]> jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/generic.py
[svt] Improve extraction and add support for pages (closes #16802)
[yt-dlp.git] / youtube_dl / extractor / generic.py
1 # coding: utf-8
2
3 from __future__ import unicode_literals
4
5 import os
6 import re
7 import sys
8
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
13 compat_str,
14 compat_urllib_parse_unquote,
15 compat_urlparse,
16 compat_xml_parse_error,
17 )
18 from ..utils import (
19 determine_ext,
20 ExtractorError,
21 float_or_none,
22 HEADRequest,
23 is_html,
24 js_to_json,
25 KNOWN_EXTENSIONS,
26 merge_dicts,
27 mimetype2ext,
28 orderedSet,
29 sanitized_Request,
30 smuggle_url,
31 unescapeHTML,
32 unified_strdate,
33 unsmuggle_url,
34 UnsupportedError,
35 xpath_text,
36 )
37 from .commonprotocols import RtmpIE
38 from .brightcove import (
39 BrightcoveLegacyIE,
40 BrightcoveNewIE,
41 )
42 from .nexx import (
43 NexxIE,
44 NexxEmbedIE,
45 )
46 from .nbc import NBCSportsVPlayerIE
47 from .ooyala import OoyalaIE
48 from .rutv import RUTVIE
49 from .tvc import TVCIE
50 from .sportbox import SportBoxEmbedIE
51 from .smotri import SmotriIE
52 from .myvi import MyviIE
53 from .condenast import CondeNastIE
54 from .udn import UDNEmbedIE
55 from .senateisvp import SenateISVPIE
56 from .svt import SVTIE
57 from .pornhub import PornHubIE
58 from .xhamster import XHamsterEmbedIE
59 from .tnaflix import TNAFlixNetworkEmbedIE
60 from .drtuber import DrTuberIE
61 from .redtube import RedTubeIE
62 from .tube8 import Tube8IE
63 from .vimeo import VimeoIE
64 from .dailymotion import DailymotionIE
65 from .dailymail import DailyMailIE
66 from .onionstudios import OnionStudiosIE
67 from .viewlift import ViewLiftEmbedIE
68 from .mtv import MTVServicesEmbeddedIE
69 from .pladform import PladformIE
70 from .videomore import VideomoreIE
71 from .webcaster import WebcasterFeedIE
72 from .googledrive import GoogleDriveIE
73 from .jwplatform import JWPlatformIE
74 from .digiteka import DigitekaIE
75 from .arkena import ArkenaIE
76 from .instagram import InstagramIE
77 from .liveleak import LiveLeakIE
78 from .threeqsdn import ThreeQSDNIE
79 from .theplatform import ThePlatformIE
80 from .vessel import VesselIE
81 from .kaltura import KalturaIE
82 from .eagleplatform import EaglePlatformIE
83 from .facebook import FacebookIE
84 from .soundcloud import SoundcloudIE
85 from .tunein import TuneInBaseIE
86 from .vbox7 import Vbox7IE
87 from .dbtv import DBTVIE
88 from .piksel import PikselIE
89 from .videa import VideaIE
90 from .twentymin import TwentyMinutenIE
91 from .ustream import UstreamIE
92 from .openload import OpenloadIE
93 from .videopress import VideoPressIE
94 from .rutube import RutubeIE
95 from .limelight import LimelightBaseIE
96 from .anvato import AnvatoIE
97 from .washingtonpost import WashingtonPostIE
98 from .wistia import WistiaIE
99 from .mediaset import MediasetIE
100 from .joj import JojIE
101 from .megaphone import MegaphoneIE
102 from .vzaar import VzaarIE
103 from .channel9 import Channel9IE
104 from .vshare import VShareIE
105 from .mediasite import MediasiteIE
106 from .springboardplatform import SpringboardPlatformIE
107 from .yapfiles import YapFilesIE
108 from .vice import ViceIE
109 from .xfileshare import XFileShareIE
110 from .cloudflarestream import CloudflareStreamIE
111 from .peertube import PeerTubeIE
112 from .indavideo import IndavideoEmbedIE
113 from .apa import APAIE
114 from .foxnews import FoxNewsIE
115
116
117 class GenericIE(InfoExtractor):
118 IE_DESC = 'Generic downloader that works on some sites'
119 _VALID_URL = r'.*'
120 IE_NAME = 'generic'
121 _TESTS = [
122 # Direct link to a video
123 {
124 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
125 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
126 'info_dict': {
127 'id': 'trailer',
128 'ext': 'mp4',
129 'title': 'trailer',
130 'upload_date': '20100513',
131 }
132 },
133 # Direct link to media delivered compressed (until Accept-Encoding is *)
134 {
135 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
136 'md5': '128c42e68b13950268b648275386fc74',
137 'info_dict': {
138 'id': 'FictionJunction-Parallel_Hearts',
139 'ext': 'flac',
140 'title': 'FictionJunction-Parallel_Hearts',
141 'upload_date': '20140522',
142 },
143 'expected_warnings': [
144 'URL could be a direct video link, returning it as such.'
145 ],
146 'skip': 'URL invalid',
147 },
148 # Direct download with broken HEAD
149 {
150 'url': 'http://ai-radio.org:8000/radio.opus',
151 'info_dict': {
152 'id': 'radio',
153 'ext': 'opus',
154 'title': 'radio',
155 },
156 'params': {
157 'skip_download': True, # infinite live stream
158 },
159 'expected_warnings': [
160 r'501.*Not Implemented',
161 r'400.*Bad Request',
162 ],
163 },
164 # Direct link with incorrect MIME type
165 {
166 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
167 'md5': '4ccbebe5f36706d85221f204d7eb5913',
168 'info_dict': {
169 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
170 'id': '5_Lennart_Poettering_-_Systemd',
171 'ext': 'webm',
172 'title': '5_Lennart_Poettering_-_Systemd',
173 'upload_date': '20141120',
174 },
175 'expected_warnings': [
176 'URL could be a direct video link, returning it as such.'
177 ]
178 },
179 # RSS feed
180 {
181 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
182 'info_dict': {
183 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
184 'title': 'Zero Punctuation',
185 'description': 're:.*groundbreaking video review series.*'
186 },
187 'playlist_mincount': 11,
188 },
189 # RSS feed with enclosure
190 {
191 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
192 'info_dict': {
193 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
194 'ext': 'm4v',
195 'upload_date': '20150228',
196 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
197 }
198 },
199 # RSS feed with enclosures and unsupported link URLs
200 {
201 'url': 'http://www.hellointernet.fm/podcast?format=rss',
202 'info_dict': {
203 'id': 'http://www.hellointernet.fm/podcast?format=rss',
204 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
205 'title': 'Hello Internet',
206 },
207 'playlist_mincount': 100,
208 },
209 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
210 {
211 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
212 'info_dict': {
213 'id': 'smil',
214 'ext': 'mp4',
215 'title': 'Automatics, robotics and biocybernetics',
216 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
217 'upload_date': '20130627',
218 'formats': 'mincount:16',
219 'subtitles': 'mincount:1',
220 },
221 'params': {
222 'force_generic_extractor': True,
223 'skip_download': True,
224 },
225 },
226 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
227 {
228 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
229 'info_dict': {
230 'id': 'hds',
231 'ext': 'flv',
232 'title': 'hds',
233 'formats': 'mincount:1',
234 },
235 'params': {
236 'skip_download': True,
237 },
238 },
239 # SMIL from https://www.restudy.dk/video/play/id/1637
240 {
241 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
242 'info_dict': {
243 'id': 'video_1637',
244 'ext': 'flv',
245 'title': 'video_1637',
246 'formats': 'mincount:3',
247 },
248 'params': {
249 'skip_download': True,
250 },
251 },
252 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
253 {
254 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
255 'info_dict': {
256 'id': 'smil-service',
257 'ext': 'flv',
258 'title': 'smil-service',
259 'formats': 'mincount:1',
260 },
261 'params': {
262 'skip_download': True,
263 },
264 },
265 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
266 {
267 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
268 'info_dict': {
269 'id': '4719370',
270 'ext': 'mp4',
271 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
272 'formats': 'mincount:3',
273 },
274 'params': {
275 'skip_download': True,
276 },
277 },
278 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
279 {
280 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
281 'info_dict': {
282 'id': 'mZlp2ctYIUEB',
283 'ext': 'mp4',
284 'title': 'Tikibad ontruimd wegens brand',
285 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
286 'thumbnail': r're:^https?://.*\.jpg$',
287 'duration': 33,
288 },
289 'params': {
290 'skip_download': True,
291 },
292 },
293 # MPD from http://dash-mse-test.appspot.com/media.html
294 {
295 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
296 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
297 'info_dict': {
298 'id': 'car-20120827-manifest',
299 'ext': 'mp4',
300 'title': 'car-20120827-manifest',
301 'formats': 'mincount:9',
302 'upload_date': '20130904',
303 },
304 'params': {
305 'format': 'bestvideo',
306 },
307 },
308 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
309 {
310 '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',
311 'info_dict': {
312 'id': 'content',
313 'ext': 'mp4',
314 'title': 'content',
315 'formats': 'mincount:8',
316 },
317 'params': {
318 # m3u8 downloads
319 'skip_download': True,
320 },
321 'skip': 'video gone',
322 },
323 # m3u8 served with Content-Type: text/plain
324 {
325 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
326 'info_dict': {
327 'id': 'index',
328 'ext': 'mp4',
329 'title': 'index',
330 'upload_date': '20140720',
331 'formats': 'mincount:11',
332 },
333 'params': {
334 # m3u8 downloads
335 'skip_download': True,
336 },
337 'skip': 'video gone',
338 },
339 # google redirect
340 {
341 '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',
342 'info_dict': {
343 'id': 'cmQHVoWB5FY',
344 'ext': 'mp4',
345 'upload_date': '20130224',
346 'uploader_id': 'TheVerge',
347 'description': r're:^Chris Ziegler takes a look at the\.*',
348 'uploader': 'The Verge',
349 'title': 'First Firefox OS phones side-by-side',
350 },
351 'params': {
352 'skip_download': False,
353 }
354 },
355 {
356 # redirect in Refresh HTTP header
357 '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',
358 'info_dict': {
359 'id': 'pO8h3EaFRdo',
360 'ext': 'mp4',
361 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
362 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
363 'upload_date': '20150917',
364 'uploader_id': 'brtvofficial',
365 'uploader': 'Boiler Room',
366 },
367 'params': {
368 'skip_download': False,
369 },
370 },
371 {
372 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
373 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
374 'info_dict': {
375 'id': '13601338388002',
376 'ext': 'mp4',
377 'uploader': 'www.hodiho.fr',
378 'title': 'R\u00e9gis plante sa Jeep',
379 }
380 },
381 # bandcamp page with custom domain
382 {
383 'add_ie': ['Bandcamp'],
384 'url': 'http://bronyrock.com/track/the-pony-mash',
385 'info_dict': {
386 'id': '3235767654',
387 'ext': 'mp3',
388 'title': 'The Pony Mash',
389 'uploader': 'M_Pallante',
390 },
391 'skip': 'There is a limit of 200 free downloads / month for the test song',
392 },
393 {
394 # embedded brightcove video
395 # it also tests brightcove videos that need to set the 'Referer'
396 # in the http requests
397 'add_ie': ['BrightcoveLegacy'],
398 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
399 'info_dict': {
400 'id': '2765128793001',
401 'ext': 'mp4',
402 'title': 'Le cours de bourse : l’analyse technique',
403 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
404 'uploader': 'BFM BUSINESS',
405 },
406 'params': {
407 'skip_download': True,
408 },
409 },
410 {
411 # embedded with itemprop embedURL and video id spelled as `idVideo`
412 'add_id': ['BrightcoveLegacy'],
413 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
414 'info_dict': {
415 'id': '5255628253001',
416 'ext': 'mp4',
417 'title': 'md5:37c519b1128915607601e75a87995fc0',
418 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
419 'uploader': 'BFM BUSINESS',
420 'uploader_id': '876450612001',
421 'timestamp': 1482255315,
422 'upload_date': '20161220',
423 },
424 'params': {
425 'skip_download': True,
426 },
427 },
428 {
429 # https://github.com/rg3/youtube-dl/issues/2253
430 'url': 'http://bcove.me/i6nfkrc3',
431 'md5': '0ba9446db037002366bab3b3eb30c88c',
432 'info_dict': {
433 'id': '3101154703001',
434 'ext': 'mp4',
435 'title': 'Still no power',
436 'uploader': 'thestar.com',
437 '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.',
438 },
439 'add_ie': ['BrightcoveLegacy'],
440 'skip': 'video gone',
441 },
442 {
443 'url': 'http://www.championat.com/video/football/v/87/87499.html',
444 'md5': 'fb973ecf6e4a78a67453647444222983',
445 'info_dict': {
446 'id': '3414141473001',
447 'ext': 'mp4',
448 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
449 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
450 'uploader': 'Championat',
451 },
452 },
453 {
454 # https://github.com/rg3/youtube-dl/issues/3541
455 'add_ie': ['BrightcoveLegacy'],
456 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
457 'info_dict': {
458 'id': '3866516442001',
459 'ext': 'mp4',
460 'title': 'Leer mij vrouwen kennen: Aflevering 1',
461 'description': 'Leer mij vrouwen kennen: Aflevering 1',
462 'uploader': 'SBS Broadcasting',
463 },
464 'skip': 'Restricted to Netherlands',
465 'params': {
466 'skip_download': True, # m3u8 download
467 },
468 },
469 {
470 # Brightcove video in <iframe>
471 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
472 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
473 'info_dict': {
474 'id': '5360463607001',
475 'ext': 'mp4',
476 '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',
477 '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。',
478 'uploader': 'United Nations',
479 'uploader_id': '1362235914001',
480 'timestamp': 1489593889,
481 'upload_date': '20170315',
482 },
483 'add_ie': ['BrightcoveLegacy'],
484 },
485 {
486 # Brightcove with alternative playerID key
487 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
488 'info_dict': {
489 'id': 'nmeth.2062_SV1',
490 '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',
491 },
492 'playlist': [{
493 'info_dict': {
494 'id': '2228375078001',
495 'ext': 'mp4',
496 'title': 'nmeth.2062-sv1',
497 'description': 'nmeth.2062-sv1',
498 'timestamp': 1363357591,
499 'upload_date': '20130315',
500 'uploader': 'Nature Publishing Group',
501 'uploader_id': '1964492299001',
502 },
503 }],
504 },
505 {
506 # Brightcove with UUID in videoPlayer
507 'url': 'http://www8.hp.com/cn/zh/home.html',
508 'info_dict': {
509 'id': '5255815316001',
510 'ext': 'mp4',
511 'title': 'Sprocket Video - China',
512 'description': 'Sprocket Video - China',
513 'uploader': 'HP-Video Gallery',
514 'timestamp': 1482263210,
515 'upload_date': '20161220',
516 'uploader_id': '1107601872001',
517 },
518 'params': {
519 'skip_download': True, # m3u8 download
520 },
521 'skip': 'video rotates...weekly?',
522 },
523 {
524 # Brightcove:new type [2].
525 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
526 'md5': '2b35148fcf48da41c9fb4591650784f3',
527 'info_dict': {
528 'id': '5348741021001',
529 'ext': 'mp4',
530 'upload_date': '20170306',
531 'uploader_id': '4191638492001',
532 'timestamp': 1488769918,
533 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
534
535 },
536 },
537 {
538 # Alternative brightcove <video> attributes
539 '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/',
540 'info_dict': {
541 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
542 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
543 },
544 'playlist': [{
545 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
546 'info_dict': {
547 'id': '5311302538001',
548 'ext': 'mp4',
549 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
550 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
551 'timestamp': 1486321708,
552 'upload_date': '20170205',
553 'uploader_id': '800000640001',
554 },
555 'only_matching': True,
556 }],
557 },
558 {
559 # Brightcove with UUID in videoPlayer
560 'url': 'http://www8.hp.com/cn/zh/home.html',
561 'info_dict': {
562 'id': '5255815316001',
563 'ext': 'mp4',
564 'title': 'Sprocket Video - China',
565 'description': 'Sprocket Video - China',
566 'uploader': 'HP-Video Gallery',
567 'timestamp': 1482263210,
568 'upload_date': '20161220',
569 'uploader_id': '1107601872001',
570 },
571 'params': {
572 'skip_download': True, # m3u8 download
573 },
574 },
575 # ooyala video
576 {
577 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
578 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
579 'info_dict': {
580 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
581 'ext': 'mp4',
582 'title': '2cc213299525360.mov', # that's what we get
583 'duration': 238.231,
584 },
585 'add_ie': ['Ooyala'],
586 },
587 {
588 # ooyala video embedded with http://player.ooyala.com/iframe.js
589 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
590 'info_dict': {
591 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
592 'ext': 'mp4',
593 'title': '"Steve Jobs: Man in the Machine" trailer',
594 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
595 'duration': 135.427,
596 },
597 'params': {
598 'skip_download': True,
599 },
600 'skip': 'movie expired',
601 },
602 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
603 {
604 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
605 'info_dict': {
606 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
607 'ext': 'mp4',
608 'title': 'Steampunk Fest Comes to Honesdale',
609 'duration': 43.276,
610 },
611 'params': {
612 'skip_download': True,
613 }
614 },
615 # embed.ly video
616 {
617 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
618 'info_dict': {
619 'id': '9ODmcdjQcHQ',
620 'ext': 'mp4',
621 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
622 'upload_date': '20140225',
623 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
624 'uploader': 'Tested',
625 'uploader_id': 'testedcom',
626 },
627 # No need to test YoutubeIE here
628 'params': {
629 'skip_download': True,
630 },
631 },
632 # funnyordie embed
633 {
634 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
635 'info_dict': {
636 'id': '18e820ec3f',
637 'ext': 'mp4',
638 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
639 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
640 },
641 # HEAD requests lead to endless 301, while GET is OK
642 'expected_warnings': ['301'],
643 },
644 # RUTV embed
645 {
646 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
647 'info_dict': {
648 'id': '776940',
649 'ext': 'mp4',
650 'title': 'Охотское море стало целиком российским',
651 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
652 },
653 'params': {
654 # m3u8 download
655 'skip_download': True,
656 },
657 },
658 # TVC embed
659 {
660 '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/',
661 'info_dict': {
662 'id': '55304',
663 'ext': 'mp4',
664 'title': 'Дошкольное воспитание',
665 },
666 },
667 # SportBox embed
668 {
669 'url': 'http://www.vestifinance.ru/articles/25753',
670 'info_dict': {
671 'id': '25753',
672 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
673 },
674 'playlist': [{
675 'info_dict': {
676 'id': '370908',
677 'title': 'Госзаказ. День 3',
678 'ext': 'mp4',
679 }
680 }, {
681 'info_dict': {
682 'id': '370905',
683 'title': 'Госзаказ. День 2',
684 'ext': 'mp4',
685 }
686 }, {
687 'info_dict': {
688 'id': '370902',
689 'title': 'Госзаказ. День 1',
690 'ext': 'mp4',
691 }
692 }],
693 'params': {
694 # m3u8 download
695 'skip_download': True,
696 },
697 },
698 # Myvi.ru embed
699 {
700 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
701 'info_dict': {
702 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
703 'ext': 'mp4',
704 'title': 'Ужастики, русский трейлер (2015)',
705 'thumbnail': r're:^https?://.*\.jpg$',
706 'duration': 153,
707 }
708 },
709 # XHamster embed
710 {
711 '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',
712 'info_dict': {
713 'id': 'showthread',
714 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
715 },
716 'playlist_mincount': 7,
717 # This forum does not allow <iframe> syntaxes anymore
718 # Now HTML tags are displayed as-is
719 'skip': 'No videos on this page',
720 },
721 # Embedded TED video
722 {
723 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
724 'md5': '65fdff94098e4a607385a60c5177c638',
725 'info_dict': {
726 'id': '1969',
727 'ext': 'mp4',
728 'title': 'Hidden miracles of the natural world',
729 'uploader': 'Louie Schwartzberg',
730 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
731 }
732 },
733 # nowvideo embed hidden behind percent encoding
734 {
735 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
736 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
737 'info_dict': {
738 'id': '06e53103ca9aa',
739 'ext': 'flv',
740 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
741 'description': 'No description',
742 },
743 },
744 # arte embed
745 {
746 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
747 'md5': '7653032cbb25bf6c80d80f217055fa43',
748 'info_dict': {
749 'id': '048195-004_PLUS7-F',
750 'ext': 'flv',
751 'title': 'X:enius',
752 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
753 'upload_date': '20140320',
754 },
755 'params': {
756 'skip_download': 'Requires rtmpdump'
757 },
758 'skip': 'video gone',
759 },
760 # francetv embed
761 {
762 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
763 'info_dict': {
764 'id': 'EV_30231',
765 'ext': 'mp4',
766 'title': 'Alcaline, le concert avec Calogero',
767 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
768 'upload_date': '20150226',
769 'timestamp': 1424989860,
770 'duration': 5400,
771 },
772 'params': {
773 # m3u8 downloads
774 'skip_download': True,
775 },
776 'expected_warnings': [
777 'Forbidden'
778 ]
779 },
780 # Condé Nast embed
781 {
782 'url': 'http://www.wired.com/2014/04/honda-asimo/',
783 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
784 'info_dict': {
785 'id': '53501be369702d3275860000',
786 'ext': 'mp4',
787 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
788 }
789 },
790 # Dailymotion embed
791 {
792 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
793 'md5': '441aeeb82eb72c422c7f14ec533999cd',
794 'info_dict': {
795 'id': 'k2mm4bCdJ6CQ2i7c8o2',
796 'ext': 'mp4',
797 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
798 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
799 'uploader': 'Spi0n',
800 'uploader_id': 'xgditw',
801 'upload_date': '20140425',
802 'timestamp': 1398441542,
803 },
804 'add_ie': ['Dailymotion'],
805 },
806 # DailyMail embed
807 {
808 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
809 'info_dict': {
810 'id': '1495629',
811 'ext': 'mp4',
812 'title': 'Care worker punches elderly dementia patient in head 11 times',
813 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
814 },
815 'add_ie': ['DailyMail'],
816 'params': {
817 'skip_download': True,
818 },
819 },
820 # YouTube embed
821 {
822 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
823 'info_dict': {
824 'id': 'FXRb4ykk4S0',
825 'ext': 'mp4',
826 'title': 'The NBL Auction 2014',
827 'uploader': 'BADMINTON England',
828 'uploader_id': 'BADMINTONEvents',
829 'upload_date': '20140603',
830 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
831 },
832 'add_ie': ['Youtube'],
833 'params': {
834 'skip_download': True,
835 }
836 },
837 # MTVSercices embed
838 {
839 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
840 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
841 'info_dict': {
842 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
843 'ext': 'mp4',
844 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
845 'description': 'Two valets share their love for movie star Liam Neesons.',
846 'timestamp': 1349922600,
847 'upload_date': '20121011',
848 },
849 },
850 # YouTube embed via <data-embed-url="">
851 {
852 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
853 'info_dict': {
854 'id': '4vAffPZIT44',
855 'ext': 'mp4',
856 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
857 'uploader': 'Gameloft',
858 'uploader_id': 'gameloft',
859 'upload_date': '20140828',
860 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
861 },
862 'params': {
863 'skip_download': True,
864 }
865 },
866 # YouTube <object> embed
867 {
868 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
869 'md5': '516718101ec834f74318df76259fb3cc',
870 'info_dict': {
871 'id': 'msN87y-iEx0',
872 'ext': 'webm',
873 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
874 'upload_date': '20080526',
875 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
876 'uploader': 'Christopher Sykes',
877 'uploader_id': 'ChristopherJSykes',
878 },
879 'add_ie': ['Youtube'],
880 },
881 # Camtasia studio
882 {
883 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
884 'playlist': [{
885 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
886 'info_dict': {
887 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
888 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
889 'ext': 'flv',
890 'duration': 2235.90,
891 }
892 }, {
893 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
894 'info_dict': {
895 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
896 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
897 'ext': 'flv',
898 'duration': 2235.93,
899 }
900 }],
901 'info_dict': {
902 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
903 }
904 },
905 # Flowplayer
906 {
907 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
908 'md5': '9d65602bf31c6e20014319c7d07fba27',
909 'info_dict': {
910 'id': '5123ea6d5e5a7',
911 'ext': 'mp4',
912 'age_limit': 18,
913 'uploader': 'www.handjobhub.com',
914 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
915 }
916 },
917 # Multiple brightcove videos
918 # https://github.com/rg3/youtube-dl/issues/2283
919 {
920 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
921 'info_dict': {
922 'id': 'always-never',
923 'title': 'Always / Never - The New Yorker',
924 },
925 'playlist_count': 3,
926 'params': {
927 'extract_flat': False,
928 'skip_download': True,
929 }
930 },
931 # MLB embed
932 {
933 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
934 'md5': '96f09a37e44da40dd083e12d9a683327',
935 'info_dict': {
936 'id': '33322633',
937 'ext': 'mp4',
938 'title': 'Ump changes call to ball',
939 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
940 'duration': 48,
941 'timestamp': 1401537900,
942 'upload_date': '20140531',
943 'thumbnail': r're:^https?://.*\.jpg$',
944 },
945 },
946 # Wistia embed
947 {
948 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
949 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
950 'info_dict': {
951 'id': '6e2wtrbdaf',
952 'ext': 'mov',
953 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
954 'description': 'a Paywall Videos video from Remilon',
955 'duration': 644.072,
956 'uploader': 'study.com',
957 'timestamp': 1459678540,
958 'upload_date': '20160403',
959 'filesize': 24687186,
960 },
961 },
962 {
963 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
964 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
965 'info_dict': {
966 'id': 'uxjb0lwrcz',
967 'ext': 'mp4',
968 'title': 'Conversation about Hexagonal Rails Part 1',
969 'description': 'a Martin Fowler video from ThoughtWorks',
970 'duration': 1715.0,
971 'uploader': 'thoughtworks.wistia.com',
972 'timestamp': 1401832161,
973 'upload_date': '20140603',
974 },
975 },
976 # Wistia standard embed (async)
977 {
978 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
979 'info_dict': {
980 'id': '807fafadvk',
981 'ext': 'mp4',
982 'title': 'Drip Brennan Dunn Workshop',
983 'description': 'a JV Webinars video from getdrip-1',
984 'duration': 4986.95,
985 'timestamp': 1463607249,
986 'upload_date': '20160518',
987 },
988 'params': {
989 'skip_download': True,
990 }
991 },
992 # Soundcloud embed
993 {
994 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
995 'info_dict': {
996 'id': '174391317',
997 'ext': 'mp3',
998 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
999 'uploader': 'Sophos Security',
1000 'title': 'Chet Chat 171 - Oct 29, 2014',
1001 'upload_date': '20141029',
1002 }
1003 },
1004 # Soundcloud multiple embeds
1005 {
1006 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1007 'info_dict': {
1008 'id': '52809',
1009 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1010 },
1011 'playlist_mincount': 7,
1012 },
1013 # TuneIn station embed
1014 {
1015 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1016 'info_dict': {
1017 'id': '204146',
1018 'ext': 'mp3',
1019 'title': 'CNRV',
1020 'location': 'Paris, France',
1021 'is_live': True,
1022 },
1023 'params': {
1024 # Live stream
1025 'skip_download': True,
1026 },
1027 },
1028 # Livestream embed
1029 {
1030 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1031 'info_dict': {
1032 'id': '67864563',
1033 'ext': 'flv',
1034 'upload_date': '20141112',
1035 'title': 'Rosetta #CometLanding webcast HL 10',
1036 }
1037 },
1038 # Another Livestream embed, without 'new.' in URL
1039 {
1040 'url': 'https://www.freespeech.org/',
1041 'info_dict': {
1042 'id': '123537347',
1043 'ext': 'mp4',
1044 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1045 },
1046 'params': {
1047 # Live stream
1048 'skip_download': True,
1049 },
1050 },
1051 # LazyYT
1052 {
1053 'url': 'https://skiplagged.com/',
1054 'info_dict': {
1055 'id': 'skiplagged',
1056 'title': 'Skiplagged: The smart way to find cheap flights',
1057 },
1058 'playlist_mincount': 1,
1059 'add_ie': ['Youtube'],
1060 },
1061 # Cinchcast embed
1062 {
1063 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1064 'info_dict': {
1065 'id': '7141703',
1066 'ext': 'mp3',
1067 'upload_date': '20141126',
1068 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1069 }
1070 },
1071 # Cinerama player
1072 {
1073 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1074 'info_dict': {
1075 'id': '730m_DandD_1901_512k',
1076 'ext': 'mp4',
1077 'uploader': 'www.abc.net.au',
1078 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1079 }
1080 },
1081 # embedded viddler video
1082 {
1083 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1084 'info_dict': {
1085 'id': '4d03aad9',
1086 'ext': 'mp4',
1087 'uploader': 'deadspin',
1088 'title': 'WALL-TO-GORTAT',
1089 'timestamp': 1422285291,
1090 'upload_date': '20150126',
1091 },
1092 'add_ie': ['Viddler'],
1093 },
1094 # Libsyn embed
1095 {
1096 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1097 'info_dict': {
1098 'id': '3377616',
1099 'ext': 'mp3',
1100 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1101 'description': 'md5:601cb790edd05908957dae8aaa866465',
1102 'upload_date': '20150220',
1103 },
1104 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1105 },
1106 # jwplayer YouTube
1107 {
1108 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1109 'info_dict': {
1110 'id': 'Mrj4DVp2zeA',
1111 'ext': 'mp4',
1112 'upload_date': '20150212',
1113 'uploader': 'The National Archives UK',
1114 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1115 'uploader_id': 'NationalArchives08',
1116 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1117 },
1118 },
1119 # jwplayer rtmp
1120 {
1121 'url': 'http://www.suffolk.edu/sjc/live.php',
1122 'info_dict': {
1123 'id': 'live',
1124 'ext': 'flv',
1125 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1126 'uploader': 'www.suffolk.edu',
1127 },
1128 'params': {
1129 'skip_download': True,
1130 },
1131 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1132 },
1133 # Complex jwplayer
1134 {
1135 'url': 'http://www.indiedb.com/games/king-machine/videos',
1136 'info_dict': {
1137 'id': 'videos',
1138 'ext': 'mp4',
1139 'title': 'king machine trailer 1',
1140 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1141 'thumbnail': r're:^https?://.*\.jpg$',
1142 },
1143 },
1144 {
1145 # JWPlayer config passed as variable
1146 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1147 'info_dict': {
1148 'id': '3326530_hq',
1149 'ext': 'mp4',
1150 'title': 'ARIELE | Tube Cup',
1151 'uploader': 'www.txxx.com',
1152 'age_limit': 18,
1153 },
1154 'params': {
1155 'skip_download': True,
1156 }
1157 },
1158 {
1159 # JWPlatform iframe
1160 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1161 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1162 'info_dict': {
1163 'id': 'O0c5JcKT',
1164 'ext': 'mp4',
1165 'upload_date': '20171122',
1166 'timestamp': 1511366290,
1167 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1168 },
1169 'add_ie': [JWPlatformIE.ie_key()],
1170 },
1171 {
1172 # Video.js embed, multiple formats
1173 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1174 'info_dict': {
1175 'id': 'yygqldloqIk',
1176 'ext': 'mp4',
1177 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1178 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1179 'upload_date': '20130314',
1180 'uploader': 'PROстое3D',
1181 'uploader_id': 'PROstoe3D',
1182 },
1183 'params': {
1184 'skip_download': True,
1185 },
1186 },
1187 {
1188 # Video.js embed, single format
1189 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1190 'info_dict': {
1191 'id': 'watch',
1192 'ext': 'mp4',
1193 'title': 'Step 1 - Good Foundation',
1194 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1195 },
1196 'params': {
1197 'skip_download': True,
1198 },
1199 },
1200 # rtl.nl embed
1201 {
1202 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1203 'playlist_mincount': 5,
1204 'info_dict': {
1205 'id': 'aanslagen-kopenhagen',
1206 'title': 'Aanslagen Kopenhagen',
1207 }
1208 },
1209 # Zapiks embed
1210 {
1211 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1212 'info_dict': {
1213 'id': '118046',
1214 'ext': 'mp4',
1215 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1216 }
1217 },
1218 # Kaltura embed (different embed code)
1219 {
1220 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1221 'info_dict': {
1222 'id': '1_a52wc67y',
1223 'ext': 'flv',
1224 'upload_date': '20150127',
1225 'uploader_id': 'PremierMedia',
1226 'timestamp': int,
1227 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1228 },
1229 },
1230 # Kaltura embed with single quotes
1231 {
1232 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1233 'info_dict': {
1234 'id': '0_izeg5utt',
1235 'ext': 'mp4',
1236 'title': '35871',
1237 'timestamp': 1355743100,
1238 'upload_date': '20121217',
1239 'uploader_id': 'cplapp@learn360.com',
1240 },
1241 'add_ie': ['Kaltura'],
1242 },
1243 {
1244 # Kaltura embedded via quoted entry_id
1245 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1246 'info_dict': {
1247 'id': '0_utuok90b',
1248 'ext': 'mp4',
1249 'title': '06_matthew_brender_raj_dutt',
1250 'timestamp': 1466638791,
1251 'upload_date': '20160622',
1252 },
1253 'add_ie': ['Kaltura'],
1254 'expected_warnings': [
1255 'Could not send HEAD request'
1256 ],
1257 'params': {
1258 'skip_download': True,
1259 }
1260 },
1261 {
1262 # Kaltura embedded, some fileExt broken (#11480)
1263 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1264 'info_dict': {
1265 'id': '1_sgtvehim',
1266 'ext': 'mp4',
1267 'title': 'Our "Standard Models" of particle physics and cosmology',
1268 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1269 'timestamp': 1321158993,
1270 'upload_date': '20111113',
1271 'uploader_id': 'kps1',
1272 },
1273 'add_ie': ['Kaltura'],
1274 },
1275 {
1276 # Kaltura iframe embed
1277 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1278 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1279 'info_dict': {
1280 'id': '0_f2cfbpwy',
1281 'ext': 'mp4',
1282 'title': 'I. M. Pei: A Centennial Celebration',
1283 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1284 'upload_date': '20170403',
1285 'uploader_id': 'batchUser',
1286 'timestamp': 1491232186,
1287 },
1288 'add_ie': ['Kaltura'],
1289 },
1290 {
1291 # Kaltura iframe embed, more sophisticated
1292 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1293 'info_dict': {
1294 'id': '1_9gzouybz',
1295 'ext': 'mp4',
1296 'title': 'lecture-05sep2017',
1297 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1298 'upload_date': '20170913',
1299 'uploader_id': 'eps2',
1300 'timestamp': 1505340777,
1301 },
1302 'params': {
1303 'skip_download': True,
1304 },
1305 'add_ie': ['Kaltura'],
1306 },
1307 {
1308 # meta twitter:player
1309 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1310 'info_dict': {
1311 'id': '0_01b42zps',
1312 'ext': 'mp4',
1313 'title': 'Main Twerk (Video)',
1314 'upload_date': '20171208',
1315 'uploader_id': 'sebastian.salinas@thechive.com',
1316 'timestamp': 1512713057,
1317 },
1318 'params': {
1319 'skip_download': True,
1320 },
1321 'add_ie': ['Kaltura'],
1322 },
1323 # referrer protected EaglePlatform embed
1324 {
1325 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1326 'info_dict': {
1327 'id': '582306',
1328 'ext': 'mp4',
1329 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1330 'thumbnail': r're:^https?://.*\.jpg$',
1331 'duration': 3382,
1332 'view_count': int,
1333 },
1334 'params': {
1335 'skip_download': True,
1336 },
1337 },
1338 # ClipYou (EaglePlatform) embed (custom URL)
1339 {
1340 'url': 'http://muz-tv.ru/play/7129/',
1341 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1342 'info_dict': {
1343 'id': '12820',
1344 'ext': 'mp4',
1345 'title': "'O Sole Mio",
1346 'thumbnail': r're:^https?://.*\.jpg$',
1347 'duration': 216,
1348 'view_count': int,
1349 },
1350 'params': {
1351 'skip_download': True,
1352 },
1353 'skip': 'This video is unavailable.',
1354 },
1355 # Pladform embed
1356 {
1357 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1358 'info_dict': {
1359 'id': '100183293',
1360 'ext': 'mp4',
1361 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1362 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1363 'thumbnail': r're:^https?://.*\.jpg$',
1364 'duration': 694,
1365 'age_limit': 0,
1366 },
1367 'skip': 'HTTP Error 404: Not Found',
1368 },
1369 # Playwire embed
1370 {
1371 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1372 'info_dict': {
1373 'id': '3519514',
1374 'ext': 'mp4',
1375 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1376 'thumbnail': r're:^https?://.*\.png$',
1377 'duration': 45.115,
1378 },
1379 },
1380 # 5min embed
1381 {
1382 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1383 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1384 'info_dict': {
1385 'id': '518726732',
1386 'ext': 'mp4',
1387 'title': 'Facebook Creates "On This Day" | Crunch Report',
1388 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1389 'timestamp': 1427237531,
1390 'uploader': 'Crunch Report',
1391 'upload_date': '20150324',
1392 },
1393 'params': {
1394 # m3u8 download
1395 'skip_download': True,
1396 },
1397 },
1398 # Crooks and Liars embed
1399 {
1400 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1401 'info_dict': {
1402 'id': '8RUoRhRi',
1403 'ext': 'mp4',
1404 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1405 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1406 'timestamp': 1428207000,
1407 'upload_date': '20150405',
1408 'uploader': 'Heather',
1409 },
1410 },
1411 # Crooks and Liars external embed
1412 {
1413 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1414 'info_dict': {
1415 'id': 'MTE3MjUtMzQ2MzA',
1416 'ext': 'mp4',
1417 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1418 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1419 'timestamp': 1265032391,
1420 'upload_date': '20100201',
1421 'uploader': 'Heather',
1422 },
1423 },
1424 # NBC Sports vplayer embed
1425 {
1426 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1427 'info_dict': {
1428 'id': 'ln7x1qSThw4k',
1429 'ext': 'flv',
1430 'title': "PFT Live: New leader in the 'new-look' defense",
1431 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1432 'uploader': 'NBCU-SPORTS',
1433 'upload_date': '20140107',
1434 'timestamp': 1389118457,
1435 },
1436 'skip': 'Invalid Page URL',
1437 },
1438 # NBC News embed
1439 {
1440 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1441 'md5': '1aa589c675898ae6d37a17913cf68d66',
1442 'info_dict': {
1443 'id': 'x_dtl_oa_LettermanliftPR_160608',
1444 'ext': 'mp4',
1445 'title': 'David Letterman: A Preview',
1446 '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.',
1447 'upload_date': '20160609',
1448 'timestamp': 1465431544,
1449 'uploader': 'NBCU-NEWS',
1450 },
1451 },
1452 # UDN embed
1453 {
1454 'url': 'https://video.udn.com/news/300346',
1455 'md5': 'fd2060e988c326991037b9aff9df21a6',
1456 'info_dict': {
1457 'id': '300346',
1458 'ext': 'mp4',
1459 'title': '中一中男師變性 全校師生力挺',
1460 'thumbnail': r're:^https?://.*\.jpg$',
1461 },
1462 'params': {
1463 # m3u8 download
1464 'skip_download': True,
1465 },
1466 'expected_warnings': ['Failed to parse JSON Expecting value'],
1467 },
1468 # Brightcove URL in single quotes
1469 {
1470 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1471 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1472 'info_dict': {
1473 'id': '4255764656001',
1474 'ext': 'mp4',
1475 'title': 'SN Presents: Russell Martin, World Citizen',
1476 '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.',
1477 'uploader': 'Rogers Sportsnet',
1478 'uploader_id': '1704050871',
1479 'upload_date': '20150525',
1480 'timestamp': 1432570283,
1481 },
1482 },
1483 # OnionStudios embed
1484 {
1485 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1486 'info_dict': {
1487 'id': '2855',
1488 'ext': 'mp4',
1489 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1490 'thumbnail': r're:^https?://.*\.jpe?g$',
1491 'uploader': 'ClickHole',
1492 'uploader_id': 'clickhole',
1493 }
1494 },
1495 # SnagFilms embed
1496 {
1497 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1498 'info_dict': {
1499 'id': '74849a00-85a9-11e1-9660-123139220831',
1500 'ext': 'mp4',
1501 'title': '#whilewewatch',
1502 }
1503 },
1504 # AdobeTVVideo embed
1505 {
1506 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1507 'md5': '43662b577c018ad707a63766462b1e87',
1508 'info_dict': {
1509 'id': '2456',
1510 'ext': 'mp4',
1511 'title': 'New experience with Acrobat DC',
1512 'description': 'New experience with Acrobat DC',
1513 'duration': 248.667,
1514 },
1515 },
1516 # BrightcoveInPageEmbed embed
1517 {
1518 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1519 'info_dict': {
1520 'id': '4238694884001',
1521 'ext': 'flv',
1522 'title': 'Tabletop: Dread, Last Thoughts',
1523 'description': 'Tabletop: Dread, Last Thoughts',
1524 'duration': 51690,
1525 },
1526 },
1527 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1528 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1529 {
1530 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1531 'info_dict': {
1532 'id': '4785848093001',
1533 'ext': 'mp4',
1534 'title': 'The Cardinal Pell Interview',
1535 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1536 'uploader': 'GlobeCast Australia - GlobeStream',
1537 'uploader_id': '2733773828001',
1538 'upload_date': '20160304',
1539 'timestamp': 1457083087,
1540 },
1541 'params': {
1542 # m3u8 downloads
1543 'skip_download': True,
1544 },
1545 },
1546 {
1547 # Brightcove embed with whitespace around attribute names
1548 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1549 'info_dict': {
1550 'id': '3167554373001',
1551 'ext': 'mp4',
1552 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1553 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1554 'uploader_id': '1079349493',
1555 'upload_date': '20140207',
1556 'timestamp': 1391810548,
1557 },
1558 'params': {
1559 'skip_download': True,
1560 },
1561 },
1562 # Another form of arte.tv embed
1563 {
1564 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1565 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1566 'info_dict': {
1567 'id': '030273-562_PLUS7-F',
1568 'ext': 'mp4',
1569 'title': 'ARTE Reportage - Nulle part, en France',
1570 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1571 'upload_date': '20160409',
1572 },
1573 },
1574 # LiveLeak embed
1575 {
1576 'url': 'http://www.wykop.pl/link/3088787/',
1577 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1578 'info_dict': {
1579 'id': '874_1459135191',
1580 'ext': 'mp4',
1581 'title': 'Man shows poor quality of new apartment building',
1582 'description': 'The wall is like a sand pile.',
1583 'uploader': 'Lake8737',
1584 },
1585 'add_ie': [LiveLeakIE.ie_key()],
1586 },
1587 # Another LiveLeak embed pattern (#13336)
1588 {
1589 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1590 'info_dict': {
1591 'id': '2eb_1496309988',
1592 'ext': 'mp4',
1593 'title': 'Thief robs place where everyone was armed',
1594 'description': 'md5:694d73ee79e535953cf2488562288eee',
1595 'uploader': 'brazilwtf',
1596 },
1597 'add_ie': [LiveLeakIE.ie_key()],
1598 },
1599 # Duplicated embedded video URLs
1600 {
1601 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1602 'info_dict': {
1603 'id': '149298443_480_16c25b74_2',
1604 'ext': 'mp4',
1605 'title': 'vs. Blue Orange Spring Game',
1606 'uploader': 'www.hudl.com',
1607 },
1608 },
1609 # twitter:player:stream embed
1610 {
1611 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1612 'info_dict': {
1613 'id': 'master',
1614 'ext': 'mp4',
1615 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1616 'uploader': 'www.rtl.be',
1617 },
1618 'params': {
1619 # m3u8 downloads
1620 'skip_download': True,
1621 },
1622 },
1623 # twitter:player embed
1624 {
1625 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1626 'md5': 'a3e0df96369831de324f0778e126653c',
1627 'info_dict': {
1628 'id': '4909620399001',
1629 'ext': 'mp4',
1630 'title': 'What Do Black Holes Sound Like?',
1631 'description': 'what do black holes sound like',
1632 'upload_date': '20160524',
1633 'uploader_id': '29913724001',
1634 'timestamp': 1464107587,
1635 'uploader': 'TheAtlantic',
1636 },
1637 'add_ie': ['BrightcoveLegacy'],
1638 },
1639 # Facebook <iframe> embed
1640 {
1641 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1642 'md5': 'fbcde74f534176ecb015849146dd3aee',
1643 'info_dict': {
1644 'id': '599637780109885',
1645 'ext': 'mp4',
1646 'title': 'Facebook video #599637780109885',
1647 },
1648 },
1649 # Facebook <iframe> embed, plugin video
1650 {
1651 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1652 'info_dict': {
1653 'id': '1754168231264132',
1654 'ext': 'mp4',
1655 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1656 'uploader': 'Tariq Ramadan (official)',
1657 'timestamp': 1496758379,
1658 'upload_date': '20170606',
1659 },
1660 'params': {
1661 'skip_download': True,
1662 },
1663 },
1664 # Facebook API embed
1665 {
1666 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1667 'md5': 'a47372ee61b39a7b90287094d447d94e',
1668 'info_dict': {
1669 'id': '10153467542406923',
1670 'ext': 'mp4',
1671 'title': 'Facebook video #10153467542406923',
1672 },
1673 },
1674 # Wordpress "YouTube Video Importer" plugin
1675 {
1676 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1677 'md5': 'd16797741b560b485194eddda8121b48',
1678 'info_dict': {
1679 'id': 'HNTXWDXV9Is',
1680 'ext': 'mp4',
1681 'title': 'Blue Devils Drumline Stanford lot 2016',
1682 'upload_date': '20160627',
1683 'uploader_id': 'GENOCIDE8GENERAL10',
1684 'uploader': 'cylus cyrus',
1685 },
1686 },
1687 {
1688 # video stored on custom kaltura server
1689 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1690 'md5': '537617d06e64dfed891fa1593c4b30cc',
1691 'info_dict': {
1692 'id': '0_1iotm5bh',
1693 'ext': 'mp4',
1694 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1695 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1696 'uploader_id': 'videos.expansion@el-mundo.net',
1697 'upload_date': '20150429',
1698 'timestamp': 1430303472,
1699 },
1700 'add_ie': ['Kaltura'],
1701 },
1702 {
1703 # Non-standard Vimeo embed
1704 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1705 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1706 'info_dict': {
1707 'id': '148867247',
1708 'ext': 'mp4',
1709 'title': 'Understanding the web - Teaser',
1710 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1711 'upload_date': '20151214',
1712 'uploader': 'OpenClassrooms',
1713 'uploader_id': 'openclassrooms',
1714 },
1715 'add_ie': ['Vimeo'],
1716 },
1717 {
1718 # generic vimeo embed that requires original URL passed as Referer
1719 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1720 'only_matching': True,
1721 },
1722 {
1723 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1724 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1725 'info_dict': {
1726 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1727 'ext': 'mp4',
1728 'title': 'Big Buck Bunny',
1729 'description': 'Royalty free test video',
1730 'timestamp': 1432816365,
1731 'upload_date': '20150528',
1732 'is_live': False,
1733 },
1734 'params': {
1735 'skip_download': True,
1736 },
1737 'add_ie': [ArkenaIE.ie_key()],
1738 },
1739 {
1740 '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/',
1741 'info_dict': {
1742 'id': '1c7141f46c',
1743 'ext': 'mp4',
1744 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1745 },
1746 'params': {
1747 'skip_download': True,
1748 },
1749 'add_ie': [Vbox7IE.ie_key()],
1750 },
1751 {
1752 # DBTV embeds
1753 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1754 'info_dict': {
1755 'id': '43254897',
1756 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1757 },
1758 'playlist_mincount': 3,
1759 },
1760 {
1761 # Videa embeds
1762 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1763 'info_dict': {
1764 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1765 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1766 },
1767 'playlist_mincount': 2,
1768 },
1769 {
1770 # 20 minuten embed
1771 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1772 'info_dict': {
1773 'id': '523629',
1774 'ext': 'mp4',
1775 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1776 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1777 },
1778 'params': {
1779 'skip_download': True,
1780 },
1781 'add_ie': [TwentyMinutenIE.ie_key()],
1782 },
1783 {
1784 # VideoPress embed
1785 'url': 'https://en.support.wordpress.com/videopress/',
1786 'info_dict': {
1787 'id': 'OcobLTqC',
1788 'ext': 'm4v',
1789 'title': 'IMG_5786',
1790 'timestamp': 1435711927,
1791 'upload_date': '20150701',
1792 },
1793 'params': {
1794 'skip_download': True,
1795 },
1796 'add_ie': [VideoPressIE.ie_key()],
1797 },
1798 {
1799 # Rutube embed
1800 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1801 'info_dict': {
1802 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1803 'ext': 'flv',
1804 'title': 'Магаззино: Казань 2',
1805 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1806 'uploader': 'Магаззино',
1807 'upload_date': '20170228',
1808 'uploader_id': '996642',
1809 },
1810 'params': {
1811 'skip_download': True,
1812 },
1813 'add_ie': [RutubeIE.ie_key()],
1814 },
1815 {
1816 # ThePlatform embedded with whitespaces in URLs
1817 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1818 'only_matching': True,
1819 },
1820 {
1821 # Senate ISVP iframe https
1822 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1823 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1824 'info_dict': {
1825 'id': 'govtaff020316',
1826 'ext': 'mp4',
1827 'title': 'Integrated Senate Video Player',
1828 },
1829 'add_ie': [SenateISVPIE.ie_key()],
1830 },
1831 {
1832 # Limelight embeds (1 channel embed + 4 media embeds)
1833 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1834 'info_dict': {
1835 'id': 'FacilitatorTraining2017',
1836 'title': 'Facilitator Training 2017',
1837 },
1838 'playlist_mincount': 5,
1839 },
1840 {
1841 # Limelight embed (LimelightPlayerUtil.embed)
1842 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1843 'info_dict': {
1844 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1845 'ext': 'mp4',
1846 'title': '07448641',
1847 'timestamp': 1499890639,
1848 'upload_date': '20170712',
1849 },
1850 'params': {
1851 'skip_download': True,
1852 },
1853 'add_ie': ['LimelightMedia'],
1854 },
1855 {
1856 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1857 'info_dict': {
1858 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1859 'title': 'Standoff with Walnut Creek murder suspect ends',
1860 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1861 },
1862 'playlist_mincount': 4,
1863 },
1864 {
1865 # WashingtonPost embed
1866 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1867 'info_dict': {
1868 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1869 'ext': 'mp4',
1870 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1871 '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.',
1872 'timestamp': 1455216756,
1873 'uploader': 'The Washington Post',
1874 'upload_date': '20160211',
1875 },
1876 'add_ie': [WashingtonPostIE.ie_key()],
1877 },
1878 {
1879 # Mediaset embed
1880 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1881 'info_dict': {
1882 'id': '720642',
1883 'ext': 'mp4',
1884 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1885 },
1886 'params': {
1887 'skip_download': True,
1888 },
1889 'add_ie': [MediasetIE.ie_key()],
1890 },
1891 {
1892 # JOJ.sk embeds
1893 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1894 'info_dict': {
1895 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1896 'title': 'Slovenskom sa prehnala vlna silných búrok',
1897 },
1898 'playlist_mincount': 5,
1899 'add_ie': [JojIE.ie_key()],
1900 },
1901 {
1902 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1903 'url': 'https://tvrain.ru/amp/418921/',
1904 'md5': 'cc00413936695987e8de148b67d14f1d',
1905 'info_dict': {
1906 'id': '418921',
1907 'ext': 'mp4',
1908 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1909 },
1910 },
1911 {
1912 # vzaar embed
1913 'url': 'http://help.vzaar.com/article/165-embedding-video',
1914 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1915 'info_dict': {
1916 'id': '8707641',
1917 'ext': 'mp4',
1918 'title': 'Building A Business Online: Principal Chairs Q & A',
1919 },
1920 },
1921 {
1922 # multiple HTML5 videos on one page
1923 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1924 'info_dict': {
1925 'id': 'keyscenarios',
1926 'title': 'Rescue Kit 14 Free Edition - Getting started',
1927 },
1928 'playlist_count': 4,
1929 },
1930 {
1931 # vshare embed
1932 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1933 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1934 'info_dict': {
1935 'id': '0f64ce6',
1936 'title': 'vl14062007715967',
1937 'ext': 'mp4',
1938 }
1939 },
1940 {
1941 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1942 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1943 'info_dict': {
1944 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1945 'ext': 'mp4',
1946 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1947 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1948 'timestamp': 1474354800,
1949 'upload_date': '20160920',
1950 }
1951 },
1952 {
1953 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1954 'info_dict': {
1955 'id': '1731611',
1956 'ext': 'mp4',
1957 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1958 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1959 'timestamp': 1516100691,
1960 'upload_date': '20180116',
1961 },
1962 'params': {
1963 'skip_download': True,
1964 },
1965 'add_ie': [SpringboardPlatformIE.ie_key()],
1966 },
1967 {
1968 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1969 'info_dict': {
1970 'id': 'uPDB5I9wfp8',
1971 'ext': 'webm',
1972 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1973 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1974 'upload_date': '20160219',
1975 'uploader': 'Pocoyo - Português (BR)',
1976 'uploader_id': 'PocoyoBrazil',
1977 },
1978 'add_ie': [YoutubeIE.ie_key()],
1979 'params': {
1980 'skip_download': True,
1981 },
1982 },
1983 {
1984 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1985 'info_dict': {
1986 'id': 'vMDE4NzI1Mjgt690b',
1987 'ext': 'mp4',
1988 'title': 'Котята',
1989 },
1990 'add_ie': [YapFilesIE.ie_key()],
1991 'params': {
1992 'skip_download': True,
1993 },
1994 },
1995 {
1996 # CloudflareStream embed
1997 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
1998 'info_dict': {
1999 'id': '31c9291ab41fac05471db4e73aa11717',
2000 'ext': 'mp4',
2001 'title': '31c9291ab41fac05471db4e73aa11717',
2002 },
2003 'add_ie': [CloudflareStreamIE.ie_key()],
2004 'params': {
2005 'skip_download': True,
2006 },
2007 },
2008 {
2009 # PeerTube embed
2010 'url': 'https://joinpeertube.org/fr/home/',
2011 'info_dict': {
2012 'id': 'home',
2013 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2014 },
2015 'playlist_count': 2,
2016 },
2017 {
2018 # Indavideo embed
2019 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2020 'info_dict': {
2021 'id': '1693903',
2022 'ext': 'mp4',
2023 'title': 'Így kell otthon hamburgert sütni',
2024 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2025 'timestamp': 1426330212,
2026 'upload_date': '20150314',
2027 'uploader': 'StreetKitchen',
2028 'uploader_id': '546363',
2029 },
2030 'add_ie': [IndavideoEmbedIE.ie_key()],
2031 'params': {
2032 'skip_download': True,
2033 },
2034 },
2035 {
2036 # APA embed via JWPlatform embed
2037 'url': 'http://www.vol.at/blue-man-group/5593454',
2038 'info_dict': {
2039 'id': 'jjv85FdZ',
2040 'ext': 'mp4',
2041 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2042 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2043 'thumbnail': r're:^https?://.*\.jpg$',
2044 'duration': 254,
2045 'timestamp': 1519211149,
2046 'upload_date': '20180221',
2047 },
2048 'params': {
2049 'skip_download': True,
2050 },
2051 },
2052 {
2053 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2054 'md5': 'b68d276de422ab07ee1d49388103f457',
2055 'info_dict': {
2056 'id': '83645793',
2057 'title': 'Lock up and get excited',
2058 'ext': 'mp4'
2059 },
2060 'skip': 'TODO: fix nested playlists processing in tests',
2061 },
2062 # {
2063 # # TODO: find another test
2064 # # http://schema.org/VideoObject
2065 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2066 # 'md5': '888dcf08b7ea671381f00fab74692755',
2067 # 'info_dict': {
2068 # 'id': 'nyvTSJMKId',
2069 # 'ext': 'mp4',
2070 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2071 # 'description': '#love for cats.',
2072 # 'timestamp': 1461244995,
2073 # 'upload_date': '20160421',
2074 # },
2075 # 'params': {
2076 # 'force_generic_extractor': True,
2077 # },
2078 # }
2079 ]
2080
2081 def report_following_redirect(self, new_url):
2082 """Report information extraction."""
2083 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2084
2085 def _extract_rss(self, url, video_id, doc):
2086 playlist_title = doc.find('./channel/title').text
2087 playlist_desc_el = doc.find('./channel/description')
2088 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2089
2090 entries = []
2091 for it in doc.findall('./channel/item'):
2092 next_url = None
2093 enclosure_nodes = it.findall('./enclosure')
2094 for e in enclosure_nodes:
2095 next_url = e.attrib.get('url')
2096 if next_url:
2097 break
2098
2099 if not next_url:
2100 next_url = xpath_text(it, 'link', fatal=False)
2101
2102 if not next_url:
2103 continue
2104
2105 entries.append({
2106 '_type': 'url_transparent',
2107 'url': next_url,
2108 'title': it.find('title').text,
2109 })
2110
2111 return {
2112 '_type': 'playlist',
2113 'id': url,
2114 'title': playlist_title,
2115 'description': playlist_desc,
2116 'entries': entries,
2117 }
2118
2119 def _extract_camtasia(self, url, video_id, webpage):
2120 """ Returns None if no camtasia video can be found. """
2121
2122 camtasia_cfg = self._search_regex(
2123 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2124 webpage, 'camtasia configuration file', default=None)
2125 if camtasia_cfg is None:
2126 return None
2127
2128 title = self._html_search_meta('DC.title', webpage, fatal=True)
2129
2130 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2131 camtasia_cfg = self._download_xml(
2132 camtasia_url, video_id,
2133 note='Downloading camtasia configuration',
2134 errnote='Failed to download camtasia configuration')
2135 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2136
2137 entries = []
2138 for n in fileset_node.getchildren():
2139 url_n = n.find('./uri')
2140 if url_n is None:
2141 continue
2142
2143 entries.append({
2144 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2145 'title': '%s - %s' % (title, n.tag),
2146 'url': compat_urlparse.urljoin(url, url_n.text),
2147 'duration': float_or_none(n.find('./duration').text),
2148 })
2149
2150 return {
2151 '_type': 'playlist',
2152 'entries': entries,
2153 'title': title,
2154 }
2155
2156 def _real_extract(self, url):
2157 if url.startswith('//'):
2158 return {
2159 '_type': 'url',
2160 'url': self.http_scheme() + url,
2161 }
2162
2163 parsed_url = compat_urlparse.urlparse(url)
2164 if not parsed_url.scheme:
2165 default_search = self._downloader.params.get('default_search')
2166 if default_search is None:
2167 default_search = 'fixup_error'
2168
2169 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2170 if '/' in url:
2171 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2172 return self.url_result('http://' + url)
2173 elif default_search != 'fixup_error':
2174 if default_search == 'auto_warning':
2175 if re.match(r'^(?:url|URL)$', url):
2176 raise ExtractorError(
2177 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2178 expected=True)
2179 else:
2180 self._downloader.report_warning(
2181 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2182 return self.url_result('ytsearch:' + url)
2183
2184 if default_search in ('error', 'fixup_error'):
2185 raise ExtractorError(
2186 '%r is not a valid URL. '
2187 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2188 % (url, url), expected=True)
2189 else:
2190 if ':' not in default_search:
2191 default_search += ':'
2192 return self.url_result(default_search + url)
2193
2194 url, smuggled_data = unsmuggle_url(url)
2195 force_videoid = None
2196 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2197 if smuggled_data and 'force_videoid' in smuggled_data:
2198 force_videoid = smuggled_data['force_videoid']
2199 video_id = force_videoid
2200 else:
2201 video_id = self._generic_id(url)
2202
2203 self.to_screen('%s: Requesting header' % video_id)
2204
2205 head_req = HEADRequest(url)
2206 head_response = self._request_webpage(
2207 head_req, video_id,
2208 note=False, errnote='Could not send HEAD request to %s' % url,
2209 fatal=False)
2210
2211 if head_response is not False:
2212 # Check for redirect
2213 new_url = compat_str(head_response.geturl())
2214 if url != new_url:
2215 self.report_following_redirect(new_url)
2216 if force_videoid:
2217 new_url = smuggle_url(
2218 new_url, {'force_videoid': force_videoid})
2219 return self.url_result(new_url)
2220
2221 full_response = None
2222 if head_response is False:
2223 request = sanitized_Request(url)
2224 request.add_header('Accept-Encoding', '*')
2225 full_response = self._request_webpage(request, video_id)
2226 head_response = full_response
2227
2228 info_dict = {
2229 'id': video_id,
2230 'title': self._generic_title(url),
2231 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2232 }
2233
2234 # Check for direct link to a video
2235 content_type = head_response.headers.get('Content-Type', '').lower()
2236 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2237 if m:
2238 format_id = compat_str(m.group('format_id'))
2239 if format_id.endswith('mpegurl'):
2240 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2241 elif format_id == 'f4m':
2242 formats = self._extract_f4m_formats(url, video_id)
2243 else:
2244 formats = [{
2245 'format_id': format_id,
2246 'url': url,
2247 'vcodec': 'none' if m.group('type') == 'audio' else None
2248 }]
2249 info_dict['direct'] = True
2250 self._sort_formats(formats)
2251 info_dict['formats'] = formats
2252 return info_dict
2253
2254 if not self._downloader.params.get('test', False) and not is_intentional:
2255 force = self._downloader.params.get('force_generic_extractor', False)
2256 self._downloader.report_warning(
2257 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2258
2259 if not full_response:
2260 request = sanitized_Request(url)
2261 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2262 # making it impossible to download only chunk of the file (yet we need only 512kB to
2263 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2264 # that will always result in downloading the whole file that is not desirable.
2265 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2266 # to accept raw bytes and being able to download only a chunk.
2267 # It may probably better to solve this by checking Content-Type for application/octet-stream
2268 # after HEAD request finishes, but not sure if we can rely on this.
2269 request.add_header('Accept-Encoding', '*')
2270 full_response = self._request_webpage(request, video_id)
2271
2272 first_bytes = full_response.read(512)
2273
2274 # Is it an M3U playlist?
2275 if first_bytes.startswith(b'#EXTM3U'):
2276 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2277 self._sort_formats(info_dict['formats'])
2278 return info_dict
2279
2280 # Maybe it's a direct link to a video?
2281 # Be careful not to download the whole thing!
2282 if not is_html(first_bytes):
2283 self._downloader.report_warning(
2284 'URL could be a direct video link, returning it as such.')
2285 info_dict.update({
2286 'direct': True,
2287 'url': url,
2288 })
2289 return info_dict
2290
2291 webpage = self._webpage_read_content(
2292 full_response, url, video_id, prefix=first_bytes)
2293
2294 self.report_extraction(video_id)
2295
2296 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2297 try:
2298 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2299 if doc.tag == 'rss':
2300 return self._extract_rss(url, video_id, doc)
2301 elif doc.tag == 'SmoothStreamingMedia':
2302 info_dict['formats'] = self._parse_ism_formats(doc, url)
2303 self._sort_formats(info_dict['formats'])
2304 return info_dict
2305 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2306 smil = self._parse_smil(doc, url, video_id)
2307 self._sort_formats(smil['formats'])
2308 return smil
2309 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2310 return self.playlist_result(
2311 self._parse_xspf(
2312 doc, video_id, xspf_url=url,
2313 xspf_base_url=compat_str(full_response.geturl())),
2314 video_id)
2315 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2316 info_dict['formats'] = self._parse_mpd_formats(
2317 doc,
2318 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2319 mpd_url=url)
2320 self._sort_formats(info_dict['formats'])
2321 return info_dict
2322 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2323 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2324 self._sort_formats(info_dict['formats'])
2325 return info_dict
2326 except compat_xml_parse_error:
2327 pass
2328
2329 # Is it a Camtasia project?
2330 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2331 if camtasia_res is not None:
2332 return camtasia_res
2333
2334 # Sometimes embedded video player is hidden behind percent encoding
2335 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2336 # Unescaping the whole page allows to handle those cases in a generic way
2337 webpage = compat_urllib_parse_unquote(webpage)
2338
2339 # it's tempting to parse this further, but you would
2340 # have to take into account all the variations like
2341 # Video Title - Site Name
2342 # Site Name | Video Title
2343 # Video Title - Tagline | Site Name
2344 # and so on and so forth; it's just not practical
2345 video_title = self._og_search_title(
2346 webpage, default=None) or self._html_search_regex(
2347 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2348 default='video')
2349
2350 # Try to detect age limit automatically
2351 age_limit = self._rta_search(webpage)
2352 # And then there are the jokers who advertise that they use RTA,
2353 # but actually don't.
2354 AGE_LIMIT_MARKERS = [
2355 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2356 ]
2357 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2358 age_limit = 18
2359
2360 # video uploader is domain name
2361 video_uploader = self._search_regex(
2362 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2363
2364 video_description = self._og_search_description(webpage, default=None)
2365 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2366
2367 info_dict.update({
2368 'title': video_title,
2369 'description': video_description,
2370 'thumbnail': video_thumbnail,
2371 'age_limit': age_limit,
2372 })
2373
2374 # Look for Brightcove Legacy Studio embeds
2375 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2376 if bc_urls:
2377 entries = [{
2378 '_type': 'url',
2379 'url': smuggle_url(bc_url, {'Referer': url}),
2380 'ie_key': 'BrightcoveLegacy'
2381 } for bc_url in bc_urls]
2382
2383 return {
2384 '_type': 'playlist',
2385 'title': video_title,
2386 'id': video_id,
2387 'entries': entries,
2388 }
2389
2390 # Look for Brightcove New Studio embeds
2391 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2392 if bc_urls:
2393 return self.playlist_from_matches(
2394 bc_urls, video_id, video_title,
2395 getter=lambda x: smuggle_url(x, {'referrer': url}),
2396 ie='BrightcoveNew')
2397
2398 # Look for Nexx embeds
2399 nexx_urls = NexxIE._extract_urls(webpage)
2400 if nexx_urls:
2401 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2402
2403 # Look for Nexx iFrame embeds
2404 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2405 if nexx_embed_urls:
2406 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2407
2408 # Look for ThePlatform embeds
2409 tp_urls = ThePlatformIE._extract_urls(webpage)
2410 if tp_urls:
2411 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2412
2413 # Look for Vessel embeds
2414 vessel_urls = VesselIE._extract_urls(webpage)
2415 if vessel_urls:
2416 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2417
2418 # Look for embedded rtl.nl player
2419 matches = re.findall(
2420 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2421 webpage)
2422 if matches:
2423 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2424
2425 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2426 if vimeo_urls:
2427 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2428
2429 vid_me_embed_url = self._search_regex(
2430 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2431 webpage, 'vid.me embed', default=None)
2432 if vid_me_embed_url is not None:
2433 return self.url_result(vid_me_embed_url, 'Vidme')
2434
2435 # Look for YouTube embeds
2436 youtube_urls = YoutubeIE._extract_urls(webpage)
2437 if youtube_urls:
2438 return self.playlist_from_matches(
2439 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2440
2441 matches = DailymotionIE._extract_urls(webpage)
2442 if matches:
2443 return self.playlist_from_matches(matches, video_id, video_title)
2444
2445 # Look for embedded Dailymotion playlist player (#3822)
2446 m = re.search(
2447 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2448 if m:
2449 playlists = re.findall(
2450 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2451 if playlists:
2452 return self.playlist_from_matches(
2453 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2454
2455 # Look for DailyMail embeds
2456 dailymail_urls = DailyMailIE._extract_urls(webpage)
2457 if dailymail_urls:
2458 return self.playlist_from_matches(
2459 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2460
2461 # Look for embedded Wistia player
2462 wistia_url = WistiaIE._extract_url(webpage)
2463 if wistia_url:
2464 return {
2465 '_type': 'url_transparent',
2466 'url': self._proto_relative_url(wistia_url),
2467 'ie_key': WistiaIE.ie_key(),
2468 'uploader': video_uploader,
2469 }
2470
2471 # Look for SVT player
2472 svt_url = SVTIE._extract_url(webpage)
2473 if svt_url:
2474 return self.url_result(svt_url, 'SVT')
2475
2476 # Look for Bandcamp pages with custom domain
2477 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2478 if mobj is not None:
2479 burl = unescapeHTML(mobj.group(1))
2480 # Don't set the extractor because it can be a track url or an album
2481 return self.url_result(burl)
2482
2483 # Look for embedded Vevo player
2484 mobj = re.search(
2485 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2486 if mobj is not None:
2487 return self.url_result(mobj.group('url'))
2488
2489 # Look for embedded Viddler player
2490 mobj = re.search(
2491 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2492 webpage)
2493 if mobj is not None:
2494 return self.url_result(mobj.group('url'))
2495
2496 # Look for NYTimes player
2497 mobj = re.search(
2498 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2499 webpage)
2500 if mobj is not None:
2501 return self.url_result(mobj.group('url'))
2502
2503 # Look for Libsyn player
2504 mobj = re.search(
2505 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2506 if mobj is not None:
2507 return self.url_result(mobj.group('url'))
2508
2509 # Look for Ooyala videos
2510 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2511 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2512 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2513 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2514 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2515 if mobj is not None:
2516 embed_token = self._search_regex(
2517 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2518 webpage, 'ooyala embed token', default=None)
2519 return OoyalaIE._build_url_result(smuggle_url(
2520 mobj.group('ec'), {
2521 'domain': url,
2522 'embed_token': embed_token,
2523 }))
2524
2525 # Look for multiple Ooyala embeds on SBN network websites
2526 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2527 if mobj is not None:
2528 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2529 if embeds:
2530 return self.playlist_from_matches(
2531 embeds, video_id, video_title,
2532 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2533
2534 # Look for Aparat videos
2535 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2536 if mobj is not None:
2537 return self.url_result(mobj.group(1), 'Aparat')
2538
2539 # Look for MPORA videos
2540 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2541 if mobj is not None:
2542 return self.url_result(mobj.group(1), 'Mpora')
2543
2544 # Look for embedded NovaMov-based player
2545 mobj = re.search(
2546 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2547 (?P<url>http://(?:(?:embed|www)\.)?
2548 (?:novamov\.com|
2549 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2550 videoweed\.(?:es|com)|
2551 movshare\.(?:net|sx|ag)|
2552 divxstage\.(?:eu|net|ch|co|at|ag))
2553 /embed\.php.+?)\1''', webpage)
2554 if mobj is not None:
2555 return self.url_result(mobj.group('url'))
2556
2557 # Look for embedded Facebook player
2558 facebook_urls = FacebookIE._extract_urls(webpage)
2559 if facebook_urls:
2560 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2561
2562 # Look for embedded VK player
2563 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2564 if mobj is not None:
2565 return self.url_result(mobj.group('url'), 'VK')
2566
2567 # Look for embedded Odnoklassniki player
2568 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2569 if mobj is not None:
2570 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2571
2572 # Look for embedded ivi player
2573 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2574 if mobj is not None:
2575 return self.url_result(mobj.group('url'), 'Ivi')
2576
2577 # Look for embedded Huffington Post player
2578 mobj = re.search(
2579 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2580 if mobj is not None:
2581 return self.url_result(mobj.group('url'), 'HuffPost')
2582
2583 # Look for embed.ly
2584 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2585 if mobj is not None:
2586 return self.url_result(mobj.group('url'))
2587 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2588 if mobj is not None:
2589 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2590
2591 # Look for funnyordie embed
2592 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2593 if matches:
2594 return self.playlist_from_matches(
2595 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2596
2597 # Look for BBC iPlayer embed
2598 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2599 if matches:
2600 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2601
2602 # Look for embedded RUTV player
2603 rutv_url = RUTVIE._extract_url(webpage)
2604 if rutv_url:
2605 return self.url_result(rutv_url, 'RUTV')
2606
2607 # Look for embedded TVC player
2608 tvc_url = TVCIE._extract_url(webpage)
2609 if tvc_url:
2610 return self.url_result(tvc_url, 'TVC')
2611
2612 # Look for embedded SportBox player
2613 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2614 if sportbox_urls:
2615 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2616
2617 # Look for embedded XHamster player
2618 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2619 if xhamster_urls:
2620 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2621
2622 # Look for embedded TNAFlixNetwork player
2623 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2624 if tnaflix_urls:
2625 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2626
2627 # Look for embedded PornHub player
2628 pornhub_urls = PornHubIE._extract_urls(webpage)
2629 if pornhub_urls:
2630 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2631
2632 # Look for embedded DrTuber player
2633 drtuber_urls = DrTuberIE._extract_urls(webpage)
2634 if drtuber_urls:
2635 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2636
2637 # Look for embedded RedTube player
2638 redtube_urls = RedTubeIE._extract_urls(webpage)
2639 if redtube_urls:
2640 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2641
2642 # Look for embedded Tube8 player
2643 tube8_urls = Tube8IE._extract_urls(webpage)
2644 if tube8_urls:
2645 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2646
2647 # Look for embedded Tvigle player
2648 mobj = re.search(
2649 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2650 if mobj is not None:
2651 return self.url_result(mobj.group('url'), 'Tvigle')
2652
2653 # Look for embedded TED player
2654 mobj = re.search(
2655 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2656 if mobj is not None:
2657 return self.url_result(mobj.group('url'), 'TED')
2658
2659 # Look for embedded Ustream videos
2660 ustream_url = UstreamIE._extract_url(webpage)
2661 if ustream_url:
2662 return self.url_result(ustream_url, UstreamIE.ie_key())
2663
2664 # Look for embedded arte.tv player
2665 mobj = re.search(
2666 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2667 webpage)
2668 if mobj is not None:
2669 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2670
2671 # Look for embedded francetv player
2672 mobj = re.search(
2673 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2674 webpage)
2675 if mobj is not None:
2676 return self.url_result(mobj.group('url'))
2677
2678 # Look for embedded smotri.com player
2679 smotri_url = SmotriIE._extract_url(webpage)
2680 if smotri_url:
2681 return self.url_result(smotri_url, 'Smotri')
2682
2683 # Look for embedded Myvi.ru player
2684 myvi_url = MyviIE._extract_url(webpage)
2685 if myvi_url:
2686 return self.url_result(myvi_url)
2687
2688 # Look for embedded soundcloud player
2689 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2690 if soundcloud_urls:
2691 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2692
2693 # Look for tunein player
2694 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2695 if tunein_urls:
2696 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2697
2698 # Look for embedded mtvservices player
2699 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2700 if mtvservices_url:
2701 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2702
2703 # Look for embedded yahoo player
2704 mobj = re.search(
2705 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2706 webpage)
2707 if mobj is not None:
2708 return self.url_result(mobj.group('url'), 'Yahoo')
2709
2710 # Look for embedded sbs.com.au player
2711 mobj = re.search(
2712 r'''(?x)
2713 (?:
2714 <meta\s+property="og:video"\s+content=|
2715 <iframe[^>]+?src=
2716 )
2717 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2718 webpage)
2719 if mobj is not None:
2720 return self.url_result(mobj.group('url'), 'SBS')
2721
2722 # Look for embedded Cinchcast player
2723 mobj = re.search(
2724 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2725 webpage)
2726 if mobj is not None:
2727 return self.url_result(mobj.group('url'), 'Cinchcast')
2728
2729 mobj = re.search(
2730 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2731 webpage)
2732 if not mobj:
2733 mobj = re.search(
2734 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2735 webpage)
2736 if mobj is not None:
2737 return self.url_result(mobj.group('url'), 'MLB')
2738
2739 mobj = re.search(
2740 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2741 webpage)
2742 if mobj is not None:
2743 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2744
2745 mobj = re.search(
2746 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2747 webpage)
2748 if mobj is not None:
2749 return self.url_result(mobj.group('url'), 'Livestream')
2750
2751 # Look for Zapiks embed
2752 mobj = re.search(
2753 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2754 if mobj is not None:
2755 return self.url_result(mobj.group('url'), 'Zapiks')
2756
2757 # Look for Kaltura embeds
2758 kaltura_url = KalturaIE._extract_url(webpage)
2759 if kaltura_url:
2760 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2761
2762 # Look for EaglePlatform embeds
2763 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2764 if eagleplatform_url:
2765 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2766
2767 # Look for ClipYou (uses EaglePlatform) embeds
2768 mobj = re.search(
2769 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2770 if mobj is not None:
2771 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2772
2773 # Look for Pladform embeds
2774 pladform_url = PladformIE._extract_url(webpage)
2775 if pladform_url:
2776 return self.url_result(pladform_url)
2777
2778 # Look for Videomore embeds
2779 videomore_url = VideomoreIE._extract_url(webpage)
2780 if videomore_url:
2781 return self.url_result(videomore_url)
2782
2783 # Look for Webcaster embeds
2784 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2785 if webcaster_url:
2786 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2787
2788 # Look for Playwire embeds
2789 mobj = re.search(
2790 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2791 if mobj is not None:
2792 return self.url_result(mobj.group('url'))
2793
2794 # Look for 5min embeds
2795 mobj = re.search(
2796 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2797 if mobj is not None:
2798 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2799
2800 # Look for Crooks and Liars embeds
2801 mobj = re.search(
2802 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2803 if mobj is not None:
2804 return self.url_result(mobj.group('url'))
2805
2806 # Look for NBC Sports VPlayer embeds
2807 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2808 if nbc_sports_url:
2809 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2810
2811 # Look for NBC News embeds
2812 nbc_news_embed_url = re.search(
2813 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2814 if nbc_news_embed_url:
2815 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2816
2817 # Look for Google Drive embeds
2818 google_drive_url = GoogleDriveIE._extract_url(webpage)
2819 if google_drive_url:
2820 return self.url_result(google_drive_url, 'GoogleDrive')
2821
2822 # Look for UDN embeds
2823 mobj = re.search(
2824 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2825 if mobj is not None:
2826 return self.url_result(
2827 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2828
2829 # Look for Senate ISVP iframe
2830 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2831 if senate_isvp_url:
2832 return self.url_result(senate_isvp_url, 'SenateISVP')
2833
2834 # Look for OnionStudios embeds
2835 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2836 if onionstudios_url:
2837 return self.url_result(onionstudios_url)
2838
2839 # Look for ViewLift embeds
2840 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2841 if viewlift_url:
2842 return self.url_result(viewlift_url)
2843
2844 # Look for JWPlatform embeds
2845 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2846 if jwplatform_urls:
2847 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2848
2849 # Look for Digiteka embeds
2850 digiteka_url = DigitekaIE._extract_url(webpage)
2851 if digiteka_url:
2852 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2853
2854 # Look for Arkena embeds
2855 arkena_url = ArkenaIE._extract_url(webpage)
2856 if arkena_url:
2857 return self.url_result(arkena_url, ArkenaIE.ie_key())
2858
2859 # Look for Piksel embeds
2860 piksel_url = PikselIE._extract_url(webpage)
2861 if piksel_url:
2862 return self.url_result(piksel_url, PikselIE.ie_key())
2863
2864 # Look for Limelight embeds
2865 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2866 if limelight_urls:
2867 return self.playlist_result(
2868 limelight_urls, video_id, video_title, video_description)
2869
2870 # Look for Anvato embeds
2871 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2872 if anvato_urls:
2873 return self.playlist_result(
2874 anvato_urls, video_id, video_title, video_description)
2875
2876 # Look for AdobeTVVideo embeds
2877 mobj = re.search(
2878 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2879 webpage)
2880 if mobj is not None:
2881 return self.url_result(
2882 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2883 'AdobeTVVideo')
2884
2885 # Look for Vine embeds
2886 mobj = re.search(
2887 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2888 webpage)
2889 if mobj is not None:
2890 return self.url_result(
2891 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2892
2893 # Look for VODPlatform embeds
2894 mobj = re.search(
2895 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2896 webpage)
2897 if mobj is not None:
2898 return self.url_result(
2899 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2900
2901 # Look for Mangomolo embeds
2902 mobj = re.search(
2903 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2904 (?:
2905 video\?.*?\bid=(?P<video_id>\d+)|
2906 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2907 ).+?)\1''', webpage)
2908 if mobj is not None:
2909 info = {
2910 '_type': 'url_transparent',
2911 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2912 'title': video_title,
2913 'description': video_description,
2914 'thumbnail': video_thumbnail,
2915 'uploader': video_uploader,
2916 }
2917 video_id = mobj.group('video_id')
2918 if video_id:
2919 info.update({
2920 'ie_key': 'MangomoloVideo',
2921 'id': video_id,
2922 })
2923 else:
2924 info.update({
2925 'ie_key': 'MangomoloLive',
2926 'id': mobj.group('channel_id'),
2927 })
2928 return info
2929
2930 # Look for Instagram embeds
2931 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2932 if instagram_embed_url is not None:
2933 return self.url_result(
2934 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2935
2936 # Look for LiveLeak embeds
2937 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2938 if liveleak_urls:
2939 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2940
2941 # Look for 3Q SDN embeds
2942 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2943 if threeqsdn_url:
2944 return {
2945 '_type': 'url_transparent',
2946 'ie_key': ThreeQSDNIE.ie_key(),
2947 'url': self._proto_relative_url(threeqsdn_url),
2948 'title': video_title,
2949 'description': video_description,
2950 'thumbnail': video_thumbnail,
2951 'uploader': video_uploader,
2952 }
2953
2954 # Look for VBOX7 embeds
2955 vbox7_url = Vbox7IE._extract_url(webpage)
2956 if vbox7_url:
2957 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2958
2959 # Look for DBTV embeds
2960 dbtv_urls = DBTVIE._extract_urls(webpage)
2961 if dbtv_urls:
2962 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2963
2964 # Look for Videa embeds
2965 videa_urls = VideaIE._extract_urls(webpage)
2966 if videa_urls:
2967 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2968
2969 # Look for 20 minuten embeds
2970 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2971 if twentymin_urls:
2972 return self.playlist_from_matches(
2973 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2974
2975 # Look for Openload embeds
2976 openload_urls = OpenloadIE._extract_urls(webpage)
2977 if openload_urls:
2978 return self.playlist_from_matches(
2979 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2980
2981 # Look for VideoPress embeds
2982 videopress_urls = VideoPressIE._extract_urls(webpage)
2983 if videopress_urls:
2984 return self.playlist_from_matches(
2985 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2986
2987 # Look for Rutube embeds
2988 rutube_urls = RutubeIE._extract_urls(webpage)
2989 if rutube_urls:
2990 return self.playlist_from_matches(
2991 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2992
2993 # Look for WashingtonPost embeds
2994 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2995 if wapo_urls:
2996 return self.playlist_from_matches(
2997 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2998
2999 # Look for Mediaset embeds
3000 mediaset_urls = MediasetIE._extract_urls(webpage)
3001 if mediaset_urls:
3002 return self.playlist_from_matches(
3003 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3004
3005 # Look for JOJ.sk embeds
3006 joj_urls = JojIE._extract_urls(webpage)
3007 if joj_urls:
3008 return self.playlist_from_matches(
3009 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3010
3011 # Look for megaphone.fm embeds
3012 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3013 if mpfn_urls:
3014 return self.playlist_from_matches(
3015 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3016
3017 # Look for vzaar embeds
3018 vzaar_urls = VzaarIE._extract_urls(webpage)
3019 if vzaar_urls:
3020 return self.playlist_from_matches(
3021 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3022
3023 channel9_urls = Channel9IE._extract_urls(webpage)
3024 if channel9_urls:
3025 return self.playlist_from_matches(
3026 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3027
3028 vshare_urls = VShareIE._extract_urls(webpage)
3029 if vshare_urls:
3030 return self.playlist_from_matches(
3031 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3032
3033 # Look for Mediasite embeds
3034 mediasite_urls = MediasiteIE._extract_urls(webpage)
3035 if mediasite_urls:
3036 entries = [
3037 self.url_result(smuggle_url(
3038 compat_urlparse.urljoin(url, mediasite_url),
3039 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3040 for mediasite_url in mediasite_urls]
3041 return self.playlist_result(entries, video_id, video_title)
3042
3043 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3044 if springboardplatform_urls:
3045 return self.playlist_from_matches(
3046 springboardplatform_urls, video_id, video_title,
3047 ie=SpringboardPlatformIE.ie_key())
3048
3049 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3050 if yapfiles_urls:
3051 return self.playlist_from_matches(
3052 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3053
3054 vice_urls = ViceIE._extract_urls(webpage)
3055 if vice_urls:
3056 return self.playlist_from_matches(
3057 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3058
3059 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3060 if xfileshare_urls:
3061 return self.playlist_from_matches(
3062 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3063
3064 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3065 if cloudflarestream_urls:
3066 return self.playlist_from_matches(
3067 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3068
3069 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3070 if peertube_urls:
3071 return self.playlist_from_matches(
3072 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3073
3074 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3075 if indavideo_urls:
3076 return self.playlist_from_matches(
3077 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3078
3079 apa_urls = APAIE._extract_urls(webpage)
3080 if apa_urls:
3081 return self.playlist_from_matches(
3082 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3083
3084 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3085 if foxnews_urls:
3086 return self.playlist_from_matches(
3087 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3088
3089 sharevideos_urls = [mobj.group('url') for mobj in re.finditer(
3090 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3091 webpage)]
3092 if sharevideos_urls:
3093 return self.playlist_from_matches(
3094 sharevideos_urls, video_id, video_title)
3095
3096 # Look for HTML5 media
3097 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3098 if entries:
3099 if len(entries) == 1:
3100 entries[0].update({
3101 'id': video_id,
3102 'title': video_title,
3103 })
3104 else:
3105 for num, entry in enumerate(entries, start=1):
3106 entry.update({
3107 'id': '%s-%s' % (video_id, num),
3108 'title': '%s (%d)' % (video_title, num),
3109 })
3110 for entry in entries:
3111 self._sort_formats(entry['formats'])
3112 return self.playlist_result(entries, video_id, video_title)
3113
3114 jwplayer_data = self._find_jwplayer_data(
3115 webpage, video_id, transform_source=js_to_json)
3116 if jwplayer_data:
3117 info = self._parse_jwplayer_data(
3118 jwplayer_data, video_id, require_title=False, base_url=url)
3119 return merge_dicts(info, info_dict)
3120
3121 # Video.js embed
3122 mobj = re.search(
3123 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3124 webpage)
3125 if mobj is not None:
3126 sources = self._parse_json(
3127 mobj.group(1), video_id, transform_source=js_to_json,
3128 fatal=False) or []
3129 if not isinstance(sources, list):
3130 sources = [sources]
3131 formats = []
3132 for source in sources:
3133 src = source.get('src')
3134 if not src or not isinstance(src, compat_str):
3135 continue
3136 src = compat_urlparse.urljoin(url, src)
3137 src_type = source.get('type')
3138 if isinstance(src_type, compat_str):
3139 src_type = src_type.lower()
3140 ext = determine_ext(src).lower()
3141 if src_type == 'video/youtube':
3142 return self.url_result(src, YoutubeIE.ie_key())
3143 if src_type == 'application/dash+xml' or ext == 'mpd':
3144 formats.extend(self._extract_mpd_formats(
3145 src, video_id, mpd_id='dash', fatal=False))
3146 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3147 formats.extend(self._extract_m3u8_formats(
3148 src, video_id, 'mp4', entry_protocol='m3u8_native',
3149 m3u8_id='hls', fatal=False))
3150 else:
3151 formats.append({
3152 'url': src,
3153 'ext': (mimetype2ext(src_type) or
3154 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3155 })
3156 if formats:
3157 self._sort_formats(formats)
3158 info_dict['formats'] = formats
3159 return info_dict
3160
3161 # Looking for http://schema.org/VideoObject
3162 json_ld = self._search_json_ld(
3163 webpage, video_id, default={}, expected_type='VideoObject')
3164 if json_ld.get('url'):
3165 return merge_dicts(json_ld, info_dict)
3166
3167 def check_video(vurl):
3168 if YoutubeIE.suitable(vurl):
3169 return True
3170 if RtmpIE.suitable(vurl):
3171 return True
3172 vpath = compat_urlparse.urlparse(vurl).path
3173 vext = determine_ext(vpath)
3174 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3175
3176 def filter_video(urls):
3177 return list(filter(check_video, urls))
3178
3179 # Start with something easy: JW Player in SWFObject
3180 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3181 if not found:
3182 # Look for gorilla-vid style embedding
3183 found = filter_video(re.findall(r'''(?sx)
3184 (?:
3185 jw_plugins|
3186 JWPlayerOptions|
3187 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3188 )
3189 .*?
3190 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3191 if not found:
3192 # Broaden the search a little bit
3193 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3194 if not found:
3195 # Broaden the findall a little bit: JWPlayer JS loader
3196 found = filter_video(re.findall(
3197 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3198 if not found:
3199 # Flow player
3200 found = filter_video(re.findall(r'''(?xs)
3201 flowplayer\("[^"]+",\s*
3202 \{[^}]+?\}\s*,
3203 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3204 ["']?url["']?\s*:\s*["']([^"']+)["']
3205 ''', webpage))
3206 if not found:
3207 # Cinerama player
3208 found = re.findall(
3209 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3210 if not found:
3211 # Try to find twitter cards info
3212 # twitter:player:stream should be checked before twitter:player since
3213 # it is expected to contain a raw stream (see
3214 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3215 found = filter_video(re.findall(
3216 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3217 if not found:
3218 # We look for Open Graph info:
3219 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3220 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3221 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3222 if m_video_type is not None:
3223 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3224 if not found:
3225 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3226 found = re.search(
3227 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3228 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3229 webpage)
3230 if not found:
3231 # Look also in Refresh HTTP header
3232 refresh_header = head_response.headers.get('Refresh')
3233 if refresh_header:
3234 # In python 2 response HTTP headers are bytestrings
3235 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3236 refresh_header = refresh_header.decode('iso-8859-1')
3237 found = re.search(REDIRECT_REGEX, refresh_header)
3238 if found:
3239 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3240 if new_url != url:
3241 self.report_following_redirect(new_url)
3242 return {
3243 '_type': 'url',
3244 'url': new_url,
3245 }
3246 else:
3247 found = None
3248
3249 if not found:
3250 # twitter:player is a https URL to iframe player that may or may not
3251 # be supported by youtube-dl thus this is checked the very last (see
3252 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3253 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3254 if embed_url and embed_url != url:
3255 return self.url_result(embed_url)
3256
3257 if not found:
3258 raise UnsupportedError(url)
3259
3260 entries = []
3261 for video_url in orderedSet(found):
3262 video_url = unescapeHTML(video_url)
3263 video_url = video_url.replace('\\/', '/')
3264 video_url = compat_urlparse.urljoin(url, video_url)
3265 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3266
3267 # Sometimes, jwplayer extraction will result in a YouTube URL
3268 if YoutubeIE.suitable(video_url):
3269 entries.append(self.url_result(video_url, 'Youtube'))
3270 continue
3271
3272 # here's a fun little line of code for you:
3273 video_id = os.path.splitext(video_id)[0]
3274
3275 entry_info_dict = {
3276 'id': video_id,
3277 'uploader': video_uploader,
3278 'title': video_title,
3279 'age_limit': age_limit,
3280 }
3281
3282 if RtmpIE.suitable(video_url):
3283 entry_info_dict.update({
3284 '_type': 'url_transparent',
3285 'ie_key': RtmpIE.ie_key(),
3286 'url': video_url,
3287 })
3288 entries.append(entry_info_dict)
3289 continue
3290
3291 ext = determine_ext(video_url)
3292 if ext == 'smil':
3293 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3294 elif ext == 'xspf':
3295 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3296 elif ext == 'm3u8':
3297 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3298 elif ext == 'mpd':
3299 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3300 elif ext == 'f4m':
3301 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3302 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3303 # Just matching .ism/manifest is not enough to be reliably sure
3304 # whether it's actually an ISM manifest or some other streaming
3305 # manifest since there are various streaming URL formats
3306 # possible (see [1]) as well as some other shenanigans like
3307 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3308 # so on.
3309 # Thus the most reasonable way to solve this is to delegate
3310 # to generic extractor in order to look into the contents of
3311 # the manifest itself.
3312 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3313 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3314 entry_info_dict = self.url_result(
3315 smuggle_url(video_url, {'to_generic': True}),
3316 GenericIE.ie_key())
3317 else:
3318 entry_info_dict['url'] = video_url
3319
3320 if entry_info_dict.get('formats'):
3321 self._sort_formats(entry_info_dict['formats'])
3322
3323 entries.append(entry_info_dict)
3324
3325 if len(entries) == 1:
3326 return entries[0]
3327 else:
3328 for num, e in enumerate(entries, start=1):
3329 # 'url' results don't have a title
3330 if e.get('title') is not None:
3331 e['title'] = '%s (%d)' % (e['title'], num)
3332 return {
3333 '_type': 'playlist',
3334 'entries': entries,
3335 }