]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/generic.py
[fragments] Pad fragments before decrypting (#1298)
[yt-dlp.git] / yt_dlp / extractor / generic.py
1 # coding: utf-8
2
3 from __future__ import unicode_literals
4
5 import os
6 import re
7 import sys
8
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
13 compat_str,
14 compat_urllib_parse_unquote,
15 compat_urlparse,
16 compat_xml_parse_error,
17 )
18 from ..utils import (
19 determine_ext,
20 ExtractorError,
21 float_or_none,
22 HEADRequest,
23 int_or_none,
24 is_html,
25 js_to_json,
26 KNOWN_EXTENSIONS,
27 merge_dicts,
28 mimetype2ext,
29 orderedSet,
30 parse_duration,
31 sanitized_Request,
32 smuggle_url,
33 unescapeHTML,
34 unified_timestamp,
35 unsmuggle_url,
36 UnsupportedError,
37 url_or_none,
38 xpath_attr,
39 xpath_text,
40 xpath_with_ns,
41 )
42 from .commonprotocols import RtmpIE
43 from .brightcove import (
44 BrightcoveLegacyIE,
45 BrightcoveNewIE,
46 )
47 from .nexx import (
48 NexxIE,
49 NexxEmbedIE,
50 )
51 from .nbc import NBCSportsVPlayerIE
52 from .ooyala import OoyalaIE
53 from .rutv import RUTVIE
54 from .tvc import TVCIE
55 from .sportbox import SportBoxIE
56 from .myvi import MyviIE
57 from .condenast import CondeNastIE
58 from .udn import UDNEmbedIE
59 from .senateisvp import SenateISVPIE
60 from .svt import SVTIE
61 from .pornhub import PornHubIE
62 from .xhamster import XHamsterEmbedIE
63 from .tnaflix import TNAFlixNetworkEmbedIE
64 from .drtuber import DrTuberIE
65 from .redtube import RedTubeIE
66 from .tube8 import Tube8IE
67 from .mofosex import MofosexEmbedIE
68 from .spankwire import SpankwireIE
69 from .youporn import YouPornIE
70 from .vimeo import (
71 VimeoIE,
72 VHXEmbedIE,
73 )
74 from .dailymotion import DailymotionIE
75 from .dailymail import DailyMailIE
76 from .onionstudios import OnionStudiosIE
77 from .viewlift import ViewLiftEmbedIE
78 from .mtv import MTVServicesEmbeddedIE
79 from .pladform import PladformIE
80 from .videomore import VideomoreIE
81 from .webcaster import WebcasterFeedIE
82 from .googledrive import GoogleDriveIE
83 from .jwplatform import JWPlatformIE
84 from .digiteka import DigitekaIE
85 from .arkena import ArkenaIE
86 from .instagram import InstagramIE
87 from .threeqsdn import ThreeQSDNIE
88 from .theplatform import ThePlatformIE
89 from .kaltura import KalturaIE
90 from .eagleplatform import EaglePlatformIE
91 from .facebook import FacebookIE
92 from .soundcloud import SoundcloudEmbedIE
93 from .tunein import TuneInBaseIE
94 from .vbox7 import Vbox7IE
95 from .dbtv import DBTVIE
96 from .piksel import PikselIE
97 from .videa import VideaIE
98 from .twentymin import TwentyMinutenIE
99 from .ustream import UstreamIE
100 from .arte import ArteTVEmbedIE
101 from .videopress import VideoPressIE
102 from .rutube import RutubeIE
103 from .limelight import LimelightBaseIE
104 from .anvato import AnvatoIE
105 from .washingtonpost import WashingtonPostIE
106 from .wistia import WistiaIE
107 from .mediaset import MediasetIE
108 from .joj import JojIE
109 from .megaphone import MegaphoneIE
110 from .vzaar import VzaarIE
111 from .channel9 import Channel9IE
112 from .vshare import VShareIE
113 from .mediasite import MediasiteIE
114 from .springboardplatform import SpringboardPlatformIE
115 from .yapfiles import YapFilesIE
116 from .vice import ViceIE
117 from .xfileshare import XFileShareIE
118 from .cloudflarestream import CloudflareStreamIE
119 from .peertube import PeerTubeIE
120 from .teachable import TeachableIE
121 from .indavideo import IndavideoEmbedIE
122 from .apa import APAIE
123 from .foxnews import FoxNewsIE
124 from .viqeo import ViqeoIE
125 from .expressen import ExpressenIE
126 from .zype import ZypeIE
127 from .odnoklassniki import OdnoklassnikiIE
128 from .vk import VKIE
129 from .kinja import KinjaEmbedIE
130 from .gedidigital import GediDigitalIE
131 from .rcs import RCSEmbedsIE
132 from .bitchute import BitChuteIE
133 from .rumble import RumbleEmbedIE
134 from .arcpublishing import ArcPublishingIE
135 from .medialaan import MedialaanIE
136 from .simplecast import SimplecastIE
137 from .wimtv import WimTVIE
138
139
140 class GenericIE(InfoExtractor):
141 IE_DESC = 'Generic downloader that works on some sites'
142 _VALID_URL = r'.*'
143 IE_NAME = 'generic'
144 _TESTS = [
145 # Direct link to a video
146 {
147 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
148 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
149 'info_dict': {
150 'id': 'trailer',
151 'ext': 'mp4',
152 'title': 'trailer',
153 'upload_date': '20100513',
154 }
155 },
156 # Direct link to media delivered compressed (until Accept-Encoding is *)
157 {
158 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
159 'md5': '128c42e68b13950268b648275386fc74',
160 'info_dict': {
161 'id': 'FictionJunction-Parallel_Hearts',
162 'ext': 'flac',
163 'title': 'FictionJunction-Parallel_Hearts',
164 'upload_date': '20140522',
165 },
166 'expected_warnings': [
167 'URL could be a direct video link, returning it as such.'
168 ],
169 'skip': 'URL invalid',
170 },
171 # Direct download with broken HEAD
172 {
173 'url': 'http://ai-radio.org:8000/radio.opus',
174 'info_dict': {
175 'id': 'radio',
176 'ext': 'opus',
177 'title': 'radio',
178 },
179 'params': {
180 'skip_download': True, # infinite live stream
181 },
182 'expected_warnings': [
183 r'501.*Not Implemented',
184 r'400.*Bad Request',
185 ],
186 },
187 # Direct link with incorrect MIME type
188 {
189 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
190 'md5': '4ccbebe5f36706d85221f204d7eb5913',
191 'info_dict': {
192 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
193 'id': '5_Lennart_Poettering_-_Systemd',
194 'ext': 'webm',
195 'title': '5_Lennart_Poettering_-_Systemd',
196 'upload_date': '20141120',
197 },
198 'expected_warnings': [
199 'URL could be a direct video link, returning it as such.'
200 ]
201 },
202 # RSS feed
203 {
204 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
205 'info_dict': {
206 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
207 'title': 'Zero Punctuation',
208 'description': 're:.*groundbreaking video review series.*'
209 },
210 'playlist_mincount': 11,
211 },
212 # RSS feed with enclosure
213 {
214 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
215 'info_dict': {
216 'id': 'http://podcastfeeds.nbcnews.com/nbcnews/video/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
217 'title': 'MSNBC Rachel Maddow (video)',
218 'description': 're:.*her unique approach to storytelling.*',
219 },
220 'playlist': [{
221 'info_dict': {
222 'ext': 'mov',
223 'id': 'pdv_maddow_netcast_mov-12-03-2020-223726',
224 'title': 'MSNBC Rachel Maddow (video) - 12-03-2020-223726',
225 'description': 're:.*her unique approach to storytelling.*',
226 'upload_date': '20201204',
227 },
228 }],
229 },
230 # RSS feed with item with description and thumbnails
231 {
232 'url': 'https://anchor.fm/s/dd00e14/podcast/rss',
233 'info_dict': {
234 'id': 'https://anchor.fm/s/dd00e14/podcast/rss',
235 'title': 're:.*100% Hydrogen.*',
236 'description': 're:.*In this episode.*',
237 },
238 'playlist': [{
239 'info_dict': {
240 'ext': 'm4a',
241 'id': 'c1c879525ce2cb640b344507e682c36d',
242 'title': 're:Hydrogen!',
243 'description': 're:.*In this episode we are going.*',
244 'timestamp': 1567977776,
245 'upload_date': '20190908',
246 'duration': 459,
247 'thumbnail': r're:^https?://.*\.jpg$',
248 'episode_number': 1,
249 'season_number': 1,
250 'age_limit': 0,
251 },
252 }],
253 'params': {
254 'skip_download': True,
255 },
256 },
257 # RSS feed with enclosures and unsupported link URLs
258 {
259 'url': 'http://www.hellointernet.fm/podcast?format=rss',
260 'info_dict': {
261 'id': 'http://www.hellointernet.fm/podcast?format=rss',
262 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
263 'title': 'Hello Internet',
264 },
265 'playlist_mincount': 100,
266 },
267 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
268 {
269 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
270 'info_dict': {
271 'id': 'smil',
272 'ext': 'mp4',
273 'title': 'Automatics, robotics and biocybernetics',
274 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
275 'upload_date': '20130627',
276 'formats': 'mincount:16',
277 'subtitles': 'mincount:1',
278 },
279 'params': {
280 'force_generic_extractor': True,
281 'skip_download': True,
282 },
283 },
284 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
285 {
286 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
287 'info_dict': {
288 'id': 'hds',
289 'ext': 'flv',
290 'title': 'hds',
291 'formats': 'mincount:1',
292 },
293 'params': {
294 'skip_download': True,
295 },
296 },
297 # SMIL from https://www.restudy.dk/video/play/id/1637
298 {
299 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
300 'info_dict': {
301 'id': 'video_1637',
302 'ext': 'flv',
303 'title': 'video_1637',
304 'formats': 'mincount:3',
305 },
306 'params': {
307 'skip_download': True,
308 },
309 },
310 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
311 {
312 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
313 'info_dict': {
314 'id': 'smil-service',
315 'ext': 'flv',
316 'title': 'smil-service',
317 'formats': 'mincount:1',
318 },
319 'params': {
320 'skip_download': True,
321 },
322 },
323 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
324 {
325 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
326 'info_dict': {
327 'id': '4719370',
328 'ext': 'mp4',
329 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
330 'formats': 'mincount:3',
331 },
332 'params': {
333 'skip_download': True,
334 },
335 },
336 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
337 {
338 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
339 'info_dict': {
340 'id': 'mZlp2ctYIUEB',
341 'ext': 'mp4',
342 'title': 'Tikibad ontruimd wegens brand',
343 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
344 'thumbnail': r're:^https?://.*\.jpg$',
345 'duration': 33,
346 },
347 'params': {
348 'skip_download': True,
349 },
350 },
351 # MPD from http://dash-mse-test.appspot.com/media.html
352 {
353 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
354 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
355 'info_dict': {
356 'id': 'car-20120827-manifest',
357 'ext': 'mp4',
358 'title': 'car-20120827-manifest',
359 'formats': 'mincount:9',
360 'upload_date': '20130904',
361 },
362 'params': {
363 'format': 'bestvideo',
364 },
365 },
366 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
367 {
368 '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',
369 'info_dict': {
370 'id': 'content',
371 'ext': 'mp4',
372 'title': 'content',
373 'formats': 'mincount:8',
374 },
375 'params': {
376 # m3u8 downloads
377 'skip_download': True,
378 },
379 'skip': 'video gone',
380 },
381 # m3u8 served with Content-Type: text/plain
382 {
383 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
384 'info_dict': {
385 'id': 'index',
386 'ext': 'mp4',
387 'title': 'index',
388 'upload_date': '20140720',
389 'formats': 'mincount:11',
390 },
391 'params': {
392 # m3u8 downloads
393 'skip_download': True,
394 },
395 'skip': 'video gone',
396 },
397 # google redirect
398 {
399 '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',
400 'info_dict': {
401 'id': 'cmQHVoWB5FY',
402 'ext': 'mp4',
403 'upload_date': '20130224',
404 'uploader_id': 'TheVerge',
405 'description': r're:^Chris Ziegler takes a look at the\.*',
406 'uploader': 'The Verge',
407 'title': 'First Firefox OS phones side-by-side',
408 },
409 'params': {
410 'skip_download': False,
411 }
412 },
413 {
414 # redirect in Refresh HTTP header
415 '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',
416 'info_dict': {
417 'id': 'pO8h3EaFRdo',
418 'ext': 'mp4',
419 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
420 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
421 'upload_date': '20150917',
422 'uploader_id': 'brtvofficial',
423 'uploader': 'Boiler Room',
424 },
425 'params': {
426 'skip_download': False,
427 },
428 },
429 {
430 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
431 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
432 'info_dict': {
433 'id': '13601338388002',
434 'ext': 'mp4',
435 'uploader': 'www.hodiho.fr',
436 'title': 'R\u00e9gis plante sa Jeep',
437 }
438 },
439 # bandcamp page with custom domain
440 {
441 'add_ie': ['Bandcamp'],
442 'url': 'http://bronyrock.com/track/the-pony-mash',
443 'info_dict': {
444 'id': '3235767654',
445 'ext': 'mp3',
446 'title': 'The Pony Mash',
447 'uploader': 'M_Pallante',
448 },
449 'skip': 'There is a limit of 200 free downloads / month for the test song',
450 },
451 {
452 # embedded brightcove video
453 # it also tests brightcove videos that need to set the 'Referer'
454 # in the http requests
455 'add_ie': ['BrightcoveLegacy'],
456 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
457 'info_dict': {
458 'id': '2765128793001',
459 'ext': 'mp4',
460 'title': 'Le cours de bourse : l’analyse technique',
461 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
462 'uploader': 'BFM BUSINESS',
463 },
464 'params': {
465 'skip_download': True,
466 },
467 },
468 {
469 # embedded with itemprop embedURL and video id spelled as `idVideo`
470 'add_id': ['BrightcoveLegacy'],
471 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
472 'info_dict': {
473 'id': '5255628253001',
474 'ext': 'mp4',
475 'title': 'md5:37c519b1128915607601e75a87995fc0',
476 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
477 'uploader': 'BFM BUSINESS',
478 'uploader_id': '876450612001',
479 'timestamp': 1482255315,
480 'upload_date': '20161220',
481 },
482 'params': {
483 'skip_download': True,
484 },
485 },
486 {
487 # https://github.com/ytdl-org/youtube-dl/issues/2253
488 'url': 'http://bcove.me/i6nfkrc3',
489 'md5': '0ba9446db037002366bab3b3eb30c88c',
490 'info_dict': {
491 'id': '3101154703001',
492 'ext': 'mp4',
493 'title': 'Still no power',
494 'uploader': 'thestar.com',
495 '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.',
496 },
497 'add_ie': ['BrightcoveLegacy'],
498 'skip': 'video gone',
499 },
500 {
501 'url': 'http://www.championat.com/video/football/v/87/87499.html',
502 'md5': 'fb973ecf6e4a78a67453647444222983',
503 'info_dict': {
504 'id': '3414141473001',
505 'ext': 'mp4',
506 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
507 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
508 'uploader': 'Championat',
509 },
510 },
511 {
512 # https://github.com/ytdl-org/youtube-dl/issues/3541
513 'add_ie': ['BrightcoveLegacy'],
514 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
515 'info_dict': {
516 'id': '3866516442001',
517 'ext': 'mp4',
518 'title': 'Leer mij vrouwen kennen: Aflevering 1',
519 'description': 'Leer mij vrouwen kennen: Aflevering 1',
520 'uploader': 'SBS Broadcasting',
521 },
522 'skip': 'Restricted to Netherlands',
523 'params': {
524 'skip_download': True, # m3u8 download
525 },
526 },
527 {
528 # Brightcove video in <iframe>
529 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
530 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
531 'info_dict': {
532 'id': '5360463607001',
533 'ext': 'mp4',
534 'title': '叙利亚失明儿童在废墟上演唱《心跳》 呼吁获得正常童年生活',
535 'description': '联合国儿童基金会中东和北非区域大使、作曲家扎德·迪拉尼(Zade Dirani)在3月15日叙利亚冲突爆发7周年纪念日之际发布了为叙利亚谱写的歌曲《心跳》(HEARTBEAT),为受到六年冲突影响的叙利亚儿童发出强烈呐喊,呼吁世界做出共同努力,使叙利亚儿童重新获得享有正常童年生活的权利。',
536 'uploader': 'United Nations',
537 'uploader_id': '1362235914001',
538 'timestamp': 1489593889,
539 'upload_date': '20170315',
540 },
541 'add_ie': ['BrightcoveLegacy'],
542 },
543 {
544 # Brightcove with alternative playerID key
545 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
546 'info_dict': {
547 'id': 'nmeth.2062_SV1',
548 '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',
549 },
550 'playlist': [{
551 'info_dict': {
552 'id': '2228375078001',
553 'ext': 'mp4',
554 'title': 'nmeth.2062-sv1',
555 'description': 'nmeth.2062-sv1',
556 'timestamp': 1363357591,
557 'upload_date': '20130315',
558 'uploader': 'Nature Publishing Group',
559 'uploader_id': '1964492299001',
560 },
561 }],
562 },
563 {
564 # Brightcove with UUID in videoPlayer
565 'url': 'http://www8.hp.com/cn/zh/home.html',
566 'info_dict': {
567 'id': '5255815316001',
568 'ext': 'mp4',
569 'title': 'Sprocket Video - China',
570 'description': 'Sprocket Video - China',
571 'uploader': 'HP-Video Gallery',
572 'timestamp': 1482263210,
573 'upload_date': '20161220',
574 'uploader_id': '1107601872001',
575 },
576 'params': {
577 'skip_download': True, # m3u8 download
578 },
579 'skip': 'video rotates...weekly?',
580 },
581 {
582 # Brightcove:new type [2].
583 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
584 'md5': '2b35148fcf48da41c9fb4591650784f3',
585 'info_dict': {
586 'id': '5348741021001',
587 'ext': 'mp4',
588 'upload_date': '20170306',
589 'uploader_id': '4191638492001',
590 'timestamp': 1488769918,
591 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
592
593 },
594 },
595 {
596 # Alternative brightcove <video> attributes
597 '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/',
598 'info_dict': {
599 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
600 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
601 },
602 'playlist': [{
603 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
604 'info_dict': {
605 'id': '5311302538001',
606 'ext': 'mp4',
607 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
608 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
609 'timestamp': 1486321708,
610 'upload_date': '20170205',
611 'uploader_id': '800000640001',
612 },
613 'only_matching': True,
614 }],
615 },
616 {
617 # Brightcove with UUID in videoPlayer
618 'url': 'http://www8.hp.com/cn/zh/home.html',
619 'info_dict': {
620 'id': '5255815316001',
621 'ext': 'mp4',
622 'title': 'Sprocket Video - China',
623 'description': 'Sprocket Video - China',
624 'uploader': 'HP-Video Gallery',
625 'timestamp': 1482263210,
626 'upload_date': '20161220',
627 'uploader_id': '1107601872001',
628 },
629 'params': {
630 'skip_download': True, # m3u8 download
631 },
632 },
633 # ooyala video
634 {
635 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
636 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
637 'info_dict': {
638 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
639 'ext': 'mp4',
640 'title': '2cc213299525360.mov', # that's what we get
641 'duration': 238.231,
642 },
643 'add_ie': ['Ooyala'],
644 },
645 {
646 # ooyala video embedded with http://player.ooyala.com/iframe.js
647 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
648 'info_dict': {
649 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
650 'ext': 'mp4',
651 'title': '"Steve Jobs: Man in the Machine" trailer',
652 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
653 'duration': 135.427,
654 },
655 'params': {
656 'skip_download': True,
657 },
658 'skip': 'movie expired',
659 },
660 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
661 {
662 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
663 'info_dict': {
664 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
665 'ext': 'mp4',
666 'title': 'Steampunk Fest Comes to Honesdale',
667 'duration': 43.276,
668 },
669 'params': {
670 'skip_download': True,
671 }
672 },
673 # embed.ly video
674 {
675 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
676 'info_dict': {
677 'id': '9ODmcdjQcHQ',
678 'ext': 'mp4',
679 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
680 'upload_date': '20140225',
681 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
682 'uploader': 'Tested',
683 'uploader_id': 'testedcom',
684 },
685 # No need to test YoutubeIE here
686 'params': {
687 'skip_download': True,
688 },
689 },
690 # funnyordie embed
691 {
692 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
693 'info_dict': {
694 'id': '18e820ec3f',
695 'ext': 'mp4',
696 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
697 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
698 },
699 # HEAD requests lead to endless 301, while GET is OK
700 'expected_warnings': ['301'],
701 },
702 # RUTV embed
703 {
704 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
705 'info_dict': {
706 'id': '776940',
707 'ext': 'mp4',
708 'title': 'Охотское море стало целиком российским',
709 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
710 },
711 'params': {
712 # m3u8 download
713 'skip_download': True,
714 },
715 },
716 # TVC embed
717 {
718 '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/',
719 'info_dict': {
720 'id': '55304',
721 'ext': 'mp4',
722 'title': 'Дошкольное воспитание',
723 },
724 },
725 # SportBox embed
726 {
727 'url': 'http://www.vestifinance.ru/articles/25753',
728 'info_dict': {
729 'id': '25753',
730 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
731 },
732 'playlist': [{
733 'info_dict': {
734 'id': '370908',
735 'title': 'Госзаказ. День 3',
736 'ext': 'mp4',
737 }
738 }, {
739 'info_dict': {
740 'id': '370905',
741 'title': 'Госзаказ. День 2',
742 'ext': 'mp4',
743 }
744 }, {
745 'info_dict': {
746 'id': '370902',
747 'title': 'Госзаказ. День 1',
748 'ext': 'mp4',
749 }
750 }],
751 'params': {
752 # m3u8 download
753 'skip_download': True,
754 },
755 },
756 # Myvi.ru embed
757 {
758 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
759 'info_dict': {
760 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
761 'ext': 'mp4',
762 'title': 'Ужастики, русский трейлер (2015)',
763 'thumbnail': r're:^https?://.*\.jpg$',
764 'duration': 153,
765 }
766 },
767 # XHamster embed
768 {
769 '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',
770 'info_dict': {
771 'id': 'showthread',
772 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
773 },
774 'playlist_mincount': 7,
775 # This forum does not allow <iframe> syntaxes anymore
776 # Now HTML tags are displayed as-is
777 'skip': 'No videos on this page',
778 },
779 # Embedded TED video
780 {
781 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
782 'md5': '65fdff94098e4a607385a60c5177c638',
783 'info_dict': {
784 'id': '1969',
785 'ext': 'mp4',
786 'title': 'Hidden miracles of the natural world',
787 'uploader': 'Louie Schwartzberg',
788 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
789 }
790 },
791 # nowvideo embed hidden behind percent encoding
792 {
793 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
794 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
795 'info_dict': {
796 'id': '06e53103ca9aa',
797 'ext': 'flv',
798 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
799 'description': 'No description',
800 },
801 },
802 # arte embed
803 {
804 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
805 'md5': '7653032cbb25bf6c80d80f217055fa43',
806 'info_dict': {
807 'id': '048195-004_PLUS7-F',
808 'ext': 'flv',
809 'title': 'X:enius',
810 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
811 'upload_date': '20140320',
812 },
813 'params': {
814 'skip_download': 'Requires rtmpdump'
815 },
816 'skip': 'video gone',
817 },
818 # francetv embed
819 {
820 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
821 'info_dict': {
822 'id': 'EV_30231',
823 'ext': 'mp4',
824 'title': 'Alcaline, le concert avec Calogero',
825 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
826 'upload_date': '20150226',
827 'timestamp': 1424989860,
828 'duration': 5400,
829 },
830 'params': {
831 # m3u8 downloads
832 'skip_download': True,
833 },
834 'expected_warnings': [
835 'Forbidden'
836 ]
837 },
838 # Condé Nast embed
839 {
840 'url': 'http://www.wired.com/2014/04/honda-asimo/',
841 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
842 'info_dict': {
843 'id': '53501be369702d3275860000',
844 'ext': 'mp4',
845 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
846 }
847 },
848 # Dailymotion embed
849 {
850 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
851 'md5': '441aeeb82eb72c422c7f14ec533999cd',
852 'info_dict': {
853 'id': 'k2mm4bCdJ6CQ2i7c8o2',
854 'ext': 'mp4',
855 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
856 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
857 'uploader': 'Spi0n',
858 'uploader_id': 'xgditw',
859 'upload_date': '20140425',
860 'timestamp': 1398441542,
861 },
862 'add_ie': ['Dailymotion'],
863 },
864 # DailyMail embed
865 {
866 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
867 'info_dict': {
868 'id': '1495629',
869 'ext': 'mp4',
870 'title': 'Care worker punches elderly dementia patient in head 11 times',
871 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
872 },
873 'add_ie': ['DailyMail'],
874 'params': {
875 'skip_download': True,
876 },
877 },
878 # YouTube embed
879 {
880 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
881 'info_dict': {
882 'id': 'FXRb4ykk4S0',
883 'ext': 'mp4',
884 'title': 'The NBL Auction 2014',
885 'uploader': 'BADMINTON England',
886 'uploader_id': 'BADMINTONEvents',
887 'upload_date': '20140603',
888 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
889 },
890 'add_ie': ['Youtube'],
891 'params': {
892 'skip_download': True,
893 }
894 },
895 # MTVServices embed
896 {
897 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
898 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
899 'info_dict': {
900 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
901 'ext': 'mp4',
902 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
903 'description': 'Two valets share their love for movie star Liam Neesons.',
904 'timestamp': 1349922600,
905 'upload_date': '20121011',
906 },
907 },
908 # YouTube embed via <data-embed-url="">
909 {
910 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
911 'info_dict': {
912 'id': '4vAffPZIT44',
913 'ext': 'mp4',
914 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
915 'uploader': 'Gameloft',
916 'uploader_id': 'gameloft',
917 'upload_date': '20140828',
918 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
919 },
920 'params': {
921 'skip_download': True,
922 }
923 },
924 # YouTube <object> embed
925 {
926 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
927 'md5': '516718101ec834f74318df76259fb3cc',
928 'info_dict': {
929 'id': 'msN87y-iEx0',
930 'ext': 'webm',
931 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
932 'upload_date': '20080526',
933 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
934 'uploader': 'Christopher Sykes',
935 'uploader_id': 'ChristopherJSykes',
936 },
937 'add_ie': ['Youtube'],
938 },
939 # Camtasia studio
940 {
941 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
942 'playlist': [{
943 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
944 'info_dict': {
945 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
946 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
947 'ext': 'flv',
948 'duration': 2235.90,
949 }
950 }, {
951 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
952 'info_dict': {
953 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
954 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
955 'ext': 'flv',
956 'duration': 2235.93,
957 }
958 }],
959 'info_dict': {
960 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
961 }
962 },
963 # Flowplayer
964 {
965 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
966 'md5': '9d65602bf31c6e20014319c7d07fba27',
967 'info_dict': {
968 'id': '5123ea6d5e5a7',
969 'ext': 'mp4',
970 'age_limit': 18,
971 'uploader': 'www.handjobhub.com',
972 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
973 }
974 },
975 # Multiple brightcove videos
976 # https://github.com/ytdl-org/youtube-dl/issues/2283
977 {
978 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
979 'info_dict': {
980 'id': 'always-never',
981 'title': 'Always / Never - The New Yorker',
982 },
983 'playlist_count': 3,
984 'params': {
985 'extract_flat': False,
986 'skip_download': True,
987 }
988 },
989 # MLB embed
990 {
991 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
992 'md5': '96f09a37e44da40dd083e12d9a683327',
993 'info_dict': {
994 'id': '33322633',
995 'ext': 'mp4',
996 'title': 'Ump changes call to ball',
997 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
998 'duration': 48,
999 'timestamp': 1401537900,
1000 'upload_date': '20140531',
1001 'thumbnail': r're:^https?://.*\.jpg$',
1002 },
1003 },
1004 # Wistia embed
1005 {
1006 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
1007 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
1008 'info_dict': {
1009 'id': '6e2wtrbdaf',
1010 'ext': 'mov',
1011 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
1012 'description': 'a Paywall Videos video from Remilon',
1013 'duration': 644.072,
1014 'uploader': 'study.com',
1015 'timestamp': 1459678540,
1016 'upload_date': '20160403',
1017 'filesize': 24687186,
1018 },
1019 },
1020 {
1021 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
1022 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
1023 'info_dict': {
1024 'id': 'uxjb0lwrcz',
1025 'ext': 'mp4',
1026 'title': 'Conversation about Hexagonal Rails Part 1',
1027 'description': 'a Martin Fowler video from ThoughtWorks',
1028 'duration': 1715.0,
1029 'uploader': 'thoughtworks.wistia.com',
1030 'timestamp': 1401832161,
1031 'upload_date': '20140603',
1032 },
1033 },
1034 # Wistia standard embed (async)
1035 {
1036 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
1037 'info_dict': {
1038 'id': '807fafadvk',
1039 'ext': 'mp4',
1040 'title': 'Drip Brennan Dunn Workshop',
1041 'description': 'a JV Webinars video from getdrip-1',
1042 'duration': 4986.95,
1043 'timestamp': 1463607249,
1044 'upload_date': '20160518',
1045 },
1046 'params': {
1047 'skip_download': True,
1048 }
1049 },
1050 # Soundcloud embed
1051 {
1052 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1053 'info_dict': {
1054 'id': '174391317',
1055 'ext': 'mp3',
1056 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1057 'uploader': 'Sophos Security',
1058 'title': 'Chet Chat 171 - Oct 29, 2014',
1059 'upload_date': '20141029',
1060 }
1061 },
1062 # Soundcloud multiple embeds
1063 {
1064 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1065 'info_dict': {
1066 'id': '52809',
1067 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1068 },
1069 'playlist_mincount': 7,
1070 },
1071 # TuneIn station embed
1072 {
1073 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1074 'info_dict': {
1075 'id': '204146',
1076 'ext': 'mp3',
1077 'title': 'CNRV',
1078 'location': 'Paris, France',
1079 'is_live': True,
1080 },
1081 'params': {
1082 # Live stream
1083 'skip_download': True,
1084 },
1085 },
1086 # Livestream embed
1087 {
1088 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1089 'info_dict': {
1090 'id': '67864563',
1091 'ext': 'flv',
1092 'upload_date': '20141112',
1093 'title': 'Rosetta #CometLanding webcast HL 10',
1094 }
1095 },
1096 # Another Livestream embed, without 'new.' in URL
1097 {
1098 'url': 'https://www.freespeech.org/',
1099 'info_dict': {
1100 'id': '123537347',
1101 'ext': 'mp4',
1102 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1103 },
1104 'params': {
1105 # Live stream
1106 'skip_download': True,
1107 },
1108 },
1109 # LazyYT
1110 {
1111 'url': 'https://skiplagged.com/',
1112 'info_dict': {
1113 'id': 'skiplagged',
1114 'title': 'Skiplagged: The smart way to find cheap flights',
1115 },
1116 'playlist_mincount': 1,
1117 'add_ie': ['Youtube'],
1118 },
1119 # Cinchcast embed
1120 {
1121 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1122 'info_dict': {
1123 'id': '7141703',
1124 'ext': 'mp3',
1125 'upload_date': '20141126',
1126 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1127 }
1128 },
1129 # Cinerama player
1130 {
1131 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1132 'info_dict': {
1133 'id': '730m_DandD_1901_512k',
1134 'ext': 'mp4',
1135 'uploader': 'www.abc.net.au',
1136 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1137 }
1138 },
1139 # embedded viddler video
1140 {
1141 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1142 'info_dict': {
1143 'id': '4d03aad9',
1144 'ext': 'mp4',
1145 'uploader': 'deadspin',
1146 'title': 'WALL-TO-GORTAT',
1147 'timestamp': 1422285291,
1148 'upload_date': '20150126',
1149 },
1150 'add_ie': ['Viddler'],
1151 },
1152 # Libsyn embed
1153 {
1154 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1155 'info_dict': {
1156 'id': '3377616',
1157 'ext': 'mp3',
1158 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1159 'description': 'md5:601cb790edd05908957dae8aaa866465',
1160 'upload_date': '20150220',
1161 },
1162 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1163 },
1164 # jwplayer YouTube
1165 {
1166 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1167 'info_dict': {
1168 'id': 'Mrj4DVp2zeA',
1169 'ext': 'mp4',
1170 'upload_date': '20150212',
1171 'uploader': 'The National Archives UK',
1172 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1173 'uploader_id': 'NationalArchives08',
1174 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1175 },
1176 },
1177 # jwplayer rtmp
1178 {
1179 'url': 'http://www.suffolk.edu/sjc/live.php',
1180 'info_dict': {
1181 'id': 'live',
1182 'ext': 'flv',
1183 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1184 'uploader': 'www.suffolk.edu',
1185 },
1186 'params': {
1187 'skip_download': True,
1188 },
1189 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1190 },
1191 # Complex jwplayer
1192 {
1193 'url': 'http://www.indiedb.com/games/king-machine/videos',
1194 'info_dict': {
1195 'id': 'videos',
1196 'ext': 'mp4',
1197 'title': 'king machine trailer 1',
1198 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1199 'thumbnail': r're:^https?://.*\.jpg$',
1200 },
1201 },
1202 {
1203 # JWPlayer config passed as variable
1204 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1205 'info_dict': {
1206 'id': '3326530_hq',
1207 'ext': 'mp4',
1208 'title': 'ARIELE | Tube Cup',
1209 'uploader': 'www.txxx.com',
1210 'age_limit': 18,
1211 },
1212 'params': {
1213 'skip_download': True,
1214 }
1215 },
1216 {
1217 # JWPlatform iframe
1218 'url': 'https://www.covermagazine.co.uk/feature/2465255/business-protection-involved',
1219 'info_dict': {
1220 'id': 'AG26UQXM',
1221 'ext': 'mp4',
1222 'upload_date': '20160719',
1223 'timestamp': 468923808,
1224 'title': '2016_05_18 Cover L&G Business Protection V1 FINAL.mp4',
1225 },
1226 'add_ie': [JWPlatformIE.ie_key()],
1227 },
1228 {
1229 # Video.js embed, multiple formats
1230 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1231 'info_dict': {
1232 'id': 'yygqldloqIk',
1233 'ext': 'mp4',
1234 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1235 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1236 'upload_date': '20130314',
1237 'uploader': 'PROстое3D',
1238 'uploader_id': 'PROstoe3D',
1239 },
1240 'params': {
1241 'skip_download': True,
1242 },
1243 },
1244 {
1245 # Video.js embed, single format
1246 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1247 'info_dict': {
1248 'id': 'watch',
1249 'ext': 'mp4',
1250 'title': 'Step 1 - Good Foundation',
1251 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1252 },
1253 'params': {
1254 'skip_download': True,
1255 },
1256 },
1257 # rtl.nl embed
1258 {
1259 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1260 'playlist_mincount': 5,
1261 'info_dict': {
1262 'id': 'aanslagen-kopenhagen',
1263 'title': 'Aanslagen Kopenhagen',
1264 }
1265 },
1266 # Zapiks embed
1267 {
1268 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1269 'info_dict': {
1270 'id': '118046',
1271 'ext': 'mp4',
1272 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1273 }
1274 },
1275 # Kaltura embed (different embed code)
1276 {
1277 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1278 'info_dict': {
1279 'id': '1_a52wc67y',
1280 'ext': 'flv',
1281 'upload_date': '20150127',
1282 'uploader_id': 'PremierMedia',
1283 'timestamp': int,
1284 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1285 },
1286 },
1287 # Kaltura embed with single quotes
1288 {
1289 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1290 'info_dict': {
1291 'id': '0_izeg5utt',
1292 'ext': 'mp4',
1293 'title': '35871',
1294 'timestamp': 1355743100,
1295 'upload_date': '20121217',
1296 'uploader_id': 'cplapp@learn360.com',
1297 },
1298 'add_ie': ['Kaltura'],
1299 },
1300 {
1301 # Kaltura embedded via quoted entry_id
1302 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1303 'info_dict': {
1304 'id': '0_utuok90b',
1305 'ext': 'mp4',
1306 'title': '06_matthew_brender_raj_dutt',
1307 'timestamp': 1466638791,
1308 'upload_date': '20160622',
1309 },
1310 'add_ie': ['Kaltura'],
1311 'expected_warnings': [
1312 'Could not send HEAD request'
1313 ],
1314 'params': {
1315 'skip_download': True,
1316 }
1317 },
1318 {
1319 # Kaltura embedded, some fileExt broken (#11480)
1320 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1321 'info_dict': {
1322 'id': '1_sgtvehim',
1323 'ext': 'mp4',
1324 'title': 'Our "Standard Models" of particle physics and cosmology',
1325 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1326 'timestamp': 1321158993,
1327 'upload_date': '20111113',
1328 'uploader_id': 'kps1',
1329 },
1330 'add_ie': ['Kaltura'],
1331 },
1332 {
1333 # Kaltura iframe embed
1334 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1335 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1336 'info_dict': {
1337 'id': '0_f2cfbpwy',
1338 'ext': 'mp4',
1339 'title': 'I. M. Pei: A Centennial Celebration',
1340 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1341 'upload_date': '20170403',
1342 'uploader_id': 'batchUser',
1343 'timestamp': 1491232186,
1344 },
1345 'add_ie': ['Kaltura'],
1346 },
1347 {
1348 # Kaltura iframe embed, more sophisticated
1349 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1350 'info_dict': {
1351 'id': '1_9gzouybz',
1352 'ext': 'mp4',
1353 'title': 'lecture-05sep2017',
1354 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1355 'upload_date': '20170913',
1356 'uploader_id': 'eps2',
1357 'timestamp': 1505340777,
1358 },
1359 'params': {
1360 'skip_download': True,
1361 },
1362 'add_ie': ['Kaltura'],
1363 },
1364 {
1365 # meta twitter:player
1366 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1367 'info_dict': {
1368 'id': '0_01b42zps',
1369 'ext': 'mp4',
1370 'title': 'Main Twerk (Video)',
1371 'upload_date': '20171208',
1372 'uploader_id': 'sebastian.salinas@thechive.com',
1373 'timestamp': 1512713057,
1374 },
1375 'params': {
1376 'skip_download': True,
1377 },
1378 'add_ie': ['Kaltura'],
1379 },
1380 # referrer protected EaglePlatform embed
1381 {
1382 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1383 'info_dict': {
1384 'id': '582306',
1385 'ext': 'mp4',
1386 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1387 'thumbnail': r're:^https?://.*\.jpg$',
1388 'duration': 3382,
1389 'view_count': int,
1390 },
1391 'params': {
1392 'skip_download': True,
1393 },
1394 },
1395 # ClipYou (EaglePlatform) embed (custom URL)
1396 {
1397 'url': 'http://muz-tv.ru/play/7129/',
1398 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1399 'info_dict': {
1400 'id': '12820',
1401 'ext': 'mp4',
1402 'title': "'O Sole Mio",
1403 'thumbnail': r're:^https?://.*\.jpg$',
1404 'duration': 216,
1405 'view_count': int,
1406 },
1407 'params': {
1408 'skip_download': True,
1409 },
1410 'skip': 'This video is unavailable.',
1411 },
1412 # Pladform embed
1413 {
1414 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1415 'info_dict': {
1416 'id': '100183293',
1417 'ext': 'mp4',
1418 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1419 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1420 'thumbnail': r're:^https?://.*\.jpg$',
1421 'duration': 694,
1422 'age_limit': 0,
1423 },
1424 'skip': 'HTTP Error 404: Not Found',
1425 },
1426 # Playwire embed
1427 {
1428 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1429 'info_dict': {
1430 'id': '3519514',
1431 'ext': 'mp4',
1432 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1433 'thumbnail': r're:^https?://.*\.png$',
1434 'duration': 45.115,
1435 },
1436 },
1437 # 5min embed
1438 {
1439 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1440 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1441 'info_dict': {
1442 'id': '518726732',
1443 'ext': 'mp4',
1444 'title': 'Facebook Creates "On This Day" | Crunch Report',
1445 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1446 'timestamp': 1427237531,
1447 'uploader': 'Crunch Report',
1448 'upload_date': '20150324',
1449 },
1450 'params': {
1451 # m3u8 download
1452 'skip_download': True,
1453 },
1454 },
1455 # Crooks and Liars embed
1456 {
1457 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1458 'info_dict': {
1459 'id': '8RUoRhRi',
1460 'ext': 'mp4',
1461 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1462 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1463 'timestamp': 1428207000,
1464 'upload_date': '20150405',
1465 'uploader': 'Heather',
1466 },
1467 },
1468 # Crooks and Liars external embed
1469 {
1470 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1471 'info_dict': {
1472 'id': 'MTE3MjUtMzQ2MzA',
1473 'ext': 'mp4',
1474 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1475 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1476 'timestamp': 1265032391,
1477 'upload_date': '20100201',
1478 'uploader': 'Heather',
1479 },
1480 },
1481 # NBC Sports vplayer embed
1482 {
1483 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1484 'info_dict': {
1485 'id': 'ln7x1qSThw4k',
1486 'ext': 'flv',
1487 'title': "PFT Live: New leader in the 'new-look' defense",
1488 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1489 'uploader': 'NBCU-SPORTS',
1490 'upload_date': '20140107',
1491 'timestamp': 1389118457,
1492 },
1493 'skip': 'Invalid Page URL',
1494 },
1495 # NBC News embed
1496 {
1497 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1498 'md5': '1aa589c675898ae6d37a17913cf68d66',
1499 'info_dict': {
1500 'id': 'x_dtl_oa_LettermanliftPR_160608',
1501 'ext': 'mp4',
1502 'title': 'David Letterman: A Preview',
1503 '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.',
1504 'upload_date': '20160609',
1505 'timestamp': 1465431544,
1506 'uploader': 'NBCU-NEWS',
1507 },
1508 },
1509 # UDN embed
1510 {
1511 'url': 'https://video.udn.com/news/300346',
1512 'md5': 'fd2060e988c326991037b9aff9df21a6',
1513 'info_dict': {
1514 'id': '300346',
1515 'ext': 'mp4',
1516 'title': '中一中男師變性 全校師生力挺',
1517 'thumbnail': r're:^https?://.*\.jpg$',
1518 },
1519 'params': {
1520 # m3u8 download
1521 'skip_download': True,
1522 },
1523 'expected_warnings': ['Failed to parse JSON Expecting value'],
1524 },
1525 # Brightcove URL in single quotes
1526 {
1527 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1528 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1529 'info_dict': {
1530 'id': '4255764656001',
1531 'ext': 'mp4',
1532 'title': 'SN Presents: Russell Martin, World Citizen',
1533 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1534 'uploader': 'Rogers Sportsnet',
1535 'uploader_id': '1704050871',
1536 'upload_date': '20150525',
1537 'timestamp': 1432570283,
1538 },
1539 },
1540 # Kinja embed
1541 {
1542 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1543 'info_dict': {
1544 'id': '106351',
1545 'ext': 'mp4',
1546 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1547 'description': 'Migrated from OnionStudios',
1548 'thumbnail': r're:^https?://.*\.jpe?g$',
1549 'uploader': 'clickhole',
1550 'upload_date': '20150527',
1551 'timestamp': 1432744860,
1552 }
1553 },
1554 # SnagFilms embed
1555 {
1556 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1557 'info_dict': {
1558 'id': '74849a00-85a9-11e1-9660-123139220831',
1559 'ext': 'mp4',
1560 'title': '#whilewewatch',
1561 }
1562 },
1563 # AdobeTVVideo embed
1564 {
1565 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1566 'md5': '43662b577c018ad707a63766462b1e87',
1567 'info_dict': {
1568 'id': '2456',
1569 'ext': 'mp4',
1570 'title': 'New experience with Acrobat DC',
1571 'description': 'New experience with Acrobat DC',
1572 'duration': 248.667,
1573 },
1574 },
1575 # BrightcoveInPageEmbed embed
1576 {
1577 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1578 'info_dict': {
1579 'id': '4238694884001',
1580 'ext': 'flv',
1581 'title': 'Tabletop: Dread, Last Thoughts',
1582 'description': 'Tabletop: Dread, Last Thoughts',
1583 'duration': 51690,
1584 },
1585 },
1586 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1587 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1588 {
1589 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1590 'info_dict': {
1591 'id': '4785848093001',
1592 'ext': 'mp4',
1593 'title': 'The Cardinal Pell Interview',
1594 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1595 'uploader': 'GlobeCast Australia - GlobeStream',
1596 'uploader_id': '2733773828001',
1597 'upload_date': '20160304',
1598 'timestamp': 1457083087,
1599 },
1600 'params': {
1601 # m3u8 downloads
1602 'skip_download': True,
1603 },
1604 },
1605 {
1606 # Brightcove embed with whitespace around attribute names
1607 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1608 'info_dict': {
1609 'id': '3167554373001',
1610 'ext': 'mp4',
1611 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1612 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1613 'uploader_id': '1079349493',
1614 'upload_date': '20140207',
1615 'timestamp': 1391810548,
1616 },
1617 'params': {
1618 'skip_download': True,
1619 },
1620 },
1621 # Another form of arte.tv embed
1622 {
1623 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1624 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1625 'info_dict': {
1626 'id': '030273-562_PLUS7-F',
1627 'ext': 'mp4',
1628 'title': 'ARTE Reportage - Nulle part, en France',
1629 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1630 'upload_date': '20160409',
1631 },
1632 },
1633 # Duplicated embedded video URLs
1634 {
1635 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1636 'info_dict': {
1637 'id': '149298443_480_16c25b74_2',
1638 'ext': 'mp4',
1639 'title': 'vs. Blue Orange Spring Game',
1640 'uploader': 'www.hudl.com',
1641 },
1642 },
1643 # twitter:player:stream embed
1644 {
1645 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1646 'info_dict': {
1647 'id': 'master',
1648 'ext': 'mp4',
1649 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1650 'uploader': 'www.rtl.be',
1651 },
1652 'params': {
1653 # m3u8 downloads
1654 'skip_download': True,
1655 },
1656 },
1657 # twitter:player embed
1658 {
1659 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1660 'md5': 'a3e0df96369831de324f0778e126653c',
1661 'info_dict': {
1662 'id': '4909620399001',
1663 'ext': 'mp4',
1664 'title': 'What Do Black Holes Sound Like?',
1665 'description': 'what do black holes sound like',
1666 'upload_date': '20160524',
1667 'uploader_id': '29913724001',
1668 'timestamp': 1464107587,
1669 'uploader': 'TheAtlantic',
1670 },
1671 'add_ie': ['BrightcoveLegacy'],
1672 },
1673 # Facebook <iframe> embed
1674 {
1675 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1676 'md5': 'fbcde74f534176ecb015849146dd3aee',
1677 'info_dict': {
1678 'id': '599637780109885',
1679 'ext': 'mp4',
1680 'title': 'Facebook video #599637780109885',
1681 },
1682 },
1683 # Facebook <iframe> embed, plugin video
1684 {
1685 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1686 'info_dict': {
1687 'id': '1754168231264132',
1688 'ext': 'mp4',
1689 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1690 'uploader': 'Tariq Ramadan (official)',
1691 'timestamp': 1496758379,
1692 'upload_date': '20170606',
1693 },
1694 'params': {
1695 'skip_download': True,
1696 },
1697 },
1698 # Facebook API embed
1699 {
1700 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1701 'md5': 'a47372ee61b39a7b90287094d447d94e',
1702 'info_dict': {
1703 'id': '10153467542406923',
1704 'ext': 'mp4',
1705 'title': 'Facebook video #10153467542406923',
1706 },
1707 },
1708 # Wordpress "YouTube Video Importer" plugin
1709 {
1710 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1711 'md5': 'd16797741b560b485194eddda8121b48',
1712 'info_dict': {
1713 'id': 'HNTXWDXV9Is',
1714 'ext': 'mp4',
1715 'title': 'Blue Devils Drumline Stanford lot 2016',
1716 'upload_date': '20160627',
1717 'uploader_id': 'GENOCIDE8GENERAL10',
1718 'uploader': 'cylus cyrus',
1719 },
1720 },
1721 {
1722 # video stored on custom kaltura server
1723 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1724 'md5': '537617d06e64dfed891fa1593c4b30cc',
1725 'info_dict': {
1726 'id': '0_1iotm5bh',
1727 'ext': 'mp4',
1728 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1729 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1730 'uploader_id': 'videos.expansion@el-mundo.net',
1731 'upload_date': '20150429',
1732 'timestamp': 1430303472,
1733 },
1734 'add_ie': ['Kaltura'],
1735 },
1736 {
1737 # multiple kaltura embeds, nsfw
1738 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
1739 'info_dict': {
1740 'id': 'kamila-avec-video-jaime-sadomie',
1741 'title': "Kamila avec vídeo “J'aime sadomie”",
1742 },
1743 'playlist_count': 8,
1744 },
1745 {
1746 # Non-standard Vimeo embed
1747 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1748 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1749 'info_dict': {
1750 'id': '148867247',
1751 'ext': 'mp4',
1752 'title': 'Understanding the web - Teaser',
1753 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1754 'upload_date': '20151214',
1755 'uploader': 'OpenClassrooms',
1756 'uploader_id': 'openclassrooms',
1757 },
1758 'add_ie': ['Vimeo'],
1759 },
1760 {
1761 # generic vimeo embed that requires original URL passed as Referer
1762 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1763 'only_matching': True,
1764 },
1765 {
1766 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1767 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1768 'info_dict': {
1769 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1770 'ext': 'mp4',
1771 'title': 'Big Buck Bunny',
1772 'description': 'Royalty free test video',
1773 'timestamp': 1432816365,
1774 'upload_date': '20150528',
1775 'is_live': False,
1776 },
1777 'params': {
1778 'skip_download': True,
1779 },
1780 'add_ie': [ArkenaIE.ie_key()],
1781 },
1782 {
1783 '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/',
1784 'info_dict': {
1785 'id': '1c7141f46c',
1786 'ext': 'mp4',
1787 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1788 },
1789 'params': {
1790 'skip_download': True,
1791 },
1792 'add_ie': [Vbox7IE.ie_key()],
1793 },
1794 {
1795 # DBTV embeds
1796 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1797 'info_dict': {
1798 'id': '43254897',
1799 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1800 },
1801 'playlist_mincount': 3,
1802 },
1803 {
1804 # Videa embeds
1805 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1806 'info_dict': {
1807 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1808 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1809 },
1810 'playlist_mincount': 2,
1811 },
1812 {
1813 # 20 minuten embed
1814 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1815 'info_dict': {
1816 'id': '523629',
1817 'ext': 'mp4',
1818 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1819 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1820 },
1821 'params': {
1822 'skip_download': True,
1823 },
1824 'add_ie': [TwentyMinutenIE.ie_key()],
1825 },
1826 {
1827 # VideoPress embed
1828 'url': 'https://en.support.wordpress.com/videopress/',
1829 'info_dict': {
1830 'id': 'OcobLTqC',
1831 'ext': 'm4v',
1832 'title': 'IMG_5786',
1833 'timestamp': 1435711927,
1834 'upload_date': '20150701',
1835 },
1836 'params': {
1837 'skip_download': True,
1838 },
1839 'add_ie': [VideoPressIE.ie_key()],
1840 },
1841 {
1842 # Rutube embed
1843 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1844 'info_dict': {
1845 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1846 'ext': 'flv',
1847 'title': 'Магаззино: Казань 2',
1848 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1849 'uploader': 'Магаззино',
1850 'upload_date': '20170228',
1851 'uploader_id': '996642',
1852 },
1853 'params': {
1854 'skip_download': True,
1855 },
1856 'add_ie': [RutubeIE.ie_key()],
1857 },
1858 {
1859 # ThePlatform embedded with whitespaces in URLs
1860 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1861 'only_matching': True,
1862 },
1863 {
1864 # Senate ISVP iframe https
1865 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1866 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1867 'info_dict': {
1868 'id': 'govtaff020316',
1869 'ext': 'mp4',
1870 'title': 'Integrated Senate Video Player',
1871 },
1872 'add_ie': [SenateISVPIE.ie_key()],
1873 },
1874 {
1875 # Limelight embeds (1 channel embed + 4 media embeds)
1876 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1877 'info_dict': {
1878 'id': 'FacilitatorTraining2017',
1879 'title': 'Facilitator Training 2017',
1880 },
1881 'playlist_mincount': 5,
1882 },
1883 {
1884 # Limelight embed (LimelightPlayerUtil.embed)
1885 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1886 'info_dict': {
1887 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1888 'ext': 'mp4',
1889 'title': '07448641',
1890 'timestamp': 1499890639,
1891 'upload_date': '20170712',
1892 },
1893 'params': {
1894 'skip_download': True,
1895 },
1896 'add_ie': ['LimelightMedia'],
1897 },
1898 {
1899 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1900 'info_dict': {
1901 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1902 'title': 'Standoff with Walnut Creek murder suspect ends',
1903 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1904 },
1905 'playlist_mincount': 4,
1906 },
1907 {
1908 # WashingtonPost embed
1909 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1910 'info_dict': {
1911 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1912 'ext': 'mp4',
1913 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1914 'description': 'Donald Trump wanted a weekly TV drama based on his life. It never aired. But The Washington Post recently obtained a scene from the pilot script — and enlisted actors.',
1915 'timestamp': 1455216756,
1916 'uploader': 'The Washington Post',
1917 'upload_date': '20160211',
1918 },
1919 'add_ie': [WashingtonPostIE.ie_key()],
1920 },
1921 {
1922 # Mediaset embed
1923 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1924 'info_dict': {
1925 'id': '720642',
1926 'ext': 'mp4',
1927 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1928 },
1929 'params': {
1930 'skip_download': True,
1931 },
1932 'add_ie': [MediasetIE.ie_key()],
1933 },
1934 {
1935 # JOJ.sk embeds
1936 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1937 'info_dict': {
1938 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1939 'title': 'Slovenskom sa prehnala vlna silných búrok',
1940 },
1941 'playlist_mincount': 5,
1942 'add_ie': [JojIE.ie_key()],
1943 },
1944 {
1945 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1946 'url': 'https://tvrain.ru/amp/418921/',
1947 'md5': 'cc00413936695987e8de148b67d14f1d',
1948 'info_dict': {
1949 'id': '418921',
1950 'ext': 'mp4',
1951 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1952 },
1953 },
1954 {
1955 # vzaar embed
1956 'url': 'http://help.vzaar.com/article/165-embedding-video',
1957 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1958 'info_dict': {
1959 'id': '8707641',
1960 'ext': 'mp4',
1961 'title': 'Building A Business Online: Principal Chairs Q & A',
1962 },
1963 },
1964 {
1965 # multiple HTML5 videos on one page
1966 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1967 'info_dict': {
1968 'id': 'keyscenarios',
1969 'title': 'Rescue Kit 14 Free Edition - Getting started',
1970 },
1971 'playlist_count': 4,
1972 },
1973 {
1974 # vshare embed
1975 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1976 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1977 'info_dict': {
1978 'id': '0f64ce6',
1979 'title': 'vl14062007715967',
1980 'ext': 'mp4',
1981 }
1982 },
1983 {
1984 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1985 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1986 'info_dict': {
1987 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1988 'ext': 'mp4',
1989 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1990 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1991 'timestamp': 1474354800,
1992 'upload_date': '20160920',
1993 }
1994 },
1995 {
1996 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1997 'info_dict': {
1998 'id': '1731611',
1999 'ext': 'mp4',
2000 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
2001 'description': 'md5:eb5f23826a027ba95277d105f248b825',
2002 'timestamp': 1516100691,
2003 'upload_date': '20180116',
2004 },
2005 'params': {
2006 'skip_download': True,
2007 },
2008 'add_ie': [SpringboardPlatformIE.ie_key()],
2009 },
2010 {
2011 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
2012 'info_dict': {
2013 'id': 'vMDE4NzI1Mjgt690b',
2014 'ext': 'mp4',
2015 'title': 'Котята',
2016 },
2017 'add_ie': [YapFilesIE.ie_key()],
2018 'params': {
2019 'skip_download': True,
2020 },
2021 },
2022 {
2023 # CloudflareStream embed
2024 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2025 'info_dict': {
2026 'id': '31c9291ab41fac05471db4e73aa11717',
2027 'ext': 'mp4',
2028 'title': '31c9291ab41fac05471db4e73aa11717',
2029 },
2030 'add_ie': [CloudflareStreamIE.ie_key()],
2031 'params': {
2032 'skip_download': True,
2033 },
2034 },
2035 {
2036 # PeerTube embed
2037 'url': 'https://joinpeertube.org/fr/home/',
2038 'info_dict': {
2039 'id': 'home',
2040 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2041 },
2042 'playlist_count': 2,
2043 },
2044 {
2045 # Indavideo embed
2046 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2047 'info_dict': {
2048 'id': '1693903',
2049 'ext': 'mp4',
2050 'title': 'Így kell otthon hamburgert sütni',
2051 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2052 'timestamp': 1426330212,
2053 'upload_date': '20150314',
2054 'uploader': 'StreetKitchen',
2055 'uploader_id': '546363',
2056 },
2057 'add_ie': [IndavideoEmbedIE.ie_key()],
2058 'params': {
2059 'skip_download': True,
2060 },
2061 },
2062 {
2063 # APA embed via JWPlatform embed
2064 'url': 'http://www.vol.at/blue-man-group/5593454',
2065 'info_dict': {
2066 'id': 'jjv85FdZ',
2067 'ext': 'mp4',
2068 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2069 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2070 'thumbnail': r're:^https?://.*\.jpg$',
2071 'duration': 254,
2072 'timestamp': 1519211149,
2073 'upload_date': '20180221',
2074 },
2075 'params': {
2076 'skip_download': True,
2077 },
2078 },
2079 {
2080 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2081 'md5': 'b68d276de422ab07ee1d49388103f457',
2082 'info_dict': {
2083 'id': '83645793',
2084 'title': 'Lock up and get excited',
2085 'ext': 'mp4'
2086 },
2087 'skip': 'TODO: fix nested playlists processing in tests',
2088 },
2089 {
2090 # Viqeo embeds
2091 'url': 'https://viqeo.tv/',
2092 'info_dict': {
2093 'id': 'viqeo',
2094 'title': 'All-new video platform',
2095 },
2096 'playlist_count': 6,
2097 },
2098 {
2099 # Squarespace video embed, 2019-08-28
2100 'url': 'http://ootboxford.com',
2101 'info_dict': {
2102 'id': 'Tc7b_JGdZfw',
2103 'title': 'Out of the Blue, at Childish Things 10',
2104 'ext': 'mp4',
2105 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
2106 'uploader_id': 'helendouglashouse',
2107 'uploader': 'Helen & Douglas House',
2108 'upload_date': '20140328',
2109 },
2110 'params': {
2111 'skip_download': True,
2112 },
2113 },
2114 # {
2115 # # Zype embed
2116 # 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2117 # 'info_dict': {
2118 # 'id': '5b400b834b32992a310622b9',
2119 # 'ext': 'mp4',
2120 # 'title': 'Smoky Barbecue Favorites',
2121 # 'thumbnail': r're:^https?://.*\.jpe?g',
2122 # 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
2123 # 'upload_date': '20170909',
2124 # 'timestamp': 1504915200,
2125 # },
2126 # 'add_ie': [ZypeIE.ie_key()],
2127 # 'params': {
2128 # 'skip_download': True,
2129 # },
2130 # },
2131 {
2132 # videojs embed
2133 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2134 'info_dict': {
2135 'id': 'shell',
2136 'ext': 'mp4',
2137 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2138 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2139 'thumbnail': r're:^https?://.*\.jpg$',
2140 },
2141 'params': {
2142 'skip_download': True,
2143 },
2144 'expected_warnings': ['Failed to download MPD manifest'],
2145 },
2146 {
2147 # DailyMotion embed with DM.player
2148 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
2149 'info_dict': {
2150 'id': 'k6aKkGHd9FJs4mtJN39',
2151 'ext': 'mp4',
2152 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
2153 'description': 'This video is private.',
2154 'uploader_id': 'x1jf30l',
2155 'uploader': 'beIN SPORTS USA',
2156 'upload_date': '20190528',
2157 'timestamp': 1559062971,
2158 },
2159 'params': {
2160 'skip_download': True,
2161 },
2162 },
2163 # {
2164 # # TODO: find another test
2165 # # http://schema.org/VideoObject
2166 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2167 # 'md5': '888dcf08b7ea671381f00fab74692755',
2168 # 'info_dict': {
2169 # 'id': 'nyvTSJMKId',
2170 # 'ext': 'mp4',
2171 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2172 # 'description': '#love for cats.',
2173 # 'timestamp': 1461244995,
2174 # 'upload_date': '20160421',
2175 # },
2176 # 'params': {
2177 # 'force_generic_extractor': True,
2178 # },
2179 # },
2180 {
2181 # VHX Embed
2182 'url': 'https://demo.vhx.tv/category-c/videos/file-example-mp4-480-1-5mg-copy',
2183 'info_dict': {
2184 'id': '858208',
2185 'ext': 'mp4',
2186 'title': 'Untitled',
2187 'uploader_id': 'user80538407',
2188 'uploader': 'OTT Videos',
2189 },
2190 },
2191 {
2192 # ArcPublishing PoWa video player
2193 'url': 'https://www.adn.com/politics/2020/11/02/video-senate-candidates-campaign-in-anchorage-on-eve-of-election-day/',
2194 'md5': 'b03b2fac8680e1e5a7cc81a5c27e71b3',
2195 'info_dict': {
2196 'id': '8c99cb6e-b29c-4bc9-9173-7bf9979225ab',
2197 'ext': 'mp4',
2198 'title': 'Senate candidates wave to voters on Anchorage streets',
2199 'description': 'md5:91f51a6511f090617353dc720318b20e',
2200 'timestamp': 1604378735,
2201 'upload_date': '20201103',
2202 'duration': 1581,
2203 },
2204 },
2205 {
2206 # MyChannels SDK embed
2207 # https://www.24kitchen.nl/populair/deskundige-dit-waarom-sommigen-gevoelig-zijn-voor-voedselallergieen
2208 'url': 'https://www.demorgen.be/nieuws/burgemeester-rotterdam-richt-zich-in-videoboodschap-tot-relschoppers-voelt-het-goed~b0bcfd741/',
2209 'md5': '90c0699c37006ef18e198c032d81739c',
2210 'info_dict': {
2211 'id': '194165',
2212 'ext': 'mp4',
2213 'title': 'Burgemeester Aboutaleb spreekt relschoppers toe',
2214 'timestamp': 1611740340,
2215 'upload_date': '20210127',
2216 'duration': 159,
2217 },
2218 },
2219 {
2220 # Simplecast player embed
2221 'url': 'https://www.bio.org/podcast',
2222 'info_dict': {
2223 'id': 'podcast',
2224 'title': 'I AM BIO Podcast | BIO',
2225 },
2226 'playlist_mincount': 52,
2227 },
2228 {
2229 # Sibnet embed (https://help.sibnet.ru/?sibnet_video_embed)
2230 'url': 'https://phpbb3.x-tk.ru/bbcode-video-sibnet-t24.html',
2231 'only_matching': True,
2232 }, {
2233 # WimTv embed player
2234 'url': 'http://www.msmotor.tv/wearefmi-pt-2-2021/',
2235 'info_dict': {
2236 'id': 'wearefmi-pt-2-2021',
2237 'title': '#WEAREFMI – PT.2 – 2021 – MsMotorTV',
2238 },
2239 'playlist_count': 1,
2240 }, {
2241 # KVS Player
2242 'url': 'https://www.kvs-demo.com/videos/105/kelis-4th-of-july/',
2243 'info_dict': {
2244 'id': '105',
2245 'display_id': 'kelis-4th-of-july',
2246 'ext': 'mp4',
2247 'title': 'Kelis - 4th Of July',
2248 'thumbnail': 'https://kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
2249 },
2250 'params': {
2251 'skip_download': True,
2252 },
2253 }, {
2254 # KVS Player
2255 'url': 'https://www.kvs-demo.com/embed/105/',
2256 'info_dict': {
2257 'id': '105',
2258 'display_id': 'kelis-4th-of-july',
2259 'ext': 'mp4',
2260 'title': 'Kelis - 4th Of July / Embed Player',
2261 'thumbnail': 'https://kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
2262 },
2263 'params': {
2264 'skip_download': True,
2265 },
2266 }, {
2267 # KVS Player
2268 'url': 'https://thisvid.com/videos/french-boy-pantsed/',
2269 'md5': '3397979512c682f6b85b3b04989df224',
2270 'info_dict': {
2271 'id': '2400174',
2272 'display_id': 'french-boy-pantsed',
2273 'ext': 'mp4',
2274 'title': 'French Boy Pantsed - ThisVid.com',
2275 'thumbnail': 'https://media.thisvid.com/contents/videos_screenshots/2400000/2400174/preview.mp4.jpg',
2276 }
2277 }, {
2278 # KVS Player
2279 'url': 'https://thisvid.com/embed/2400174/',
2280 'md5': '3397979512c682f6b85b3b04989df224',
2281 'info_dict': {
2282 'id': '2400174',
2283 'display_id': 'french-boy-pantsed',
2284 'ext': 'mp4',
2285 'title': 'French Boy Pantsed - ThisVid.com',
2286 'thumbnail': 'https://media.thisvid.com/contents/videos_screenshots/2400000/2400174/preview.mp4.jpg',
2287 }
2288 }, {
2289 # KVS Player
2290 'url': 'https://youix.com/video/leningrad-zoj/',
2291 'md5': '94f96ba95706dc3880812b27b7d8a2b8',
2292 'info_dict': {
2293 'id': '18485',
2294 'display_id': 'leningrad-zoj',
2295 'ext': 'mp4',
2296 'title': 'Клип: Ленинград - ЗОЖ скачать, смотреть онлайн | Youix.com',
2297 'thumbnail': 'https://youix.com/contents/videos_screenshots/18000/18485/preview_480x320_youix_com.mp4.jpg',
2298 }
2299 }, {
2300 # KVS Player
2301 'url': 'https://youix.com/embed/18485',
2302 'md5': '94f96ba95706dc3880812b27b7d8a2b8',
2303 'info_dict': {
2304 'id': '18485',
2305 'display_id': 'leningrad-zoj',
2306 'ext': 'mp4',
2307 'title': 'Ленинград - ЗОЖ',
2308 'thumbnail': 'https://youix.com/contents/videos_screenshots/18000/18485/preview_480x320_youix_com.mp4.jpg',
2309 }
2310 }, {
2311 # KVS Player
2312 'url': 'https://bogmedia.org/videos/21217/40-nochey-40-nights-2016/',
2313 'md5': '94166bdb26b4cb1fb9214319a629fc51',
2314 'info_dict': {
2315 'id': '21217',
2316 'display_id': '40-nochey-40-nights-2016',
2317 'ext': 'mp4',
2318 'title': '40 ночей (2016) - BogMedia.org',
2319 'thumbnail': 'https://bogmedia.org/contents/videos_screenshots/21000/21217/preview_480p.mp4.jpg',
2320 }
2321 },
2322 ]
2323
2324 def report_following_redirect(self, new_url):
2325 """Report information extraction."""
2326 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2327
2328 def _extract_rss(self, url, video_id, doc):
2329 playlist_title = doc.find('./channel/title').text
2330 playlist_desc_el = doc.find('./channel/description')
2331 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2332
2333 NS_MAP = {
2334 'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
2335 }
2336
2337 entries = []
2338 for it in doc.findall('./channel/item'):
2339 next_url = None
2340 enclosure_nodes = it.findall('./enclosure')
2341 for e in enclosure_nodes:
2342 next_url = e.attrib.get('url')
2343 if next_url:
2344 break
2345
2346 if not next_url:
2347 next_url = xpath_text(it, 'link', fatal=False)
2348
2349 if not next_url:
2350 continue
2351
2352 def itunes(key):
2353 return xpath_text(
2354 it, xpath_with_ns('./itunes:%s' % key, NS_MAP),
2355 default=None)
2356
2357 duration = itunes('duration')
2358 explicit = (itunes('explicit') or '').lower()
2359 if explicit in ('true', 'yes'):
2360 age_limit = 18
2361 elif explicit in ('false', 'no'):
2362 age_limit = 0
2363 else:
2364 age_limit = None
2365
2366 entries.append({
2367 '_type': 'url_transparent',
2368 'url': next_url,
2369 'title': it.find('title').text,
2370 'description': xpath_text(it, 'description', default=None),
2371 'timestamp': unified_timestamp(
2372 xpath_text(it, 'pubDate', default=None)),
2373 'duration': int_or_none(duration) or parse_duration(duration),
2374 'thumbnail': url_or_none(xpath_attr(it, xpath_with_ns('./itunes:image', NS_MAP), 'href')),
2375 'episode': itunes('title'),
2376 'episode_number': int_or_none(itunes('episode')),
2377 'season_number': int_or_none(itunes('season')),
2378 'age_limit': age_limit,
2379 })
2380
2381 return {
2382 '_type': 'playlist',
2383 'id': url,
2384 'title': playlist_title,
2385 'description': playlist_desc,
2386 'entries': entries,
2387 }
2388
2389 def _extract_camtasia(self, url, video_id, webpage):
2390 """ Returns None if no camtasia video can be found. """
2391
2392 camtasia_cfg = self._search_regex(
2393 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2394 webpage, 'camtasia configuration file', default=None)
2395 if camtasia_cfg is None:
2396 return None
2397
2398 title = self._html_search_meta('DC.title', webpage, fatal=True)
2399
2400 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2401 camtasia_cfg = self._download_xml(
2402 camtasia_url, video_id,
2403 note='Downloading camtasia configuration',
2404 errnote='Failed to download camtasia configuration')
2405 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2406
2407 entries = []
2408 for n in fileset_node.getchildren():
2409 url_n = n.find('./uri')
2410 if url_n is None:
2411 continue
2412
2413 entries.append({
2414 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2415 'title': '%s - %s' % (title, n.tag),
2416 'url': compat_urlparse.urljoin(url, url_n.text),
2417 'duration': float_or_none(n.find('./duration').text),
2418 })
2419
2420 return {
2421 '_type': 'playlist',
2422 'entries': entries,
2423 'title': title,
2424 }
2425
2426 def _kvs_getrealurl(self, video_url, license_code):
2427 if not video_url.startswith('function/0/'):
2428 return video_url # not obfuscated
2429
2430 url_path, _, url_query = video_url.partition('?')
2431 urlparts = url_path.split('/')[2:]
2432 license = self._kvs_getlicensetoken(license_code)
2433 newmagic = urlparts[5][:32]
2434
2435 for o in range(len(newmagic) - 1, -1, -1):
2436 new = ''
2437 l = (o + sum([int(n) for n in license[o:]])) % 32
2438
2439 for i in range(0, len(newmagic)):
2440 if i == o:
2441 new += newmagic[l]
2442 elif i == l:
2443 new += newmagic[o]
2444 else:
2445 new += newmagic[i]
2446 newmagic = new
2447
2448 urlparts[5] = newmagic + urlparts[5][32:]
2449 return '/'.join(urlparts) + '?' + url_query
2450
2451 def _kvs_getlicensetoken(self, license):
2452 modlicense = license.replace('$', '').replace('0', '1')
2453 center = int(len(modlicense) / 2)
2454 fronthalf = int(modlicense[:center + 1])
2455 backhalf = int(modlicense[center:])
2456
2457 modlicense = str(4 * abs(fronthalf - backhalf))
2458 retval = ''
2459 for o in range(0, center + 1):
2460 for i in range(1, 5):
2461 retval += str((int(license[o + i]) + int(modlicense[o])) % 10)
2462 return retval
2463
2464 def _real_extract(self, url):
2465 if url.startswith('//'):
2466 return self.url_result(self.http_scheme() + url)
2467
2468 parsed_url = compat_urlparse.urlparse(url)
2469 if not parsed_url.scheme:
2470 default_search = self.get_param('default_search')
2471 if default_search is None:
2472 default_search = 'fixup_error'
2473
2474 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2475 if re.match(r'^[^\s/]+\.[^\s/]+/', url):
2476 self.report_warning('The url doesn\'t specify the protocol, trying with http')
2477 return self.url_result('http://' + url)
2478 elif default_search != 'fixup_error':
2479 if default_search == 'auto_warning':
2480 if re.match(r'^(?:url|URL)$', url):
2481 raise ExtractorError(
2482 'Invalid URL: %r . Call yt-dlp like this: yt-dlp -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2483 expected=True)
2484 else:
2485 self.report_warning(
2486 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2487 return self.url_result('ytsearch:' + url)
2488
2489 if default_search in ('error', 'fixup_error'):
2490 raise ExtractorError(
2491 '%r is not a valid URL. '
2492 'Set --default-search "ytsearch" (or run yt-dlp "ytsearch:%s" ) to search YouTube'
2493 % (url, url), expected=True)
2494 else:
2495 if ':' not in default_search:
2496 default_search += ':'
2497 return self.url_result(default_search + url)
2498
2499 url, smuggled_data = unsmuggle_url(url)
2500 force_videoid = None
2501 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2502 if smuggled_data and 'force_videoid' in smuggled_data:
2503 force_videoid = smuggled_data['force_videoid']
2504 video_id = force_videoid
2505 else:
2506 video_id = self._generic_id(url)
2507
2508 self.to_screen('%s: Requesting header' % video_id)
2509
2510 head_req = HEADRequest(url)
2511 head_response = self._request_webpage(
2512 head_req, video_id,
2513 note=False, errnote='Could not send HEAD request to %s' % url,
2514 fatal=False)
2515
2516 if head_response is not False:
2517 # Check for redirect
2518 new_url = head_response.geturl()
2519 if url != new_url:
2520 self.report_following_redirect(new_url)
2521 if force_videoid:
2522 new_url = smuggle_url(
2523 new_url, {'force_videoid': force_videoid})
2524 return self.url_result(new_url)
2525
2526 full_response = None
2527 if head_response is False:
2528 request = sanitized_Request(url)
2529 request.add_header('Accept-Encoding', '*')
2530 full_response = self._request_webpage(request, video_id)
2531 head_response = full_response
2532
2533 info_dict = {
2534 'id': video_id,
2535 'title': self._generic_title(url),
2536 'timestamp': unified_timestamp(head_response.headers.get('Last-Modified'))
2537 }
2538
2539 # Check for direct link to a video
2540 content_type = head_response.headers.get('Content-Type', '').lower()
2541 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2542 if m:
2543 format_id = compat_str(m.group('format_id'))
2544 subtitles = {}
2545 if format_id.endswith('mpegurl'):
2546 formats, subtitles = self._extract_m3u8_formats_and_subtitles(url, video_id, 'mp4')
2547 elif format_id == 'f4m':
2548 formats = self._extract_f4m_formats(url, video_id)
2549 else:
2550 formats = [{
2551 'format_id': format_id,
2552 'url': url,
2553 'vcodec': 'none' if m.group('type') == 'audio' else None
2554 }]
2555 info_dict['direct'] = True
2556 self._sort_formats(formats)
2557 info_dict['formats'] = formats
2558 info_dict['subtitles'] = subtitles
2559 return info_dict
2560
2561 if not self.get_param('test', False) and not is_intentional:
2562 force = self.get_param('force_generic_extractor', False)
2563 self.report_warning(
2564 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2565
2566 if not full_response:
2567 request = sanitized_Request(url)
2568 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2569 # making it impossible to download only chunk of the file (yet we need only 512kB to
2570 # test whether it's HTML or not). According to yt-dlp default Accept-Encoding
2571 # that will always result in downloading the whole file that is not desirable.
2572 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2573 # to accept raw bytes and being able to download only a chunk.
2574 # It may probably better to solve this by checking Content-Type for application/octet-stream
2575 # after HEAD request finishes, but not sure if we can rely on this.
2576 request.add_header('Accept-Encoding', '*')
2577 full_response = self._request_webpage(request, video_id)
2578
2579 first_bytes = full_response.read(512)
2580
2581 # Is it an M3U playlist?
2582 if first_bytes.startswith(b'#EXTM3U'):
2583 info_dict['formats'], info_dict['subtitles'] = self._extract_m3u8_formats_and_subtitles(url, video_id, 'mp4')
2584 self._sort_formats(info_dict['formats'])
2585 return info_dict
2586
2587 # Maybe it's a direct link to a video?
2588 # Be careful not to download the whole thing!
2589 if not is_html(first_bytes):
2590 self.report_warning(
2591 'URL could be a direct video link, returning it as such.')
2592 info_dict.update({
2593 'direct': True,
2594 'url': url,
2595 })
2596 return info_dict
2597
2598 webpage = self._webpage_read_content(
2599 full_response, url, video_id, prefix=first_bytes)
2600
2601 if '<title>DPG Media Privacy Gate</title>' in webpage:
2602 webpage = self._download_webpage(url, video_id)
2603
2604 self.report_extraction(video_id)
2605
2606 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2607 try:
2608 try:
2609 doc = compat_etree_fromstring(webpage)
2610 except compat_xml_parse_error:
2611 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2612 if doc.tag == 'rss':
2613 return self._extract_rss(url, video_id, doc)
2614 elif doc.tag == 'SmoothStreamingMedia':
2615 info_dict['formats'], info_dict['subtitles'] = self._parse_ism_formats_and_subtitles(doc, url)
2616 self._sort_formats(info_dict['formats'])
2617 return info_dict
2618 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2619 smil = self._parse_smil(doc, url, video_id)
2620 self._sort_formats(smil['formats'])
2621 return smil
2622 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2623 return self.playlist_result(
2624 self._parse_xspf(
2625 doc, video_id, xspf_url=url,
2626 xspf_base_url=full_response.geturl()),
2627 video_id)
2628 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2629 info_dict['formats'], info_dict['subtitles'] = self._parse_mpd_formats_and_subtitles(
2630 doc,
2631 mpd_base_url=full_response.geturl().rpartition('/')[0],
2632 mpd_url=url)
2633 self._sort_formats(info_dict['formats'])
2634 return info_dict
2635 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2636 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2637 self._sort_formats(info_dict['formats'])
2638 return info_dict
2639 except compat_xml_parse_error:
2640 pass
2641
2642 # Is it a Camtasia project?
2643 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2644 if camtasia_res is not None:
2645 return camtasia_res
2646
2647 # Sometimes embedded video player is hidden behind percent encoding
2648 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
2649 # Unescaping the whole page allows to handle those cases in a generic way
2650 # FIXME: unescaping the whole page may break URLs, commenting out for now.
2651 # There probably should be a second run of generic extractor on unescaped webpage.
2652 # webpage = compat_urllib_parse_unquote(webpage)
2653
2654 # Unescape squarespace embeds to be detected by generic extractor,
2655 # see https://github.com/ytdl-org/youtube-dl/issues/21294
2656 webpage = re.sub(
2657 r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
2658 lambda x: unescapeHTML(x.group(0)), webpage)
2659
2660 # it's tempting to parse this further, but you would
2661 # have to take into account all the variations like
2662 # Video Title - Site Name
2663 # Site Name | Video Title
2664 # Video Title - Tagline | Site Name
2665 # and so on and so forth; it's just not practical
2666 video_title = self._og_search_title(
2667 webpage, default=None) or self._html_search_regex(
2668 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2669 default='video')
2670
2671 # Try to detect age limit automatically
2672 age_limit = self._rta_search(webpage)
2673 # And then there are the jokers who advertise that they use RTA,
2674 # but actually don't.
2675 AGE_LIMIT_MARKERS = [
2676 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2677 ]
2678 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2679 age_limit = 18
2680
2681 # video uploader is domain name
2682 video_uploader = self._search_regex(
2683 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2684
2685 video_description = self._og_search_description(webpage, default=None)
2686 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2687
2688 info_dict.update({
2689 'title': video_title,
2690 'description': video_description,
2691 'thumbnail': video_thumbnail,
2692 'age_limit': age_limit,
2693 })
2694
2695 # Look for Brightcove Legacy Studio embeds
2696 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2697 if bc_urls:
2698 entries = [{
2699 '_type': 'url',
2700 'url': smuggle_url(bc_url, {'Referer': url}),
2701 'ie_key': 'BrightcoveLegacy'
2702 } for bc_url in bc_urls]
2703
2704 return {
2705 '_type': 'playlist',
2706 'title': video_title,
2707 'id': video_id,
2708 'entries': entries,
2709 }
2710
2711 # Look for Brightcove New Studio embeds
2712 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2713 if bc_urls:
2714 return self.playlist_from_matches(
2715 bc_urls, video_id, video_title,
2716 getter=lambda x: smuggle_url(x, {'referrer': url}),
2717 ie='BrightcoveNew')
2718
2719 # Look for Nexx embeds
2720 nexx_urls = NexxIE._extract_urls(webpage)
2721 if nexx_urls:
2722 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2723
2724 # Look for Nexx iFrame embeds
2725 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2726 if nexx_embed_urls:
2727 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2728
2729 # Look for ThePlatform embeds
2730 tp_urls = ThePlatformIE._extract_urls(webpage)
2731 if tp_urls:
2732 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2733
2734 arc_urls = ArcPublishingIE._extract_urls(webpage)
2735 if arc_urls:
2736 return self.playlist_from_matches(arc_urls, video_id, video_title, ie=ArcPublishingIE.ie_key())
2737
2738 mychannels_urls = MedialaanIE._extract_urls(webpage)
2739 if mychannels_urls:
2740 return self.playlist_from_matches(
2741 mychannels_urls, video_id, video_title, ie=MedialaanIE.ie_key())
2742
2743 # Look for embedded rtl.nl player
2744 matches = re.findall(
2745 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2746 webpage)
2747 if matches:
2748 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2749
2750 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2751 if vimeo_urls:
2752 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2753
2754 vhx_url = VHXEmbedIE._extract_url(webpage)
2755 if vhx_url:
2756 return self.url_result(vhx_url, VHXEmbedIE.ie_key())
2757
2758 # Invidious Instances
2759 # https://github.com/yt-dlp/yt-dlp/issues/195
2760 # https://github.com/iv-org/invidious/pull/1730
2761 youtube_url = self._search_regex(
2762 r'<link rel="alternate" href="(https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
2763 webpage, 'youtube link', default=None)
2764 if youtube_url:
2765 return self.url_result(youtube_url, YoutubeIE.ie_key())
2766
2767 # Look for YouTube embeds
2768 youtube_urls = YoutubeIE._extract_urls(webpage)
2769 if youtube_urls:
2770 return self.playlist_from_matches(
2771 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2772
2773 matches = DailymotionIE._extract_urls(webpage)
2774 if matches:
2775 return self.playlist_from_matches(matches, video_id, video_title)
2776
2777 # Look for embedded Dailymotion playlist player (#3822)
2778 m = re.search(
2779 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2780 if m:
2781 playlists = re.findall(
2782 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2783 if playlists:
2784 return self.playlist_from_matches(
2785 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2786
2787 # Look for DailyMail embeds
2788 dailymail_urls = DailyMailIE._extract_urls(webpage)
2789 if dailymail_urls:
2790 return self.playlist_from_matches(
2791 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2792
2793 # Look for Teachable embeds, must be before Wistia
2794 teachable_url = TeachableIE._extract_url(webpage, url)
2795 if teachable_url:
2796 return self.url_result(teachable_url)
2797
2798 # Look for embedded Wistia player
2799 wistia_urls = WistiaIE._extract_urls(webpage)
2800 if wistia_urls:
2801 playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
2802 for entry in playlist['entries']:
2803 entry.update({
2804 '_type': 'url_transparent',
2805 'uploader': video_uploader,
2806 })
2807 return playlist
2808
2809 # Look for SVT player
2810 svt_url = SVTIE._extract_url(webpage)
2811 if svt_url:
2812 return self.url_result(svt_url, 'SVT')
2813
2814 # Look for Bandcamp pages with custom domain
2815 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2816 if mobj is not None:
2817 burl = unescapeHTML(mobj.group(1))
2818 # Don't set the extractor because it can be a track url or an album
2819 return self.url_result(burl)
2820
2821 # Look for embedded Vevo player
2822 mobj = re.search(
2823 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2824 if mobj is not None:
2825 return self.url_result(mobj.group('url'))
2826
2827 # Look for embedded Viddler player
2828 mobj = re.search(
2829 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2830 webpage)
2831 if mobj is not None:
2832 return self.url_result(mobj.group('url'))
2833
2834 # Look for NYTimes player
2835 mobj = re.search(
2836 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2837 webpage)
2838 if mobj is not None:
2839 return self.url_result(mobj.group('url'))
2840
2841 # Look for Libsyn player
2842 mobj = re.search(
2843 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2844 if mobj is not None:
2845 return self.url_result(mobj.group('url'))
2846
2847 # Look for Ooyala videos
2848 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
2849 or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2850 or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2851 or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
2852 or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2853 if mobj is not None:
2854 embed_token = self._search_regex(
2855 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2856 webpage, 'ooyala embed token', default=None)
2857 return OoyalaIE._build_url_result(smuggle_url(
2858 mobj.group('ec'), {
2859 'domain': url,
2860 'embed_token': embed_token,
2861 }))
2862
2863 # Look for multiple Ooyala embeds on SBN network websites
2864 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2865 if mobj is not None:
2866 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2867 if embeds:
2868 return self.playlist_from_matches(
2869 embeds, video_id, video_title,
2870 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2871
2872 # Look for Aparat videos
2873 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2874 if mobj is not None:
2875 return self.url_result(mobj.group(1), 'Aparat')
2876
2877 # Look for MPORA videos
2878 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2879 if mobj is not None:
2880 return self.url_result(mobj.group(1), 'Mpora')
2881
2882 # Look for embedded Facebook player
2883 facebook_urls = FacebookIE._extract_urls(webpage)
2884 if facebook_urls:
2885 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2886
2887 # Look for embedded VK player
2888 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2889 if mobj is not None:
2890 return self.url_result(mobj.group('url'), 'VK')
2891
2892 # Look for embedded Odnoklassniki player
2893 odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
2894 if odnoklassniki_url:
2895 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
2896
2897 # Look for sibnet embedded player
2898 sibnet_urls = VKIE._extract_sibnet_urls(webpage)
2899 if sibnet_urls:
2900 return self.playlist_from_matches(sibnet_urls, video_id, video_title)
2901
2902 # Look for embedded ivi player
2903 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2904 if mobj is not None:
2905 return self.url_result(mobj.group('url'), 'Ivi')
2906
2907 # Look for embedded Huffington Post player
2908 mobj = re.search(
2909 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2910 if mobj is not None:
2911 return self.url_result(mobj.group('url'), 'HuffPost')
2912
2913 # Look for embed.ly
2914 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2915 if mobj is not None:
2916 return self.url_result(mobj.group('url'))
2917 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2918 if mobj is not None:
2919 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2920
2921 # Look for funnyordie embed
2922 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2923 if matches:
2924 return self.playlist_from_matches(
2925 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2926
2927 # Look for Simplecast embeds
2928 simplecast_urls = SimplecastIE._extract_urls(webpage)
2929 if simplecast_urls:
2930 return self.playlist_from_matches(
2931 simplecast_urls, video_id, video_title)
2932
2933 # Look for BBC iPlayer embed
2934 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2935 if matches:
2936 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2937
2938 # Look for embedded RUTV player
2939 rutv_url = RUTVIE._extract_url(webpage)
2940 if rutv_url:
2941 return self.url_result(rutv_url, 'RUTV')
2942
2943 # Look for embedded TVC player
2944 tvc_url = TVCIE._extract_url(webpage)
2945 if tvc_url:
2946 return self.url_result(tvc_url, 'TVC')
2947
2948 # Look for embedded SportBox player
2949 sportbox_urls = SportBoxIE._extract_urls(webpage)
2950 if sportbox_urls:
2951 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
2952
2953 # Look for embedded XHamster player
2954 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2955 if xhamster_urls:
2956 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2957
2958 # Look for embedded TNAFlixNetwork player
2959 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2960 if tnaflix_urls:
2961 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2962
2963 # Look for embedded PornHub player
2964 pornhub_urls = PornHubIE._extract_urls(webpage)
2965 if pornhub_urls:
2966 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2967
2968 # Look for embedded DrTuber player
2969 drtuber_urls = DrTuberIE._extract_urls(webpage)
2970 if drtuber_urls:
2971 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2972
2973 # Look for embedded RedTube player
2974 redtube_urls = RedTubeIE._extract_urls(webpage)
2975 if redtube_urls:
2976 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2977
2978 # Look for embedded Tube8 player
2979 tube8_urls = Tube8IE._extract_urls(webpage)
2980 if tube8_urls:
2981 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2982
2983 # Look for embedded Mofosex player
2984 mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
2985 if mofosex_urls:
2986 return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
2987
2988 # Look for embedded Spankwire player
2989 spankwire_urls = SpankwireIE._extract_urls(webpage)
2990 if spankwire_urls:
2991 return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
2992
2993 # Look for embedded YouPorn player
2994 youporn_urls = YouPornIE._extract_urls(webpage)
2995 if youporn_urls:
2996 return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
2997
2998 # Look for embedded Tvigle player
2999 mobj = re.search(
3000 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
3001 if mobj is not None:
3002 return self.url_result(mobj.group('url'), 'Tvigle')
3003
3004 # Look for embedded TED player
3005 mobj = re.search(
3006 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
3007 if mobj is not None:
3008 return self.url_result(mobj.group('url'), 'TED')
3009
3010 # Look for embedded Ustream videos
3011 ustream_url = UstreamIE._extract_url(webpage)
3012 if ustream_url:
3013 return self.url_result(ustream_url, UstreamIE.ie_key())
3014
3015 # Look for embedded arte.tv player
3016 arte_urls = ArteTVEmbedIE._extract_urls(webpage)
3017 if arte_urls:
3018 return self.playlist_from_matches(arte_urls, video_id, video_title)
3019
3020 # Look for embedded francetv player
3021 mobj = re.search(
3022 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
3023 webpage)
3024 if mobj is not None:
3025 return self.url_result(mobj.group('url'))
3026
3027 # Look for embedded Myvi.ru player
3028 myvi_url = MyviIE._extract_url(webpage)
3029 if myvi_url:
3030 return self.url_result(myvi_url)
3031
3032 # Look for embedded soundcloud player
3033 soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
3034 if soundcloud_urls:
3035 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
3036
3037 # Look for tunein player
3038 tunein_urls = TuneInBaseIE._extract_urls(webpage)
3039 if tunein_urls:
3040 return self.playlist_from_matches(tunein_urls, video_id, video_title)
3041
3042 # Look for embedded mtvservices player
3043 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
3044 if mtvservices_url:
3045 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
3046
3047 # Look for embedded yahoo player
3048 mobj = re.search(
3049 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
3050 webpage)
3051 if mobj is not None:
3052 return self.url_result(mobj.group('url'), 'Yahoo')
3053
3054 # Look for embedded sbs.com.au player
3055 mobj = re.search(
3056 r'''(?x)
3057 (?:
3058 <meta\s+property="og:video"\s+content=|
3059 <iframe[^>]+?src=
3060 )
3061 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
3062 webpage)
3063 if mobj is not None:
3064 return self.url_result(mobj.group('url'), 'SBS')
3065
3066 # Look for embedded Cinchcast player
3067 mobj = re.search(
3068 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
3069 webpage)
3070 if mobj is not None:
3071 return self.url_result(mobj.group('url'), 'Cinchcast')
3072
3073 mobj = re.search(
3074 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
3075 webpage)
3076 if not mobj:
3077 mobj = re.search(
3078 r'data-video-link=["\'](?P<url>http://m\.mlb\.com/video/[^"\']+)',
3079 webpage)
3080 if mobj is not None:
3081 return self.url_result(mobj.group('url'), 'MLB')
3082
3083 mobj = re.search(
3084 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
3085 webpage)
3086 if mobj is not None:
3087 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
3088
3089 mobj = re.search(
3090 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
3091 webpage)
3092 if mobj is not None:
3093 return self.url_result(mobj.group('url'), 'Livestream')
3094
3095 # Look for Zapiks embed
3096 mobj = re.search(
3097 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
3098 if mobj is not None:
3099 return self.url_result(mobj.group('url'), 'Zapiks')
3100
3101 # Look for Kaltura embeds
3102 kaltura_urls = KalturaIE._extract_urls(webpage)
3103 if kaltura_urls:
3104 return self.playlist_from_matches(
3105 kaltura_urls, video_id, video_title,
3106 getter=lambda x: smuggle_url(x, {'source_url': url}),
3107 ie=KalturaIE.ie_key())
3108
3109 # Look for EaglePlatform embeds
3110 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
3111 if eagleplatform_url:
3112 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
3113
3114 # Look for ClipYou (uses EaglePlatform) embeds
3115 mobj = re.search(
3116 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
3117 if mobj is not None:
3118 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
3119
3120 # Look for Pladform embeds
3121 pladform_url = PladformIE._extract_url(webpage)
3122 if pladform_url:
3123 return self.url_result(pladform_url)
3124
3125 # Look for Videomore embeds
3126 videomore_url = VideomoreIE._extract_url(webpage)
3127 if videomore_url:
3128 return self.url_result(videomore_url)
3129
3130 # Look for Webcaster embeds
3131 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
3132 if webcaster_url:
3133 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
3134
3135 # Look for Playwire embeds
3136 mobj = re.search(
3137 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
3138 if mobj is not None:
3139 return self.url_result(mobj.group('url'))
3140
3141 # Look for 5min embeds
3142 mobj = re.search(
3143 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
3144 if mobj is not None:
3145 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
3146
3147 # Look for Crooks and Liars embeds
3148 mobj = re.search(
3149 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
3150 if mobj is not None:
3151 return self.url_result(mobj.group('url'))
3152
3153 # Look for NBC Sports VPlayer embeds
3154 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
3155 if nbc_sports_url:
3156 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
3157
3158 # Look for NBC News embeds
3159 nbc_news_embed_url = re.search(
3160 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
3161 if nbc_news_embed_url:
3162 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
3163
3164 # Look for Google Drive embeds
3165 google_drive_url = GoogleDriveIE._extract_url(webpage)
3166 if google_drive_url:
3167 return self.url_result(google_drive_url, 'GoogleDrive')
3168
3169 # Look for UDN embeds
3170 mobj = re.search(
3171 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
3172 if mobj is not None:
3173 return self.url_result(
3174 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
3175
3176 # Look for Senate ISVP iframe
3177 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
3178 if senate_isvp_url:
3179 return self.url_result(senate_isvp_url, 'SenateISVP')
3180
3181 # Look for Kinja embeds
3182 kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
3183 if kinja_embed_urls:
3184 return self.playlist_from_matches(
3185 kinja_embed_urls, video_id, video_title)
3186
3187 # Look for OnionStudios embeds
3188 onionstudios_url = OnionStudiosIE._extract_url(webpage)
3189 if onionstudios_url:
3190 return self.url_result(onionstudios_url)
3191
3192 # Look for ViewLift embeds
3193 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
3194 if viewlift_url:
3195 return self.url_result(viewlift_url)
3196
3197 # Look for JWPlatform embeds
3198 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
3199 if jwplatform_urls:
3200 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
3201
3202 # Look for Digiteka embeds
3203 digiteka_url = DigitekaIE._extract_url(webpage)
3204 if digiteka_url:
3205 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
3206
3207 # Look for Arkena embeds
3208 arkena_url = ArkenaIE._extract_url(webpage)
3209 if arkena_url:
3210 return self.url_result(arkena_url, ArkenaIE.ie_key())
3211
3212 # Look for Piksel embeds
3213 piksel_url = PikselIE._extract_url(webpage)
3214 if piksel_url:
3215 return self.url_result(piksel_url, PikselIE.ie_key())
3216
3217 # Look for Limelight embeds
3218 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
3219 if limelight_urls:
3220 return self.playlist_result(
3221 limelight_urls, video_id, video_title, video_description)
3222
3223 # Look for Anvato embeds
3224 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
3225 if anvato_urls:
3226 return self.playlist_result(
3227 anvato_urls, video_id, video_title, video_description)
3228
3229 # Look for AdobeTVVideo embeds
3230 mobj = re.search(
3231 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
3232 webpage)
3233 if mobj is not None:
3234 return self.url_result(
3235 self._proto_relative_url(unescapeHTML(mobj.group(1))),
3236 'AdobeTVVideo')
3237
3238 # Look for Vine embeds
3239 mobj = re.search(
3240 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
3241 webpage)
3242 if mobj is not None:
3243 return self.url_result(
3244 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
3245
3246 # Look for VODPlatform embeds
3247 mobj = re.search(
3248 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
3249 webpage)
3250 if mobj is not None:
3251 return self.url_result(
3252 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
3253
3254 # Look for Mangomolo embeds
3255 mobj = re.search(
3256 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
3257 (?:
3258 admin\.mangomolo\.com/analytics/index\.php/customers/embed|
3259 player\.mangomolo\.com/v1
3260 )/
3261 (?:
3262 video\?.*?\bid=(?P<video_id>\d+)|
3263 (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
3264 ).+?)\1''', webpage)
3265 if mobj is not None:
3266 info = {
3267 '_type': 'url_transparent',
3268 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
3269 'title': video_title,
3270 'description': video_description,
3271 'thumbnail': video_thumbnail,
3272 'uploader': video_uploader,
3273 }
3274 video_id = mobj.group('video_id')
3275 if video_id:
3276 info.update({
3277 'ie_key': 'MangomoloVideo',
3278 'id': video_id,
3279 })
3280 else:
3281 info.update({
3282 'ie_key': 'MangomoloLive',
3283 'id': mobj.group('channel_id'),
3284 })
3285 return info
3286
3287 # Look for Instagram embeds
3288 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
3289 if instagram_embed_url is not None:
3290 return self.url_result(
3291 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
3292
3293 # Look for 3Q SDN embeds
3294 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
3295 if threeqsdn_url:
3296 return {
3297 '_type': 'url_transparent',
3298 'ie_key': ThreeQSDNIE.ie_key(),
3299 'url': self._proto_relative_url(threeqsdn_url),
3300 'title': video_title,
3301 'description': video_description,
3302 'thumbnail': video_thumbnail,
3303 'uploader': video_uploader,
3304 }
3305
3306 # Look for VBOX7 embeds
3307 vbox7_url = Vbox7IE._extract_url(webpage)
3308 if vbox7_url:
3309 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3310
3311 # Look for DBTV embeds
3312 dbtv_urls = DBTVIE._extract_urls(webpage)
3313 if dbtv_urls:
3314 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
3315
3316 # Look for Videa embeds
3317 videa_urls = VideaIE._extract_urls(webpage)
3318 if videa_urls:
3319 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
3320
3321 # Look for 20 minuten embeds
3322 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3323 if twentymin_urls:
3324 return self.playlist_from_matches(
3325 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3326
3327 # Look for VideoPress embeds
3328 videopress_urls = VideoPressIE._extract_urls(webpage)
3329 if videopress_urls:
3330 return self.playlist_from_matches(
3331 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3332
3333 # Look for Rutube embeds
3334 rutube_urls = RutubeIE._extract_urls(webpage)
3335 if rutube_urls:
3336 return self.playlist_from_matches(
3337 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3338
3339 # Look for WashingtonPost embeds
3340 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3341 if wapo_urls:
3342 return self.playlist_from_matches(
3343 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3344
3345 # Look for Mediaset embeds
3346 mediaset_urls = MediasetIE._extract_urls(self, webpage)
3347 if mediaset_urls:
3348 return self.playlist_from_matches(
3349 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3350
3351 # Look for JOJ.sk embeds
3352 joj_urls = JojIE._extract_urls(webpage)
3353 if joj_urls:
3354 return self.playlist_from_matches(
3355 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3356
3357 # Look for megaphone.fm embeds
3358 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3359 if mpfn_urls:
3360 return self.playlist_from_matches(
3361 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3362
3363 # Look for vzaar embeds
3364 vzaar_urls = VzaarIE._extract_urls(webpage)
3365 if vzaar_urls:
3366 return self.playlist_from_matches(
3367 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3368
3369 channel9_urls = Channel9IE._extract_urls(webpage)
3370 if channel9_urls:
3371 return self.playlist_from_matches(
3372 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3373
3374 vshare_urls = VShareIE._extract_urls(webpage)
3375 if vshare_urls:
3376 return self.playlist_from_matches(
3377 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3378
3379 # Look for Mediasite embeds
3380 mediasite_urls = MediasiteIE._extract_urls(webpage)
3381 if mediasite_urls:
3382 entries = [
3383 self.url_result(smuggle_url(
3384 compat_urlparse.urljoin(url, mediasite_url),
3385 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3386 for mediasite_url in mediasite_urls]
3387 return self.playlist_result(entries, video_id, video_title)
3388
3389 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3390 if springboardplatform_urls:
3391 return self.playlist_from_matches(
3392 springboardplatform_urls, video_id, video_title,
3393 ie=SpringboardPlatformIE.ie_key())
3394
3395 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3396 if yapfiles_urls:
3397 return self.playlist_from_matches(
3398 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3399
3400 vice_urls = ViceIE._extract_urls(webpage)
3401 if vice_urls:
3402 return self.playlist_from_matches(
3403 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3404
3405 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3406 if xfileshare_urls:
3407 return self.playlist_from_matches(
3408 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3409
3410 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3411 if cloudflarestream_urls:
3412 return self.playlist_from_matches(
3413 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3414
3415 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3416 if peertube_urls:
3417 return self.playlist_from_matches(
3418 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3419
3420 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3421 if indavideo_urls:
3422 return self.playlist_from_matches(
3423 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3424
3425 apa_urls = APAIE._extract_urls(webpage)
3426 if apa_urls:
3427 return self.playlist_from_matches(
3428 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3429
3430 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3431 if foxnews_urls:
3432 return self.playlist_from_matches(
3433 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3434
3435 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3436 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3437 webpage)]
3438 if sharevideos_urls:
3439 return self.playlist_from_matches(
3440 sharevideos_urls, video_id, video_title)
3441
3442 viqeo_urls = ViqeoIE._extract_urls(webpage)
3443 if viqeo_urls:
3444 return self.playlist_from_matches(
3445 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3446
3447 expressen_urls = ExpressenIE._extract_urls(webpage)
3448 if expressen_urls:
3449 return self.playlist_from_matches(
3450 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3451
3452 zype_urls = ZypeIE._extract_urls(webpage)
3453 if zype_urls:
3454 return self.playlist_from_matches(
3455 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3456
3457 gedi_urls = GediDigitalIE._extract_urls(webpage)
3458 if gedi_urls:
3459 return self.playlist_from_matches(
3460 gedi_urls, video_id, video_title, ie=GediDigitalIE.ie_key())
3461
3462 # Look for RCS media group embeds
3463 rcs_urls = RCSEmbedsIE._extract_urls(webpage)
3464 if rcs_urls:
3465 return self.playlist_from_matches(
3466 rcs_urls, video_id, video_title, ie=RCSEmbedsIE.ie_key())
3467
3468 wimtv_urls = WimTVIE._extract_urls(webpage)
3469 if wimtv_urls:
3470 return self.playlist_from_matches(
3471 wimtv_urls, video_id, video_title, ie=WimTVIE.ie_key())
3472
3473 bitchute_urls = BitChuteIE._extract_urls(webpage)
3474 if bitchute_urls:
3475 return self.playlist_from_matches(
3476 bitchute_urls, video_id, video_title, ie=BitChuteIE.ie_key())
3477
3478 rumble_urls = RumbleEmbedIE._extract_urls(webpage)
3479 if len(rumble_urls) == 1:
3480 return self.url_result(rumble_urls[0], RumbleEmbedIE.ie_key())
3481 if rumble_urls:
3482 return self.playlist_from_matches(
3483 rumble_urls, video_id, video_title, ie=RumbleEmbedIE.ie_key())
3484
3485 # Look for HTML5 media
3486 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3487 if entries:
3488 if len(entries) == 1:
3489 entries[0].update({
3490 'id': video_id,
3491 'title': video_title,
3492 })
3493 else:
3494 for num, entry in enumerate(entries, start=1):
3495 entry.update({
3496 'id': '%s-%s' % (video_id, num),
3497 'title': '%s (%d)' % (video_title, num),
3498 })
3499 for entry in entries:
3500 self._sort_formats(entry['formats'])
3501 return self.playlist_result(entries, video_id, video_title)
3502
3503 jwplayer_data = self._find_jwplayer_data(
3504 webpage, video_id, transform_source=js_to_json)
3505 if jwplayer_data:
3506 try:
3507 info = self._parse_jwplayer_data(
3508 jwplayer_data, video_id, require_title=False, base_url=url)
3509 return merge_dicts(info, info_dict)
3510 except ExtractorError:
3511 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3512 pass
3513
3514 # Video.js embed
3515 mobj = re.search(
3516 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3517 webpage)
3518 if mobj is not None:
3519 sources = self._parse_json(
3520 mobj.group(1), video_id, transform_source=js_to_json,
3521 fatal=False) or []
3522 if not isinstance(sources, list):
3523 sources = [sources]
3524 formats = []
3525 subtitles = {}
3526 for source in sources:
3527 src = source.get('src')
3528 if not src or not isinstance(src, compat_str):
3529 continue
3530 src = compat_urlparse.urljoin(url, src)
3531 src_type = source.get('type')
3532 if isinstance(src_type, compat_str):
3533 src_type = src_type.lower()
3534 ext = determine_ext(src).lower()
3535 if src_type == 'video/youtube':
3536 return self.url_result(src, YoutubeIE.ie_key())
3537 if src_type == 'application/dash+xml' or ext == 'mpd':
3538 fmts, subs = self._extract_mpd_formats_and_subtitles(
3539 src, video_id, mpd_id='dash', fatal=False)
3540 formats.extend(fmts)
3541 self._merge_subtitles(subs, target=subtitles)
3542 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3543 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3544 src, video_id, 'mp4', entry_protocol='m3u8_native',
3545 m3u8_id='hls', fatal=False)
3546 formats.extend(fmts)
3547 self._merge_subtitles(subs, target=subtitles)
3548 else:
3549 formats.append({
3550 'url': src,
3551 'ext': (mimetype2ext(src_type)
3552 or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3553 'http_headers': {
3554 'Referer': full_response.geturl(),
3555 },
3556 })
3557 if formats or subtitles:
3558 self._sort_formats(formats)
3559 info_dict['formats'] = formats
3560 info_dict['subtitles'] = subtitles
3561 return info_dict
3562
3563 # Looking for http://schema.org/VideoObject
3564 json_ld = self._search_json_ld(
3565 webpage, video_id, default={}, expected_type='VideoObject')
3566 if json_ld.get('url'):
3567 return merge_dicts(json_ld, info_dict)
3568
3569 def check_video(vurl):
3570 if YoutubeIE.suitable(vurl):
3571 return True
3572 if RtmpIE.suitable(vurl):
3573 return True
3574 vpath = compat_urlparse.urlparse(vurl).path
3575 vext = determine_ext(vpath)
3576 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3577
3578 def filter_video(urls):
3579 return list(filter(check_video, urls))
3580
3581 # Start with something easy: JW Player in SWFObject
3582 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3583 if not found:
3584 # Look for gorilla-vid style embedding
3585 found = filter_video(re.findall(r'''(?sx)
3586 (?:
3587 jw_plugins|
3588 JWPlayerOptions|
3589 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3590 )
3591 .*?
3592 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3593 if not found:
3594 # Look for generic KVS player
3595 found = re.search(r'<script [^>]*?src="https://.+?/kt_player\.js\?v=(?P<ver>(?P<maj_ver>\d+)(\.\d+)+)".*?>', webpage)
3596 if found:
3597 if found.group('maj_ver') not in ['4', '5']:
3598 self.report_warning('Untested major version (%s) in player engine--Download may fail.' % found.group('ver'))
3599 flashvars = re.search(r'(?ms)<script.*?>.*?var\s+flashvars\s*=\s*(\{.*?\});.*?</script>', webpage)
3600 flashvars = self._parse_json(flashvars.group(1), video_id, transform_source=js_to_json)
3601
3602 # extract the part after the last / as the display_id from the
3603 # canonical URL.
3604 display_id = self._search_regex(
3605 r'(?:<link href="https?://[^"]+/(.+?)/?" rel="canonical"\s*/?>'
3606 r'|<link rel="canonical" href="https?://[^"]+/(.+?)/?"\s*/?>)',
3607 webpage, 'display_id', fatal=False
3608 )
3609 title = self._html_search_regex(r'<(?:h1|title)>(?:Video: )?(.+?)</(?:h1|title)>', webpage, 'title')
3610
3611 thumbnail = flashvars['preview_url']
3612 if thumbnail.startswith('//'):
3613 protocol, _, _ = url.partition('/')
3614 thumbnail = protocol + thumbnail
3615
3616 formats = []
3617 for key in ('video_url', 'video_alt_url', 'video_alt_url2'):
3618 if key in flashvars and '/get_file/' in flashvars[key]:
3619 next_format = {
3620 'url': self._kvs_getrealurl(flashvars[key], flashvars['license_code']),
3621 'format_id': flashvars.get(key + '_text', key),
3622 'ext': 'mp4',
3623 }
3624 height = re.search(r'%s_(\d+)p\.mp4(?:/[?].*)?$' % flashvars['video_id'], flashvars[key])
3625 if height:
3626 next_format['height'] = int(height.group(1))
3627 else:
3628 next_format['quality'] = 1
3629 formats.append(next_format)
3630 self._sort_formats(formats)
3631
3632 return {
3633 'id': flashvars['video_id'],
3634 'display_id': display_id,
3635 'title': title,
3636 'thumbnail': thumbnail,
3637 'formats': formats,
3638 }
3639 if not found:
3640 # Broaden the search a little bit
3641 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3642 if not found:
3643 # Broaden the findall a little bit: JWPlayer JS loader
3644 found = filter_video(re.findall(
3645 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3646 if not found:
3647 # Flow player
3648 found = filter_video(re.findall(r'''(?xs)
3649 flowplayer\("[^"]+",\s*
3650 \{[^}]+?\}\s*,
3651 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3652 ["']?url["']?\s*:\s*["']([^"']+)["']
3653 ''', webpage))
3654 if not found:
3655 # Cinerama player
3656 found = re.findall(
3657 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3658 if not found:
3659 # Try to find twitter cards info
3660 # twitter:player:stream should be checked before twitter:player since
3661 # it is expected to contain a raw stream (see
3662 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3663 found = filter_video(re.findall(
3664 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3665 if not found:
3666 # We look for Open Graph info:
3667 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3668 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3669 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3670 if m_video_type is not None:
3671 found = filter_video(re.findall(r'<meta.*?property="og:(?:video|audio)".*?content="(.*?)"', webpage))
3672 if not found:
3673 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3674 found = re.search(
3675 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3676 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3677 webpage)
3678 if not found:
3679 # Look also in Refresh HTTP header
3680 refresh_header = head_response.headers.get('Refresh')
3681 if refresh_header:
3682 # In python 2 response HTTP headers are bytestrings
3683 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3684 refresh_header = refresh_header.decode('iso-8859-1')
3685 found = re.search(REDIRECT_REGEX, refresh_header)
3686 if found:
3687 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3688 if new_url != url:
3689 self.report_following_redirect(new_url)
3690 return {
3691 '_type': 'url',
3692 'url': new_url,
3693 }
3694 else:
3695 found = None
3696
3697 if not found:
3698 # twitter:player is a https URL to iframe player that may or may not
3699 # be supported by yt-dlp thus this is checked the very last (see
3700 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3701 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3702 if embed_url and embed_url != url:
3703 return self.url_result(embed_url)
3704
3705 if not found:
3706 raise UnsupportedError(url)
3707
3708 entries = []
3709 for video_url in orderedSet(found):
3710 video_url = unescapeHTML(video_url)
3711 video_url = video_url.replace('\\/', '/')
3712 video_url = compat_urlparse.urljoin(url, video_url)
3713 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3714
3715 # Sometimes, jwplayer extraction will result in a YouTube URL
3716 if YoutubeIE.suitable(video_url):
3717 entries.append(self.url_result(video_url, 'Youtube'))
3718 continue
3719
3720 # here's a fun little line of code for you:
3721 video_id = os.path.splitext(video_id)[0]
3722
3723 entry_info_dict = {
3724 'id': video_id,
3725 'uploader': video_uploader,
3726 'title': video_title,
3727 'age_limit': age_limit,
3728 }
3729
3730 if RtmpIE.suitable(video_url):
3731 entry_info_dict.update({
3732 '_type': 'url_transparent',
3733 'ie_key': RtmpIE.ie_key(),
3734 'url': video_url,
3735 })
3736 entries.append(entry_info_dict)
3737 continue
3738
3739 ext = determine_ext(video_url)
3740 if ext == 'smil':
3741 entry_info_dict = {**self._extract_smil_info(video_url, video_id), **entry_info_dict}
3742 elif ext == 'xspf':
3743 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3744 elif ext == 'm3u8':
3745 entry_info_dict['formats'], entry_info_dict['subtitles'] = self._extract_m3u8_formats_and_subtitles(video_url, video_id, ext='mp4')
3746 elif ext == 'mpd':
3747 entry_info_dict['formats'], entry_info_dict['subtitles'] = self._extract_mpd_formats_and_subtitles(video_url, video_id)
3748 elif ext == 'f4m':
3749 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3750 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3751 # Just matching .ism/manifest is not enough to be reliably sure
3752 # whether it's actually an ISM manifest or some other streaming
3753 # manifest since there are various streaming URL formats
3754 # possible (see [1]) as well as some other shenanigans like
3755 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3756 # so on.
3757 # Thus the most reasonable way to solve this is to delegate
3758 # to generic extractor in order to look into the contents of
3759 # the manifest itself.
3760 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3761 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3762 entry_info_dict = self.url_result(
3763 smuggle_url(video_url, {'to_generic': True}),
3764 GenericIE.ie_key())
3765 else:
3766 entry_info_dict['url'] = video_url
3767
3768 if entry_info_dict.get('formats'):
3769 self._sort_formats(entry_info_dict['formats'])
3770
3771 entries.append(entry_info_dict)
3772
3773 if len(entries) == 1:
3774 return entries[0]
3775 else:
3776 for num, e in enumerate(entries, start=1):
3777 # 'url' results don't have a title
3778 if e.get('title') is not None:
3779 e['title'] = '%s (%d)' % (e['title'], num)
3780 return {
3781 '_type': 'playlist',
3782 'entries': entries,
3783 }