webpage))
3257 # Broaden the findall a little bit: JWPlayer JS loader
3258 found = filter_video(re.findall(
3259 r'[^A-Za-z0-9]?(?:file|video_url)["\']?
:\s
*["\'](http(?![^\'"]+\
.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3262 found = filter_video(re.findall(r'''(?xs)
3263 flowplayer\("[^
"]+",\s
*
3265 \s
*\
{[^
}]+?
["']?clip["']?\s*:\s*\{\s*
3266 ["']?url
["']?\s*:\s*["']([^"']+)["']
3271 r"cinerama\
.embedPlayer\
(\s
*\'[^
']+\',\s*'([^
']+)'", webpage)
3273 # Try to find twitter cards info
3274 # twitter:player:stream should be checked before twitter:player since
3275 # it is expected to contain a raw stream (see
3276 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3277 found = filter_video(re.findall(
3278 r'<meta (?:property|name)="twitter
:player
:stream
" (?:content|value)="(.+?
)"', webpage))
3280 # We look for Open Graph info:
3281 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3282 m_video_type = re.findall(r'<meta.*?property="og
:video
:type".*?content="video
/(.*?
)"', webpage)
3283 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3284 if m_video_type is not None:
3285 found = filter_video(re.findall(r'<meta.*?property="og
:video
".*?content="(.*?
)"', webpage))
3287 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3289 r'(?i
)<meta\s
+(?
=(?
:[a
-z
-]+="[^"]+"\s+)*http-equiv="refresh
")'
3290 r'(?:[a-z-]+="[^
"]+"\s
+)*?content
="%s' % REDIRECT_REGEX,
3293 # Look also in Refresh HTTP header
3294 refresh_header = head_response.headers.get('Refresh')
3296 # In python 2 response HTTP headers are bytestrings
3297 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3298 refresh_header = refresh_header.decode('iso-8859-1')
3299 found = re.search(REDIRECT_REGEX, refresh_header)
3301 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3303 self.report_following_redirect(new_url)
3312 # twitter:player is a https URL to iframe player that may or may not
3313 # be supported by youtube-dl thus this is checked the very last (see
3314 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3315 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3316 if embed_url and embed_url != url:
3317 return self.url_result(embed_url)
3320 raise UnsupportedError(url)
3323 for video_url in orderedSet(found):
3324 video_url = unescapeHTML(video_url)
3325 video_url = video_url.replace('\\/', '/')
3326 video_url = compat_urlparse.urljoin(url, video_url)
3327 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3329 # Sometimes, jwplayer extraction will result in a YouTube URL
3330 if YoutubeIE.suitable(video_url):
3331 entries.append(self.url_result(video_url, 'Youtube'))
3334 # here's a fun little line of code for you:
3335 video_id = os.path.splitext(video_id)[0]
3339 'uploader': video_uploader,
3340 'title': video_title,
3341 'age_limit': age_limit,
3344 if RtmpIE.suitable(video_url):
3345 entry_info_dict.update({
3346 '_type': 'url_transparent',
3347 'ie_key': RtmpIE.ie_key(),
3350 entries.append(entry_info_dict)
3353 ext = determine_ext(video_url)
3355 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3357 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3359 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3361 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3363 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3364 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3365 # Just matching .ism/manifest is not enough to be reliably sure
3366 # whether it's actually an ISM manifest or some other streaming
3367 # manifest since there are various streaming URL formats
3368 # possible (see [1]) as well as some other shenanigans like
3369 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3371 # Thus the most reasonable way to solve this is to delegate
3372 # to generic extractor in order to look into the contents of
3373 # the manifest itself.
3374 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3375 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3376 entry_info_dict = self.url_result(
3377 smuggle_url(video_url, {'to_generic': True}),
3380 entry_info_dict['url'] = video_url
3382 if entry_info_dict.get('formats'):
3383 self._sort_formats(entry_info_dict['formats'])
3385 entries.append(entry_info_dict)
3387 if len(entries) == 1:
3390 for num, e in enumerate(entries, start=1):
3391 # 'url' results don't have a title
3392 if e.get('title') is not None:
3393 e['title'] = '%s (%d)' % (e['title'], num)
3395 '_type': 'playlist',