1 # coding: utf-8
2
3 from __future__ import unicode_literals
4
5 import os
6 import re
7 import sys
8
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
13 compat_str,
14 compat_urllib_parse_unquote,
15 compat_urlparse,
16 compat_xml_parse_error,
17 )
18 from ..utils import (
19 determine_ext,
20 ExtractorError,
21 float_or_none,
22 HEADRequest,
23 int_or_none,
24 is_html,
25 js_to_json,
26 KNOWN_EXTENSIONS,
27 merge_dicts,
28 mimetype2ext,
29 orderedSet,
30 parse_duration,
31 parse_resolution,
32 sanitized_Request,
33 smuggle_url,
34 unescapeHTML,
35 unified_timestamp,
36 unsmuggle_url,
37 UnsupportedError,
38 url_or_none,
39 xpath_attr,
40 xpath_text,
41 xpath_with_ns,
42 )
43 from .commonprotocols import RtmpIE
44 from .brightcove import (
45 BrightcoveLegacyIE,
46 BrightcoveNewIE,
47 )
48 from .nexx import (
49 NexxIE,
50 NexxEmbedIE,
51 )
52 from .nbc import NBCSportsVPlayerIE
53 from .ooyala import OoyalaIE
54 from .rutv import RUTVIE
55 from .tvc import TVCIE
56 from .sportbox import SportBoxIE
57 from .myvi import MyviIE
58 from .condenast import CondeNastIE
59 from .udn import UDNEmbedIE
60 from .senateisvp import SenateISVPIE
61 from .svt import SVTIE
62 from .pornhub import PornHubIE
63 from .xhamster import XHamsterEmbedIE
64 from .tnaflix import TNAFlixNetworkEmbedIE
65 from .drtuber import DrTuberIE
66 from .redtube import RedTubeIE
67 from .tube8 import Tube8IE
68 from .mofosex import MofosexEmbedIE
69 from .spankwire import SpankwireIE
70 from .youporn import YouPornIE
71 from .vimeo import (
72 VimeoIE,
73 VHXEmbedIE,
74 )
75 from .dailymotion import DailymotionIE
76 from .dailymail import DailyMailIE
77 from .onionstudios import OnionStudiosIE
78 from .viewlift import ViewLiftEmbedIE
79 from .mtv import MTVServicesEmbeddedIE
80 from .pladform import PladformIE
81 from .videomore import VideomoreIE
82 from .webcaster import WebcasterFeedIE
83 from .googledrive import GoogleDriveIE
84 from .jwplatform import JWPlatformIE
85 from .digiteka import DigitekaIE
86 from .arkena import ArkenaIE
87 from .instagram import InstagramIE
88 from .threeqsdn import ThreeQSDNIE
89 from .theplatform import ThePlatformIE
90 from .kaltura import KalturaIE
91 from .eagleplatform import EaglePlatformIE
92 from .facebook import FacebookIE
93 from .soundcloud import SoundcloudEmbedIE
94 from .tunein import TuneInBaseIE
95 from .vbox7 import Vbox7IE
96 from .dbtv import DBTVIE
97 from .piksel import PikselIE
98 from .videa import VideaIE
99 from .twentymin import TwentyMinutenIE
100 from .ustream import UstreamIE
101 from .arte import ArteTVEmbedIE
102 from .videopress import VideoPressIE
103 from .rutube import RutubeIE
104 from .limelight import LimelightBaseIE
105 from .anvato import AnvatoIE
106 from .washingtonpost import WashingtonPostIE
107 from .wistia import WistiaIE
108 from .mediaset import MediasetIE
109 from .joj import JojIE
110 from .megaphone import MegaphoneIE
111 from .vzaar import VzaarIE
112 from .channel9 import Channel9IE
113 from .vshare import VShareIE
114 from .mediasite import MediasiteIE
115 from .springboardplatform import SpringboardPlatformIE
116 from .yapfiles import YapFilesIE
117 from .vice import ViceIE
118 from .xfileshare import XFileShareIE
119 from .cloudflarestream import CloudflareStreamIE
120 from .peertube import PeerTubeIE
121 from .teachable import TeachableIE
122 from .indavideo import IndavideoEmbedIE
123 from .apa import APAIE
124 from .foxnews import FoxNewsIE
125 from .viqeo import ViqeoIE
126 from .expressen import ExpressenIE
127 from .zype import ZypeIE
128 from .odnoklassniki import OdnoklassnikiIE
129 from .vk import VKIE
130 from .kinja import KinjaEmbedIE
131 from .arcpublishing import ArcPublishingIE
132 from .medialaan import MedialaanIE
133 from .simplecast import SimplecastIE
134
135
136 class GenericIE(InfoExtractor):
137 IE_DESC = 'Generic downloader that works on some sites'
138 _VALID_URL = r'.*'
139 IE_NAME = 'generic'
140 _TESTS = [
141 # Direct link to a video
142 {
143 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
144 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
145 'info_dict': {
146 'id': 'trailer',
147 'ext': 'mp4',
148 'title': 'trailer',
149 'upload_date': '20100513',
150 }
151 },
152 # Direct link to media delivered compressed (until Accept-Encoding is *)
153 {
154 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
155 'md5': '128c42e68b13950268b648275386fc74',
156 'info_dict': {
157 'id': 'FictionJunction-Parallel_Hearts',
158 'ext': 'flac',
159 'title': 'FictionJunction-Parallel_Hearts',
160 'upload_date': '20140522',
161 },
162 'expected_warnings': [
163 'URL could be a direct video link, returning it as such.'
164 ],
165 'skip': 'URL invalid',
166 },
167 # Direct download with broken HEAD
168 {
169 'url': 'http://ai-radio.org:8000/radio.opus',
170 'info_dict': {
171 'id': 'radio',
172 'ext': 'opus',
173 'title': 'radio',
174 },
175 'params': {
176 'skip_download': True, # infinite live stream
177 },
178 'expected_warnings': [
179 r'501.*Not Implemented',
180 r'400.*Bad Request',
181 ],
182 },
183 # Direct link with incorrect MIME type
184 {
185 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
186 'md5': '4ccbebe5f36706d85221f204d7eb5913',
187 'info_dict': {
188 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
189 'id': '5_Lennart_Poettering_-_Systemd',
190 'ext': 'webm',
191 'title': '5_Lennart_Poettering_-_Systemd',
192 'upload_date': '20141120',
193 },
194 'expected_warnings': [
195 'URL could be a direct video link, returning it as such.'
196 ]
197 },
198 # RSS feed
199 {
200 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
201 'info_dict': {
202 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
203 'title': 'Zero Punctuation',
204 'description': 're:.*groundbreaking video review series.*'
205 },
206 'playlist_mincount': 11,
207 },
208 # RSS feed with enclosure
209 {
210 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
211 'info_dict': {
212 'id': 'http://podcastfeeds.nbcnews.com/nbcnews/video/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
213 'title': 'MSNBC Rachel Maddow (video)',
214 'description': 're:.*her unique approach to storytelling.*',
215 },
216 'playlist': [{
217 'info_dict': {
218 'ext': 'mov',
219 'id': 'pdv_maddow_netcast_mov-12-04-2020-224335',
220 'title': 're:MSNBC Rachel Maddow',
221 'description': 're:.*her unique approach to storytelling.*',
222 'timestamp': int,
223 'upload_date': compat_str,
224 'duration': float,
225 },
226 }],
227 },
228 # RSS feed with item with description and thumbnails
229 {
230 'url': 'https://anchor.fm/s/dd00e14/podcast/rss',
231 'info_dict': {
232 'id': 'https://anchor.fm/s/dd00e14/podcast/rss',
233 'title': 're:.*100% Hydrogen.*',
234 'description': 're:.*In this episode.*',
235 },
236 'playlist': [{
237 'info_dict': {
238 'ext': 'm4a',
239 'id': 'c1c879525ce2cb640b344507e682c36d',
240 'title': 're:Hydrogen!',
241 'description': 're:.*In this episode we are going.*',
242 'timestamp': 1567977776,
243 'upload_date': '20190908',
244 'duration': 459,
245 'thumbnail': r're:^https?://.*\.jpg$',
246 'episode_number': 1,
247 'season_number': 1,
248 'age_limit': 0,
249 },
250 }],
251 'params': {
252 'skip_download': True,
253 },
254 },
255 # RSS feed with enclosures and unsupported link URLs
256 {
257 'url': 'http://www.hellointernet.fm/podcast?format=rss',
258 'info_dict': {
259 'id': 'http://www.hellointernet.fm/podcast?format=rss',
260 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
261 'title': 'Hello Internet',
262 },
263 'playlist_mincount': 100,
264 },
265 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
266 {
267 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
268 'info_dict': {
269 'id': 'smil',
270 'ext': 'mp4',
271 'title': 'Automatics, robotics and biocybernetics',
272 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
273 'upload_date': '20130627',
274 'formats': 'mincount:16',
275 'subtitles': 'mincount:1',
276 },
277 'params': {
278 'force_generic_extractor': True,
279 'skip_download': True,
280 },
281 },
282 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
283 {
284 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
285 'info_dict': {
286 'id': 'hds',
287 'ext': 'flv',
288 'title': 'hds',
289 'formats': 'mincount:1',
290 },
291 'params': {
292 'skip_download': True,
293 },
294 },
295 # SMIL from https://www.restudy.dk/video/play/id/1637
296 {
297 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
298 'info_dict': {
299 'id': 'video_1637',
300 'ext': 'flv',
301 'title': 'video_1637',
302 'formats': 'mincount:3',
303 },
304 'params': {
305 'skip_download': True,
306 },
307 },
308 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
309 {
310 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
311 'info_dict': {
312 'id': 'smil-service',
313 'ext': 'flv',
314 'title': 'smil-service',
315 'formats': 'mincount:1',
316 },
317 'params': {
318 'skip_download': True,
319 },
320 },
321 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
322 {
323 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
324 'info_dict': {
325 'id': '4719370',
326 'ext': 'mp4',
327 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
328 'formats': 'mincount:3',
329 },
330 'params': {
331 'skip_download': True,
332 },
333 },
334 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
335 {
336 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
337 'info_dict': {
338 'id': 'mZlp2ctYIUEB',
339 'ext': 'mp4',
340 'title': 'Tikibad ontruimd wegens brand',
341 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
342 'thumbnail': r're:^https?://.*\.jpg$',
343 'duration': 33,
344 },
345 'params': {
346 'skip_download': True,
347 },
348 },
349 # MPD from http://dash-mse-test.appspot.com/media.html
350 {
351 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
352 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
353 'info_dict': {
354 'id': 'car-20120827-manifest',
355 'ext': 'mp4',
356 'title': 'car-20120827-manifest',
357 'formats': 'mincount:9',
358 'upload_date': '20130904',
359 },
360 'params': {
361 'format': 'bestvideo',
362 },
363 },
364 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
365 {
366 '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',
367 'info_dict': {
368 'id': 'content',
369 'ext': 'mp4',
370 'title': 'content',
371 'formats': 'mincount:8',
372 },
373 'params': {
374 # m3u8 downloads
375 'skip_download': True,
376 },
377 'skip': 'video gone',
378 },
379 # m3u8 served with Content-Type: text/plain
380 {
381 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
382 'info_dict': {
383 'id': 'index',
384 'ext': 'mp4',
385 'title': 'index',
386 'upload_date': '20140720',
387 'formats': 'mincount:11',
388 },
389 'params': {
390 # m3u8 downloads
391 'skip_download': True,
392 },
393 'skip': 'video gone',
394 },
395 # google redirect
396 {
397 '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',
398 'info_dict': {
399 'id': 'cmQHVoWB5FY',
400 'ext': 'mp4',
401 'upload_date': '20130224',
402 'uploader_id': 'TheVerge',
403 'description': r're:^Chris Ziegler takes a look at the\.*',
404 'uploader': 'The Verge',
405 'title': 'First Firefox OS phones side-by-side',
406 },
407 'params': {
408 'skip_download': False,
409 }
410 },
411 {
412 # redirect in Refresh HTTP header
413 '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',
414 'info_dict': {
415 'id': 'pO8h3EaFRdo',
416 'ext': 'mp4',
417 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
418 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
419 'upload_date': '20150917',
420 'uploader_id': 'brtvofficial',
421 'uploader': 'Boiler Room',
422 },
423 'params': {
424 'skip_download': False,
425 },
426 },
427 {
428 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
429 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
430 'info_dict': {
431 'id': '13601338388002',
432 'ext': 'mp4',
433 'uploader': 'www.hodiho.fr',
434 'title': 'R\u00e9gis plante sa Jeep',
435 }
436 },
437 # bandcamp page with custom domain
438 {
439 'add_ie': ['Bandcamp'],
440 'url': 'http://bronyrock.com/track/the-pony-mash',
441 'info_dict': {
442 'id': '3235767654',
443 'ext': 'mp3',
444 'title': 'The Pony Mash',
445 'uploader': 'M_Pallante',
446 },
447 'skip': 'There is a limit of 200 free downloads / month for the test song',
448 },
449 {
450 # embedded brightcove video
451 # it also tests brightcove videos that need to set the 'Referer'
452 # in the http requests
453 'add_ie': ['BrightcoveLegacy'],
454 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
455 'info_dict': {
456 'id': '2765128793001',
457 'ext': 'mp4',
458 'title': 'Le cours de bourse : l’analyse technique',
459 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
460 'uploader': 'BFM BUSINESS',
461 },
462 'params': {
463 'skip_download': True,
464 },
465 },
466 {
467 # embedded with itemprop embedURL and video id spelled as `idVideo`
468 'add_id': ['BrightcoveLegacy'],
469 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
470 'info_dict': {
471 'id': '5255628253001',
472 'ext': 'mp4',
473 'title': 'md5:37c519b1128915607601e75a87995fc0',
474 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
475 'uploader': 'BFM BUSINESS',
476 'uploader_id': '876450612001',
477 'timestamp': 1482255315,
478 'upload_date': '20161220',
479 },
480 'params': {
481 'skip_download': True,
482 },
483 },
484 {
485 # https://github.com/ytdl-org/youtube-dl/issues/2253
486 'url': 'http://bcove.me/i6nfkrc3',
487 'md5': '0ba9446db037002366bab3b3eb30c88c',
488 'info_dict': {
489 'id': '3101154703001',
490 'ext': 'mp4',
491 'title': 'Still no power',
492 'uploader': 'thestar.com',
493 '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.',
494 },
495 'add_ie': ['BrightcoveLegacy'],
496 'skip': 'video gone',
497 },
498 {
499 'url': 'http://www.championat.com/video/football/v/87/87499.html',
500 'md5': 'fb973ecf6e4a78a67453647444222983',
501 'info_dict': {
502 'id': '3414141473001',
503 'ext': 'mp4',
504 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
505 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
506 'uploader': 'Championat',
507 },
508 },
509 {
510 # https://github.com/ytdl-org/youtube-dl/issues/3541
511 'add_ie': ['BrightcoveLegacy'],
512 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
513 'info_dict': {
514 'id': '3866516442001',
515 'ext': 'mp4',
516 'title': 'Leer mij vrouwen kennen: Aflevering 1',
517 'description': 'Leer mij vrouwen kennen: Aflevering 1',
518 'uploader': 'SBS Broadcasting',
519 },
520 'skip': 'Restricted to Netherlands',
521 'params': {
522 'skip_download': True, # m3u8 download
523 },
524 },
525 {
526 # Brightcove video in <iframe>
527 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
528 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
529 'info_dict': {
530 'id': '5360463607001',
531 'ext': 'mp4',
532 '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',
533 '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。',
534 'uploader': 'United Nations',
535 'uploader_id': '1362235914001',
536 'timestamp': 1489593889,
537 'upload_date': '20170315',
538 },
539 'add_ie': ['BrightcoveLegacy'],
540 },
541 {
542 # Brightcove with alternative playerID key
543 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
544 'info_dict': {
545 'id': 'nmeth.2062_SV1',
546 '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',
547 },
548 'playlist': [{
549 'info_dict': {
550 'id': '2228375078001',
551 'ext': 'mp4',
552 'title': 'nmeth.2062-sv1',
553 'description': 'nmeth.2062-sv1',
554 'timestamp': 1363357591,
555 'upload_date': '20130315',
556 'uploader': 'Nature Publishing Group',
557 'uploader_id': '1964492299001',
558 },
559 }],
560 },
561 {
562 # Brightcove with UUID in videoPlayer
563 'url': 'http://www8.hp.com/cn/zh/home.html',
564 'info_dict': {
565 'id': '5255815316001',
566 'ext': 'mp4',
567 'title': 'Sprocket Video - China',
568 'description': 'Sprocket Video - China',
569 'uploader': 'HP-Video Gallery',
570 'timestamp': 1482263210,
571 'upload_date': '20161220',
572 'uploader_id': '1107601872001',
573 },
574 'params': {
575 'skip_download': True, # m3u8 download
576 },
577 'skip': 'video rotates...weekly?',
578 },
579 {
580 # Brightcove:new type [2].
581 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
582 'md5': '2b35148fcf48da41c9fb4591650784f3',
583 'info_dict': {
584 'id': '5348741021001',
585 'ext': 'mp4',
586 'upload_date': '20170306',
587 'uploader_id': '4191638492001',
588 'timestamp': 1488769918,
589 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
590
591 },
592 },
593 {
594 # Alternative brightcove <video> attributes
595 '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/',
596 'info_dict': {
597 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
598 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
599 },
600 'playlist': [{
601 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
602 'info_dict': {
603 'id': '5311302538001',
604 'ext': 'mp4',
605 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
606 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
607 'timestamp': 1486321708,
608 'upload_date': '20170205',
609 'uploader_id': '800000640001',
610 },
611 'only_matching': True,
612 }],
613 },
614 {
615 # Brightcove with UUID in videoPlayer
616 'url': 'http://www8.hp.com/cn/zh/home.html',
617 'info_dict': {
618 'id': '5255815316001',
619 'ext': 'mp4',
620 'title': 'Sprocket Video - China',
621 'description': 'Sprocket Video - China',
622 'uploader': 'HP-Video Gallery',
623 'timestamp': 1482263210,
624 'upload_date': '20161220',
625 'uploader_id': '1107601872001',
626 },
627 'params': {
628 'skip_download': True, # m3u8 download
629 },
630 },
631 # ooyala video
632 {
633 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
634 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
635 'info_dict': {
636 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
637 'ext': 'mp4',
638 'title': '2cc213299525360.mov', # that's what we get
639 'duration': 238.231,
640 },
641 'add_ie': ['Ooyala'],
642 },
643 {
644 # ooyala video embedded with http://player.ooyala.com/iframe.js
645 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
646 'info_dict': {
647 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
648 'ext': 'mp4',
649 'title': '"Steve Jobs: Man in the Machine" trailer',
650 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
651 'duration': 135.427,
652 },
653 'params': {
654 'skip_download': True,
655 },
656 'skip': 'movie expired',
657 },
658 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
659 {
660 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
661 'info_dict': {
662 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
663 'ext': 'mp4',
664 'title': 'Steampunk Fest Comes to Honesdale',
665 'duration': 43.276,
666 },
667 'params': {
668 'skip_download': True,
669 }
670 },
671 # embed.ly video
672 {
673 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
674 'info_dict': {
675 'id': '9ODmcdjQcHQ',
676 'ext': 'mp4',
677 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
678 'upload_date': '20140225',
679 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
680 'uploader': 'Tested',
681 'uploader_id': 'testedcom',
682 },
683 # No need to test YoutubeIE here
684 'params': {
685 'skip_download': True,
686 },
687 },
688 # funnyordie embed
689 {
690 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
691 'info_dict': {
692 'id': '18e820ec3f',
693 'ext': 'mp4',
694 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
695 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
696 },
697 # HEAD requests lead to endless 301, while GET is OK
698 'expected_warnings': ['301'],
699 },
700 # RUTV embed
701 {
702 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
703 'info_dict': {
704 'id': '776940',
705 'ext': 'mp4',
706 'title': 'Охотское море стало целиком российским',
707 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
708 },
709 'params': {
710 # m3u8 download
711 'skip_download': True,
712 },
713 },
714 # TVC embed
715 {
716 '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/',
717 'info_dict': {
718 'id': '55304',
719 'ext': 'mp4',
720 'title': 'Дошкольное воспитание',
721 },
722 },
723 # SportBox embed
724 {
725 'url': 'http://www.vestifinance.ru/articles/25753',
726 'info_dict': {
727 'id': '25753',
728 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
729 },
730 'playlist': [{
731 'info_dict': {
732 'id': '370908',
733 'title': 'Госзаказ. День 3',
734 'ext': 'mp4',
735 }
736 }, {
737 'info_dict': {
738 'id': '370905',
739 'title': 'Госзаказ. День 2',
740 'ext': 'mp4',
741 }
742 }, {
743 'info_dict': {
744 'id': '370902',
745 'title': 'Госзаказ. День 1',
746 'ext': 'mp4',
747 }
748 }],
749 'params': {
750 # m3u8 download
751 'skip_download': True,
752 },
753 },
754 # Myvi.ru embed
755 {
756 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
757 'info_dict': {
758 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
759 'ext': 'mp4',
760 'title': 'Ужастики, русский трейлер (2015)',
761 'thumbnail': r're:^https?://.*\.jpg$',
762 'duration': 153,
763 }
764 },
765 # XHamster embed
766 {
767 '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',
768 'info_dict': {
769 'id': 'showthread',
770 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
771 },
772 'playlist_mincount': 7,
773 # This forum does not allow <iframe> syntaxes anymore
774 # Now HTML tags are displayed as-is
775 'skip': 'No videos on this page',
776 },
777 # Embedded TED video
778 {
779 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
780 'md5': '65fdff94098e4a607385a60c5177c638',
781 'info_dict': {
782 'id': '1969',
783 'ext': 'mp4',
784 'title': 'Hidden miracles of the natural world',
785 'uploader': 'Louie Schwartzberg',
786 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
787 }
788 },
789 # nowvideo embed hidden behind percent encoding
790 {
791 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
792 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
793 'info_dict': {
794 'id': '06e53103ca9aa',
795 'ext': 'flv',
796 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
797 'description': 'No description',
798 },
799 },
800 # arte embed
801 {
802 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
803 'md5': '7653032cbb25bf6c80d80f217055fa43',
804 'info_dict': {
805 'id': '048195-004_PLUS7-F',
806 'ext': 'flv',
807 'title': 'X:enius',
808 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
809 'upload_date': '20140320',
810 },
811 'params': {
812 'skip_download': 'Requires rtmpdump'
813 },
814 'skip': 'video gone',
815 },
816 # francetv embed
817 {
818 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
819 'info_dict': {
820 'id': 'EV_30231',
821 'ext': 'mp4',
822 'title': 'Alcaline, le concert avec Calogero',
823 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
824 'upload_date': '20150226',
825 'timestamp': 1424989860,
826 'duration': 5400,
827 },
828 'params': {
829 # m3u8 downloads
830 'skip_download': True,
831 },
832 'expected_warnings': [
833 'Forbidden'
834 ]
835 },
836 # Condé Nast embed
837 {
838 'url': 'http://www.wired.com/2014/04/honda-asimo/',
839 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
840 'info_dict': {
841 'id': '53501be369702d3275860000',
842 'ext': 'mp4',
843 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
844 }
845 },
846 # Dailymotion embed
847 {
848 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
849 'md5': '441aeeb82eb72c422c7f14ec533999cd',
850 'info_dict': {
851 'id': 'k2mm4bCdJ6CQ2i7c8o2',
852 'ext': 'mp4',
853 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
854 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
855 'uploader': 'Spi0n',
856 'uploader_id': 'xgditw',
857 'upload_date': '20140425',
858 'timestamp': 1398441542,
859 },
860 'add_ie': ['Dailymotion'],
861 },
862 # DailyMail embed
863 {
864 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
865 'info_dict': {
866 'id': '1495629',
867 'ext': 'mp4',
868 'title': 'Care worker punches elderly dementia patient in head 11 times',
869 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
870 },
871 'add_ie': ['DailyMail'],
872 'params': {
873 'skip_download': True,
874 },
875 },
876 # YouTube embed
877 {
878 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
879 'info_dict': {
880 'id': 'FXRb4ykk4S0',
881 'ext': 'mp4',
882 'title': 'The NBL Auction 2014',
883 'uploader': 'BADMINTON England',
884 'uploader_id': 'BADMINTONEvents',
885 'upload_date': '20140603',
886 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
887 },
888 'add_ie': ['Youtube'],
889 'params': {
890 'skip_download': True,
891 }
892 },
893 # MTVServices embed
894 {
895 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
896 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
897 'info_dict': {
898 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
899 'ext': 'mp4',
900 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
901 'description': 'Two valets share their love for movie star Liam Neesons.',
902 'timestamp': 1349922600,
903 'upload_date': '20121011',
904 },
905 },
906 # YouTube embed via <data-embed-url="">
907 {
908 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
909 'info_dict': {
910 'id': '4vAffPZIT44',
911 'ext': 'mp4',
912 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
913 'uploader': 'Gameloft',
914 'uploader_id': 'gameloft',
915 'upload_date': '20140828',
916 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
917 },
918 'params': {
919 'skip_download': True,
920 }
921 },
922 # YouTube <object> embed
923 {
924 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
925 'md5': '516718101ec834f74318df76259fb3cc',
926 'info_dict': {
927 'id': 'msN87y-iEx0',
928 'ext': 'webm',
929 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
930 'upload_date': '20080526',
931 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
932 'uploader': 'Christopher Sykes',
933 'uploader_id': 'ChristopherJSykes',
934 },
935 'add_ie': ['Youtube'],
936 },
937 # Camtasia studio
938 {
939 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
940 'playlist': [{
941 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
942 'info_dict': {
943 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
944 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
945 'ext': 'flv',
946 'duration': 2235.90,
947 }
948 }, {
949 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
950 'info_dict': {
951 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
952 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
953 'ext': 'flv',
954 'duration': 2235.93,
955 }
956 }],
957 'info_dict': {
958 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
959 }
960 },
961 # Flowplayer
962 {
963 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
964 'md5': '9d65602bf31c6e20014319c7d07fba27',
965 'info_dict': {
966 'id': '5123ea6d5e5a7',
967 'ext': 'mp4',
968 'age_limit': 18,
969 'uploader': 'www.handjobhub.com',
970 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
971 }
972 },
973 # Multiple brightcove videos
974 # https://github.com/ytdl-org/youtube-dl/issues/2283
975 {
976 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
977 'info_dict': {
978 'id': 'always-never',
979 'title': 'Always / Never - The New Yorker',
980 },
981 'playlist_count': 3,
982 'params': {
983 'extract_flat': False,
984 'skip_download': True,
985 }
986 },
987 # MLB embed
988 {
989 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
990 'md5': '96f09a37e44da40dd083e12d9a683327',
991 'info_dict': {
992 'id': '33322633',
993 'ext': 'mp4',
994 'title': 'Ump changes call to ball',
995 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
996 'duration': 48,
997 'timestamp': 1401537900,
998 'upload_date': '20140531',
999 'thumbnail': r're:^https?://.*\.jpg$',
1000 },
1001 },
1002 # Wistia embed
1003 {
1004 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
1005 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
1006 'info_dict': {
1007 'id': '6e2wtrbdaf',
1008 'ext': 'mov',
1009 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
1010 'description': 'a Paywall Videos video from Remilon',
1011 'duration': 644.072,
1012 'uploader': 'study.com',
1013 'timestamp': 1459678540,
1014 'upload_date': '20160403',
1015 'filesize': 24687186,
1016 },
1017 },
1018 {
1019 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
1020 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
1021 'info_dict': {
1022 'id': 'uxjb0lwrcz',
1023 'ext': 'mp4',
1024 'title': 'Conversation about Hexagonal Rails Part 1',
1025 'description': 'a Martin Fowler video from ThoughtWorks',
1026 'duration': 1715.0,
1027 'uploader': 'thoughtworks.wistia.com',
1028 'timestamp': 1401832161,
1029 'upload_date': '20140603',
1030 },
1031 },
1032 # Wistia standard embed (async)
1033 {
1034 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
1035 'info_dict': {
1036 'id': '807fafadvk',
1037 'ext': 'mp4',
1038 'title': 'Drip Brennan Dunn Workshop',
1039 'description': 'a JV Webinars video from getdrip-1',
1040 'duration': 4986.95,
1041 'timestamp': 1463607249,
1042 'upload_date': '20160518',
1043 },
1044 'params': {
1045 'skip_download': True,
1046 }
1047 },
1048 # Soundcloud embed
1049 {
1050 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1051 'info_dict': {
1052 'id': '174391317',
1053 'ext': 'mp3',
1054 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1055 'uploader': 'Sophos Security',
1056 'title': 'Chet Chat 171 - Oct 29, 2014',
1057 'upload_date': '20141029',
1058 }
1059 },
1060 # Soundcloud multiple embeds
1061 {
1062 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1063 'info_dict': {
1064 'id': '52809',
1065 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1066 },
1067 'playlist_mincount': 7,
1068 },
1069 # TuneIn station embed
1070 {
1071 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1072 'info_dict': {
1073 'id': '204146',
1074 'ext': 'mp3',
1075 'title': 'CNRV',
1076 'location': 'Paris, France',
1077 'is_live': True,
1078 },
1079 'params': {
1080 # Live stream
1081 'skip_download': True,
1082 },
1083 },
1084 # Livestream embed
1085 {
1086 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1087 'info_dict': {
1088 'id': '67864563',
1089 'ext': 'flv',
1090 'upload_date': '20141112',
1091 'title': 'Rosetta #CometLanding webcast HL 10',
1092 }
1093 },
1094 # Another Livestream embed, without 'new.' in URL
1095 {
1096 'url': 'https://www.freespeech.org/',
1097 'info_dict': {
1098 'id': '123537347',
1099 'ext': 'mp4',
1100 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1101 },
1102 'params': {
1103 # Live stream
1104 'skip_download': True,
1105 },
1106 },
1107 # LazyYT
1108 {
1109 'url': 'https://skiplagged.com/',
1110 'info_dict': {
1111 'id': 'skiplagged',
1112 'title': 'Skiplagged: The smart way to find cheap flights',
1113 },
1114 'playlist_mincount': 1,
1115 'add_ie': ['Youtube'],
1116 },
1117 # Cinchcast embed
1118 {
1119 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1120 'info_dict': {
1121 'id': '7141703',
1122 'ext': 'mp3',
1123 'upload_date': '20141126',
1124 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1125 }
1126 },
1127 # Cinerama player
1128 {
1129 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1130 'info_dict': {
1131 'id': '730m_DandD_1901_512k',
1132 'ext': 'mp4',
1133 'uploader': 'www.abc.net.au',
1134 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1135 }
1136 },
1137 # embedded viddler video
1138 {
1139 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1140 'info_dict': {
1141 'id': '4d03aad9',
1142 'ext': 'mp4',
1143 'uploader': 'deadspin',
1144 'title': 'WALL-TO-GORTAT',
1145 'timestamp': 1422285291,
1146 'upload_date': '20150126',
1147 },
1148 'add_ie': ['Viddler'],
1149 },
1150 # Libsyn embed
1151 {
1152 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1153 'info_dict': {
1154 'id': '3377616',
1155 'ext': 'mp3',
1156 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1157 'description': 'md5:601cb790edd05908957dae8aaa866465',
1158 'upload_date': '20150220',
1159 },
1160 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1161 },
1162 # jwplayer YouTube
1163 {
1164 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1165 'info_dict': {
1166 'id': 'Mrj4DVp2zeA',
1167 'ext': 'mp4',
1168 'upload_date': '20150212',
1169 'uploader': 'The National Archives UK',
1170 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1171 'uploader_id': 'NationalArchives08',
1172 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1173 },
1174 },
1175 # jwplayer rtmp
1176 {
1177 'url': 'http://www.suffolk.edu/sjc/live.php',
1178 'info_dict': {
1179 'id': 'live',
1180 'ext': 'flv',
1181 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1182 'uploader': 'www.suffolk.edu',
1183 },
1184 'params': {
1185 'skip_download': True,
1186 },
1187 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1188 },
1189 # Complex jwplayer
1190 {
1191 'url': 'http://www.indiedb.com/games/king-machine/videos',
1192 'info_dict': {
1193 'id': 'videos',
1194 'ext': 'mp4',
1195 'title': 'king machine trailer 1',
1196 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1197 'thumbnail': r're:^https?://.*\.jpg$',
1198 },
1199 },
1200 {
1201 # JWPlayer config passed as variable
1202 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1203 'info_dict': {
1204 'id': '3326530_hq',
1205 'ext': 'mp4',
1206 'title': 'ARIELE | Tube Cup',
1207 'uploader': 'www.txxx.com',
1208 'age_limit': 18,
1209 },
1210 'params': {
1211 'skip_download': True,
1212 }
1213 },
1214 {
1215 # JWPlatform iframe
1216 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1217 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1218 'info_dict': {
1219 'id': 'O0c5JcKT',
1220 'ext': 'mp4',
1221 'upload_date': '20171122',
1222 'timestamp': 1511366290,
1223 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1224 },
1225 'add_ie': [JWPlatformIE.ie_key()],
1226 },
1227 {
1228 # Video.js embed, multiple formats
1229 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1230 'info_dict': {
1231 'id': 'yygqldloqIk',
1232 'ext': 'mp4',
1233 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1234 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1235 'upload_date': '20130314',
1236 'uploader': 'PROстое3D',
1237 'uploader_id': 'PROstoe3D',
1238 },
1239 'params': {
1240 'skip_download': True,
1241 },
1242 },
1243 {
1244 # Video.js embed, single format
1245 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1246 'info_dict': {
1247 'id': 'watch',
1248 'ext': 'mp4',
1249 'title': 'Step 1 - Good Foundation',
1250 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1251 },
1252 'params': {
1253 'skip_download': True,
1254 },
1255 },
1256 # rtl.nl embed
1257 {
1258 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1259 'playlist_mincount': 5,
1260 'info_dict': {
1261 'id': 'aanslagen-kopenhagen',
1262 'title': 'Aanslagen Kopenhagen',
1263 }
1264 },
1265 # Zapiks embed
1266 {
1267 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1268 'info_dict': {
1269 'id': '118046',
1270 'ext': 'mp4',
1271 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1272 }
1273 },
1274 # Kaltura embed (different embed code)
1275 {
1276 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1277 'info_dict': {
1278 'id': '1_a52wc67y',
1279 'ext': 'flv',
1280 'upload_date': '20150127',
1281 'uploader_id': 'PremierMedia',
1282 'timestamp': int,
1283 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1284 },
1285 },
1286 # Kaltura embed with single quotes
1287 {
1288 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1289 'info_dict': {
1290 'id': '0_izeg5utt',
1291 'ext': 'mp4',
1292 'title': '35871',
1293 'timestamp': 1355743100,
1294 'upload_date': '20121217',
1295 'uploader_id': 'cplapp@learn360.com',
1296 },
1297 'add_ie': ['Kaltura'],
1298 },
1299 {
1300 # Kaltura embedded via quoted entry_id
1301 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1302 'info_dict': {
1303 'id': '0_utuok90b',
1304 'ext': 'mp4',
1305 'title': '06_matthew_brender_raj_dutt',
1306 'timestamp': 1466638791,
1307 'upload_date': '20160622',
1308 },
1309 'add_ie': ['Kaltura'],
1310 'expected_warnings': [
1311 'Could not send HEAD request'
1312 ],
1313 'params': {
1314 'skip_download': True,
1315 }
1316 },
1317 {
1318 # Kaltura embedded, some fileExt broken (#11480)
1319 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1320 'info_dict': {
1321 'id': '1_sgtvehim',
1322 'ext': 'mp4',
1323 'title': 'Our "Standard Models" of particle physics and cosmology',
1324 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1325 'timestamp': 1321158993,
1326 'upload_date': '20111113',
1327 'uploader_id': 'kps1',
1328 },
1329 'add_ie': ['Kaltura'],
1330 },
1331 {
1332 # Kaltura iframe embed
1333 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1334 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1335 'info_dict': {
1336 'id': '0_f2cfbpwy',
1337 'ext': 'mp4',
1338 'title': 'I. M. Pei: A Centennial Celebration',
1339 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1340 'upload_date': '20170403',
1341 'uploader_id': 'batchUser',
1342 'timestamp': 1491232186,
1343 },
1344 'add_ie': ['Kaltura'],
1345 },
1346 {
1347 # Kaltura iframe embed, more sophisticated
1348 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1349 'info_dict': {
1350 'id': '1_9gzouybz',
1351 'ext': 'mp4',
1352 'title': 'lecture-05sep2017',
1353 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1354 'upload_date': '20170913',
1355 'uploader_id': 'eps2',
1356 'timestamp': 1505340777,
1357 },
1358 'params': {
1359 'skip_download': True,
1360 },
1361 'add_ie': ['Kaltura'],
1362 },
1363 {
1364 # meta twitter:player
1365 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1366 'info_dict': {
1367 'id': '0_01b42zps',
1368 'ext': 'mp4',
1369 'title': 'Main Twerk (Video)',
1370 'upload_date': '20171208',
1371 'uploader_id': 'sebastian.salinas@thechive.com',
1372 'timestamp': 1512713057,
1373 },
1374 'params': {
1375 'skip_download': True,
1376 },
1377 'add_ie': ['Kaltura'],
1378 },
1379 # referrer protected EaglePlatform embed
1380 {
1381 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1382 'info_dict': {
1383 'id': '582306',
1384 'ext': 'mp4',
1385 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1386 'thumbnail': r're:^https?://.*\.jpg$',
1387 'duration': 3382,
1388 'view_count': int,
1389 },
1390 'params': {
1391 'skip_download': True,
1392 },
1393 },
1394 # ClipYou (EaglePlatform) embed (custom URL)
1395 {
1396 'url': 'http://muz-tv.ru/play/7129/',
1397 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1398 'info_dict': {
1399 'id': '12820',
1400 'ext': 'mp4',
1401 'title': "'O Sole Mio",
1402 'thumbnail': r're:^https?://.*\.jpg$',
1403 'duration': 216,
1404 'view_count': int,
1405 },
1406 'params': {
1407 'skip_download': True,
1408 },
1409 'skip': 'This video is unavailable.',
1410 },
1411 # Pladform embed
1412 {
1413 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1414 'info_dict': {
1415 'id': '100183293',
1416 'ext': 'mp4',
1417 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1418 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1419 'thumbnail': r're:^https?://.*\.jpg$',
1420 'duration': 694,
1421 'age_limit': 0,
1422 },
1423 'skip': 'HTTP Error 404: Not Found',
1424 },
1425 # Playwire embed
1426 {
1427 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1428 'info_dict': {
1429 'id': '3519514',
1430 'ext': 'mp4',
1431 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1432 'thumbnail': r're:^https?://.*\.png$',
1433 'duration': 45.115,
1434 },
1435 },
1436 # 5min embed
1437 {
1438 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1439 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1440 'info_dict': {
1441 'id': '518726732',
1442 'ext': 'mp4',
1443 'title': 'Facebook Creates "On This Day" | Crunch Report',
1444 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1445 'timestamp': 1427237531,
1446 'uploader': 'Crunch Report',
1447 'upload_date': '20150324',
1448 },
1449 'params': {
1450 # m3u8 download
1451 'skip_download': True,
1452 },
1453 },
1454 # Crooks and Liars embed
1455 {
1456 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1457 'info_dict': {
1458 'id': '8RUoRhRi',
1459 'ext': 'mp4',
1460 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1461 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1462 'timestamp': 1428207000,
1463 'upload_date': '20150405',
1464 'uploader': 'Heather',
1465 },
1466 },
1467 # Crooks and Liars external embed
1468 {
1469 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1470 'info_dict': {
1471 'id': 'MTE3MjUtMzQ2MzA',
1472 'ext': 'mp4',
1473 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1474 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1475 'timestamp': 1265032391,
1476 'upload_date': '20100201',
1477 'uploader': 'Heather',
1478 },
1479 },
1480 # NBC Sports vplayer embed
1481 {
1482 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1483 'info_dict': {
1484 'id': 'ln7x1qSThw4k',
1485 'ext': 'flv',
1486 'title': "PFT Live: New leader in the 'new-look' defense",
1487 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1488 'uploader': 'NBCU-SPORTS',
1489 'upload_date': '20140107',
1490 'timestamp': 1389118457,
1491 },
1492 'skip': 'Invalid Page URL',
1493 },
1494 # NBC News embed
1495 {
1496 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1497 'md5': '1aa589c675898ae6d37a17913cf68d66',
1498 'info_dict': {
1499 'id': 'x_dtl_oa_LettermanliftPR_160608',
1500 'ext': 'mp4',
1501 'title': 'David Letterman: A Preview',
1502 '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.',
1503 'upload_date': '20160609',
1504 'timestamp': 1465431544,
1505 'uploader': 'NBCU-NEWS',
1506 },
1507 },
1508 # UDN embed
1509 {
1510 'url': 'https://video.udn.com/news/300346',
1511 'md5': 'fd2060e988c326991037b9aff9df21a6',
1512 'info_dict': {
1513 'id': '300346',
1514 'ext': 'mp4',
1515 'title': '中一中男師變性 全校師生力挺',
1516 'thumbnail': r're:^https?://.*\.jpg$',
1517 },
1518 'params': {
1519 # m3u8 download
1520 'skip_download': True,
1521 },
1522 'expected_warnings': ['Failed to parse JSON Expecting value'],
1523 },
1524 # Brightcove URL in single quotes
1525 {
1526 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1527 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1528 'info_dict': {
1529 'id': '4255764656001',
1530 'ext': 'mp4',
1531 'title': 'SN Presents: Russell Martin, World Citizen',
1532 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1533 'uploader': 'Rogers Sportsnet',
1534 'uploader_id': '1704050871',
1535 'upload_date': '20150525',
1536 'timestamp': 1432570283,
1537 },
1538 },
1539 # Kinja embed
1540 {
1541 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1542 'info_dict': {
1543 'id': '106351',
1544 'ext': 'mp4',
1545 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1546 'description': 'Migrated from OnionStudios',
1547 'thumbnail': r're:^https?://.*\.jpe?g$',
1548 'uploader': 'clickhole',
1549 'upload_date': '20150527',
1550 'timestamp': 1432744860,
1551 }
1552 },
1553 # SnagFilms embed
1554 {
1555 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1556 'info_dict': {
1557 'id': '74849a00-85a9-11e1-9660-123139220831',
1558 'ext': 'mp4',
1559 'title': '#whilewewatch',
1560 }
1561 },
1562 # AdobeTVVideo embed
1563 {
1564 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1565 'md5': '43662b577c018ad707a63766462b1e87',
1566 'info_dict': {
1567 'id': '2456',
1568 'ext': 'mp4',
1569 'title': 'New experience with Acrobat DC',
1570 'description': 'New experience with Acrobat DC',
1571 'duration': 248.667,
1572 },
1573 },
1574 # BrightcoveInPageEmbed embed
1575 {
1576 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1577 'info_dict': {
1578 'id': '4238694884001',
1579 'ext': 'flv',
1580 'title': 'Tabletop: Dread, Last Thoughts',
1581 'description': 'Tabletop: Dread, Last Thoughts',
1582 'duration': 51690,
1583 },
1584 },
1585 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1586 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1587 {
1588 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1589 'info_dict': {
1590 'id': '4785848093001',
1591 'ext': 'mp4',
1592 'title': 'The Cardinal Pell Interview',
1593 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1594 'uploader': 'GlobeCast Australia - GlobeStream',
1595 'uploader_id': '2733773828001',
1596 'upload_date': '20160304',
1597 'timestamp': 1457083087,
1598 },
1599 'params': {
1600 # m3u8 downloads
1601 'skip_download': True,
1602 },
1603 },
1604 {
1605 # Brightcove embed with whitespace around attribute names
1606 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1607 'info_dict': {
1608 'id': '3167554373001',
1609 'ext': 'mp4',
1610 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1611 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1612 'uploader_id': '1079349493',
1613 'upload_date': '20140207',
1614 'timestamp': 1391810548,
1615 },
1616 'params': {
1617 'skip_download': True,
1618 },
1619 },
1620 # Another form of arte.tv embed
1621 {
1622 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1623 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1624 'info_dict': {
1625 'id': '030273-562_PLUS7-F',
1626 'ext': 'mp4',
1627 'title': 'ARTE Reportage - Nulle part, en France',
1628 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1629 'upload_date': '20160409',
1630 },
1631 },
1632 # Duplicated embedded video URLs
1633 {
1634 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1635 'info_dict': {
1636 'id': '149298443_480_16c25b74_2',
1637 'ext': 'mp4',
1638 'title': 'vs. Blue Orange Spring Game',
1639 'uploader': 'www.hudl.com',
1640 },
1641 },
1642 # twitter:player:stream embed
1643 {
1644 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1645 'info_dict': {
1646 'id': 'master',
1647 'ext': 'mp4',
1648 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1649 'uploader': 'www.rtl.be',
1650 },
1651 'params': {
1652 # m3u8 downloads
1653 'skip_download': True,
1654 },
1655 },
1656 # twitter:player embed
1657 {
1658 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1659 'md5': 'a3e0df96369831de324f0778e126653c',
1660 'info_dict': {
1661 'id': '4909620399001',
1662 'ext': 'mp4',
1663 'title': 'What Do Black Holes Sound Like?',
1664 'description': 'what do black holes sound like',
1665 'upload_date': '20160524',
1666 'uploader_id': '29913724001',
1667 'timestamp': 1464107587,
1668 'uploader': 'TheAtlantic',
1669 },
1670 'add_ie': ['BrightcoveLegacy'],
1671 },
1672 # Facebook <iframe> embed
1673 {
1674 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1675 'md5': 'fbcde74f534176ecb015849146dd3aee',
1676 'info_dict': {
1677 'id': '599637780109885',
1678 'ext': 'mp4',
1679 'title': 'Facebook video #599637780109885',
1680 },
1681 },
1682 # Facebook <iframe> embed, plugin video
1683 {
1684 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1685 'info_dict': {
1686 'id': '1754168231264132',
1687 'ext': 'mp4',
1688 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1689 'uploader': 'Tariq Ramadan (official)',
1690 'timestamp': 1496758379,
1691 'upload_date': '20170606',
1692 },
1693 'params': {
1694 'skip_download': True,
1695 },
1696 },
1697 # Facebook API embed
1698 {
1699 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1700 'md5': 'a47372ee61b39a7b90287094d447d94e',
1701 'info_dict': {
1702 'id': '10153467542406923',
1703 'ext': 'mp4',
1704 'title': 'Facebook video #10153467542406923',
1705 },
1706 },
1707 # Wordpress "YouTube Video Importer" plugin
1708 {
1709 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1710 'md5': 'd16797741b560b485194eddda8121b48',
1711 'info_dict': {
1712 'id': 'HNTXWDXV9Is',
1713 'ext': 'mp4',
1714 'title': 'Blue Devils Drumline Stanford lot 2016',
1715 'upload_date': '20160627',
1716 'uploader_id': 'GENOCIDE8GENERAL10',
1717 'uploader': 'cylus cyrus',
1718 },
1719 },
1720 {
1721 # video stored on custom kaltura server
1722 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1723 'md5': '537617d06e64dfed891fa1593c4b30cc',
1724 'info_dict': {
1725 'id': '0_1iotm5bh',
1726 'ext': 'mp4',
1727 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1728 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1729 'uploader_id': 'videos.expansion@el-mundo.net',
1730 'upload_date': '20150429',
1731 'timestamp': 1430303472,
1732 },
1733 'add_ie': ['Kaltura'],
1734 },
1735 {
1736 # multiple kaltura embeds, nsfw
1737 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
1738 'info_dict': {
1739 'id': 'kamila-avec-video-jaime-sadomie',
1740 'title': "Kamila avec vídeo “J'aime sadomie”",
1741 },
1742 'playlist_count': 8,
1743 },
1744 {
1745 # Non-standard Vimeo embed
1746 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1747 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1748 'info_dict': {
1749 'id': '148867247',
1750 'ext': 'mp4',
1751 'title': 'Understanding the web - Teaser',
1752 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1753 'upload_date': '20151214',
1754 'uploader': 'OpenClassrooms',
1755 'uploader_id': 'openclassrooms',
1756 },
1757 'add_ie': ['Vimeo'],
1758 },
1759 {
1760 # generic vimeo embed that requires original URL passed as Referer
1761 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1762 'only_matching': True,
1763 },
1764 {
1765 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1766 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1767 'info_dict': {
1768 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1769 'ext': 'mp4',
1770 'title': 'Big Buck Bunny',
1771 'description': 'Royalty free test video',
1772 'timestamp': 1432816365,
1773 'upload_date': '20150528',
1774 'is_live': False,
1775 },
1776 'params': {
1777 'skip_download': True,
1778 },
1779 'add_ie': [ArkenaIE.ie_key()],
1780 },
1781 {
1782 '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/',
1783 'info_dict': {
1784 'id': '1c7141f46c',
1785 'ext': 'mp4',
1786 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1787 },
1788 'params': {
1789 'skip_download': True,
1790 },
1791 'add_ie': [Vbox7IE.ie_key()],
1792 },
1793 {
1794 # DBTV embeds
1795 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1796 'info_dict': {
1797 'id': '43254897',
1798 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1799 },
1800 'playlist_mincount': 3,
1801 },
1802 {
1803 # Videa embeds
1804 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1805 'info_dict': {
1806 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1807 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1808 },
1809 'playlist_mincount': 2,
1810 },
1811 {
1812 # 20 minuten embed
1813 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1814 'info_dict': {
1815 'id': '523629',
1816 'ext': 'mp4',
1817 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1818 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1819 },
1820 'params': {
1821 'skip_download': True,
1822 },
1823 'add_ie': [TwentyMinutenIE.ie_key()],
1824 },
1825 {
1826 # VideoPress embed
1827 'url': 'https://en.support.wordpress.com/videopress/',
1828 'info_dict': {
1829 'id': 'OcobLTqC',
1830 'ext': 'm4v',
1831 'title': 'IMG_5786',
1832 'timestamp': 1435711927,
1833 'upload_date': '20150701',
1834 },
1835 'params': {
1836 'skip_download': True,
1837 },
1838 'add_ie': [VideoPressIE.ie_key()],
1839 },
1840 {
1841 # Rutube embed
1842 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1843 'info_dict': {
1844 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1845 'ext': 'flv',
1846 'title': 'Магаззино: Казань 2',
1847 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1848 'uploader': 'Магаззино',
1849 'upload_date': '20170228',
1850 'uploader_id': '996642',
1851 },
1852 'params': {
1853 'skip_download': True,
1854 },
1855 'add_ie': [RutubeIE.ie_key()],
1856 },
1857 {
1858 # ThePlatform embedded with whitespaces in URLs
1859 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1860 'only_matching': True,
1861 },
1862 {
1863 # Senate ISVP iframe https
1864 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1865 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1866 'info_dict': {
1867 'id': 'govtaff020316',
1868 'ext': 'mp4',
1869 'title': 'Integrated Senate Video Player',
1870 },
1871 'add_ie': [SenateISVPIE.ie_key()],
1872 },
1873 {
1874 # Limelight embeds (1 channel embed + 4 media embeds)
1875 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1876 'info_dict': {
1877 'id': 'FacilitatorTraining2017',
1878 'title': 'Facilitator Training 2017',
1879 },
1880 'playlist_mincount': 5,
1881 },
1882 {
1883 # Limelight embed (LimelightPlayerUtil.embed)
1884 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1885 'info_dict': {
1886 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1887 'ext': 'mp4',
1888 'title': '07448641',
1889 'timestamp': 1499890639,
1890 'upload_date': '20170712',
1891 },
1892 'params': {
1893 'skip_download': True,
1894 },
1895 'add_ie': ['LimelightMedia'],
1896 },
1897 {
1898 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1899 'info_dict': {
1900 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1901 'title': 'Standoff with Walnut Creek murder suspect ends',
1902 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1903 },
1904 'playlist_mincount': 4,
1905 },
1906 {
1907 # WashingtonPost embed
1908 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1909 'info_dict': {
1910 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1911 'ext': 'mp4',
1912 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1913 '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.',
1914 'timestamp': 1455216756,
1915 'uploader': 'The Washington Post',
1916 'upload_date': '20160211',
1917 },
1918 'add_ie': [WashingtonPostIE.ie_key()],
1919 },
1920 {
1921 # Mediaset embed
1922 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1923 'info_dict': {
1924 'id': '720642',
1925 'ext': 'mp4',
1926 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1927 },
1928 'params': {
1929 'skip_download': True,
1930 },
1931 'add_ie': [MediasetIE.ie_key()],
1932 },
1933 {
1934 # JOJ.sk embeds
1935 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1936 'info_dict': {
1937 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1938 'title': 'Slovenskom sa prehnala vlna silných búrok',
1939 },
1940 'playlist_mincount': 5,
1941 'add_ie': [JojIE.ie_key()],
1942 },
1943 {
1944 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1945 'url': 'https://tvrain.ru/amp/418921/',
1946 'md5': 'cc00413936695987e8de148b67d14f1d',
1947 'info_dict': {
1948 'id': '418921',
1949 'ext': 'mp4',
1950 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1951 },
1952 },
1953 {
1954 # vzaar embed
1955 'url': 'http://help.vzaar.com/article/165-embedding-video',
1956 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1957 'info_dict': {
1958 'id': '8707641',
1959 'ext': 'mp4',
1960 'title': 'Building A Business Online: Principal Chairs Q & A',
1961 },
1962 },
1963 {
1964 # multiple HTML5 videos on one page
1965 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1966 'info_dict': {
1967 'id': 'keyscenarios',
1968 'title': 'Rescue Kit 14 Free Edition - Getting started',
1969 },
1970 'playlist_count': 4,
1971 },
1972 {
1973 # vshare embed
1974 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1975 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1976 'info_dict': {
1977 'id': '0f64ce6',
1978 'title': 'vl14062007715967',
1979 'ext': 'mp4',
1980 }
1981 },
1982 {
1983 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1984 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1985 'info_dict': {
1986 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1987 'ext': 'mp4',
1988 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1989 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1990 'timestamp': 1474354800,
1991 'upload_date': '20160920',
1992 }
1993 },
1994 {
1995 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1996 'info_dict': {
1997 'id': '1731611',
1998 'ext': 'mp4',
1999 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
2000 'description': 'md5:eb5f23826a027ba95277d105f248b825',
2001 'timestamp': 1516100691,
2002 'upload_date': '20180116',
2003 },
2004 'params': {
2005 'skip_download': True,
2006 },
2007 'add_ie': [SpringboardPlatformIE.ie_key()],
2008 },
2009 {
2010 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
2011 'info_dict': {
2012 'id': 'vMDE4NzI1Mjgt690b',
2013 'ext': 'mp4',
2014 'title': 'Котята',
2015 },
2016 'add_ie': [YapFilesIE.ie_key()],
2017 'params': {
2018 'skip_download': True,
2019 },
2020 },
2021 {
2022 # CloudflareStream embed
2023 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2024 'info_dict': {
2025 'id': '31c9291ab41fac05471db4e73aa11717',
2026 'ext': 'mp4',
2027 'title': '31c9291ab41fac05471db4e73aa11717',
2028 },
2029 'add_ie': [CloudflareStreamIE.ie_key()],
2030 'params': {
2031 'skip_download': True,
2032 },
2033 },
2034 {
2035 # PeerTube embed
2036 'url': 'https://joinpeertube.org/fr/home/',
2037 'info_dict': {
2038 'id': 'home',
2039 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2040 },
2041 'playlist_count': 2,
2042 },
2043 {
2044 # Indavideo embed
2045 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2046 'info_dict': {
2047 'id': '1693903',
2048 'ext': 'mp4',
2049 'title': 'Így kell otthon hamburgert sütni',
2050 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2051 'timestamp': 1426330212,
2052 'upload_date': '20150314',
2053 'uploader': 'StreetKitchen',
2054 'uploader_id': '546363',
2055 },
2056 'add_ie': [IndavideoEmbedIE.ie_key()],
2057 'params': {
2058 'skip_download': True,
2059 },
2060 },
2061 {
2062 # APA embed via JWPlatform embed
2063 'url': 'http://www.vol.at/blue-man-group/5593454',
2064 'info_dict': {
2065 'id': 'jjv85FdZ',
2066 'ext': 'mp4',
2067 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2068 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2069 'thumbnail': r're:^https?://.*\.jpg$',
2070 'duration': 254,
2071 'timestamp': 1519211149,
2072 'upload_date': '20180221',
2073 },
2074 'params': {
2075 'skip_download': True,
2076 },
2077 },
2078 {
2079 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2080 'md5': 'b68d276de422ab07ee1d49388103f457',
2081 'info_dict': {
2082 'id': '83645793',
2083 'title': 'Lock up and get excited',
2084 'ext': 'mp4'
2085 },
2086 'skip': 'TODO: fix nested playlists processing in tests',
2087 },
2088 {
2089 # Viqeo embeds
2090 'url': 'https://viqeo.tv/',
2091 'info_dict': {
2092 'id': 'viqeo',
2093 'title': 'All-new video platform',
2094 },
2095 'playlist_count': 6,
2096 },
2097 {
2098 # Squarespace video embed, 2019-08-28
2099 'url': 'http://ootboxford.com',
2100 'info_dict': {
2101 'id': 'Tc7b_JGdZfw',
2102 'title': 'Out of the Blue, at Childish Things 10',
2103 'ext': 'mp4',
2104 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
2105 'uploader_id': 'helendouglashouse',
2106 'uploader': 'Helen & Douglas House',
2107 'upload_date': '20140328',
2108 },
2109 'params': {
2110 'skip_download': True,
2111 },
2112 },
2113 # {
2114 # # Zype embed
2115 # 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2116 # 'info_dict': {
2117 # 'id': '5b400b834b32992a310622b9',
2118 # 'ext': 'mp4',
2119 # 'title': 'Smoky Barbecue Favorites',
2120 # 'thumbnail': r're:^https?://.*\.jpe?g',
2121 # 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
2122 # 'upload_date': '20170909',
2123 # 'timestamp': 1504915200,
2124 # },
2125 # 'add_ie': [ZypeIE.ie_key()],
2126 # 'params': {
2127 # 'skip_download': True,
2128 # },
2129 # },
2130 {
2131 # videojs embed
2132 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2133 'info_dict': {
2134 'id': 'shell',
2135 'ext': 'mp4',
2136 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2137 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2138 'thumbnail': r're:^https?://.*\.jpg$',
2139 },
2140 'params': {
2141 'skip_download': True,
2142 },
2143 'expected_warnings': ['Failed to download MPD manifest'],
2144 },
2145 {
2146 # DailyMotion embed with DM.player
2147 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
2148 'info_dict': {
2149 'id': 'k6aKkGHd9FJs4mtJN39',
2150 'ext': 'mp4',
2151 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
2152 'description': 'This video is private.',
2153 'uploader_id': 'x1jf30l',
2154 'uploader': 'beIN SPORTS USA',
2155 'upload_date': '20190528',
2156 'timestamp': 1559062971,
2157 },
2158 'params': {
2159 'skip_download': True,
2160 },
2161 },
2162 # {
2163 # # TODO: find another test
2164 # # http://schema.org/VideoObject
2165 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2166 # 'md5': '888dcf08b7ea671381f00fab74692755',
2167 # 'info_dict': {
2168 # 'id': 'nyvTSJMKId',
2169 # 'ext': 'mp4',
2170 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2171 # 'description': '#love for cats.',
2172 # 'timestamp': 1461244995,
2173 # 'upload_date': '20160421',
2174 # },
2175 # 'params': {
2176 # 'force_generic_extractor': True,
2177 # },
2178 # },
2179 {
2180 # VHX Embed
2181 'url': 'https://demo.vhx.tv/category-c/videos/file-example-mp4-480-1-5mg-copy',
2182 'info_dict': {
2183 'id': '858208',
2184 'ext': 'mp4',
2185 'title': 'Untitled',
2186 'uploader_id': 'user80538407',
2187 'uploader': 'OTT Videos',
2188 },
2189 },
2190 {
2191 # ArcPublishing PoWa video player
2192 'url': 'https://www.adn.com/politics/2020/11/02/video-senate-candidates-campaign-in-anchorage-on-eve-of-election-day/',
2193 'md5': 'b03b2fac8680e1e5a7cc81a5c27e71b3',
2194 'info_dict': {
2195 'id': '8c99cb6e-b29c-4bc9-9173-7bf9979225ab',
2196 'ext': 'mp4',
2197 'title': 'Senate candidates wave to voters on Anchorage streets',
2198 'description': 'md5:91f51a6511f090617353dc720318b20e',
2199 'timestamp': 1604378735,
2200 'upload_date': '20201103',
2201 'duration': 1581,
2202 },
2203 },
2204 {
2205 # MyChannels SDK embed
2206 # https://www.24kitchen.nl/populair/deskundige-dit-waarom-sommigen-gevoelig-zijn-voor-voedselallergieen
2207 'url': 'https://www.demorgen.be/nieuws/burgemeester-rotterdam-richt-zich-in-videoboodschap-tot-relschoppers-voelt-het-goed~b0bcfd741/',
2208 'md5': '90c0699c37006ef18e198c032d81739c',
2209 'info_dict': {
2210 'id': '194165',
2211 'ext': 'mp4',
2212 'title': 'Burgemeester Aboutaleb spreekt relschoppers toe',
2213 'timestamp': 1611740340,
2214 'upload_date': '20210127',
2215 'duration': 159,
2216 },
2217 },
2218 {
2219 # Simplecast player embed
2220 'url': 'https://www.bio.org/podcast',
2221 'info_dict': {
2222 'id': 'podcast',
2223 'title': 'I AM BIO Podcast | BIO',
2224 },
2225 'playlist_mincount': 52,
2226 },
2227 {
2228 # Sibnet embed (https://help.sibnet.ru/?sibnet_video_embed)
2229 'url': 'https://phpbb3.x-tk.ru/bbcode-video-sibnet-t24.html',
2230 'only_matching': True,
2231 }, {
2232 # KVS Player
2233 'url': 'https://www.kvs-demo.com/videos/105/kelis-4th-of-july/',
2234 'info_dict': {
2235 'id': '105',
2236 'display_id': 'kelis-4th-of-july',
2237 'ext': 'mp4',
2238 'title': 'Kelis - 4th Of July',
2239 'thumbnail': r're:https://(?:www\.)?kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
2240 },
2241 }, {
2242 # KVS Player
2243 'url': 'https://www.kvs-demo.com/embed/105/',
2244 'info_dict': {
2245 'id': '105',
2246 'display_id': 'kelis-4th-of-july',
2247 'ext': 'mp4',
2248 'title': 'Kelis - 4th Of July / Embed Player',
2249 'thumbnail': r're:https://(?:www\.)?kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
2250 },
2251 'params': {
2252 'skip_download': True,
2253 },
2254 }, {
2255 # KVS Player (tested also in thisvid.py)
2256 'url': 'https://youix.com/video/leningrad-zoj/',
2257 'md5': '94f96ba95706dc3880812b27b7d8a2b8',
2258 'info_dict': {
2259 'id': '18485',
2260 'display_id': 'leningrad-zoj',
2261 'ext': 'mp4',
2262 'title': 'Клип: Ленинград - ЗОЖ скачать, смотреть онлайн | Youix.com',
2263 'thumbnail': r're:https://youix.com/contents/videos_screenshots/18000/18485/preview(?:_480x320_youix_com.mp4)?\.jpg',
2264 },
2265 }, {
2266 # KVS Player
2267 'url': 'https://youix.com/embed/18485',
2268 'md5': '94f96ba95706dc3880812b27b7d8a2b8',
2269 'info_dict': {
2270 'id': '18485',
2271 'display_id': 'leningrad-zoj',
2272 'ext': 'mp4',
2273 'title': 'Ленинград - ЗОЖ',
2274 'thumbnail': r're:https://youix.com/contents/videos_screenshots/18000/18485/preview(?:_480x320_youix_com.mp4)?\.jpg',
2275 },
2276 }, {
2277 # KVS Player
2278 'url': 'https://bogmedia.org/videos/21217/40-nochey-40-nights-2016/',
2279 'md5': '94166bdb26b4cb1fb9214319a629fc51',
2280 'info_dict': {
2281 'id': '21217',
2282 'display_id': '40-nochey-2016',
2283 'ext': 'mp4',
2284 'title': '40 ночей (2016) - BogMedia.org',
2285 'description': 'md5:4e6d7d622636eb7948275432eb256dc3',
2286 'thumbnail': 'https://bogmedia.org/contents/videos_screenshots/21000/21217/preview_480p.mp4.jpg',
2287 },
2288 }, {
2289 # KVS Player (for sites that serve kt_player.js via non-https urls)
2290 'url': 'http://www.camhub.world/embed/389508',
2291 'md5': 'fbe89af4cfb59c8fd9f34a202bb03e32',
2292 'info_dict': {
2293 'id': '389508',
2294 'display_id': 'syren-de-mer-onlyfans-05-07-2020have-a-happy-safe-holiday5f014e68a220979bdb8cd-source',
2295 'ext': 'mp4',
2296 'title': 'Syren De Mer onlyfans_05-07-2020Have_a_happy_safe_holiday5f014e68a220979bdb8cd_source / Embed плеер',
2297 'thumbnail': r're:https?://www\.camhub\.world/contents/videos_screenshots/389000/389508/preview\.mp4\.jpg',
2298 },
2299 }, {
2300 'url': 'https://mrdeepfakes.com/video/5/selena-gomez-pov-deep-fakes',
2301 'md5': 'fec4ad5ec150f655e0c74c696a4a2ff4',
2302 'info_dict': {
2303 'id': '5',
2304 'display_id': 'selena-gomez-pov-deep-fakes',
2305 'ext': 'mp4',
2306 'title': 'Selena Gomez POV (Deep Fakes) DeepFake Porn - MrDeepFakes',
2307 'description': 'md5:17d1f84b578c9c26875ac5ef9a932354',
2308 'height': 720,
2309 'age_limit': 18,
2310 },
2311 },
2312 ]
2313
2314 def report_following_redirect(self, new_url):
2315 """Report information extraction."""
2316 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2317
2318 def _extract_rss(self, url, video_id, doc):
2319 playlist_title = doc.find('./channel/title').text
2320 playlist_desc_el = doc.find('./channel/description')
2321 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2322
2323 NS_MAP = {
2324 'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
2325 }
2326
2327 entries = []
2328 for it in doc.findall('./channel/item'):
2329 next_url = None
2330 enclosure_nodes = it.findall('./enclosure')
2331 for e in enclosure_nodes:
2332 next_url = e.attrib.get('url')
2333 if next_url:
2334 break
2335
2336 if not next_url:
2337 next_url = xpath_text(it, 'link', fatal=False)
2338
2339 if not next_url:
2340 continue
2341
2342 def itunes(key):
2343 return xpath_text(
2344 it, xpath_with_ns('./itunes:%s' % key, NS_MAP),
2345 default=None)
2346
2347 duration = itunes('duration')
2348 explicit = (itunes('explicit') or '').lower()
2349 if explicit in ('true', 'yes'):
2350 age_limit = 18
2351 elif explicit in ('false', 'no'):
2352 age_limit = 0
2353 else:
2354 age_limit = None
2355
2356 entries.append({
2357 '_type': 'url_transparent',
2358 'url': next_url,
2359 'title': it.find('title').text,
2360 'description': xpath_text(it, 'description', default=None),
2361 'timestamp': unified_timestamp(
2362 xpath_text(it, 'pubDate', default=None)),
2363 'duration': int_or_none(duration) or parse_duration(duration),
2364 'thumbnail': url_or_none(xpath_attr(it, xpath_with_ns('./itunes:image', NS_MAP), 'href')),
2365 'episode': itunes('title'),
2366 'episode_number': int_or_none(itunes('episode')),
2367 'season_number': int_or_none(itunes('season')),
2368 'age_limit': age_limit,
2369 })
2370
2371 return {
2372 '_type': 'playlist',
2373 'id': url,
2374 'title': playlist_title,
2375 'description': playlist_desc,
2376 'entries': entries,
2377 }
2378
2379 def _extract_camtasia(self, url, video_id, webpage):
2380 """ Returns None if no camtasia video can be found. """
2381
2382 camtasia_cfg = self._search_regex(
2383 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2384 webpage, 'camtasia configuration file', default=None)
2385 if camtasia_cfg is None:
2386 return None
2387
2388 title = self._html_search_meta('DC.title', webpage, fatal=True)
2389
2390 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2391 camtasia_cfg = self._download_xml(
2392 camtasia_url, video_id,
2393 note='Downloading camtasia configuration',
2394 errnote='Failed to download camtasia configuration')
2395 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2396
2397 entries = []
2398 for n in fileset_node.getchildren():
2399 url_n = n.find('./uri')
2400 if url_n is None:
2401 continue
2402
2403 entries.append({
2404 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2405 'title': '%s - %s' % (title, n.tag),
2406 'url': compat_urlparse.urljoin(url, url_n.text),
2407 'duration': float_or_none(n.find('./duration').text),
2408 })
2409
2410 return {
2411 '_type': 'playlist',
2412 'entries': entries,
2413 'title': title,
2414 }
2415
2416 def _extract_kvs(self, url, webpage, video_id):
2417
2418 def getlicensetoken(license):
2419 modlicense = license.replace('$', '').replace('0', '1')
2420 center = int(len(modlicense) / 2)
2421 fronthalf = int(modlicense[:center + 1])
2422 backhalf = int(modlicense[center:])
2423
2424 modlicense = compat_str(4 * abs(fronthalf - backhalf))
2425
2426 def parts():
2427 for o in range(0, center + 1):
2428 for i in range(1, 5):
2429 yield compat_str((int(license[o + i]) + int(modlicense[o])) % 10)
2430
2431 return ''.join(parts())
2432
2433 def getrealurl(video_url, license_code):
2434 if not video_url.startswith('function/0/'):
2435 return video_url # not obfuscated
2436
2437 url_path, _, url_query = video_url.partition('?')
2438 urlparts = url_path.split('/')[2:]
2439 license = getlicensetoken(license_code)
2440 newmagic = urlparts[5][:32]
2441
2442 def spells(x, o):
2443 l = (o + sum(int(n) for n in license[o:])) % 32
2444 for i in range(0, len(x)):
2445 yield {l: x[o], o: x[l]}.get(i, x[i])
2446
2447 for o in range(len(newmagic) - 1, -1, -1):
2448 newmagic = ''.join(spells(newmagic, o))
2449
2450 urlparts[5] = newmagic + urlparts[5][32:]
2451 return '/'.join(urlparts) + '?' + url_query
2452
2453 flashvars = self._search_regex(
2454 r'(?s)<script\b[^>]*>.*?var\s+flashvars\s*=\s*(\{.+?\});.*?</script>',
2455 webpage, 'flashvars')
2456 flashvars = self._parse_json(flashvars, video_id, transform_source=js_to_json)
2457
2458 # extract the part after the last / as the display_id from the
2459 # canonical URL.
2460 display_id = self._search_regex(
2461 r'(?:<link href="https?://[^"]+/(.+?)/?" rel="canonical"\s*/?>'
2462 r'|<link rel="canonical" href="https?://[^"]+/(.+?)/?"\s*/?>)',
2463 webpage, 'display_id', fatal=False
2464 )
2465 title = self._html_search_regex(r'<(?:h1|title)>(?:Video: )?(.+?)</(?:h1|title)>', webpage, 'title')
2466
2467 thumbnail = flashvars['preview_url']
2468 if thumbnail.startswith('//'):
2469 protocol, _, _ = url.partition('/')
2470 thumbnail = protocol + thumbnail
2471
2472 url_keys = list(filter(re.compile(r'^video_(?:url|alt_url\d*)$').match, flashvars.keys()))
2473 formats = []
2474 for key in url_keys:
2475 if '/get_file/' not in flashvars[key]:
2476 continue
2477 format_id = flashvars.get(key + '_text', key)
2478 formats.append(merge_dicts(
2479 parse_resolution(format_id) or parse_resolution(flashvars[key]), {
2480 'url': getrealurl(flashvars[key], flashvars['license_code']),
2481 'format_id': format_id,
2482 'ext': 'mp4',
2483 'http_headers': {'Referer': url},
2484 }))
2485 if not formats[-1].get('height'):
2486 formats[-1]['quality'] = 1
2487
2488 self._sort_formats(formats)
2489
2490 return {
2491 'id': flashvars['video_id'],
2492 'display_id': display_id,
2493 'title': title,
2494 'thumbnail': thumbnail,
2495 'formats': formats,
2496 }
2497
2498 def _real_extract(self, url):
2499 if url.startswith('//'):
2500 return self.url_result(self.http_scheme() + url)
2501
2502 parsed_url = compat_urlparse.urlparse(url)
2503 if not parsed_url.scheme:
2504 default_search = self._downloader.params.get('default_search')
2505 if default_search is None:
2506 default_search = 'fixup_error'
2507
2508 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2509 if re.match(r'^[^\s/]+\.[^\s/]+/', url):
2510 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2511 return self.url_result('http://' + url)
2512 elif default_search != 'fixup_error':
2513 if default_search == 'auto_warning':
2514 if re.match(r'^(?:url|URL)$', url):
2515 raise ExtractorError(
2516 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2517 expected=True)
2518 else:
2519 self._downloader.report_warning(
2520 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2521 return self.url_result('ytsearch:' + url)
2522
2523 if default_search in ('error', 'fixup_error'):
2524 raise ExtractorError(
2525 '%r is not a valid URL. '
2526 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2527 % (url, url), expected=True)
2528 else:
2529 if ':' not in default_search:
2530 default_search += ':'
2531 return self.url_result(default_search + url)
2532
2533 url, smuggled_data = unsmuggle_url(url)
2534 force_videoid = None
2535 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2536 if smuggled_data and 'force_videoid' in smuggled_data:
2537 force_videoid = smuggled_data['force_videoid']
2538 video_id = force_videoid
2539 else:
2540 video_id = self._generic_id(url)
2541
2542 self.to_screen('%s: Requesting header' % video_id)
2543
2544 head_req = HEADRequest(url)
2545 head_response = self._request_webpage(
2546 head_req, video_id,
2547 note=False, errnote='Could not send HEAD request to %s' % url,
2548 fatal=False)
2549
2550 if head_response is not False:
2551 # Check for redirect
2552 new_url = head_response.geturl()
2553 if url != new_url:
2554 self.report_following_redirect(new_url)
2555 if force_videoid:
2556 new_url = smuggle_url(
2557 new_url, {'force_videoid': force_videoid})
2558 return self.url_result(new_url)
2559
2560 full_response = None
2561 if head_response is False:
2562 request = sanitized_Request(url)
2563 request.add_header('Accept-Encoding', '*')
2564 full_response = self._request_webpage(request, video_id)
2565 head_response = full_response
2566
2567 info_dict = {
2568 'id': video_id,
2569 'title': self._generic_title(url),
2570 'timestamp': unified_timestamp(head_response.headers.get('Last-Modified'))
2571 }
2572
2573 # Check for direct link to a video
2574 content_type = head_response.headers.get('Content-Type', '').lower()
2575 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2576 if m:
2577 format_id = compat_str(m.group('format_id'))
2578 if format_id.endswith('mpegurl'):
2579 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2580 elif format_id == 'f4m':
2581 formats = self._extract_f4m_formats(url, video_id)
2582 else:
2583 formats = [{
2584 'format_id': format_id,
2585 'url': url,
2586 'vcodec': 'none' if m.group('type') == 'audio' else None
2587 }]
2588 info_dict['direct'] = True
2589 self._sort_formats(formats)
2590 info_dict['formats'] = formats
2591 return info_dict
2592
2593 if not self._downloader.params.get('test', False) and not is_intentional:
2594 force = self._downloader.params.get('force_generic_extractor', False)
2595 self._downloader.report_warning(
2596 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2597
2598 if not full_response:
2599 request = sanitized_Request(url)
2600 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2601 # making it impossible to download only chunk of the file (yet we need only 512kB to
2602 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2603 # that will always result in downloading the whole file that is not desirable.
2604 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2605 # to accept raw bytes and being able to download only a chunk.
2606 # It may probably better to solve this by checking Content-Type for application/octet-stream
2607 # after HEAD request finishes, but not sure if we can rely on this.
2608 request.add_header('Accept-Encoding', '*')
2609 full_response = self._request_webpage(request, video_id)
2610
2611 first_bytes = full_response.read(512)
2612
2613 # Is it an M3U playlist?
2614 if first_bytes.startswith(b'#EXTM3U'):
2615 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2616 self._sort_formats(info_dict['formats'])
2617 return info_dict
2618
2619 # Maybe it's a direct link to a video?
2620 # Be careful not to download the whole thing!
2621 if not is_html(first_bytes):
2622 self._downloader.report_warning(
2623 'URL could be a direct video link, returning it as such.')
2624 info_dict.update({
2625 'direct': True,
2626 'url': url,
2627 })
2628 return info_dict
2629
2630 webpage = self._webpage_read_content(
2631 full_response, url, video_id, prefix=first_bytes)
2632
2633 if '<title>DPG Media Privacy Gate</title>' in webpage:
2634 webpage = self._download_webpage(url, video_id)
2635
2636 self.report_extraction(video_id)
2637
2638 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2639 try:
2640 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2641 if doc.tag == 'rss':
2642 return self._extract_rss(url, video_id, doc)
2643 elif doc.tag == 'SmoothStreamingMedia':
2644 info_dict['formats'] = self._parse_ism_formats(doc, url)
2645 self._sort_formats(info_dict['formats'])
2646 return info_dict
2647 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2648 smil = self._parse_smil(doc, url, video_id)
2649 self._sort_formats(smil['formats'])
2650 return smil
2651 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2652 return self.playlist_result(
2653 self._parse_xspf(
2654 doc, video_id, xspf_url=url,
2655 xspf_base_url=full_response.geturl()),
2656 video_id)
2657 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2658 info_dict['formats'] = self._parse_mpd_formats(
2659 doc,
2660 mpd_base_url=full_response.geturl().rpartition('/')[0],
2661 mpd_url=url)
2662 self._sort_formats(info_dict['formats'])
2663 return info_dict
2664 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2665 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2666 self._sort_formats(info_dict['formats'])
2667 return info_dict
2668 except compat_xml_parse_error:
2669 pass
2670
2671 # Is it a Camtasia project?
2672 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2673 if camtasia_res is not None:
2674 return camtasia_res
2675
2676 # Sometimes embedded video player is hidden behind percent encoding
2677 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
2678 # Unescaping the whole page allows to handle those cases in a generic way
2679 # FIXME: unescaping the whole page may break URLs, commenting out for now.
2680 # There probably should be a second run of generic extractor on unescaped webpage.
2681 # webpage = compat_urllib_parse_unquote(webpage)
2682
2683 # Unescape squarespace embeds to be detected by generic extractor,
2684 # see https://github.com/ytdl-org/youtube-dl/issues/21294
2685 webpage = re.sub(
2686 r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
2687 lambda x: unescapeHTML(x.group(0)), webpage)
2688
2689 # it's tempting to parse this further, but you would
2690 # have to take into account all the variations like
2691 # Video Title - Site Name
2692 # Site Name | Video Title
2693 # Video Title - Tagline | Site Name
2694 # and so on and so forth; it's just not practical
2695 video_title = self._og_search_title(
2696 webpage, default=None) or self._html_search_regex(
2697 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2698 default='video')
2699
2700 # Try to detect age limit automatically
2701 age_limit = self._rta_search(webpage)
2702 # And then there are the jokers who advertise that they use RTA,
2703 # but actually don't.
2704 AGE_LIMIT_MARKERS = [
2705 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2706 r'>[^<]*you acknowledge you are at least (\d+) years old',
2707 ]
2708 for marker in AGE_LIMIT_MARKERS:
2709 m = re.search(marker, webpage)
2710 if not m:
2711 continue
2712 age_limit = max(
2713 age_limit or 0,
2714 int_or_none(m.groups() and m.group(1), default=18))
2715
2716 # video uploader is domain name
2717 video_uploader = self._search_regex(
2718 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2719
2720 video_description = self._og_search_description(webpage, default=None)
2721 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2722
2723 info_dict.update({
2724 'title': video_title,
2725 'description': video_description,
2726 'thumbnail': video_thumbnail,
2727 'age_limit': age_limit,
2728 })
2729
2730 # Look for Brightcove Legacy Studio embeds
2731 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2732 if bc_urls:
2733 entries = [{
2734 '_type': 'url',
2735 'url': smuggle_url(bc_url, {'Referer': url}),
2736 'ie_key': 'BrightcoveLegacy'
2737 } for bc_url in bc_urls]
2738
2739 return {
2740 '_type': 'playlist',
2741 'title': video_title,
2742 'id': video_id,
2743 'entries': entries,
2744 }
2745
2746 # Look for Brightcove New Studio embeds
2747 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2748 if bc_urls:
2749 return self.playlist_from_matches(
2750 bc_urls, video_id, video_title,
2751 getter=lambda x: smuggle_url(x, {'referrer': url}),
2752 ie='BrightcoveNew')
2753
2754 # Look for Nexx embeds
2755 nexx_urls = NexxIE._extract_urls(webpage)
2756 if nexx_urls:
2757 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2758
2759 # Look for Nexx iFrame embeds
2760 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2761 if nexx_embed_urls:
2762 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2763
2764 # Look for ThePlatform embeds
2765 tp_urls = ThePlatformIE._extract_urls(webpage)
2766 if tp_urls:
2767 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2768
2769 arc_urls = ArcPublishingIE._extract_urls(webpage)
2770 if arc_urls:
2771 return self.playlist_from_matches(arc_urls, video_id, video_title, ie=ArcPublishingIE.ie_key())
2772
2773 mychannels_urls = MedialaanIE._extract_urls(webpage)
2774 if mychannels_urls:
2775 return self.playlist_from_matches(
2776 mychannels_urls, video_id, video_title, ie=MedialaanIE.ie_key())
2777
2778 # Look for embedded rtl.nl player
2779 matches = re.findall(
2780 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2781 webpage)
2782 if matches:
2783 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2784
2785 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2786 if vimeo_urls:
2787 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2788
2789 vhx_url = VHXEmbedIE._extract_url(webpage)
2790 if vhx_url:
2791 return self.url_result(vhx_url, VHXEmbedIE.ie_key())
2792
2793 vid_me_embed_url = self._search_regex(
2794 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2795 webpage, 'vid.me embed', default=None)
2796 if vid_me_embed_url is not None:
2797 return self.url_result(vid_me_embed_url, 'Vidme')
2798
2799 # Look for YouTube embeds
2800 youtube_urls = YoutubeIE._extract_urls(webpage)
2801 if youtube_urls:
2802 return self.playlist_from_matches(
2803 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2804
2805 matches = DailymotionIE._extract_urls(webpage)
2806 if matches:
2807 return self.playlist_from_matches(matches, video_id, video_title)
2808
2809 # Look for embedded Dailymotion playlist player (#3822)
2810 m = re.search(
2811 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2812 if m:
2813 playlists = re.findall(
2814 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2815 if playlists:
2816 return self.playlist_from_matches(
2817 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2818
2819 # Look for DailyMail embeds
2820 dailymail_urls = DailyMailIE._extract_urls(webpage)
2821 if dailymail_urls:
2822 return self.playlist_from_matches(
2823 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2824
2825 # Look for Teachable embeds, must be before Wistia
2826 teachable_url = TeachableIE._extract_url(webpage, url)
2827 if teachable_url:
2828 return self.url_result(teachable_url)
2829
2830 # Look for embedded Wistia player
2831 wistia_urls = WistiaIE._extract_urls(webpage)
2832 if wistia_urls:
2833 playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
2834 for entry in playlist['entries']:
2835 entry.update({
2836 '_type': 'url_transparent',
2837 'uploader': video_uploader,
2838 })
2839 return playlist
2840
2841 # Look for SVT player
2842 svt_url = SVTIE._extract_url(webpage)
2843 if svt_url:
2844 return self.url_result(svt_url, 'SVT')
2845
2846 # Look for Bandcamp pages with custom domain
2847 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2848 if mobj is not None:
2849 burl = unescapeHTML(mobj.group(1))
2850 # Don't set the extractor because it can be a track url or an album
2851 return self.url_result(burl)
2852
2853 # Look for embedded Vevo player
2854 mobj = re.search(
2855 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2856 if mobj is not None:
2857 return self.url_result(mobj.group('url'))
2858
2859 # Look for embedded Viddler player
2860 mobj = re.search(
2861 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2862 webpage)
2863 if mobj is not None:
2864 return self.url_result(mobj.group('url'))
2865
2866 # Look for NYTimes player
2867 mobj = re.search(
2868 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2869 webpage)
2870 if mobj is not None:
2871 return self.url_result(mobj.group('url'))
2872
2873 # Look for Libsyn player
2874 mobj = re.search(
2875 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2876 if mobj is not None:
2877 return self.url_result(mobj.group('url'))
2878
2879 # Look for Ooyala videos
2880 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
2881 or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2882 or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2883 or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
2884 or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2885 if mobj is not None:
2886 embed_token = self._search_regex(
2887 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2888 webpage, 'ooyala embed token', default=None)
2889 return OoyalaIE._build_url_result(smuggle_url(
2890 mobj.group('ec'), {
2891 'domain': url,
2892 'embed_token': embed_token,
2893 }))
2894
2895 # Look for multiple Ooyala embeds on SBN network websites
2896 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2897 if mobj is not None:
2898 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2899 if embeds:
2900 return self.playlist_from_matches(
2901 embeds, video_id, video_title,
2902 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2903
2904 # Look for Aparat videos
2905 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2906 if mobj is not None:
2907 return self.url_result(mobj.group(1), 'Aparat')
2908
2909 # Look for MPORA videos
2910 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2911 if mobj is not None:
2912 return self.url_result(mobj.group(1), 'Mpora')
2913
2914 # Look for embedded Facebook player
2915 facebook_urls = FacebookIE._extract_urls(webpage)
2916 if facebook_urls:
2917 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2918
2919 # Look for embedded VK player
2920 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2921 if mobj is not None:
2922 return self.url_result(mobj.group('url'), 'VK')
2923
2924 # Look for embedded Odnoklassniki player
2925 odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
2926 if odnoklassniki_url:
2927 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
2928
2929 # Look for sibnet embedded player
2930 sibnet_urls = VKIE._extract_sibnet_urls(webpage)
2931 if sibnet_urls:
2932 return self.playlist_from_matches(sibnet_urls, video_id, video_title)
2933
2934 # Look for embedded ivi player
2935 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2936 if mobj is not None:
2937 return self.url_result(mobj.group('url'), 'Ivi')
2938
2939 # Look for embedded Huffington Post player
2940 mobj = re.search(
2941 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2942 if mobj is not None:
2943 return self.url_result(mobj.group('url'), 'HuffPost')
2944
2945 # Look for embed.ly
2946 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2947 if mobj is not None:
2948 return self.url_result(mobj.group('url'))
2949 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2950 if mobj is not None:
2951 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2952
2953 # Look for funnyordie embed
2954 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2955 if matches:
2956 return self.playlist_from_matches(
2957 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2958
2959 # Look for Simplecast embeds
2960 simplecast_urls = SimplecastIE._extract_urls(webpage)
2961 if simplecast_urls:
2962 return self.playlist_from_matches(
2963 simplecast_urls, video_id, video_title)
2964
2965 # Look for BBC iPlayer embed
2966 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2967 if matches:
2968 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2969
2970 # Look for embedded RUTV player
2971 rutv_url = RUTVIE._extract_url(webpage)
2972 if rutv_url:
2973 return self.url_result(rutv_url, 'RUTV')
2974
2975 # Look for embedded TVC player
2976 tvc_url = TVCIE._extract_url(webpage)
2977 if tvc_url:
2978 return self.url_result(tvc_url, 'TVC')
2979
2980 # Look for embedded SportBox player
2981 sportbox_urls = SportBoxIE._extract_urls(webpage)
2982 if sportbox_urls:
2983 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
2984
2985 # Look for embedded XHamster player
2986 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2987 if xhamster_urls:
2988 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2989
2990 # Look for embedded TNAFlixNetwork player
2991 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2992 if tnaflix_urls:
2993 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2994
2995 # Look for embedded PornHub player
2996 pornhub_urls = PornHubIE._extract_urls(webpage)
2997 if pornhub_urls:
2998 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2999
3000 # Look for embedded DrTuber player
3001 drtuber_urls = DrTuberIE._extract_urls(webpage)
3002 if drtuber_urls:
3003 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
3004
3005 # Look for embedded RedTube player
3006 redtube_urls = RedTubeIE._extract_urls(webpage)
3007 if redtube_urls:
3008 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
3009
3010 # Look for embedded Tube8 player
3011 tube8_urls = Tube8IE._extract_urls(webpage)
3012 if tube8_urls:
3013 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
3014
3015 # Look for embedded Mofosex player
3016 mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
3017 if mofosex_urls:
3018 return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
3019
3020 # Look for embedded Spankwire player
3021 spankwire_urls = SpankwireIE._extract_urls(webpage)
3022 if spankwire_urls:
3023 return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
3024
3025 # Look for embedded YouPorn player
3026 youporn_urls = YouPornIE._extract_urls(webpage)
3027 if youporn_urls:
3028 return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
3029
3030 # Look for embedded Tvigle player
3031 mobj = re.search(
3032 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
3033 if mobj is not None:
3034 return self.url_result(mobj.group('url'), 'Tvigle')
3035
3036 # Look for embedded TED player
3037 mobj = re.search(
3038 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
3039 if mobj is not None:
3040 return self.url_result(mobj.group('url'), 'TED')
3041
3042 # Look for embedded Ustream videos
3043 ustream_url = UstreamIE._extract_url(webpage)
3044 if ustream_url:
3045 return self.url_result(ustream_url, UstreamIE.ie_key())
3046
3047 # Look for embedded arte.tv player
3048 arte_urls = ArteTVEmbedIE._extract_urls(webpage)
3049 if arte_urls:
3050 return self.playlist_from_matches(arte_urls, video_id, video_title)
3051
3052 # Look for embedded francetv player
3053 mobj = re.search(
3054 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
3055 webpage)
3056 if mobj is not None:
3057 return self.url_result(mobj.group('url'))
3058
3059 # Look for embedded Myvi.ru player
3060 myvi_url = MyviIE._extract_url(webpage)
3061 if myvi_url:
3062 return self.url_result(myvi_url)
3063
3064 # Look for embedded soundcloud player
3065 soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
3066 if soundcloud_urls:
3067 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
3068
3069 # Look for tunein player
3070 tunein_urls = TuneInBaseIE._extract_urls(webpage)
3071 if tunein_urls:
3072 return self.playlist_from_matches(tunein_urls, video_id, video_title)
3073
3074 # Look for embedded mtvservices player
3075 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
3076 if mtvservices_url:
3077 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
3078
3079 # Look for embedded yahoo player
3080 mobj = re.search(
3081 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
3082 webpage)
3083 if mobj is not None:
3084 return self.url_result(mobj.group('url'), 'Yahoo')
3085
3086 # Look for embedded sbs.com.au player
3087 mobj = re.search(
3088 r'''(?x)
3089 (?:
3090 <meta\s+property="og:video"\s+content=|
3091 <iframe[^>]+?src=
3092 )
3093 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
3094 webpage)
3095 if mobj is not None:
3096 return self.url_result(mobj.group('url'), 'SBS')
3097
3098 # Look for embedded Cinchcast player
3099 mobj = re.search(
3100 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
3101 webpage)
3102 if mobj is not None:
3103 return self.url_result(mobj.group('url'), 'Cinchcast')
3104
3105 mobj = re.search(
3106 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
3107 webpage)
3108 if not mobj:
3109 mobj = re.search(
3110 r'data-video-link=["\'](?P<url>http://m\.mlb\.com/video/[^"\']+)',
3111 webpage)
3112 if mobj is not None:
3113 return self.url_result(mobj.group('url'), 'MLB')
3114
3115 mobj = re.search(
3116 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
3117 webpage)
3118 if mobj is not None:
3119 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
3120
3121 mobj = re.search(
3122 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
3123 webpage)
3124 if mobj is not None:
3125 return self.url_result(mobj.group('url'), 'Livestream')
3126
3127 # Look for Zapiks embed
3128 mobj = re.search(
3129 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
3130 if mobj is not None:
3131 return self.url_result(mobj.group('url'), 'Zapiks')
3132
3133 # Look for Kaltura embeds
3134 kaltura_urls = KalturaIE._extract_urls(webpage)
3135 if kaltura_urls:
3136 return self.playlist_from_matches(
3137 kaltura_urls, video_id, video_title,
3138 getter=lambda x: smuggle_url(x, {'source_url': url}),
3139 ie=KalturaIE.ie_key())
3140
3141 # Look for EaglePlatform embeds
3142 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
3143 if eagleplatform_url:
3144 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
3145
3146 # Look for ClipYou (uses EaglePlatform) embeds
3147 mobj = re.search(
3148 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
3149 if mobj is not None:
3150 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
3151
3152 # Look for Pladform embeds
3153 pladform_url = PladformIE._extract_url(webpage)
3154 if pladform_url:
3155 return self.url_result(pladform_url)
3156
3157 # Look for Videomore embeds
3158 videomore_url = VideomoreIE._extract_url(webpage)
3159 if videomore_url:
3160 return self.url_result(videomore_url)
3161
3162 # Look for Webcaster embeds
3163 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
3164 if webcaster_url:
3165 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
3166
3167 # Look for Playwire embeds
3168 mobj = re.search(
3169 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
3170 if mobj is not None:
3171 return self.url_result(mobj.group('url'))
3172
3173 # Look for 5min embeds
3174 mobj = re.search(
3175 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
3176 if mobj is not None:
3177 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
3178
3179 # Look for Crooks and Liars embeds
3180 mobj = re.search(
3181 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
3182 if mobj is not None:
3183 return self.url_result(mobj.group('url'))
3184
3185 # Look for NBC Sports VPlayer embeds
3186 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
3187 if nbc_sports_url:
3188 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
3189
3190 # Look for NBC News embeds
3191 nbc_news_embed_url = re.search(
3192 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
3193 if nbc_news_embed_url:
3194 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
3195
3196 # Look for Google Drive embeds
3197 google_drive_url = GoogleDriveIE._extract_url(webpage)
3198 if google_drive_url:
3199 return self.url_result(google_drive_url, 'GoogleDrive')
3200
3201 # Look for UDN embeds
3202 mobj = re.search(
3203 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
3204 if mobj is not None:
3205 return self.url_result(
3206 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
3207
3208 # Look for Senate ISVP iframe
3209 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
3210 if senate_isvp_url:
3211 return self.url_result(senate_isvp_url, 'SenateISVP')
3212
3213 # Look for Kinja embeds
3214 kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
3215 if kinja_embed_urls:
3216 return self.playlist_from_matches(
3217 kinja_embed_urls, video_id, video_title)
3218
3219 # Look for OnionStudios embeds
3220 onionstudios_url = OnionStudiosIE._extract_url(webpage)
3221 if onionstudios_url:
3222 return self.url_result(onionstudios_url)
3223
3224 # Look for ViewLift embeds
3225 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
3226 if viewlift_url:
3227 return self.url_result(viewlift_url)
3228
3229 # Look for JWPlatform embeds
3230 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
3231 if jwplatform_urls:
3232 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
3233
3234 # Look for Digiteka embeds
3235 digiteka_url = DigitekaIE._extract_url(webpage)
3236 if digiteka_url:
3237 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
3238
3239 # Look for Arkena embeds
3240 arkena_url = ArkenaIE._extract_url(webpage)
3241 if arkena_url:
3242 return self.url_result(arkena_url, ArkenaIE.ie_key())
3243
3244 # Look for Piksel embeds
3245 piksel_url = PikselIE._extract_url(webpage)
3246 if piksel_url:
3247 return self.url_result(piksel_url, PikselIE.ie_key())
3248
3249 # Look for Limelight embeds
3250 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
3251 if limelight_urls:
3252 return self.playlist_result(
3253 limelight_urls, video_id, video_title, video_description)
3254
3255 # Look for Anvato embeds
3256 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
3257 if anvato_urls:
3258 return self.playlist_result(
3259 anvato_urls, video_id, video_title, video_description)
3260
3261 # Look for AdobeTVVideo embeds
3262 mobj = re.search(
3263 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
3264 webpage)
3265 if mobj is not None:
3266 return self.url_result(
3267 self._proto_relative_url(unescapeHTML(mobj.group(1))),
3268 'AdobeTVVideo')
3269
3270 # Look for Vine embeds
3271 mobj = re.search(
3272 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
3273 webpage)
3274 if mobj is not None:
3275 return self.url_result(
3276 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
3277
3278 # Look for VODPlatform embeds
3279 mobj = re.search(
3280 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
3281 webpage)
3282 if mobj is not None:
3283 return self.url_result(
3284 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
3285
3286 # Look for Mangomolo embeds
3287 mobj = re.search(
3288 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
3289 (?:
3290 admin\.mangomolo\.com/analytics/index\.php/customers/embed|
3291 player\.mangomolo\.com/v1
3292 )/
3293 (?:
3294 video\?.*?\bid=(?P<video_id>\d+)|
3295 (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
3296 ).+?)\1''', webpage)
3297 if mobj is not None:
3298 info = {
3299 '_type': 'url_transparent',
3300 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
3301 'title': video_title,
3302 'description': video_description,
3303 'thumbnail': video_thumbnail,
3304 'uploader': video_uploader,
3305 }
3306 video_id = mobj.group('video_id')
3307 if video_id:
3308 info.update({
3309 'ie_key': 'MangomoloVideo',
3310 'id': video_id,
3311 })
3312 else:
3313 info.update({
3314 'ie_key': 'MangomoloLive',
3315 'id': mobj.group('channel_id'),
3316 })
3317 return info
3318
3319 # Look for Instagram embeds
3320 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
3321 if instagram_embed_url is not None:
3322 return self.url_result(
3323 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
3324
3325 # Look for 3Q SDN embeds
3326 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
3327 if threeqsdn_url:
3328 return {
3329 '_type': 'url_transparent',
3330 'ie_key': ThreeQSDNIE.ie_key(),
3331 'url': self._proto_relative_url(threeqsdn_url),
3332 'title': video_title,
3333 'description': video_description,
3334 'thumbnail': video_thumbnail,
3335 'uploader': video_uploader,
3336 }
3337
3338 # Look for VBOX7 embeds
3339 vbox7_url = Vbox7IE._extract_url(webpage)
3340 if vbox7_url:
3341 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3342
3343 # Look for DBTV embeds
3344 dbtv_urls = DBTVIE._extract_urls(webpage)
3345 if dbtv_urls:
3346 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
3347
3348 # Look for Videa embeds
3349 videa_urls = VideaIE._extract_urls(webpage)
3350 if videa_urls:
3351 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
3352
3353 # Look for 20 minuten embeds
3354 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3355 if twentymin_urls:
3356 return self.playlist_from_matches(
3357 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3358
3359 # Look for VideoPress embeds
3360 videopress_urls = VideoPressIE._extract_urls(webpage)
3361 if videopress_urls:
3362 return self.playlist_from_matches(
3363 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3364
3365 # Look for Rutube embeds
3366 rutube_urls = RutubeIE._extract_urls(webpage)
3367 if rutube_urls:
3368 return self.playlist_from_matches(
3369 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3370
3371 # Look for WashingtonPost embeds
3372 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3373 if wapo_urls:
3374 return self.playlist_from_matches(
3375 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3376
3377 # Look for Mediaset embeds
3378 mediaset_urls = MediasetIE._extract_urls(self, webpage)
3379 if mediaset_urls:
3380 return self.playlist_from_matches(
3381 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3382
3383 # Look for JOJ.sk embeds
3384 joj_urls = JojIE._extract_urls(webpage)
3385 if joj_urls:
3386 return self.playlist_from_matches(
3387 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3388
3389 # Look for megaphone.fm embeds
3390 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3391 if mpfn_urls:
3392 return self.playlist_from_matches(
3393 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3394
3395 # Look for vzaar embeds
3396 vzaar_urls = VzaarIE._extract_urls(webpage)
3397 if vzaar_urls:
3398 return self.playlist_from_matches(
3399 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3400
3401 channel9_urls = Channel9IE._extract_urls(webpage)
3402 if channel9_urls:
3403 return self.playlist_from_matches(
3404 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3405
3406 vshare_urls = VShareIE._extract_urls(webpage)
3407 if vshare_urls:
3408 return self.playlist_from_matches(
3409 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3410
3411 # Look for Mediasite embeds
3412 mediasite_urls = MediasiteIE._extract_urls(webpage)
3413 if mediasite_urls:
3414 entries = [
3415 self.url_result(smuggle_url(
3416 compat_urlparse.urljoin(url, mediasite_url),
3417 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3418 for mediasite_url in mediasite_urls]
3419 return self.playlist_result(entries, video_id, video_title)
3420
3421 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3422 if springboardplatform_urls:
3423 return self.playlist_from_matches(
3424 springboardplatform_urls, video_id, video_title,
3425 ie=SpringboardPlatformIE.ie_key())
3426
3427 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3428 if yapfiles_urls:
3429 return self.playlist_from_matches(
3430 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3431
3432 vice_urls = ViceIE._extract_urls(webpage)
3433 if vice_urls:
3434 return self.playlist_from_matches(
3435 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3436
3437 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3438 if xfileshare_urls:
3439 return self.playlist_from_matches(
3440 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3441
3442 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3443 if cloudflarestream_urls:
3444 return self.playlist_from_matches(
3445 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3446
3447 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3448 if peertube_urls:
3449 return self.playlist_from_matches(
3450 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3451
3452 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3453 if indavideo_urls:
3454 return self.playlist_from_matches(
3455 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3456
3457 apa_urls = APAIE._extract_urls(webpage)
3458 if apa_urls:
3459 return self.playlist_from_matches(
3460 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3461
3462 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3463 if foxnews_urls:
3464 return self.playlist_from_matches(
3465 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3466
3467 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3468 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3469 webpage)]
3470 if sharevideos_urls:
3471 return self.playlist_from_matches(
3472 sharevideos_urls, video_id, video_title)
3473
3474 viqeo_urls = ViqeoIE._extract_urls(webpage)
3475 if viqeo_urls:
3476 return self.playlist_from_matches(
3477 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3478
3479 expressen_urls = ExpressenIE._extract_urls(webpage)
3480 if expressen_urls:
3481 return self.playlist_from_matches(
3482 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3483
3484 zype_urls = ZypeIE._extract_urls(webpage)
3485 if zype_urls:
3486 return self.playlist_from_matches(
3487 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3488
3489 # Look for HTML5 media
3490 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3491 if entries:
3492 if len(entries) == 1:
3493 entries[0].update({
3494 'id': video_id,
3495 'title': video_title,
3496 })
3497 else:
3498 for num, entry in enumerate(entries, start=1):
3499 entry.update({
3500 'id': '%s-%s' % (video_id, num),
3501 'title': '%s (%d)' % (video_title, num),
3502 })
3503 for entry in entries:
3504 self._sort_formats(entry['formats'])
3505 return self.playlist_result(entries, video_id, video_title)
3506
3507 jwplayer_data = self._find_jwplayer_data(
3508 webpage, video_id, transform_source=js_to_json)
3509 if jwplayer_data:
3510 try:
3511 info = self._parse_jwplayer_data(
3512 jwplayer_data, video_id, require_title=False, base_url=url)
3513 return merge_dicts(info, info_dict)
3514 except ExtractorError:
3515 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3516 pass
3517
3518 # Video.js embed
3519 mobj = re.search(
3520 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3521 webpage)
3522 if mobj is not None:
3523 sources = self._parse_json(
3524 mobj.group(1), video_id, transform_source=js_to_json,
3525 fatal=False) or []
3526 if not isinstance(sources, list):
3527 sources = [sources]
3528 formats = []
3529 for source in sources:
3530 src = source.get('src')
3531 if not src or not isinstance(src, compat_str):
3532 continue
3533 src = compat_urlparse.urljoin(url, src)
3534 src_type = source.get('type')
3535 if isinstance(src_type, compat_str):
3536 src_type = src_type.lower()
3537 ext = determine_ext(src).lower()
3538 if src_type == 'video/youtube':
3539 return self.url_result(src, YoutubeIE.ie_key())
3540 if src_type == 'application/dash+xml' or ext == 'mpd':
3541 formats.extend(self._extract_mpd_formats(
3542 src, video_id, mpd_id='dash', fatal=False))
3543 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3544 formats.extend(self._extract_m3u8_formats(
3545 src, video_id, 'mp4', entry_protocol='m3u8_native',
3546 m3u8_id='hls', fatal=False))
3547 else:
3548 formats.append({
3549 'url': src,
3550 'ext': (mimetype2ext(src_type)
3551 or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3552 'http_headers': {
3553 'Referer': full_response.geturl(),
3554 },
3555 })
3556 if formats:
3557 self._sort_formats(formats)
3558 info_dict['formats'] = formats
3559 return info_dict
3560
3561 # Look for generic KVS player (before ld+json for tests)
3562 found = re.search(
3563 r'<script\b[^>]+?\bsrc\s*=\s*(["\'])https?://(?:\S+?/)+kt_player\.js\?v=(?P<ver>(?P<maj_ver>\d+)(\.\d+)+)\1[^>]*>',
3564 webpage)
3565 if found:
3566 self.report_extraction('KVS Player')
3567 if found.group('maj_ver') not in ('4', '5', '6'):
3568 self.report_warning('Untested major version (%s) in player engine - download may fail.' % (found.group('ver'), ))
3569 return merge_dicts(
3570 self._extract_kvs(url, webpage, video_id),
3571 info_dict)
3572
3573 # Looking for http://schema.org/VideoObject
3574 json_ld = self._search_json_ld(
3575 webpage, video_id, default={}, expected_type='VideoObject')
3576 if json_ld.get('url'):
3577 return merge_dicts(json_ld, info_dict)
3578
3579 def check_video(vurl):
3580 if YoutubeIE.suitable(vurl):
3581 return True
3582 if RtmpIE.suitable(vurl):
3583 return True
3584 vpath = compat_urlparse.urlparse(vurl).path
3585 vext = determine_ext(vpath)
3586 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3587
3588 def filter_video(urls):
3589 return list(filter(check_video, urls))
3590
3591 # Start with something easy: JW Player in SWFObject
3592 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3593 if not found:
3594 # Look for gorilla-vid style embedding
3595 found = filter_video(re.findall(r'''(?sx)
3596 (?:
3597 jw_plugins|
3598 JWPlayerOptions|
3599 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3600 )
3601 .*?
3602 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3603 if not found:
3604 # Broaden the search a little bit
3605 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3606 if not found:
3607 # Broaden the findall a little bit: JWPlayer JS loader
3608 found = filter_video(re.findall(
3609 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3610 if not found:
3611 # Flow player
3612 found = filter_video(re.findall(r'''(?xs)
3613 flowplayer\("[^"]+",\s*
3614 \{[^}]+?\}\s*,
3615 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3616 ["']?url["']?\s*:\s*["']([^"']+)["']
3617 ''', webpage))
3618 if not found:
3619 # Cinerama player
3620 found = re.findall(
3621 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3622 if not found:
3623 # Try to find twitter cards info
3624 # twitter:player:stream should be checked before twitter:player since
3625 # it is expected to contain a raw stream (see
3626 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3627 found = filter_video(re.findall(
3628 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3629 if not found:
3630 # We look for Open Graph info:
3631 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3632 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3633 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3634 if m_video_type is not None:
3635 found = filter_video(re.findall(r'<meta.*?property="og:(?:video|audio)".*?content="(.*?)"', webpage))
3636 if not found:
3637 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3638 found = re.search(
3639 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3640 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3641 webpage)
3642 if not found:
3643 # Look also in Refresh HTTP header
3644 refresh_header = head_response.headers.get('Refresh')
3645 if refresh_header:
3646 # In python 2 response HTTP headers are bytestrings
3647 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3648 refresh_header = refresh_header.decode('iso-8859-1')
3649 found = re.search(REDIRECT_REGEX, refresh_header)
3650 if found:
3651 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3652 if new_url != url:
3653 self.report_following_redirect(new_url)
3654 return {
3655 '_type': 'url',
3656 'url': new_url,
3657 }
3658 else:
3659 found = None
3660
3661 if not found:
3662 # twitter:player is a https URL to iframe player that may or may not
3663 # be supported by youtube-dl thus this is checked the very last (see
3664 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3665 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3666 if embed_url and embed_url != url:
3667 return self.url_result(embed_url)
3668
3669 if not found:
3670 raise UnsupportedError(url)
3671
3672 entries = []
3673 for video_url in orderedSet(found):
3674 video_url = unescapeHTML(video_url)
3675 video_url = video_url.replace('\\/', '/')
3676 video_url = compat_urlparse.urljoin(url, video_url)
3677 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3678
3679 # Sometimes, jwplayer extraction will result in a YouTube URL
3680 if YoutubeIE.suitable(video_url):
3681 entries.append(self.url_result(video_url, 'Youtube'))
3682 continue
3683
3684 # here's a fun little line of code for you:
3685 video_id = os.path.splitext(video_id)[0]
3686
3687 entry_info_dict = {
3688 'id': video_id,
3689 'uploader': video_uploader,
3690 'title': video_title,
3691 'age_limit': age_limit,
3692 }
3693
3694 if RtmpIE.suitable(video_url):
3695 entry_info_dict.update({
3696 '_type': 'url_transparent',
3697 'ie_key': RtmpIE.ie_key(),
3698 'url': video_url,
3699 })
3700 entries.append(entry_info_dict)
3701 continue
3702
3703 ext = determine_ext(video_url)
3704 if ext == 'smil':
3705 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3706 elif ext == 'xspf':
3707 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3708 elif ext == 'm3u8':
3709 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3710 elif ext == 'mpd':
3711 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3712 elif ext == 'f4m':
3713 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3714 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3715 # Just matching .ism/manifest is not enough to be reliably sure
3716 # whether it's actually an ISM manifest or some other streaming
3717 # manifest since there are various streaming URL formats
3718 # possible (see [1]) as well as some other shenanigans like
3719 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3720 # so on.
3721 # Thus the most reasonable way to solve this is to delegate
3722 # to generic extractor in order to look into the contents of
3723 # the manifest itself.
3724 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3725 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3726 entry_info_dict = self.url_result(
3727 smuggle_url(video_url, {'to_generic': True}),
3728 GenericIE.ie_key())
3729 else:
3730 entry_info_dict['url'] = video_url
3731
3732 if entry_info_dict.get('formats'):
3733 self._sort_formats(entry_info_dict['formats'])
3734
3735 entries.append(entry_info_dict)
3736
3737 if len(entries) == 1:
3738 return entries[0]
3739 else:
3740 for num, e in enumerate(entries, start=1):
3741 # 'url' results don't have a title
3742 if e.get('title') is not None:
3743 e['title'] = '%s (%d)' % (e['title'], num)
3744 return {
3745 '_type': 'playlist',
3746 'entries': entries,
3747 }
|