]> jfr.im git - yt-dlp.git/blob - youtube_dlc/extractor/generic.py
Update to ytdl-2021.01.03
[yt-dlp.git] / youtube_dlc / 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 is_html,
24 js_to_json,
25 KNOWN_EXTENSIONS,
26 merge_dicts,
27 mimetype2ext,
28 orderedSet,
29 sanitized_Request,
30 smuggle_url,
31 unescapeHTML,
32 unified_timestamp,
33 unsmuggle_url,
34 UnsupportedError,
35 url_or_none,
36 xpath_attr,
37 xpath_text,
38 )
39 from .commonprotocols import RtmpIE
40 from .brightcove import (
41 BrightcoveLegacyIE,
42 BrightcoveNewIE,
43 )
44 from .nexx import (
45 NexxIE,
46 NexxEmbedIE,
47 )
48 from .nbc import NBCSportsVPlayerIE
49 from .ooyala import OoyalaIE
50 from .rutv import RUTVIE
51 from .tvc import TVCIE
52 from .sportbox import SportBoxIE
53 from .myvi import MyviIE
54 from .condenast import CondeNastIE
55 from .udn import UDNEmbedIE
56 from .senateisvp import SenateISVPIE
57 from .svt import SVTIE
58 from .pornhub import PornHubIE
59 from .xhamster import XHamsterEmbedIE
60 from .tnaflix import TNAFlixNetworkEmbedIE
61 from .drtuber import DrTuberIE
62 from .redtube import RedTubeIE
63 from .tube8 import Tube8IE
64 from .mofosex import MofosexEmbedIE
65 from .spankwire import SpankwireIE
66 from .youporn import YouPornIE
67 from .vimeo import (
68 VimeoIE,
69 VHXEmbedIE,
70 )
71 from .dailymotion import DailymotionIE
72 from .dailymail import DailyMailIE
73 from .onionstudios import OnionStudiosIE
74 from .viewlift import ViewLiftEmbedIE
75 from .mtv import MTVServicesEmbeddedIE
76 from .pladform import PladformIE
77 from .videomore import VideomoreIE
78 from .webcaster import WebcasterFeedIE
79 from .googledrive import GoogleDriveIE
80 from .jwplatform import JWPlatformIE
81 from .digiteka import DigitekaIE
82 from .arkena import ArkenaIE
83 from .instagram import InstagramIE
84 from .liveleak import LiveLeakIE
85 from .threeqsdn import ThreeQSDNIE
86 from .theplatform import ThePlatformIE
87 from .kaltura import KalturaIE
88 from .eagleplatform import EaglePlatformIE
89 from .facebook import FacebookIE
90 from .soundcloud import SoundcloudEmbedIE
91 from .tunein import TuneInBaseIE
92 from .vbox7 import Vbox7IE
93 from .dbtv import DBTVIE
94 from .piksel import PikselIE
95 from .videa import VideaIE
96 from .twentymin import TwentyMinutenIE
97 from .ustream import UstreamIE
98 from .arte import ArteTVEmbedIE
99 from .videopress import VideoPressIE
100 from .rutube import RutubeIE
101 from .limelight import LimelightBaseIE
102 from .anvato import AnvatoIE
103 from .washingtonpost import WashingtonPostIE
104 from .wistia import WistiaIE
105 from .mediaset import MediasetIE
106 from .joj import JojIE
107 from .megaphone import MegaphoneIE
108 from .vzaar import VzaarIE
109 from .channel9 import Channel9IE
110 from .vshare import VShareIE
111 from .mediasite import MediasiteIE
112 from .springboardplatform import SpringboardPlatformIE
113 from .yapfiles import YapFilesIE
114 from .vice import ViceIE
115 from .xfileshare import XFileShareIE
116 from .cloudflarestream import CloudflareStreamIE
117 from .peertube import PeerTubeIE
118 from .teachable import TeachableIE
119 from .indavideo import IndavideoEmbedIE
120 from .apa import APAIE
121 from .foxnews import FoxNewsIE
122 from .viqeo import ViqeoIE
123 from .expressen import ExpressenIE
124 from .zype import ZypeIE
125 from .odnoklassniki import OdnoklassnikiIE
126 from .kinja import KinjaEmbedIE
127 from .gedi import GediEmbedsIE
128 from .rcs import RCSEmbedsIE
129 from .bitchute import BitChuteIE
130 from .arcpublishing import ArcPublishingIE
131
132
133 class GenericIE(InfoExtractor):
134 IE_DESC = 'Generic downloader that works on some sites'
135 _VALID_URL = r'.*'
136 IE_NAME = 'generic'
137 _TESTS = [
138 # Direct link to a video
139 {
140 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
141 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
142 'info_dict': {
143 'id': 'trailer',
144 'ext': 'mp4',
145 'title': 'trailer',
146 'upload_date': '20100513',
147 }
148 },
149 # Direct link to media delivered compressed (until Accept-Encoding is *)
150 {
151 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
152 'md5': '128c42e68b13950268b648275386fc74',
153 'info_dict': {
154 'id': 'FictionJunction-Parallel_Hearts',
155 'ext': 'flac',
156 'title': 'FictionJunction-Parallel_Hearts',
157 'upload_date': '20140522',
158 },
159 'expected_warnings': [
160 'URL could be a direct video link, returning it as such.'
161 ],
162 'skip': 'URL invalid',
163 },
164 # Direct download with broken HEAD
165 {
166 'url': 'http://ai-radio.org:8000/radio.opus',
167 'info_dict': {
168 'id': 'radio',
169 'ext': 'opus',
170 'title': 'radio',
171 },
172 'params': {
173 'skip_download': True, # infinite live stream
174 },
175 'expected_warnings': [
176 r'501.*Not Implemented',
177 r'400.*Bad Request',
178 ],
179 },
180 # Direct link with incorrect MIME type
181 {
182 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
183 'md5': '4ccbebe5f36706d85221f204d7eb5913',
184 'info_dict': {
185 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
186 'id': '5_Lennart_Poettering_-_Systemd',
187 'ext': 'webm',
188 'title': '5_Lennart_Poettering_-_Systemd',
189 'upload_date': '20141120',
190 },
191 'expected_warnings': [
192 'URL could be a direct video link, returning it as such.'
193 ]
194 },
195 # RSS feed
196 {
197 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
198 'info_dict': {
199 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
200 'title': 'Zero Punctuation',
201 'description': 're:.*groundbreaking video review series.*'
202 },
203 'playlist_mincount': 11,
204 },
205 # RSS feed with enclosure
206 {
207 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
208 'info_dict': {
209 'id': 'http://podcastfeeds.nbcnews.com/nbcnews/video/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
210 'title': 'MSNBC Rachel Maddow (video)',
211 'description': 're:.*her unique approach to storytelling.*',
212 },
213 'playlist': [{
214 'info_dict': {
215 'ext': 'mov',
216 'id': 'pdv_maddow_netcast_mov-12-03-2020-223726',
217 'title': 'MSNBC Rachel Maddow (video) - 12-03-2020-223726',
218 'description': 're:.*her unique approach to storytelling.*',
219 'upload_date': '20201204',
220 },
221 }],
222 },
223 # RSS feed with item with description and thumbnails
224 {
225 'url': 'https://anchor.fm/s/dd00e14/podcast/rss',
226 'info_dict': {
227 'id': 'https://anchor.fm/s/dd00e14/podcast/rss',
228 'title': 're:.*100% Hydrogen.*',
229 'description': 're:.*In this episode.*',
230 },
231 'playlist': [{
232 'info_dict': {
233 'ext': 'm4a',
234 'id': 'c1c879525ce2cb640b344507e682c36d',
235 'title': 're:Hydrogen!',
236 'description': 're:.*In this episode we are going.*',
237 'timestamp': 1567977776,
238 'upload_date': '20190908',
239 'duration': 459,
240 'thumbnail': r're:^https?://.*\.jpg$',
241 'episode_number': 1,
242 'season_number': 1,
243 'age_limit': 0,
244 },
245 }],
246 'params': {
247 'skip_download': True,
248 },
249 },
250 # RSS feed with enclosures and unsupported link URLs
251 {
252 'url': 'http://www.hellointernet.fm/podcast?format=rss',
253 'info_dict': {
254 'id': 'http://www.hellointernet.fm/podcast?format=rss',
255 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
256 'title': 'Hello Internet',
257 },
258 'playlist_mincount': 100,
259 },
260 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
261 {
262 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
263 'info_dict': {
264 'id': 'smil',
265 'ext': 'mp4',
266 'title': 'Automatics, robotics and biocybernetics',
267 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
268 'upload_date': '20130627',
269 'formats': 'mincount:16',
270 'subtitles': 'mincount:1',
271 },
272 'params': {
273 'force_generic_extractor': True,
274 'skip_download': True,
275 },
276 },
277 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
278 {
279 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
280 'info_dict': {
281 'id': 'hds',
282 'ext': 'flv',
283 'title': 'hds',
284 'formats': 'mincount:1',
285 },
286 'params': {
287 'skip_download': True,
288 },
289 },
290 # SMIL from https://www.restudy.dk/video/play/id/1637
291 {
292 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
293 'info_dict': {
294 'id': 'video_1637',
295 'ext': 'flv',
296 'title': 'video_1637',
297 'formats': 'mincount:3',
298 },
299 'params': {
300 'skip_download': True,
301 },
302 },
303 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
304 {
305 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
306 'info_dict': {
307 'id': 'smil-service',
308 'ext': 'flv',
309 'title': 'smil-service',
310 'formats': 'mincount:1',
311 },
312 'params': {
313 'skip_download': True,
314 },
315 },
316 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
317 {
318 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
319 'info_dict': {
320 'id': '4719370',
321 'ext': 'mp4',
322 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
323 'formats': 'mincount:3',
324 },
325 'params': {
326 'skip_download': True,
327 },
328 },
329 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
330 {
331 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
332 'info_dict': {
333 'id': 'mZlp2ctYIUEB',
334 'ext': 'mp4',
335 'title': 'Tikibad ontruimd wegens brand',
336 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
337 'thumbnail': r're:^https?://.*\.jpg$',
338 'duration': 33,
339 },
340 'params': {
341 'skip_download': True,
342 },
343 },
344 # MPD from http://dash-mse-test.appspot.com/media.html
345 {
346 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
347 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
348 'info_dict': {
349 'id': 'car-20120827-manifest',
350 'ext': 'mp4',
351 'title': 'car-20120827-manifest',
352 'formats': 'mincount:9',
353 'upload_date': '20130904',
354 },
355 'params': {
356 'format': 'bestvideo',
357 },
358 },
359 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
360 {
361 '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',
362 'info_dict': {
363 'id': 'content',
364 'ext': 'mp4',
365 'title': 'content',
366 'formats': 'mincount:8',
367 },
368 'params': {
369 # m3u8 downloads
370 'skip_download': True,
371 },
372 'skip': 'video gone',
373 },
374 # m3u8 served with Content-Type: text/plain
375 {
376 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
377 'info_dict': {
378 'id': 'index',
379 'ext': 'mp4',
380 'title': 'index',
381 'upload_date': '20140720',
382 'formats': 'mincount:11',
383 },
384 'params': {
385 # m3u8 downloads
386 'skip_download': True,
387 },
388 'skip': 'video gone',
389 },
390 # google redirect
391 {
392 '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',
393 'info_dict': {
394 'id': 'cmQHVoWB5FY',
395 'ext': 'mp4',
396 'upload_date': '20130224',
397 'uploader_id': 'TheVerge',
398 'description': r're:^Chris Ziegler takes a look at the\.*',
399 'uploader': 'The Verge',
400 'title': 'First Firefox OS phones side-by-side',
401 },
402 'params': {
403 'skip_download': False,
404 }
405 },
406 {
407 # redirect in Refresh HTTP header
408 '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',
409 'info_dict': {
410 'id': 'pO8h3EaFRdo',
411 'ext': 'mp4',
412 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
413 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
414 'upload_date': '20150917',
415 'uploader_id': 'brtvofficial',
416 'uploader': 'Boiler Room',
417 },
418 'params': {
419 'skip_download': False,
420 },
421 },
422 {
423 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
424 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
425 'info_dict': {
426 'id': '13601338388002',
427 'ext': 'mp4',
428 'uploader': 'www.hodiho.fr',
429 'title': 'R\u00e9gis plante sa Jeep',
430 }
431 },
432 # bandcamp page with custom domain
433 {
434 'add_ie': ['Bandcamp'],
435 'url': 'http://bronyrock.com/track/the-pony-mash',
436 'info_dict': {
437 'id': '3235767654',
438 'ext': 'mp3',
439 'title': 'The Pony Mash',
440 'uploader': 'M_Pallante',
441 },
442 'skip': 'There is a limit of 200 free downloads / month for the test song',
443 },
444 {
445 # embedded brightcove video
446 # it also tests brightcove videos that need to set the 'Referer'
447 # in the http requests
448 'add_ie': ['BrightcoveLegacy'],
449 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
450 'info_dict': {
451 'id': '2765128793001',
452 'ext': 'mp4',
453 'title': 'Le cours de bourse : l’analyse technique',
454 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
455 'uploader': 'BFM BUSINESS',
456 },
457 'params': {
458 'skip_download': True,
459 },
460 },
461 {
462 # embedded with itemprop embedURL and video id spelled as `idVideo`
463 'add_id': ['BrightcoveLegacy'],
464 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
465 'info_dict': {
466 'id': '5255628253001',
467 'ext': 'mp4',
468 'title': 'md5:37c519b1128915607601e75a87995fc0',
469 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
470 'uploader': 'BFM BUSINESS',
471 'uploader_id': '876450612001',
472 'timestamp': 1482255315,
473 'upload_date': '20161220',
474 },
475 'params': {
476 'skip_download': True,
477 },
478 },
479 {
480 # https://github.com/ytdl-org/youtube-dl/issues/2253
481 'url': 'http://bcove.me/i6nfkrc3',
482 'md5': '0ba9446db037002366bab3b3eb30c88c',
483 'info_dict': {
484 'id': '3101154703001',
485 'ext': 'mp4',
486 'title': 'Still no power',
487 'uploader': 'thestar.com',
488 '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.',
489 },
490 'add_ie': ['BrightcoveLegacy'],
491 'skip': 'video gone',
492 },
493 {
494 'url': 'http://www.championat.com/video/football/v/87/87499.html',
495 'md5': 'fb973ecf6e4a78a67453647444222983',
496 'info_dict': {
497 'id': '3414141473001',
498 'ext': 'mp4',
499 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
500 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
501 'uploader': 'Championat',
502 },
503 },
504 {
505 # https://github.com/ytdl-org/youtube-dl/issues/3541
506 'add_ie': ['BrightcoveLegacy'],
507 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
508 'info_dict': {
509 'id': '3866516442001',
510 'ext': 'mp4',
511 'title': 'Leer mij vrouwen kennen: Aflevering 1',
512 'description': 'Leer mij vrouwen kennen: Aflevering 1',
513 'uploader': 'SBS Broadcasting',
514 },
515 'skip': 'Restricted to Netherlands',
516 'params': {
517 'skip_download': True, # m3u8 download
518 },
519 },
520 {
521 # Brightcove video in <iframe>
522 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
523 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
524 'info_dict': {
525 'id': '5360463607001',
526 'ext': 'mp4',
527 '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',
528 '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。',
529 'uploader': 'United Nations',
530 'uploader_id': '1362235914001',
531 'timestamp': 1489593889,
532 'upload_date': '20170315',
533 },
534 'add_ie': ['BrightcoveLegacy'],
535 },
536 {
537 # Brightcove with alternative playerID key
538 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
539 'info_dict': {
540 'id': 'nmeth.2062_SV1',
541 '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',
542 },
543 'playlist': [{
544 'info_dict': {
545 'id': '2228375078001',
546 'ext': 'mp4',
547 'title': 'nmeth.2062-sv1',
548 'description': 'nmeth.2062-sv1',
549 'timestamp': 1363357591,
550 'upload_date': '20130315',
551 'uploader': 'Nature Publishing Group',
552 'uploader_id': '1964492299001',
553 },
554 }],
555 },
556 {
557 # Brightcove with UUID in videoPlayer
558 'url': 'http://www8.hp.com/cn/zh/home.html',
559 'info_dict': {
560 'id': '5255815316001',
561 'ext': 'mp4',
562 'title': 'Sprocket Video - China',
563 'description': 'Sprocket Video - China',
564 'uploader': 'HP-Video Gallery',
565 'timestamp': 1482263210,
566 'upload_date': '20161220',
567 'uploader_id': '1107601872001',
568 },
569 'params': {
570 'skip_download': True, # m3u8 download
571 },
572 'skip': 'video rotates...weekly?',
573 },
574 {
575 # Brightcove:new type [2].
576 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
577 'md5': '2b35148fcf48da41c9fb4591650784f3',
578 'info_dict': {
579 'id': '5348741021001',
580 'ext': 'mp4',
581 'upload_date': '20170306',
582 'uploader_id': '4191638492001',
583 'timestamp': 1488769918,
584 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
585
586 },
587 },
588 {
589 # Alternative brightcove <video> attributes
590 '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/',
591 'info_dict': {
592 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
593 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
594 },
595 'playlist': [{
596 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
597 'info_dict': {
598 'id': '5311302538001',
599 'ext': 'mp4',
600 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
601 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
602 'timestamp': 1486321708,
603 'upload_date': '20170205',
604 'uploader_id': '800000640001',
605 },
606 'only_matching': True,
607 }],
608 },
609 {
610 # Brightcove with UUID in videoPlayer
611 'url': 'http://www8.hp.com/cn/zh/home.html',
612 'info_dict': {
613 'id': '5255815316001',
614 'ext': 'mp4',
615 'title': 'Sprocket Video - China',
616 'description': 'Sprocket Video - China',
617 'uploader': 'HP-Video Gallery',
618 'timestamp': 1482263210,
619 'upload_date': '20161220',
620 'uploader_id': '1107601872001',
621 },
622 'params': {
623 'skip_download': True, # m3u8 download
624 },
625 },
626 # ooyala video
627 {
628 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
629 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
630 'info_dict': {
631 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
632 'ext': 'mp4',
633 'title': '2cc213299525360.mov', # that's what we get
634 'duration': 238.231,
635 },
636 'add_ie': ['Ooyala'],
637 },
638 {
639 # ooyala video embedded with http://player.ooyala.com/iframe.js
640 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
641 'info_dict': {
642 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
643 'ext': 'mp4',
644 'title': '"Steve Jobs: Man in the Machine" trailer',
645 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
646 'duration': 135.427,
647 },
648 'params': {
649 'skip_download': True,
650 },
651 'skip': 'movie expired',
652 },
653 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
654 {
655 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
656 'info_dict': {
657 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
658 'ext': 'mp4',
659 'title': 'Steampunk Fest Comes to Honesdale',
660 'duration': 43.276,
661 },
662 'params': {
663 'skip_download': True,
664 }
665 },
666 # embed.ly video
667 {
668 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
669 'info_dict': {
670 'id': '9ODmcdjQcHQ',
671 'ext': 'mp4',
672 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
673 'upload_date': '20140225',
674 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
675 'uploader': 'Tested',
676 'uploader_id': 'testedcom',
677 },
678 # No need to test YoutubeIE here
679 'params': {
680 'skip_download': True,
681 },
682 },
683 # funnyordie embed
684 {
685 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
686 'info_dict': {
687 'id': '18e820ec3f',
688 'ext': 'mp4',
689 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
690 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
691 },
692 # HEAD requests lead to endless 301, while GET is OK
693 'expected_warnings': ['301'],
694 },
695 # RUTV embed
696 {
697 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
698 'info_dict': {
699 'id': '776940',
700 'ext': 'mp4',
701 'title': 'Охотское море стало целиком российским',
702 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
703 },
704 'params': {
705 # m3u8 download
706 'skip_download': True,
707 },
708 },
709 # TVC embed
710 {
711 '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/',
712 'info_dict': {
713 'id': '55304',
714 'ext': 'mp4',
715 'title': 'Дошкольное воспитание',
716 },
717 },
718 # SportBox embed
719 {
720 'url': 'http://www.vestifinance.ru/articles/25753',
721 'info_dict': {
722 'id': '25753',
723 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
724 },
725 'playlist': [{
726 'info_dict': {
727 'id': '370908',
728 'title': 'Госзаказ. День 3',
729 'ext': 'mp4',
730 }
731 }, {
732 'info_dict': {
733 'id': '370905',
734 'title': 'Госзаказ. День 2',
735 'ext': 'mp4',
736 }
737 }, {
738 'info_dict': {
739 'id': '370902',
740 'title': 'Госзаказ. День 1',
741 'ext': 'mp4',
742 }
743 }],
744 'params': {
745 # m3u8 download
746 'skip_download': True,
747 },
748 },
749 # Myvi.ru embed
750 {
751 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
752 'info_dict': {
753 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
754 'ext': 'mp4',
755 'title': 'Ужастики, русский трейлер (2015)',
756 'thumbnail': r're:^https?://.*\.jpg$',
757 'duration': 153,
758 }
759 },
760 # XHamster embed
761 {
762 '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',
763 'info_dict': {
764 'id': 'showthread',
765 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
766 },
767 'playlist_mincount': 7,
768 # This forum does not allow <iframe> syntaxes anymore
769 # Now HTML tags are displayed as-is
770 'skip': 'No videos on this page',
771 },
772 # Embedded TED video
773 {
774 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
775 'md5': '65fdff94098e4a607385a60c5177c638',
776 'info_dict': {
777 'id': '1969',
778 'ext': 'mp4',
779 'title': 'Hidden miracles of the natural world',
780 'uploader': 'Louie Schwartzberg',
781 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
782 }
783 },
784 # nowvideo embed hidden behind percent encoding
785 {
786 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
787 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
788 'info_dict': {
789 'id': '06e53103ca9aa',
790 'ext': 'flv',
791 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
792 'description': 'No description',
793 },
794 },
795 # arte embed
796 {
797 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
798 'md5': '7653032cbb25bf6c80d80f217055fa43',
799 'info_dict': {
800 'id': '048195-004_PLUS7-F',
801 'ext': 'flv',
802 'title': 'X:enius',
803 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
804 'upload_date': '20140320',
805 },
806 'params': {
807 'skip_download': 'Requires rtmpdump'
808 },
809 'skip': 'video gone',
810 },
811 # francetv embed
812 {
813 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
814 'info_dict': {
815 'id': 'EV_30231',
816 'ext': 'mp4',
817 'title': 'Alcaline, le concert avec Calogero',
818 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
819 'upload_date': '20150226',
820 'timestamp': 1424989860,
821 'duration': 5400,
822 },
823 'params': {
824 # m3u8 downloads
825 'skip_download': True,
826 },
827 'expected_warnings': [
828 'Forbidden'
829 ]
830 },
831 # Condé Nast embed
832 {
833 'url': 'http://www.wired.com/2014/04/honda-asimo/',
834 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
835 'info_dict': {
836 'id': '53501be369702d3275860000',
837 'ext': 'mp4',
838 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
839 }
840 },
841 # Dailymotion embed
842 {
843 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
844 'md5': '441aeeb82eb72c422c7f14ec533999cd',
845 'info_dict': {
846 'id': 'k2mm4bCdJ6CQ2i7c8o2',
847 'ext': 'mp4',
848 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
849 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
850 'uploader': 'Spi0n',
851 'uploader_id': 'xgditw',
852 'upload_date': '20140425',
853 'timestamp': 1398441542,
854 },
855 'add_ie': ['Dailymotion'],
856 },
857 # DailyMail embed
858 {
859 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
860 'info_dict': {
861 'id': '1495629',
862 'ext': 'mp4',
863 'title': 'Care worker punches elderly dementia patient in head 11 times',
864 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
865 },
866 'add_ie': ['DailyMail'],
867 'params': {
868 'skip_download': True,
869 },
870 },
871 # YouTube embed
872 {
873 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
874 'info_dict': {
875 'id': 'FXRb4ykk4S0',
876 'ext': 'mp4',
877 'title': 'The NBL Auction 2014',
878 'uploader': 'BADMINTON England',
879 'uploader_id': 'BADMINTONEvents',
880 'upload_date': '20140603',
881 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
882 },
883 'add_ie': ['Youtube'],
884 'params': {
885 'skip_download': True,
886 }
887 },
888 # MTVServices embed
889 {
890 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
891 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
892 'info_dict': {
893 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
894 'ext': 'mp4',
895 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
896 'description': 'Two valets share their love for movie star Liam Neesons.',
897 'timestamp': 1349922600,
898 'upload_date': '20121011',
899 },
900 },
901 # YouTube embed via <data-embed-url="">
902 {
903 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
904 'info_dict': {
905 'id': '4vAffPZIT44',
906 'ext': 'mp4',
907 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
908 'uploader': 'Gameloft',
909 'uploader_id': 'gameloft',
910 'upload_date': '20140828',
911 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
912 },
913 'params': {
914 'skip_download': True,
915 }
916 },
917 # YouTube <object> embed
918 {
919 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
920 'md5': '516718101ec834f74318df76259fb3cc',
921 'info_dict': {
922 'id': 'msN87y-iEx0',
923 'ext': 'webm',
924 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
925 'upload_date': '20080526',
926 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
927 'uploader': 'Christopher Sykes',
928 'uploader_id': 'ChristopherJSykes',
929 },
930 'add_ie': ['Youtube'],
931 },
932 # Camtasia studio
933 {
934 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
935 'playlist': [{
936 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
937 'info_dict': {
938 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
939 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
940 'ext': 'flv',
941 'duration': 2235.90,
942 }
943 }, {
944 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
945 'info_dict': {
946 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
947 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
948 'ext': 'flv',
949 'duration': 2235.93,
950 }
951 }],
952 'info_dict': {
953 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
954 }
955 },
956 # Flowplayer
957 {
958 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
959 'md5': '9d65602bf31c6e20014319c7d07fba27',
960 'info_dict': {
961 'id': '5123ea6d5e5a7',
962 'ext': 'mp4',
963 'age_limit': 18,
964 'uploader': 'www.handjobhub.com',
965 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
966 }
967 },
968 # Multiple brightcove videos
969 # https://github.com/ytdl-org/youtube-dl/issues/2283
970 {
971 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
972 'info_dict': {
973 'id': 'always-never',
974 'title': 'Always / Never - The New Yorker',
975 },
976 'playlist_count': 3,
977 'params': {
978 'extract_flat': False,
979 'skip_download': True,
980 }
981 },
982 # MLB embed
983 {
984 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
985 'md5': '96f09a37e44da40dd083e12d9a683327',
986 'info_dict': {
987 'id': '33322633',
988 'ext': 'mp4',
989 'title': 'Ump changes call to ball',
990 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
991 'duration': 48,
992 'timestamp': 1401537900,
993 'upload_date': '20140531',
994 'thumbnail': r're:^https?://.*\.jpg$',
995 },
996 },
997 # Wistia embed
998 {
999 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
1000 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
1001 'info_dict': {
1002 'id': '6e2wtrbdaf',
1003 'ext': 'mov',
1004 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
1005 'description': 'a Paywall Videos video from Remilon',
1006 'duration': 644.072,
1007 'uploader': 'study.com',
1008 'timestamp': 1459678540,
1009 'upload_date': '20160403',
1010 'filesize': 24687186,
1011 },
1012 },
1013 {
1014 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
1015 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
1016 'info_dict': {
1017 'id': 'uxjb0lwrcz',
1018 'ext': 'mp4',
1019 'title': 'Conversation about Hexagonal Rails Part 1',
1020 'description': 'a Martin Fowler video from ThoughtWorks',
1021 'duration': 1715.0,
1022 'uploader': 'thoughtworks.wistia.com',
1023 'timestamp': 1401832161,
1024 'upload_date': '20140603',
1025 },
1026 },
1027 # Wistia standard embed (async)
1028 {
1029 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
1030 'info_dict': {
1031 'id': '807fafadvk',
1032 'ext': 'mp4',
1033 'title': 'Drip Brennan Dunn Workshop',
1034 'description': 'a JV Webinars video from getdrip-1',
1035 'duration': 4986.95,
1036 'timestamp': 1463607249,
1037 'upload_date': '20160518',
1038 },
1039 'params': {
1040 'skip_download': True,
1041 }
1042 },
1043 # Soundcloud embed
1044 {
1045 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1046 'info_dict': {
1047 'id': '174391317',
1048 'ext': 'mp3',
1049 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1050 'uploader': 'Sophos Security',
1051 'title': 'Chet Chat 171 - Oct 29, 2014',
1052 'upload_date': '20141029',
1053 }
1054 },
1055 # Soundcloud multiple embeds
1056 {
1057 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1058 'info_dict': {
1059 'id': '52809',
1060 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1061 },
1062 'playlist_mincount': 7,
1063 },
1064 # TuneIn station embed
1065 {
1066 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1067 'info_dict': {
1068 'id': '204146',
1069 'ext': 'mp3',
1070 'title': 'CNRV',
1071 'location': 'Paris, France',
1072 'is_live': True,
1073 },
1074 'params': {
1075 # Live stream
1076 'skip_download': True,
1077 },
1078 },
1079 # Livestream embed
1080 {
1081 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1082 'info_dict': {
1083 'id': '67864563',
1084 'ext': 'flv',
1085 'upload_date': '20141112',
1086 'title': 'Rosetta #CometLanding webcast HL 10',
1087 }
1088 },
1089 # Another Livestream embed, without 'new.' in URL
1090 {
1091 'url': 'https://www.freespeech.org/',
1092 'info_dict': {
1093 'id': '123537347',
1094 'ext': 'mp4',
1095 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1096 },
1097 'params': {
1098 # Live stream
1099 'skip_download': True,
1100 },
1101 },
1102 # LazyYT
1103 {
1104 'url': 'https://skiplagged.com/',
1105 'info_dict': {
1106 'id': 'skiplagged',
1107 'title': 'Skiplagged: The smart way to find cheap flights',
1108 },
1109 'playlist_mincount': 1,
1110 'add_ie': ['Youtube'],
1111 },
1112 # Cinchcast embed
1113 {
1114 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1115 'info_dict': {
1116 'id': '7141703',
1117 'ext': 'mp3',
1118 'upload_date': '20141126',
1119 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1120 }
1121 },
1122 # Cinerama player
1123 {
1124 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1125 'info_dict': {
1126 'id': '730m_DandD_1901_512k',
1127 'ext': 'mp4',
1128 'uploader': 'www.abc.net.au',
1129 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1130 }
1131 },
1132 # embedded viddler video
1133 {
1134 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1135 'info_dict': {
1136 'id': '4d03aad9',
1137 'ext': 'mp4',
1138 'uploader': 'deadspin',
1139 'title': 'WALL-TO-GORTAT',
1140 'timestamp': 1422285291,
1141 'upload_date': '20150126',
1142 },
1143 'add_ie': ['Viddler'],
1144 },
1145 # Libsyn embed
1146 {
1147 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1148 'info_dict': {
1149 'id': '3377616',
1150 'ext': 'mp3',
1151 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1152 'description': 'md5:601cb790edd05908957dae8aaa866465',
1153 'upload_date': '20150220',
1154 },
1155 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1156 },
1157 # jwplayer YouTube
1158 {
1159 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1160 'info_dict': {
1161 'id': 'Mrj4DVp2zeA',
1162 'ext': 'mp4',
1163 'upload_date': '20150212',
1164 'uploader': 'The National Archives UK',
1165 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1166 'uploader_id': 'NationalArchives08',
1167 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1168 },
1169 },
1170 # jwplayer rtmp
1171 {
1172 'url': 'http://www.suffolk.edu/sjc/live.php',
1173 'info_dict': {
1174 'id': 'live',
1175 'ext': 'flv',
1176 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1177 'uploader': 'www.suffolk.edu',
1178 },
1179 'params': {
1180 'skip_download': True,
1181 },
1182 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1183 },
1184 # Complex jwplayer
1185 {
1186 'url': 'http://www.indiedb.com/games/king-machine/videos',
1187 'info_dict': {
1188 'id': 'videos',
1189 'ext': 'mp4',
1190 'title': 'king machine trailer 1',
1191 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1192 'thumbnail': r're:^https?://.*\.jpg$',
1193 },
1194 },
1195 {
1196 # JWPlayer config passed as variable
1197 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1198 'info_dict': {
1199 'id': '3326530_hq',
1200 'ext': 'mp4',
1201 'title': 'ARIELE | Tube Cup',
1202 'uploader': 'www.txxx.com',
1203 'age_limit': 18,
1204 },
1205 'params': {
1206 'skip_download': True,
1207 }
1208 },
1209 {
1210 # JWPlatform iframe
1211 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1212 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1213 'info_dict': {
1214 'id': 'O0c5JcKT',
1215 'ext': 'mp4',
1216 'upload_date': '20171122',
1217 'timestamp': 1511366290,
1218 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1219 },
1220 'add_ie': [JWPlatformIE.ie_key()],
1221 },
1222 {
1223 # Video.js embed, multiple formats
1224 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1225 'info_dict': {
1226 'id': 'yygqldloqIk',
1227 'ext': 'mp4',
1228 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1229 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1230 'upload_date': '20130314',
1231 'uploader': 'PROстое3D',
1232 'uploader_id': 'PROstoe3D',
1233 },
1234 'params': {
1235 'skip_download': True,
1236 },
1237 },
1238 {
1239 # Video.js embed, single format
1240 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1241 'info_dict': {
1242 'id': 'watch',
1243 'ext': 'mp4',
1244 'title': 'Step 1 - Good Foundation',
1245 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1246 },
1247 'params': {
1248 'skip_download': True,
1249 },
1250 },
1251 # rtl.nl embed
1252 {
1253 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1254 'playlist_mincount': 5,
1255 'info_dict': {
1256 'id': 'aanslagen-kopenhagen',
1257 'title': 'Aanslagen Kopenhagen',
1258 }
1259 },
1260 # Zapiks embed
1261 {
1262 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1263 'info_dict': {
1264 'id': '118046',
1265 'ext': 'mp4',
1266 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1267 }
1268 },
1269 # Kaltura embed (different embed code)
1270 {
1271 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1272 'info_dict': {
1273 'id': '1_a52wc67y',
1274 'ext': 'flv',
1275 'upload_date': '20150127',
1276 'uploader_id': 'PremierMedia',
1277 'timestamp': int,
1278 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1279 },
1280 },
1281 # Kaltura embed with single quotes
1282 {
1283 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1284 'info_dict': {
1285 'id': '0_izeg5utt',
1286 'ext': 'mp4',
1287 'title': '35871',
1288 'timestamp': 1355743100,
1289 'upload_date': '20121217',
1290 'uploader_id': 'cplapp@learn360.com',
1291 },
1292 'add_ie': ['Kaltura'],
1293 },
1294 {
1295 # Kaltura embedded via quoted entry_id
1296 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1297 'info_dict': {
1298 'id': '0_utuok90b',
1299 'ext': 'mp4',
1300 'title': '06_matthew_brender_raj_dutt',
1301 'timestamp': 1466638791,
1302 'upload_date': '20160622',
1303 },
1304 'add_ie': ['Kaltura'],
1305 'expected_warnings': [
1306 'Could not send HEAD request'
1307 ],
1308 'params': {
1309 'skip_download': True,
1310 }
1311 },
1312 {
1313 # Kaltura embedded, some fileExt broken (#11480)
1314 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1315 'info_dict': {
1316 'id': '1_sgtvehim',
1317 'ext': 'mp4',
1318 'title': 'Our "Standard Models" of particle physics and cosmology',
1319 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1320 'timestamp': 1321158993,
1321 'upload_date': '20111113',
1322 'uploader_id': 'kps1',
1323 },
1324 'add_ie': ['Kaltura'],
1325 },
1326 {
1327 # Kaltura iframe embed
1328 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1329 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1330 'info_dict': {
1331 'id': '0_f2cfbpwy',
1332 'ext': 'mp4',
1333 'title': 'I. M. Pei: A Centennial Celebration',
1334 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1335 'upload_date': '20170403',
1336 'uploader_id': 'batchUser',
1337 'timestamp': 1491232186,
1338 },
1339 'add_ie': ['Kaltura'],
1340 },
1341 {
1342 # Kaltura iframe embed, more sophisticated
1343 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1344 'info_dict': {
1345 'id': '1_9gzouybz',
1346 'ext': 'mp4',
1347 'title': 'lecture-05sep2017',
1348 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1349 'upload_date': '20170913',
1350 'uploader_id': 'eps2',
1351 'timestamp': 1505340777,
1352 },
1353 'params': {
1354 'skip_download': True,
1355 },
1356 'add_ie': ['Kaltura'],
1357 },
1358 {
1359 # meta twitter:player
1360 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1361 'info_dict': {
1362 'id': '0_01b42zps',
1363 'ext': 'mp4',
1364 'title': 'Main Twerk (Video)',
1365 'upload_date': '20171208',
1366 'uploader_id': 'sebastian.salinas@thechive.com',
1367 'timestamp': 1512713057,
1368 },
1369 'params': {
1370 'skip_download': True,
1371 },
1372 'add_ie': ['Kaltura'],
1373 },
1374 # referrer protected EaglePlatform embed
1375 {
1376 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1377 'info_dict': {
1378 'id': '582306',
1379 'ext': 'mp4',
1380 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1381 'thumbnail': r're:^https?://.*\.jpg$',
1382 'duration': 3382,
1383 'view_count': int,
1384 },
1385 'params': {
1386 'skip_download': True,
1387 },
1388 },
1389 # ClipYou (EaglePlatform) embed (custom URL)
1390 {
1391 'url': 'http://muz-tv.ru/play/7129/',
1392 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1393 'info_dict': {
1394 'id': '12820',
1395 'ext': 'mp4',
1396 'title': "'O Sole Mio",
1397 'thumbnail': r're:^https?://.*\.jpg$',
1398 'duration': 216,
1399 'view_count': int,
1400 },
1401 'params': {
1402 'skip_download': True,
1403 },
1404 'skip': 'This video is unavailable.',
1405 },
1406 # Pladform embed
1407 {
1408 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1409 'info_dict': {
1410 'id': '100183293',
1411 'ext': 'mp4',
1412 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1413 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1414 'thumbnail': r're:^https?://.*\.jpg$',
1415 'duration': 694,
1416 'age_limit': 0,
1417 },
1418 'skip': 'HTTP Error 404: Not Found',
1419 },
1420 # Playwire embed
1421 {
1422 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1423 'info_dict': {
1424 'id': '3519514',
1425 'ext': 'mp4',
1426 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1427 'thumbnail': r're:^https?://.*\.png$',
1428 'duration': 45.115,
1429 },
1430 },
1431 # 5min embed
1432 {
1433 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1434 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1435 'info_dict': {
1436 'id': '518726732',
1437 'ext': 'mp4',
1438 'title': 'Facebook Creates "On This Day" | Crunch Report',
1439 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1440 'timestamp': 1427237531,
1441 'uploader': 'Crunch Report',
1442 'upload_date': '20150324',
1443 },
1444 'params': {
1445 # m3u8 download
1446 'skip_download': True,
1447 },
1448 },
1449 # Crooks and Liars embed
1450 {
1451 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1452 'info_dict': {
1453 'id': '8RUoRhRi',
1454 'ext': 'mp4',
1455 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1456 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1457 'timestamp': 1428207000,
1458 'upload_date': '20150405',
1459 'uploader': 'Heather',
1460 },
1461 },
1462 # Crooks and Liars external embed
1463 {
1464 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1465 'info_dict': {
1466 'id': 'MTE3MjUtMzQ2MzA',
1467 'ext': 'mp4',
1468 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1469 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1470 'timestamp': 1265032391,
1471 'upload_date': '20100201',
1472 'uploader': 'Heather',
1473 },
1474 },
1475 # NBC Sports vplayer embed
1476 {
1477 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1478 'info_dict': {
1479 'id': 'ln7x1qSThw4k',
1480 'ext': 'flv',
1481 'title': "PFT Live: New leader in the 'new-look' defense",
1482 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1483 'uploader': 'NBCU-SPORTS',
1484 'upload_date': '20140107',
1485 'timestamp': 1389118457,
1486 },
1487 'skip': 'Invalid Page URL',
1488 },
1489 # NBC News embed
1490 {
1491 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1492 'md5': '1aa589c675898ae6d37a17913cf68d66',
1493 'info_dict': {
1494 'id': 'x_dtl_oa_LettermanliftPR_160608',
1495 'ext': 'mp4',
1496 'title': 'David Letterman: A Preview',
1497 '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.',
1498 'upload_date': '20160609',
1499 'timestamp': 1465431544,
1500 'uploader': 'NBCU-NEWS',
1501 },
1502 },
1503 # UDN embed
1504 {
1505 'url': 'https://video.udn.com/news/300346',
1506 'md5': 'fd2060e988c326991037b9aff9df21a6',
1507 'info_dict': {
1508 'id': '300346',
1509 'ext': 'mp4',
1510 'title': '中一中男師變性 全校師生力挺',
1511 'thumbnail': r're:^https?://.*\.jpg$',
1512 },
1513 'params': {
1514 # m3u8 download
1515 'skip_download': True,
1516 },
1517 'expected_warnings': ['Failed to parse JSON Expecting value'],
1518 },
1519 # Brightcove URL in single quotes
1520 {
1521 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1522 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1523 'info_dict': {
1524 'id': '4255764656001',
1525 'ext': 'mp4',
1526 'title': 'SN Presents: Russell Martin, World Citizen',
1527 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1528 'uploader': 'Rogers Sportsnet',
1529 'uploader_id': '1704050871',
1530 'upload_date': '20150525',
1531 'timestamp': 1432570283,
1532 },
1533 },
1534 # Kinja embed
1535 {
1536 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1537 'info_dict': {
1538 'id': '106351',
1539 'ext': 'mp4',
1540 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1541 'description': 'Migrated from OnionStudios',
1542 'thumbnail': r're:^https?://.*\.jpe?g$',
1543 'uploader': 'clickhole',
1544 'upload_date': '20150527',
1545 'timestamp': 1432744860,
1546 }
1547 },
1548 # SnagFilms embed
1549 {
1550 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1551 'info_dict': {
1552 'id': '74849a00-85a9-11e1-9660-123139220831',
1553 'ext': 'mp4',
1554 'title': '#whilewewatch',
1555 }
1556 },
1557 # AdobeTVVideo embed
1558 {
1559 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1560 'md5': '43662b577c018ad707a63766462b1e87',
1561 'info_dict': {
1562 'id': '2456',
1563 'ext': 'mp4',
1564 'title': 'New experience with Acrobat DC',
1565 'description': 'New experience with Acrobat DC',
1566 'duration': 248.667,
1567 },
1568 },
1569 # BrightcoveInPageEmbed embed
1570 {
1571 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1572 'info_dict': {
1573 'id': '4238694884001',
1574 'ext': 'flv',
1575 'title': 'Tabletop: Dread, Last Thoughts',
1576 'description': 'Tabletop: Dread, Last Thoughts',
1577 'duration': 51690,
1578 },
1579 },
1580 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1581 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1582 {
1583 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1584 'info_dict': {
1585 'id': '4785848093001',
1586 'ext': 'mp4',
1587 'title': 'The Cardinal Pell Interview',
1588 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1589 'uploader': 'GlobeCast Australia - GlobeStream',
1590 'uploader_id': '2733773828001',
1591 'upload_date': '20160304',
1592 'timestamp': 1457083087,
1593 },
1594 'params': {
1595 # m3u8 downloads
1596 'skip_download': True,
1597 },
1598 },
1599 {
1600 # Brightcove embed with whitespace around attribute names
1601 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1602 'info_dict': {
1603 'id': '3167554373001',
1604 'ext': 'mp4',
1605 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1606 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1607 'uploader_id': '1079349493',
1608 'upload_date': '20140207',
1609 'timestamp': 1391810548,
1610 },
1611 'params': {
1612 'skip_download': True,
1613 },
1614 },
1615 # Another form of arte.tv embed
1616 {
1617 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1618 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1619 'info_dict': {
1620 'id': '030273-562_PLUS7-F',
1621 'ext': 'mp4',
1622 'title': 'ARTE Reportage - Nulle part, en France',
1623 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1624 'upload_date': '20160409',
1625 },
1626 },
1627 # LiveLeak embed
1628 {
1629 'url': 'http://www.wykop.pl/link/3088787/',
1630 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1631 'info_dict': {
1632 'id': '874_1459135191',
1633 'ext': 'mp4',
1634 'title': 'Man shows poor quality of new apartment building',
1635 'description': 'The wall is like a sand pile.',
1636 'uploader': 'Lake8737',
1637 },
1638 'add_ie': [LiveLeakIE.ie_key()],
1639 },
1640 # Another LiveLeak embed pattern (#13336)
1641 {
1642 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1643 'info_dict': {
1644 'id': '2eb_1496309988',
1645 'ext': 'mp4',
1646 'title': 'Thief robs place where everyone was armed',
1647 'description': 'md5:694d73ee79e535953cf2488562288eee',
1648 'uploader': 'brazilwtf',
1649 },
1650 'add_ie': [LiveLeakIE.ie_key()],
1651 },
1652 # Duplicated embedded video URLs
1653 {
1654 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1655 'info_dict': {
1656 'id': '149298443_480_16c25b74_2',
1657 'ext': 'mp4',
1658 'title': 'vs. Blue Orange Spring Game',
1659 'uploader': 'www.hudl.com',
1660 },
1661 },
1662 # twitter:player:stream embed
1663 {
1664 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1665 'info_dict': {
1666 'id': 'master',
1667 'ext': 'mp4',
1668 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1669 'uploader': 'www.rtl.be',
1670 },
1671 'params': {
1672 # m3u8 downloads
1673 'skip_download': True,
1674 },
1675 },
1676 # twitter:player embed
1677 {
1678 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1679 'md5': 'a3e0df96369831de324f0778e126653c',
1680 'info_dict': {
1681 'id': '4909620399001',
1682 'ext': 'mp4',
1683 'title': 'What Do Black Holes Sound Like?',
1684 'description': 'what do black holes sound like',
1685 'upload_date': '20160524',
1686 'uploader_id': '29913724001',
1687 'timestamp': 1464107587,
1688 'uploader': 'TheAtlantic',
1689 },
1690 'add_ie': ['BrightcoveLegacy'],
1691 },
1692 # Facebook <iframe> embed
1693 {
1694 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1695 'md5': 'fbcde74f534176ecb015849146dd3aee',
1696 'info_dict': {
1697 'id': '599637780109885',
1698 'ext': 'mp4',
1699 'title': 'Facebook video #599637780109885',
1700 },
1701 },
1702 # Facebook <iframe> embed, plugin video
1703 {
1704 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1705 'info_dict': {
1706 'id': '1754168231264132',
1707 'ext': 'mp4',
1708 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1709 'uploader': 'Tariq Ramadan (official)',
1710 'timestamp': 1496758379,
1711 'upload_date': '20170606',
1712 },
1713 'params': {
1714 'skip_download': True,
1715 },
1716 },
1717 # Facebook API embed
1718 {
1719 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1720 'md5': 'a47372ee61b39a7b90287094d447d94e',
1721 'info_dict': {
1722 'id': '10153467542406923',
1723 'ext': 'mp4',
1724 'title': 'Facebook video #10153467542406923',
1725 },
1726 },
1727 # Wordpress "YouTube Video Importer" plugin
1728 {
1729 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1730 'md5': 'd16797741b560b485194eddda8121b48',
1731 'info_dict': {
1732 'id': 'HNTXWDXV9Is',
1733 'ext': 'mp4',
1734 'title': 'Blue Devils Drumline Stanford lot 2016',
1735 'upload_date': '20160627',
1736 'uploader_id': 'GENOCIDE8GENERAL10',
1737 'uploader': 'cylus cyrus',
1738 },
1739 },
1740 {
1741 # video stored on custom kaltura server
1742 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1743 'md5': '537617d06e64dfed891fa1593c4b30cc',
1744 'info_dict': {
1745 'id': '0_1iotm5bh',
1746 'ext': 'mp4',
1747 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1748 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1749 'uploader_id': 'videos.expansion@el-mundo.net',
1750 'upload_date': '20150429',
1751 'timestamp': 1430303472,
1752 },
1753 'add_ie': ['Kaltura'],
1754 },
1755 {
1756 # multiple kaltura embeds, nsfw
1757 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
1758 'info_dict': {
1759 'id': 'kamila-avec-video-jaime-sadomie',
1760 'title': "Kamila avec vídeo “J'aime sadomie”",
1761 },
1762 'playlist_count': 8,
1763 },
1764 {
1765 # Non-standard Vimeo embed
1766 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1767 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1768 'info_dict': {
1769 'id': '148867247',
1770 'ext': 'mp4',
1771 'title': 'Understanding the web - Teaser',
1772 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1773 'upload_date': '20151214',
1774 'uploader': 'OpenClassrooms',
1775 'uploader_id': 'openclassrooms',
1776 },
1777 'add_ie': ['Vimeo'],
1778 },
1779 {
1780 # generic vimeo embed that requires original URL passed as Referer
1781 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1782 'only_matching': True,
1783 },
1784 {
1785 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1786 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1787 'info_dict': {
1788 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1789 'ext': 'mp4',
1790 'title': 'Big Buck Bunny',
1791 'description': 'Royalty free test video',
1792 'timestamp': 1432816365,
1793 'upload_date': '20150528',
1794 'is_live': False,
1795 },
1796 'params': {
1797 'skip_download': True,
1798 },
1799 'add_ie': [ArkenaIE.ie_key()],
1800 },
1801 {
1802 '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/',
1803 'info_dict': {
1804 'id': '1c7141f46c',
1805 'ext': 'mp4',
1806 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1807 },
1808 'params': {
1809 'skip_download': True,
1810 },
1811 'add_ie': [Vbox7IE.ie_key()],
1812 },
1813 {
1814 # DBTV embeds
1815 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1816 'info_dict': {
1817 'id': '43254897',
1818 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1819 },
1820 'playlist_mincount': 3,
1821 },
1822 {
1823 # Videa embeds
1824 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1825 'info_dict': {
1826 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1827 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1828 },
1829 'playlist_mincount': 2,
1830 },
1831 {
1832 # 20 minuten embed
1833 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1834 'info_dict': {
1835 'id': '523629',
1836 'ext': 'mp4',
1837 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1838 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1839 },
1840 'params': {
1841 'skip_download': True,
1842 },
1843 'add_ie': [TwentyMinutenIE.ie_key()],
1844 },
1845 {
1846 # VideoPress embed
1847 'url': 'https://en.support.wordpress.com/videopress/',
1848 'info_dict': {
1849 'id': 'OcobLTqC',
1850 'ext': 'm4v',
1851 'title': 'IMG_5786',
1852 'timestamp': 1435711927,
1853 'upload_date': '20150701',
1854 },
1855 'params': {
1856 'skip_download': True,
1857 },
1858 'add_ie': [VideoPressIE.ie_key()],
1859 },
1860 {
1861 # Rutube embed
1862 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1863 'info_dict': {
1864 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1865 'ext': 'flv',
1866 'title': 'Магаззино: Казань 2',
1867 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1868 'uploader': 'Магаззино',
1869 'upload_date': '20170228',
1870 'uploader_id': '996642',
1871 },
1872 'params': {
1873 'skip_download': True,
1874 },
1875 'add_ie': [RutubeIE.ie_key()],
1876 },
1877 {
1878 # ThePlatform embedded with whitespaces in URLs
1879 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1880 'only_matching': True,
1881 },
1882 {
1883 # Senate ISVP iframe https
1884 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1885 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1886 'info_dict': {
1887 'id': 'govtaff020316',
1888 'ext': 'mp4',
1889 'title': 'Integrated Senate Video Player',
1890 },
1891 'add_ie': [SenateISVPIE.ie_key()],
1892 },
1893 {
1894 # Limelight embeds (1 channel embed + 4 media embeds)
1895 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1896 'info_dict': {
1897 'id': 'FacilitatorTraining2017',
1898 'title': 'Facilitator Training 2017',
1899 },
1900 'playlist_mincount': 5,
1901 },
1902 {
1903 # Limelight embed (LimelightPlayerUtil.embed)
1904 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1905 'info_dict': {
1906 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1907 'ext': 'mp4',
1908 'title': '07448641',
1909 'timestamp': 1499890639,
1910 'upload_date': '20170712',
1911 },
1912 'params': {
1913 'skip_download': True,
1914 },
1915 'add_ie': ['LimelightMedia'],
1916 },
1917 {
1918 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1919 'info_dict': {
1920 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1921 'title': 'Standoff with Walnut Creek murder suspect ends',
1922 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1923 },
1924 'playlist_mincount': 4,
1925 },
1926 {
1927 # WashingtonPost embed
1928 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1929 'info_dict': {
1930 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1931 'ext': 'mp4',
1932 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1933 '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.',
1934 'timestamp': 1455216756,
1935 'uploader': 'The Washington Post',
1936 'upload_date': '20160211',
1937 },
1938 'add_ie': [WashingtonPostIE.ie_key()],
1939 },
1940 {
1941 # Mediaset embed
1942 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1943 'info_dict': {
1944 'id': '720642',
1945 'ext': 'mp4',
1946 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1947 },
1948 'params': {
1949 'skip_download': True,
1950 },
1951 'add_ie': [MediasetIE.ie_key()],
1952 },
1953 {
1954 # JOJ.sk embeds
1955 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1956 'info_dict': {
1957 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1958 'title': 'Slovenskom sa prehnala vlna silných búrok',
1959 },
1960 'playlist_mincount': 5,
1961 'add_ie': [JojIE.ie_key()],
1962 },
1963 {
1964 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1965 'url': 'https://tvrain.ru/amp/418921/',
1966 'md5': 'cc00413936695987e8de148b67d14f1d',
1967 'info_dict': {
1968 'id': '418921',
1969 'ext': 'mp4',
1970 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1971 },
1972 },
1973 {
1974 # vzaar embed
1975 'url': 'http://help.vzaar.com/article/165-embedding-video',
1976 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1977 'info_dict': {
1978 'id': '8707641',
1979 'ext': 'mp4',
1980 'title': 'Building A Business Online: Principal Chairs Q & A',
1981 },
1982 },
1983 {
1984 # multiple HTML5 videos on one page
1985 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1986 'info_dict': {
1987 'id': 'keyscenarios',
1988 'title': 'Rescue Kit 14 Free Edition - Getting started',
1989 },
1990 'playlist_count': 4,
1991 },
1992 {
1993 # vshare embed
1994 'url': 'https://youtube-dlc-demo.neocities.org/vshare.html',
1995 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1996 'info_dict': {
1997 'id': '0f64ce6',
1998 'title': 'vl14062007715967',
1999 'ext': 'mp4',
2000 }
2001 },
2002 {
2003 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
2004 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
2005 'info_dict': {
2006 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
2007 'ext': 'mp4',
2008 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
2009 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
2010 'timestamp': 1474354800,
2011 'upload_date': '20160920',
2012 }
2013 },
2014 {
2015 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
2016 'info_dict': {
2017 'id': '1731611',
2018 'ext': 'mp4',
2019 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
2020 'description': 'md5:eb5f23826a027ba95277d105f248b825',
2021 'timestamp': 1516100691,
2022 'upload_date': '20180116',
2023 },
2024 'params': {
2025 'skip_download': True,
2026 },
2027 'add_ie': [SpringboardPlatformIE.ie_key()],
2028 },
2029 {
2030 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
2031 'info_dict': {
2032 'id': 'vMDE4NzI1Mjgt690b',
2033 'ext': 'mp4',
2034 'title': 'Котята',
2035 },
2036 'add_ie': [YapFilesIE.ie_key()],
2037 'params': {
2038 'skip_download': True,
2039 },
2040 },
2041 {
2042 # CloudflareStream embed
2043 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2044 'info_dict': {
2045 'id': '31c9291ab41fac05471db4e73aa11717',
2046 'ext': 'mp4',
2047 'title': '31c9291ab41fac05471db4e73aa11717',
2048 },
2049 'add_ie': [CloudflareStreamIE.ie_key()],
2050 'params': {
2051 'skip_download': True,
2052 },
2053 },
2054 {
2055 # PeerTube embed
2056 'url': 'https://joinpeertube.org/fr/home/',
2057 'info_dict': {
2058 'id': 'home',
2059 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2060 },
2061 'playlist_count': 2,
2062 },
2063 {
2064 # Indavideo embed
2065 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2066 'info_dict': {
2067 'id': '1693903',
2068 'ext': 'mp4',
2069 'title': 'Így kell otthon hamburgert sütni',
2070 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2071 'timestamp': 1426330212,
2072 'upload_date': '20150314',
2073 'uploader': 'StreetKitchen',
2074 'uploader_id': '546363',
2075 },
2076 'add_ie': [IndavideoEmbedIE.ie_key()],
2077 'params': {
2078 'skip_download': True,
2079 },
2080 },
2081 {
2082 # APA embed via JWPlatform embed
2083 'url': 'http://www.vol.at/blue-man-group/5593454',
2084 'info_dict': {
2085 'id': 'jjv85FdZ',
2086 'ext': 'mp4',
2087 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2088 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2089 'thumbnail': r're:^https?://.*\.jpg$',
2090 'duration': 254,
2091 'timestamp': 1519211149,
2092 'upload_date': '20180221',
2093 },
2094 'params': {
2095 'skip_download': True,
2096 },
2097 },
2098 {
2099 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2100 'md5': 'b68d276de422ab07ee1d49388103f457',
2101 'info_dict': {
2102 'id': '83645793',
2103 'title': 'Lock up and get excited',
2104 'ext': 'mp4'
2105 },
2106 'skip': 'TODO: fix nested playlists processing in tests',
2107 },
2108 {
2109 # Viqeo embeds
2110 'url': 'https://viqeo.tv/',
2111 'info_dict': {
2112 'id': 'viqeo',
2113 'title': 'All-new video platform',
2114 },
2115 'playlist_count': 6,
2116 },
2117 {
2118 # Squarespace video embed, 2019-08-28
2119 'url': 'http://ootboxford.com',
2120 'info_dict': {
2121 'id': 'Tc7b_JGdZfw',
2122 'title': 'Out of the Blue, at Childish Things 10',
2123 'ext': 'mp4',
2124 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
2125 'uploader_id': 'helendouglashouse',
2126 'uploader': 'Helen & Douglas House',
2127 'upload_date': '20140328',
2128 },
2129 'params': {
2130 'skip_download': True,
2131 },
2132 },
2133 # {
2134 # # Zype embed
2135 # 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2136 # 'info_dict': {
2137 # 'id': '5b400b834b32992a310622b9',
2138 # 'ext': 'mp4',
2139 # 'title': 'Smoky Barbecue Favorites',
2140 # 'thumbnail': r're:^https?://.*\.jpe?g',
2141 # 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
2142 # 'upload_date': '20170909',
2143 # 'timestamp': 1504915200,
2144 # },
2145 # 'add_ie': [ZypeIE.ie_key()],
2146 # 'params': {
2147 # 'skip_download': True,
2148 # },
2149 # },
2150 {
2151 # videojs embed
2152 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2153 'info_dict': {
2154 'id': 'shell',
2155 'ext': 'mp4',
2156 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2157 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2158 'thumbnail': r're:^https?://.*\.jpg$',
2159 },
2160 'params': {
2161 'skip_download': True,
2162 },
2163 'expected_warnings': ['Failed to download MPD manifest'],
2164 },
2165 {
2166 # DailyMotion embed with DM.player
2167 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
2168 'info_dict': {
2169 'id': 'k6aKkGHd9FJs4mtJN39',
2170 'ext': 'mp4',
2171 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
2172 'description': 'This video is private.',
2173 'uploader_id': 'x1jf30l',
2174 'uploader': 'beIN SPORTS USA',
2175 'upload_date': '20190528',
2176 'timestamp': 1559062971,
2177 },
2178 'params': {
2179 'skip_download': True,
2180 },
2181 },
2182 # {
2183 # # TODO: find another test
2184 # # http://schema.org/VideoObject
2185 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2186 # 'md5': '888dcf08b7ea671381f00fab74692755',
2187 # 'info_dict': {
2188 # 'id': 'nyvTSJMKId',
2189 # 'ext': 'mp4',
2190 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2191 # 'description': '#love for cats.',
2192 # 'timestamp': 1461244995,
2193 # 'upload_date': '20160421',
2194 # },
2195 # 'params': {
2196 # 'force_generic_extractor': True,
2197 # },
2198 # },
2199 {
2200 # VHX Embed
2201 'url': 'https://demo.vhx.tv/category-c/videos/file-example-mp4-480-1-5mg-copy',
2202 'info_dict': {
2203 'id': '858208',
2204 'ext': 'mp4',
2205 'title': 'Untitled',
2206 'uploader_id': 'user80538407',
2207 'uploader': 'OTT Videos',
2208 },
2209 },
2210 {
2211 # ArcPublishing PoWa video player
2212 'url': 'https://www.adn.com/politics/2020/11/02/video-senate-candidates-campaign-in-anchorage-on-eve-of-election-day/',
2213 'md5': 'b03b2fac8680e1e5a7cc81a5c27e71b3',
2214 'info_dict': {
2215 'id': '8c99cb6e-b29c-4bc9-9173-7bf9979225ab',
2216 'ext': 'mp4',
2217 'title': 'Senate candidates wave to voters on Anchorage streets',
2218 'description': 'md5:91f51a6511f090617353dc720318b20e',
2219 'timestamp': 1604378735,
2220 'upload_date': '20201103',
2221 'duration': 1581,
2222 },
2223 },
2224 ]
2225
2226 def report_following_redirect(self, new_url):
2227 """Report information extraction."""
2228 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2229
2230 def _extract_rss(self, url, video_id, doc):
2231 playlist_title = doc.find('./channel/title').text
2232 playlist_desc_el = doc.find('./channel/description')
2233 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2234
2235 NS_MAP = {
2236 'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
2237 }
2238
2239 entries = []
2240 for it in doc.findall('./channel/item'):
2241 next_url = None
2242 enclosure_nodes = it.findall('./enclosure')
2243 for e in enclosure_nodes:
2244 next_url = e.attrib.get('url')
2245 if next_url:
2246 break
2247
2248 if not next_url:
2249 next_url = xpath_text(it, 'link', fatal=False)
2250
2251 if not next_url:
2252 continue
2253
2254 def itunes(key):
2255 return xpath_text(
2256 it, xpath_with_ns('./itunes:%s' % key, NS_MAP),
2257 default=None)
2258
2259 duration = itunes('duration')
2260 explicit = (itunes('explicit') or '').lower()
2261 if explicit in ('true', 'yes'):
2262 age_limit = 18
2263 elif explicit in ('false', 'no'):
2264 age_limit = 0
2265 else:
2266 age_limit = None
2267
2268 entries.append({
2269 '_type': 'url_transparent',
2270 'url': next_url,
2271 'title': it.find('title').text,
2272 'description': xpath_text(it, 'description', default=None),
2273 'timestamp': unified_timestamp(
2274 xpath_text(it, 'pubDate', default=None)),
2275 'duration': int_or_none(duration) or parse_duration(duration),
2276 'thumbnail': url_or_none(xpath_attr(it, xpath_with_ns('./itunes:image', NS_MAP), 'href')),
2277 'episode': itunes('title'),
2278 'episode_number': int_or_none(itunes('episode')),
2279 'season_number': int_or_none(itunes('season')),
2280 'age_limit': age_limit,
2281 })
2282
2283 return {
2284 '_type': 'playlist',
2285 'id': url,
2286 'title': playlist_title,
2287 'description': playlist_desc,
2288 'entries': entries,
2289 }
2290
2291 def _extract_camtasia(self, url, video_id, webpage):
2292 """ Returns None if no camtasia video can be found. """
2293
2294 camtasia_cfg = self._search_regex(
2295 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2296 webpage, 'camtasia configuration file', default=None)
2297 if camtasia_cfg is None:
2298 return None
2299
2300 title = self._html_search_meta('DC.title', webpage, fatal=True)
2301
2302 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2303 camtasia_cfg = self._download_xml(
2304 camtasia_url, video_id,
2305 note='Downloading camtasia configuration',
2306 errnote='Failed to download camtasia configuration')
2307 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2308
2309 entries = []
2310 for n in fileset_node.getchildren():
2311 url_n = n.find('./uri')
2312 if url_n is None:
2313 continue
2314
2315 entries.append({
2316 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2317 'title': '%s - %s' % (title, n.tag),
2318 'url': compat_urlparse.urljoin(url, url_n.text),
2319 'duration': float_or_none(n.find('./duration').text),
2320 })
2321
2322 return {
2323 '_type': 'playlist',
2324 'entries': entries,
2325 'title': title,
2326 }
2327
2328 def _real_extract(self, url):
2329 if url.startswith('//'):
2330 return self.url_result(self.http_scheme() + url)
2331
2332 parsed_url = compat_urlparse.urlparse(url)
2333 if not parsed_url.scheme:
2334 default_search = self._downloader.params.get('default_search')
2335 if default_search is None:
2336 default_search = 'fixup_error'
2337
2338 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2339 if re.match(r'^[^\s/]+\.[^\s/]+/', url):
2340 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2341 return self.url_result('http://' + url)
2342 elif default_search != 'fixup_error':
2343 if default_search == 'auto_warning':
2344 if re.match(r'^(?:url|URL)$', url):
2345 raise ExtractorError(
2346 'Invalid URL: %r . Call youtube-dlc like this: youtube-dlc -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2347 expected=True)
2348 else:
2349 self._downloader.report_warning(
2350 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2351 return self.url_result('ytsearch:' + url)
2352
2353 if default_search in ('error', 'fixup_error'):
2354 raise ExtractorError(
2355 '%r is not a valid URL. '
2356 'Set --default-search "ytsearch" (or run youtube-dlc "ytsearch:%s" ) to search YouTube'
2357 % (url, url), expected=True)
2358 else:
2359 if ':' not in default_search:
2360 default_search += ':'
2361 return self.url_result(default_search + url)
2362
2363 url, smuggled_data = unsmuggle_url(url)
2364 force_videoid = None
2365 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2366 if smuggled_data and 'force_videoid' in smuggled_data:
2367 force_videoid = smuggled_data['force_videoid']
2368 video_id = force_videoid
2369 else:
2370 video_id = self._generic_id(url)
2371
2372 self.to_screen('%s: Requesting header' % video_id)
2373
2374 head_req = HEADRequest(url)
2375 head_response = self._request_webpage(
2376 head_req, video_id,
2377 note=False, errnote='Could not send HEAD request to %s' % url,
2378 fatal=False)
2379
2380 if head_response is not False:
2381 # Check for redirect
2382 new_url = head_response.geturl()
2383 if url != new_url:
2384 self.report_following_redirect(new_url)
2385 if force_videoid:
2386 new_url = smuggle_url(
2387 new_url, {'force_videoid': force_videoid})
2388 return self.url_result(new_url)
2389
2390 full_response = None
2391 if head_response is False:
2392 request = sanitized_Request(url)
2393 request.add_header('Accept-Encoding', '*')
2394 full_response = self._request_webpage(request, video_id)
2395 head_response = full_response
2396
2397 info_dict = {
2398 'id': video_id,
2399 'title': self._generic_title(url),
2400 'timestamp': unified_timestamp(head_response.headers.get('Last-Modified'))
2401 }
2402
2403 # Check for direct link to a video
2404 content_type = head_response.headers.get('Content-Type', '').lower()
2405 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2406 if m:
2407 format_id = compat_str(m.group('format_id'))
2408 if format_id.endswith('mpegurl'):
2409 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2410 elif format_id == 'f4m':
2411 formats = self._extract_f4m_formats(url, video_id)
2412 else:
2413 formats = [{
2414 'format_id': format_id,
2415 'url': url,
2416 'vcodec': 'none' if m.group('type') == 'audio' else None
2417 }]
2418 info_dict['direct'] = True
2419 self._sort_formats(formats)
2420 info_dict['formats'] = formats
2421 return info_dict
2422
2423 if not self._downloader.params.get('test', False) and not is_intentional:
2424 force = self._downloader.params.get('force_generic_extractor', False)
2425 self._downloader.report_warning(
2426 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2427
2428 if not full_response:
2429 request = sanitized_Request(url)
2430 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2431 # making it impossible to download only chunk of the file (yet we need only 512kB to
2432 # test whether it's HTML or not). According to youtube-dlc default Accept-Encoding
2433 # that will always result in downloading the whole file that is not desirable.
2434 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2435 # to accept raw bytes and being able to download only a chunk.
2436 # It may probably better to solve this by checking Content-Type for application/octet-stream
2437 # after HEAD request finishes, but not sure if we can rely on this.
2438 request.add_header('Accept-Encoding', '*')
2439 full_response = self._request_webpage(request, video_id)
2440
2441 first_bytes = full_response.read(512)
2442
2443 # Is it an M3U playlist?
2444 if first_bytes.startswith(b'#EXTM3U'):
2445 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2446 self._sort_formats(info_dict['formats'])
2447 return info_dict
2448
2449 # Maybe it's a direct link to a video?
2450 # Be careful not to download the whole thing!
2451 if not is_html(first_bytes):
2452 self._downloader.report_warning(
2453 'URL could be a direct video link, returning it as such.')
2454 info_dict.update({
2455 'direct': True,
2456 'url': url,
2457 })
2458 return info_dict
2459
2460 webpage = self._webpage_read_content(
2461 full_response, url, video_id, prefix=first_bytes)
2462
2463 self.report_extraction(video_id)
2464
2465 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2466 try:
2467 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2468 if doc.tag == 'rss':
2469 return self._extract_rss(url, video_id, doc)
2470 elif doc.tag == 'SmoothStreamingMedia':
2471 info_dict['formats'] = self._parse_ism_formats(doc, url)
2472 self._sort_formats(info_dict['formats'])
2473 return info_dict
2474 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2475 smil = self._parse_smil(doc, url, video_id)
2476 self._sort_formats(smil['formats'])
2477 return smil
2478 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2479 return self.playlist_result(
2480 self._parse_xspf(
2481 doc, video_id, xspf_url=url,
2482 xspf_base_url=full_response.geturl()),
2483 video_id)
2484 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2485 info_dict['formats'] = self._parse_mpd_formats(
2486 doc,
2487 mpd_base_url=full_response.geturl().rpartition('/')[0],
2488 mpd_url=url)
2489 self._sort_formats(info_dict['formats'])
2490 return info_dict
2491 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2492 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2493 self._sort_formats(info_dict['formats'])
2494 return info_dict
2495 except compat_xml_parse_error:
2496 pass
2497
2498 # Is it a Camtasia project?
2499 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2500 if camtasia_res is not None:
2501 return camtasia_res
2502
2503 # Sometimes embedded video player is hidden behind percent encoding
2504 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
2505 # Unescaping the whole page allows to handle those cases in a generic way
2506 # FIXME: unescaping the whole page may break URLs, commenting out for now.
2507 # There probably should be a second run of generic extractor on unescaped webpage.
2508 # webpage = compat_urllib_parse_unquote(webpage)
2509
2510 # Unescape squarespace embeds to be detected by generic extractor,
2511 # see https://github.com/ytdl-org/youtube-dl/issues/21294
2512 webpage = re.sub(
2513 r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
2514 lambda x: unescapeHTML(x.group(0)), webpage)
2515
2516 # it's tempting to parse this further, but you would
2517 # have to take into account all the variations like
2518 # Video Title - Site Name
2519 # Site Name | Video Title
2520 # Video Title - Tagline | Site Name
2521 # and so on and so forth; it's just not practical
2522 video_title = self._og_search_title(
2523 webpage, default=None) or self._html_search_regex(
2524 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2525 default='video')
2526
2527 # Try to detect age limit automatically
2528 age_limit = self._rta_search(webpage)
2529 # And then there are the jokers who advertise that they use RTA,
2530 # but actually don't.
2531 AGE_LIMIT_MARKERS = [
2532 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2533 ]
2534 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2535 age_limit = 18
2536
2537 # video uploader is domain name
2538 video_uploader = self._search_regex(
2539 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2540
2541 video_description = self._og_search_description(webpage, default=None)
2542 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2543
2544 info_dict.update({
2545 'title': video_title,
2546 'description': video_description,
2547 'thumbnail': video_thumbnail,
2548 'age_limit': age_limit,
2549 })
2550
2551 # Look for Brightcove Legacy Studio embeds
2552 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2553 if bc_urls:
2554 entries = [{
2555 '_type': 'url',
2556 'url': smuggle_url(bc_url, {'Referer': url}),
2557 'ie_key': 'BrightcoveLegacy'
2558 } for bc_url in bc_urls]
2559
2560 return {
2561 '_type': 'playlist',
2562 'title': video_title,
2563 'id': video_id,
2564 'entries': entries,
2565 }
2566
2567 # Look for Brightcove New Studio embeds
2568 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2569 if bc_urls:
2570 return self.playlist_from_matches(
2571 bc_urls, video_id, video_title,
2572 getter=lambda x: smuggle_url(x, {'referrer': url}),
2573 ie='BrightcoveNew')
2574
2575 # Look for Nexx embeds
2576 nexx_urls = NexxIE._extract_urls(webpage)
2577 if nexx_urls:
2578 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2579
2580 # Look for Nexx iFrame embeds
2581 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2582 if nexx_embed_urls:
2583 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2584
2585 # Look for ThePlatform embeds
2586 tp_urls = ThePlatformIE._extract_urls(webpage)
2587 if tp_urls:
2588 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2589
2590 arc_urls = ArcPublishingIE._extract_urls(webpage)
2591 if arc_urls:
2592 return self.playlist_from_matches(arc_urls, video_id, video_title, ie=ArcPublishingIE.ie_key())
2593
2594 # Look for embedded rtl.nl player
2595 matches = re.findall(
2596 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2597 webpage)
2598 if matches:
2599 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2600
2601 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2602 if vimeo_urls:
2603 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2604
2605 vhx_url = VHXEmbedIE._extract_url(webpage)
2606 if vhx_url:
2607 return self.url_result(vhx_url, VHXEmbedIE.ie_key())
2608
2609 vid_me_embed_url = self._search_regex(
2610 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2611 webpage, 'vid.me embed', default=None)
2612 if vid_me_embed_url is not None:
2613 return self.url_result(vid_me_embed_url, 'Vidme')
2614
2615 # Look for YouTube embeds
2616 youtube_urls = YoutubeIE._extract_urls(webpage)
2617 if youtube_urls:
2618 return self.playlist_from_matches(
2619 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2620
2621 matches = DailymotionIE._extract_urls(webpage)
2622 if matches:
2623 return self.playlist_from_matches(matches, video_id, video_title)
2624
2625 # Look for embedded Dailymotion playlist player (#3822)
2626 m = re.search(
2627 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2628 if m:
2629 playlists = re.findall(
2630 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2631 if playlists:
2632 return self.playlist_from_matches(
2633 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2634
2635 # Look for DailyMail embeds
2636 dailymail_urls = DailyMailIE._extract_urls(webpage)
2637 if dailymail_urls:
2638 return self.playlist_from_matches(
2639 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2640
2641 # Look for Teachable embeds, must be before Wistia
2642 teachable_url = TeachableIE._extract_url(webpage, url)
2643 if teachable_url:
2644 return self.url_result(teachable_url)
2645
2646 # Look for embedded Wistia player
2647 wistia_urls = WistiaIE._extract_urls(webpage)
2648 if wistia_urls:
2649 playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
2650 for entry in playlist['entries']:
2651 entry.update({
2652 '_type': 'url_transparent',
2653 'uploader': video_uploader,
2654 })
2655 return playlist
2656
2657 # Look for SVT player
2658 svt_url = SVTIE._extract_url(webpage)
2659 if svt_url:
2660 return self.url_result(svt_url, 'SVT')
2661
2662 # Look for Bandcamp pages with custom domain
2663 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2664 if mobj is not None:
2665 burl = unescapeHTML(mobj.group(1))
2666 # Don't set the extractor because it can be a track url or an album
2667 return self.url_result(burl)
2668
2669 # Look for embedded Vevo player
2670 mobj = re.search(
2671 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2672 if mobj is not None:
2673 return self.url_result(mobj.group('url'))
2674
2675 # Look for embedded Viddler player
2676 mobj = re.search(
2677 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2678 webpage)
2679 if mobj is not None:
2680 return self.url_result(mobj.group('url'))
2681
2682 # Look for NYTimes player
2683 mobj = re.search(
2684 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2685 webpage)
2686 if mobj is not None:
2687 return self.url_result(mobj.group('url'))
2688
2689 # Look for Libsyn player
2690 mobj = re.search(
2691 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2692 if mobj is not None:
2693 return self.url_result(mobj.group('url'))
2694
2695 # Look for Ooyala videos
2696 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
2697 or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2698 or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2699 or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
2700 or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2701 if mobj is not None:
2702 embed_token = self._search_regex(
2703 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2704 webpage, 'ooyala embed token', default=None)
2705 return OoyalaIE._build_url_result(smuggle_url(
2706 mobj.group('ec'), {
2707 'domain': url,
2708 'embed_token': embed_token,
2709 }))
2710
2711 # Look for multiple Ooyala embeds on SBN network websites
2712 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2713 if mobj is not None:
2714 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2715 if embeds:
2716 return self.playlist_from_matches(
2717 embeds, video_id, video_title,
2718 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2719
2720 # Look for Aparat videos
2721 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2722 if mobj is not None:
2723 return self.url_result(mobj.group(1), 'Aparat')
2724
2725 # Look for MPORA videos
2726 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2727 if mobj is not None:
2728 return self.url_result(mobj.group(1), 'Mpora')
2729
2730 # Look for embedded Facebook player
2731 facebook_urls = FacebookIE._extract_urls(webpage)
2732 if facebook_urls:
2733 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2734
2735 # Look for embedded VK player
2736 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2737 if mobj is not None:
2738 return self.url_result(mobj.group('url'), 'VK')
2739
2740 # Look for embedded Odnoklassniki player
2741 odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
2742 if odnoklassniki_url:
2743 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
2744
2745 # Look for embedded ivi player
2746 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2747 if mobj is not None:
2748 return self.url_result(mobj.group('url'), 'Ivi')
2749
2750 # Look for embedded Huffington Post player
2751 mobj = re.search(
2752 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2753 if mobj is not None:
2754 return self.url_result(mobj.group('url'), 'HuffPost')
2755
2756 # Look for embed.ly
2757 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2758 if mobj is not None:
2759 return self.url_result(mobj.group('url'))
2760 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2761 if mobj is not None:
2762 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2763
2764 # Look for funnyordie embed
2765 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2766 if matches:
2767 return self.playlist_from_matches(
2768 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2769
2770 # Look for BBC iPlayer embed
2771 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2772 if matches:
2773 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2774
2775 # Look for embedded RUTV player
2776 rutv_url = RUTVIE._extract_url(webpage)
2777 if rutv_url:
2778 return self.url_result(rutv_url, 'RUTV')
2779
2780 # Look for embedded TVC player
2781 tvc_url = TVCIE._extract_url(webpage)
2782 if tvc_url:
2783 return self.url_result(tvc_url, 'TVC')
2784
2785 # Look for embedded SportBox player
2786 sportbox_urls = SportBoxIE._extract_urls(webpage)
2787 if sportbox_urls:
2788 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
2789
2790 # Look for embedded XHamster player
2791 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2792 if xhamster_urls:
2793 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2794
2795 # Look for embedded TNAFlixNetwork player
2796 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2797 if tnaflix_urls:
2798 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2799
2800 # Look for embedded PornHub player
2801 pornhub_urls = PornHubIE._extract_urls(webpage)
2802 if pornhub_urls:
2803 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2804
2805 # Look for embedded DrTuber player
2806 drtuber_urls = DrTuberIE._extract_urls(webpage)
2807 if drtuber_urls:
2808 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2809
2810 # Look for embedded RedTube player
2811 redtube_urls = RedTubeIE._extract_urls(webpage)
2812 if redtube_urls:
2813 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2814
2815 # Look for embedded Tube8 player
2816 tube8_urls = Tube8IE._extract_urls(webpage)
2817 if tube8_urls:
2818 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2819
2820 # Look for embedded Mofosex player
2821 mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
2822 if mofosex_urls:
2823 return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
2824
2825 # Look for embedded Spankwire player
2826 spankwire_urls = SpankwireIE._extract_urls(webpage)
2827 if spankwire_urls:
2828 return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
2829
2830 # Look for embedded YouPorn player
2831 youporn_urls = YouPornIE._extract_urls(webpage)
2832 if youporn_urls:
2833 return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
2834
2835 # Look for embedded Tvigle player
2836 mobj = re.search(
2837 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2838 if mobj is not None:
2839 return self.url_result(mobj.group('url'), 'Tvigle')
2840
2841 # Look for embedded TED player
2842 mobj = re.search(
2843 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2844 if mobj is not None:
2845 return self.url_result(mobj.group('url'), 'TED')
2846
2847 # Look for embedded Ustream videos
2848 ustream_url = UstreamIE._extract_url(webpage)
2849 if ustream_url:
2850 return self.url_result(ustream_url, UstreamIE.ie_key())
2851
2852 # Look for embedded arte.tv player
2853 arte_urls = ArteTVEmbedIE._extract_urls(webpage)
2854 if arte_urls:
2855 return self.playlist_from_matches(arte_urls, video_id, video_title)
2856
2857 # Look for embedded francetv player
2858 mobj = re.search(
2859 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2860 webpage)
2861 if mobj is not None:
2862 return self.url_result(mobj.group('url'))
2863
2864 # Look for embedded Myvi.ru player
2865 myvi_url = MyviIE._extract_url(webpage)
2866 if myvi_url:
2867 return self.url_result(myvi_url)
2868
2869 # Look for embedded soundcloud player
2870 soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
2871 if soundcloud_urls:
2872 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
2873
2874 # Look for tunein player
2875 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2876 if tunein_urls:
2877 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2878
2879 # Look for embedded mtvservices player
2880 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2881 if mtvservices_url:
2882 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2883
2884 # Look for embedded yahoo player
2885 mobj = re.search(
2886 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2887 webpage)
2888 if mobj is not None:
2889 return self.url_result(mobj.group('url'), 'Yahoo')
2890
2891 # Look for embedded sbs.com.au player
2892 mobj = re.search(
2893 r'''(?x)
2894 (?:
2895 <meta\s+property="og:video"\s+content=|
2896 <iframe[^>]+?src=
2897 )
2898 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2899 webpage)
2900 if mobj is not None:
2901 return self.url_result(mobj.group('url'), 'SBS')
2902
2903 # Look for embedded Cinchcast player
2904 mobj = re.search(
2905 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2906 webpage)
2907 if mobj is not None:
2908 return self.url_result(mobj.group('url'), 'Cinchcast')
2909
2910 mobj = re.search(
2911 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2912 webpage)
2913 if not mobj:
2914 mobj = re.search(
2915 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2916 webpage)
2917 if mobj is not None:
2918 return self.url_result(mobj.group('url'), 'MLB')
2919
2920 mobj = re.search(
2921 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2922 webpage)
2923 if mobj is not None:
2924 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2925
2926 mobj = re.search(
2927 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2928 webpage)
2929 if mobj is not None:
2930 return self.url_result(mobj.group('url'), 'Livestream')
2931
2932 # Look for Zapiks embed
2933 mobj = re.search(
2934 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2935 if mobj is not None:
2936 return self.url_result(mobj.group('url'), 'Zapiks')
2937
2938 # Look for Kaltura embeds
2939 kaltura_urls = KalturaIE._extract_urls(webpage)
2940 if kaltura_urls:
2941 return self.playlist_from_matches(
2942 kaltura_urls, video_id, video_title,
2943 getter=lambda x: smuggle_url(x, {'source_url': url}),
2944 ie=KalturaIE.ie_key())
2945
2946 # Look for EaglePlatform embeds
2947 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2948 if eagleplatform_url:
2949 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2950
2951 # Look for ClipYou (uses EaglePlatform) embeds
2952 mobj = re.search(
2953 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2954 if mobj is not None:
2955 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2956
2957 # Look for Pladform embeds
2958 pladform_url = PladformIE._extract_url(webpage)
2959 if pladform_url:
2960 return self.url_result(pladform_url)
2961
2962 # Look for Videomore embeds
2963 videomore_url = VideomoreIE._extract_url(webpage)
2964 if videomore_url:
2965 return self.url_result(videomore_url)
2966
2967 # Look for Webcaster embeds
2968 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2969 if webcaster_url:
2970 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2971
2972 # Look for Playwire embeds
2973 mobj = re.search(
2974 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2975 if mobj is not None:
2976 return self.url_result(mobj.group('url'))
2977
2978 # Look for 5min embeds
2979 mobj = re.search(
2980 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2981 if mobj is not None:
2982 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2983
2984 # Look for Crooks and Liars embeds
2985 mobj = re.search(
2986 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2987 if mobj is not None:
2988 return self.url_result(mobj.group('url'))
2989
2990 # Look for NBC Sports VPlayer embeds
2991 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2992 if nbc_sports_url:
2993 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2994
2995 # Look for NBC News embeds
2996 nbc_news_embed_url = re.search(
2997 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2998 if nbc_news_embed_url:
2999 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
3000
3001 # Look for Google Drive embeds
3002 google_drive_url = GoogleDriveIE._extract_url(webpage)
3003 if google_drive_url:
3004 return self.url_result(google_drive_url, 'GoogleDrive')
3005
3006 # Look for UDN embeds
3007 mobj = re.search(
3008 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
3009 if mobj is not None:
3010 return self.url_result(
3011 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
3012
3013 # Look for Senate ISVP iframe
3014 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
3015 if senate_isvp_url:
3016 return self.url_result(senate_isvp_url, 'SenateISVP')
3017
3018 # Look for Kinja embeds
3019 kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
3020 if kinja_embed_urls:
3021 return self.playlist_from_matches(
3022 kinja_embed_urls, video_id, video_title)
3023
3024 # Look for OnionStudios embeds
3025 onionstudios_url = OnionStudiosIE._extract_url(webpage)
3026 if onionstudios_url:
3027 return self.url_result(onionstudios_url)
3028
3029 # Look for ViewLift embeds
3030 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
3031 if viewlift_url:
3032 return self.url_result(viewlift_url)
3033
3034 # Look for JWPlatform embeds
3035 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
3036 if jwplatform_urls:
3037 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
3038
3039 # Look for Digiteka embeds
3040 digiteka_url = DigitekaIE._extract_url(webpage)
3041 if digiteka_url:
3042 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
3043
3044 # Look for Arkena embeds
3045 arkena_url = ArkenaIE._extract_url(webpage)
3046 if arkena_url:
3047 return self.url_result(arkena_url, ArkenaIE.ie_key())
3048
3049 # Look for Piksel embeds
3050 piksel_url = PikselIE._extract_url(webpage)
3051 if piksel_url:
3052 return self.url_result(piksel_url, PikselIE.ie_key())
3053
3054 # Look for Limelight embeds
3055 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
3056 if limelight_urls:
3057 return self.playlist_result(
3058 limelight_urls, video_id, video_title, video_description)
3059
3060 # Look for Anvato embeds
3061 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
3062 if anvato_urls:
3063 return self.playlist_result(
3064 anvato_urls, video_id, video_title, video_description)
3065
3066 # Look for AdobeTVVideo embeds
3067 mobj = re.search(
3068 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
3069 webpage)
3070 if mobj is not None:
3071 return self.url_result(
3072 self._proto_relative_url(unescapeHTML(mobj.group(1))),
3073 'AdobeTVVideo')
3074
3075 # Look for Vine embeds
3076 mobj = re.search(
3077 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
3078 webpage)
3079 if mobj is not None:
3080 return self.url_result(
3081 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
3082
3083 # Look for VODPlatform embeds
3084 mobj = re.search(
3085 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
3086 webpage)
3087 if mobj is not None:
3088 return self.url_result(
3089 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
3090
3091 # Look for Mangomolo embeds
3092 mobj = re.search(
3093 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
3094 (?:
3095 admin\.mangomolo\.com/analytics/index\.php/customers/embed|
3096 player\.mangomolo\.com/v1
3097 )/
3098 (?:
3099 video\?.*?\bid=(?P<video_id>\d+)|
3100 (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
3101 ).+?)\1''', webpage)
3102 if mobj is not None:
3103 info = {
3104 '_type': 'url_transparent',
3105 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
3106 'title': video_title,
3107 'description': video_description,
3108 'thumbnail': video_thumbnail,
3109 'uploader': video_uploader,
3110 }
3111 video_id = mobj.group('video_id')
3112 if video_id:
3113 info.update({
3114 'ie_key': 'MangomoloVideo',
3115 'id': video_id,
3116 })
3117 else:
3118 info.update({
3119 'ie_key': 'MangomoloLive',
3120 'id': mobj.group('channel_id'),
3121 })
3122 return info
3123
3124 # Look for Instagram embeds
3125 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
3126 if instagram_embed_url is not None:
3127 return self.url_result(
3128 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
3129
3130 # Look for LiveLeak embeds
3131 liveleak_urls = LiveLeakIE._extract_urls(webpage)
3132 if liveleak_urls:
3133 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
3134
3135 # Look for 3Q SDN embeds
3136 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
3137 if threeqsdn_url:
3138 return {
3139 '_type': 'url_transparent',
3140 'ie_key': ThreeQSDNIE.ie_key(),
3141 'url': self._proto_relative_url(threeqsdn_url),
3142 'title': video_title,
3143 'description': video_description,
3144 'thumbnail': video_thumbnail,
3145 'uploader': video_uploader,
3146 }
3147
3148 # Look for VBOX7 embeds
3149 vbox7_url = Vbox7IE._extract_url(webpage)
3150 if vbox7_url:
3151 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3152
3153 # Look for DBTV embeds
3154 dbtv_urls = DBTVIE._extract_urls(webpage)
3155 if dbtv_urls:
3156 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
3157
3158 # Look for Videa embeds
3159 videa_urls = VideaIE._extract_urls(webpage)
3160 if videa_urls:
3161 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
3162
3163 # Look for 20 minuten embeds
3164 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3165 if twentymin_urls:
3166 return self.playlist_from_matches(
3167 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3168
3169 # Look for VideoPress embeds
3170 videopress_urls = VideoPressIE._extract_urls(webpage)
3171 if videopress_urls:
3172 return self.playlist_from_matches(
3173 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3174
3175 # Look for Rutube embeds
3176 rutube_urls = RutubeIE._extract_urls(webpage)
3177 if rutube_urls:
3178 return self.playlist_from_matches(
3179 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3180
3181 # Look for WashingtonPost embeds
3182 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3183 if wapo_urls:
3184 return self.playlist_from_matches(
3185 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3186
3187 # Look for Mediaset embeds
3188 mediaset_urls = MediasetIE._extract_urls(self, webpage)
3189 if mediaset_urls:
3190 return self.playlist_from_matches(
3191 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3192
3193 # Look for JOJ.sk embeds
3194 joj_urls = JojIE._extract_urls(webpage)
3195 if joj_urls:
3196 return self.playlist_from_matches(
3197 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3198
3199 # Look for megaphone.fm embeds
3200 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3201 if mpfn_urls:
3202 return self.playlist_from_matches(
3203 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3204
3205 # Look for vzaar embeds
3206 vzaar_urls = VzaarIE._extract_urls(webpage)
3207 if vzaar_urls:
3208 return self.playlist_from_matches(
3209 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3210
3211 channel9_urls = Channel9IE._extract_urls(webpage)
3212 if channel9_urls:
3213 return self.playlist_from_matches(
3214 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3215
3216 vshare_urls = VShareIE._extract_urls(webpage)
3217 if vshare_urls:
3218 return self.playlist_from_matches(
3219 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3220
3221 # Look for Mediasite embeds
3222 mediasite_urls = MediasiteIE._extract_urls(webpage)
3223 if mediasite_urls:
3224 entries = [
3225 self.url_result(smuggle_url(
3226 compat_urlparse.urljoin(url, mediasite_url),
3227 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3228 for mediasite_url in mediasite_urls]
3229 return self.playlist_result(entries, video_id, video_title)
3230
3231 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3232 if springboardplatform_urls:
3233 return self.playlist_from_matches(
3234 springboardplatform_urls, video_id, video_title,
3235 ie=SpringboardPlatformIE.ie_key())
3236
3237 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3238 if yapfiles_urls:
3239 return self.playlist_from_matches(
3240 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3241
3242 vice_urls = ViceIE._extract_urls(webpage)
3243 if vice_urls:
3244 return self.playlist_from_matches(
3245 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3246
3247 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3248 if xfileshare_urls:
3249 return self.playlist_from_matches(
3250 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3251
3252 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3253 if cloudflarestream_urls:
3254 return self.playlist_from_matches(
3255 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3256
3257 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3258 if peertube_urls:
3259 return self.playlist_from_matches(
3260 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3261
3262 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3263 if indavideo_urls:
3264 return self.playlist_from_matches(
3265 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3266
3267 apa_urls = APAIE._extract_urls(webpage)
3268 if apa_urls:
3269 return self.playlist_from_matches(
3270 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3271
3272 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3273 if foxnews_urls:
3274 return self.playlist_from_matches(
3275 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3276
3277 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3278 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3279 webpage)]
3280 if sharevideos_urls:
3281 return self.playlist_from_matches(
3282 sharevideos_urls, video_id, video_title)
3283
3284 viqeo_urls = ViqeoIE._extract_urls(webpage)
3285 if viqeo_urls:
3286 return self.playlist_from_matches(
3287 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3288
3289 expressen_urls = ExpressenIE._extract_urls(webpage)
3290 if expressen_urls:
3291 return self.playlist_from_matches(
3292 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3293
3294 zype_urls = ZypeIE._extract_urls(webpage)
3295 if zype_urls:
3296 return self.playlist_from_matches(
3297 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3298
3299 # Look for RCS media group embeds
3300 gedi_urls = GediEmbedsIE._extract_urls(webpage)
3301 if gedi_urls:
3302 return self.playlist_from_matches(
3303 gedi_urls, video_id, video_title, ie=GediEmbedsIE.ie_key())
3304
3305 rcs_urls = RCSEmbedsIE._extract_urls(webpage)
3306 if rcs_urls:
3307 return self.playlist_from_matches(
3308 rcs_urls, video_id, video_title, ie=RCSEmbedsIE.ie_key())
3309
3310 bitchute_urls = BitChuteIE._extract_urls(webpage)
3311 if bitchute_urls:
3312 return self.playlist_from_matches(
3313 bitchute_urls, video_id, video_title, ie=BitChuteIE.ie_key())
3314
3315 # Look for HTML5 media
3316 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3317 if entries:
3318 if len(entries) == 1:
3319 entries[0].update({
3320 'id': video_id,
3321 'title': video_title,
3322 })
3323 else:
3324 for num, entry in enumerate(entries, start=1):
3325 entry.update({
3326 'id': '%s-%s' % (video_id, num),
3327 'title': '%s (%d)' % (video_title, num),
3328 })
3329 for entry in entries:
3330 self._sort_formats(entry['formats'])
3331 return self.playlist_result(entries, video_id, video_title)
3332
3333 jwplayer_data = self._find_jwplayer_data(
3334 webpage, video_id, transform_source=js_to_json)
3335 if jwplayer_data:
3336 try:
3337 info = self._parse_jwplayer_data(
3338 jwplayer_data, video_id, require_title=False, base_url=url)
3339 return merge_dicts(info, info_dict)
3340 except ExtractorError:
3341 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3342 pass
3343
3344 # Video.js embed
3345 mobj = re.search(
3346 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3347 webpage)
3348 if mobj is not None:
3349 sources = self._parse_json(
3350 mobj.group(1), video_id, transform_source=js_to_json,
3351 fatal=False) or []
3352 if not isinstance(sources, list):
3353 sources = [sources]
3354 formats = []
3355 for source in sources:
3356 src = source.get('src')
3357 if not src or not isinstance(src, compat_str):
3358 continue
3359 src = compat_urlparse.urljoin(url, src)
3360 src_type = source.get('type')
3361 if isinstance(src_type, compat_str):
3362 src_type = src_type.lower()
3363 ext = determine_ext(src).lower()
3364 if src_type == 'video/youtube':
3365 return self.url_result(src, YoutubeIE.ie_key())
3366 if src_type == 'application/dash+xml' or ext == 'mpd':
3367 formats.extend(self._extract_mpd_formats(
3368 src, video_id, mpd_id='dash', fatal=False))
3369 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3370 formats.extend(self._extract_m3u8_formats(
3371 src, video_id, 'mp4', entry_protocol='m3u8_native',
3372 m3u8_id='hls', fatal=False))
3373 else:
3374 formats.append({
3375 'url': src,
3376 'ext': (mimetype2ext(src_type)
3377 or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3378 })
3379 if formats:
3380 self._sort_formats(formats)
3381 info_dict['formats'] = formats
3382 return info_dict
3383
3384 # Looking for http://schema.org/VideoObject
3385 json_ld = self._search_json_ld(
3386 webpage, video_id, default={}, expected_type='VideoObject')
3387 if json_ld.get('url'):
3388 return merge_dicts(json_ld, info_dict)
3389
3390 def check_video(vurl):
3391 if YoutubeIE.suitable(vurl):
3392 return True
3393 if RtmpIE.suitable(vurl):
3394 return True
3395 vpath = compat_urlparse.urlparse(vurl).path
3396 vext = determine_ext(vpath)
3397 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3398
3399 def filter_video(urls):
3400 return list(filter(check_video, urls))
3401
3402 # Start with something easy: JW Player in SWFObject
3403 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3404 if not found:
3405 # Look for gorilla-vid style embedding
3406 found = filter_video(re.findall(r'''(?sx)
3407 (?:
3408 jw_plugins|
3409 JWPlayerOptions|
3410 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3411 )
3412 .*?
3413 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3414 if not found:
3415 # Broaden the search a little bit
3416 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3417 if not found:
3418 # Broaden the findall a little bit: JWPlayer JS loader
3419 found = filter_video(re.findall(
3420 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3421 if not found:
3422 # Flow player
3423 found = filter_video(re.findall(r'''(?xs)
3424 flowplayer\("[^"]+",\s*
3425 \{[^}]+?\}\s*,
3426 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3427 ["']?url["']?\s*:\s*["']([^"']+)["']
3428 ''', webpage))
3429 if not found:
3430 # Cinerama player
3431 found = re.findall(
3432 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3433 if not found:
3434 # Try to find twitter cards info
3435 # twitter:player:stream should be checked before twitter:player since
3436 # it is expected to contain a raw stream (see
3437 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3438 found = filter_video(re.findall(
3439 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3440 if not found:
3441 # We look for Open Graph info:
3442 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3443 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3444 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3445 if m_video_type is not None:
3446 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3447 if not found:
3448 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3449 found = re.search(
3450 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3451 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3452 webpage)
3453 if not found:
3454 # Look also in Refresh HTTP header
3455 refresh_header = head_response.headers.get('Refresh')
3456 if refresh_header:
3457 # In python 2 response HTTP headers are bytestrings
3458 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3459 refresh_header = refresh_header.decode('iso-8859-1')
3460 found = re.search(REDIRECT_REGEX, refresh_header)
3461 if found:
3462 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3463 if new_url != url:
3464 self.report_following_redirect(new_url)
3465 return {
3466 '_type': 'url',
3467 'url': new_url,
3468 }
3469 else:
3470 found = None
3471
3472 if not found:
3473 # twitter:player is a https URL to iframe player that may or may not
3474 # be supported by youtube-dlc thus this is checked the very last (see
3475 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3476 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3477 if embed_url and embed_url != url:
3478 return self.url_result(embed_url)
3479
3480 if not found:
3481 raise UnsupportedError(url)
3482
3483 entries = []
3484 for video_url in orderedSet(found):
3485 video_url = unescapeHTML(video_url)
3486 video_url = video_url.replace('\\/', '/')
3487 video_url = compat_urlparse.urljoin(url, video_url)
3488 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3489
3490 # Sometimes, jwplayer extraction will result in a YouTube URL
3491 if YoutubeIE.suitable(video_url):
3492 entries.append(self.url_result(video_url, 'Youtube'))
3493 continue
3494
3495 # here's a fun little line of code for you:
3496 video_id = os.path.splitext(video_id)[0]
3497
3498 entry_info_dict = {
3499 'id': video_id,
3500 'uploader': video_uploader,
3501 'title': video_title,
3502 'age_limit': age_limit,
3503 }
3504
3505 if RtmpIE.suitable(video_url):
3506 entry_info_dict.update({
3507 '_type': 'url_transparent',
3508 'ie_key': RtmpIE.ie_key(),
3509 'url': video_url,
3510 })
3511 entries.append(entry_info_dict)
3512 continue
3513
3514 ext = determine_ext(video_url)
3515 if ext == 'smil':
3516 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3517 elif ext == 'xspf':
3518 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3519 elif ext == 'm3u8':
3520 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3521 elif ext == 'mpd':
3522 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3523 elif ext == 'f4m':
3524 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3525 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3526 # Just matching .ism/manifest is not enough to be reliably sure
3527 # whether it's actually an ISM manifest or some other streaming
3528 # manifest since there are various streaming URL formats
3529 # possible (see [1]) as well as some other shenanigans like
3530 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3531 # so on.
3532 # Thus the most reasonable way to solve this is to delegate
3533 # to generic extractor in order to look into the contents of
3534 # the manifest itself.
3535 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3536 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3537 entry_info_dict = self.url_result(
3538 smuggle_url(video_url, {'to_generic': True}),
3539 GenericIE.ie_key())
3540 else:
3541 entry_info_dict['url'] = video_url
3542
3543 if entry_info_dict.get('formats'):
3544 self._sort_formats(entry_info_dict['formats'])
3545
3546 entries.append(entry_info_dict)
3547
3548 if len(entries) == 1:
3549 return entries[0]
3550 else:
3551 for num, e in enumerate(entries, start=1):
3552 # 'url' results don't have a title
3553 if e.get('title') is not None:
3554 e['title'] = '%s (%d)' % (e['title'], num)
3555 return {
3556 '_type': 'playlist',
3557 'entries': entries,
3558 }