]> jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/generic.py
[generic] Add test for Senate ISVP iframe embed
[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_urllib_parse_unquote,
14 compat_urlparse,
15 compat_xml_parse_error,
16 )
17 from ..utils import (
18 determine_ext,
19 ExtractorError,
20 float_or_none,
21 HEADRequest,
22 is_html,
23 js_to_json,
24 orderedSet,
25 sanitized_Request,
26 smuggle_url,
27 unescapeHTML,
28 unified_strdate,
29 unsmuggle_url,
30 UnsupportedError,
31 xpath_text,
32 )
33 from .commonprotocols import RtmpIE
34 from .brightcove import (
35 BrightcoveLegacyIE,
36 BrightcoveNewIE,
37 )
38 from .nbc import NBCSportsVPlayerIE
39 from .ooyala import OoyalaIE
40 from .rutv import RUTVIE
41 from .tvc import TVCIE
42 from .sportbox import SportBoxEmbedIE
43 from .smotri import SmotriIE
44 from .myvi import MyviIE
45 from .condenast import CondeNastIE
46 from .udn import UDNEmbedIE
47 from .senateisvp import SenateISVPIE
48 from .svt import SVTIE
49 from .pornhub import PornHubIE
50 from .xhamster import XHamsterEmbedIE
51 from .tnaflix import TNAFlixNetworkEmbedIE
52 from .drtuber import DrTuberIE
53 from .redtube import RedTubeIE
54 from .vimeo import VimeoIE
55 from .dailymotion import (
56 DailymotionIE,
57 DailymotionCloudIE,
58 )
59 from .onionstudios import OnionStudiosIE
60 from .viewlift import ViewLiftEmbedIE
61 from .mtv import MTVServicesEmbeddedIE
62 from .pladform import PladformIE
63 from .videomore import VideomoreIE
64 from .webcaster import WebcasterFeedIE
65 from .googledrive import GoogleDriveIE
66 from .jwplatform import JWPlatformIE
67 from .digiteka import DigitekaIE
68 from .arkena import ArkenaIE
69 from .instagram import InstagramIE
70 from .liveleak import LiveLeakIE
71 from .threeqsdn import ThreeQSDNIE
72 from .theplatform import ThePlatformIE
73 from .vessel import VesselIE
74 from .kaltura import KalturaIE
75 from .eagleplatform import EaglePlatformIE
76 from .facebook import FacebookIE
77 from .soundcloud import SoundcloudIE
78 from .tunein import TuneInBaseIE
79 from .vbox7 import Vbox7IE
80 from .dbtv import DBTVIE
81 from .piksel import PikselIE
82 from .videa import VideaIE
83 from .twentymin import TwentyMinutenIE
84 from .ustream import UstreamIE
85 from .openload import OpenloadIE
86 from .videopress import VideoPressIE
87 from .rutube import RutubeIE
88
89
90 class GenericIE(InfoExtractor):
91 IE_DESC = 'Generic downloader that works on some sites'
92 _VALID_URL = r'.*'
93 IE_NAME = 'generic'
94 _TESTS = [
95 # Direct link to a video
96 {
97 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
98 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
99 'info_dict': {
100 'id': 'trailer',
101 'ext': 'mp4',
102 'title': 'trailer',
103 'upload_date': '20100513',
104 }
105 },
106 # Direct link to media delivered compressed (until Accept-Encoding is *)
107 {
108 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
109 'md5': '128c42e68b13950268b648275386fc74',
110 'info_dict': {
111 'id': 'FictionJunction-Parallel_Hearts',
112 'ext': 'flac',
113 'title': 'FictionJunction-Parallel_Hearts',
114 'upload_date': '20140522',
115 },
116 'expected_warnings': [
117 'URL could be a direct video link, returning it as such.'
118 ],
119 'skip': 'URL invalid',
120 },
121 # Direct download with broken HEAD
122 {
123 'url': 'http://ai-radio.org:8000/radio.opus',
124 'info_dict': {
125 'id': 'radio',
126 'ext': 'opus',
127 'title': 'radio',
128 },
129 'params': {
130 'skip_download': True, # infinite live stream
131 },
132 'expected_warnings': [
133 r'501.*Not Implemented',
134 r'400.*Bad Request',
135 ],
136 },
137 # Direct link with incorrect MIME type
138 {
139 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
140 'md5': '4ccbebe5f36706d85221f204d7eb5913',
141 'info_dict': {
142 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
143 'id': '5_Lennart_Poettering_-_Systemd',
144 'ext': 'webm',
145 'title': '5_Lennart_Poettering_-_Systemd',
146 'upload_date': '20141120',
147 },
148 'expected_warnings': [
149 'URL could be a direct video link, returning it as such.'
150 ]
151 },
152 # RSS feed
153 {
154 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
155 'info_dict': {
156 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
157 'title': 'Zero Punctuation',
158 'description': 're:.*groundbreaking video review series.*'
159 },
160 'playlist_mincount': 11,
161 },
162 # RSS feed with enclosure
163 {
164 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
165 'info_dict': {
166 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
167 'ext': 'm4v',
168 'upload_date': '20150228',
169 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
170 }
171 },
172 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
173 {
174 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
175 'info_dict': {
176 'id': 'smil',
177 'ext': 'mp4',
178 'title': 'Automatics, robotics and biocybernetics',
179 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
180 'upload_date': '20130627',
181 'formats': 'mincount:16',
182 'subtitles': 'mincount:1',
183 },
184 'params': {
185 'force_generic_extractor': True,
186 'skip_download': True,
187 },
188 },
189 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
190 {
191 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
192 'info_dict': {
193 'id': 'hds',
194 'ext': 'flv',
195 'title': 'hds',
196 'formats': 'mincount:1',
197 },
198 'params': {
199 'skip_download': True,
200 },
201 },
202 # SMIL from https://www.restudy.dk/video/play/id/1637
203 {
204 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
205 'info_dict': {
206 'id': 'video_1637',
207 'ext': 'flv',
208 'title': 'video_1637',
209 'formats': 'mincount:3',
210 },
211 'params': {
212 'skip_download': True,
213 },
214 },
215 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
216 {
217 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
218 'info_dict': {
219 'id': 'smil-service',
220 'ext': 'flv',
221 'title': 'smil-service',
222 'formats': 'mincount:1',
223 },
224 'params': {
225 'skip_download': True,
226 },
227 },
228 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
229 {
230 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
231 'info_dict': {
232 'id': '4719370',
233 'ext': 'mp4',
234 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
235 'formats': 'mincount:3',
236 },
237 'params': {
238 'skip_download': True,
239 },
240 },
241 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
242 {
243 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
244 'info_dict': {
245 'id': 'mZlp2ctYIUEB',
246 'ext': 'mp4',
247 'title': 'Tikibad ontruimd wegens brand',
248 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
249 'thumbnail': r're:^https?://.*\.jpg$',
250 'duration': 33,
251 },
252 'params': {
253 'skip_download': True,
254 },
255 },
256 # MPD from http://dash-mse-test.appspot.com/media.html
257 {
258 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
259 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
260 'info_dict': {
261 'id': 'car-20120827-manifest',
262 'ext': 'mp4',
263 'title': 'car-20120827-manifest',
264 'formats': 'mincount:9',
265 'upload_date': '20130904',
266 },
267 'params': {
268 'format': 'bestvideo',
269 },
270 },
271 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
272 {
273 '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',
274 'info_dict': {
275 'id': 'content',
276 'ext': 'mp4',
277 'title': 'content',
278 'formats': 'mincount:8',
279 },
280 'params': {
281 # m3u8 downloads
282 'skip_download': True,
283 },
284 'skip': 'video gone',
285 },
286 # m3u8 served with Content-Type: text/plain
287 {
288 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
289 'info_dict': {
290 'id': 'index',
291 'ext': 'mp4',
292 'title': 'index',
293 'upload_date': '20140720',
294 'formats': 'mincount:11',
295 },
296 'params': {
297 # m3u8 downloads
298 'skip_download': True,
299 },
300 'skip': 'video gone',
301 },
302 # google redirect
303 {
304 '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',
305 'info_dict': {
306 'id': 'cmQHVoWB5FY',
307 'ext': 'mp4',
308 'upload_date': '20130224',
309 'uploader_id': 'TheVerge',
310 'description': r're:^Chris Ziegler takes a look at the\.*',
311 'uploader': 'The Verge',
312 'title': 'First Firefox OS phones side-by-side',
313 },
314 'params': {
315 'skip_download': False,
316 }
317 },
318 {
319 # redirect in Refresh HTTP header
320 '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',
321 'info_dict': {
322 'id': 'pO8h3EaFRdo',
323 'ext': 'mp4',
324 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
325 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
326 'upload_date': '20150917',
327 'uploader_id': 'brtvofficial',
328 'uploader': 'Boiler Room',
329 },
330 'params': {
331 'skip_download': False,
332 },
333 },
334 {
335 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
336 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
337 'info_dict': {
338 'id': '13601338388002',
339 'ext': 'mp4',
340 'uploader': 'www.hodiho.fr',
341 'title': 'R\u00e9gis plante sa Jeep',
342 }
343 },
344 # bandcamp page with custom domain
345 {
346 'add_ie': ['Bandcamp'],
347 'url': 'http://bronyrock.com/track/the-pony-mash',
348 'info_dict': {
349 'id': '3235767654',
350 'ext': 'mp3',
351 'title': 'The Pony Mash',
352 'uploader': 'M_Pallante',
353 },
354 'skip': 'There is a limit of 200 free downloads / month for the test song',
355 },
356 {
357 # embedded brightcove video
358 # it also tests brightcove videos that need to set the 'Referer'
359 # in the http requests
360 'add_ie': ['BrightcoveLegacy'],
361 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
362 'info_dict': {
363 'id': '2765128793001',
364 'ext': 'mp4',
365 'title': 'Le cours de bourse : l’analyse technique',
366 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
367 'uploader': 'BFM BUSINESS',
368 },
369 'params': {
370 'skip_download': True,
371 },
372 },
373 {
374 # embedded with itemprop embedURL and video id spelled as `idVideo`
375 'add_id': ['BrightcoveLegacy'],
376 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
377 'info_dict': {
378 'id': '5255628253001',
379 'ext': 'mp4',
380 'title': 'md5:37c519b1128915607601e75a87995fc0',
381 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
382 'uploader': 'BFM BUSINESS',
383 'uploader_id': '876450612001',
384 'timestamp': 1482255315,
385 'upload_date': '20161220',
386 },
387 'params': {
388 'skip_download': True,
389 },
390 },
391 {
392 # https://github.com/rg3/youtube-dl/issues/2253
393 'url': 'http://bcove.me/i6nfkrc3',
394 'md5': '0ba9446db037002366bab3b3eb30c88c',
395 'info_dict': {
396 'id': '3101154703001',
397 'ext': 'mp4',
398 'title': 'Still no power',
399 'uploader': 'thestar.com',
400 '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.',
401 },
402 'add_ie': ['BrightcoveLegacy'],
403 'skip': 'video gone',
404 },
405 {
406 'url': 'http://www.championat.com/video/football/v/87/87499.html',
407 'md5': 'fb973ecf6e4a78a67453647444222983',
408 'info_dict': {
409 'id': '3414141473001',
410 'ext': 'mp4',
411 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
412 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
413 'uploader': 'Championat',
414 },
415 },
416 {
417 # https://github.com/rg3/youtube-dl/issues/3541
418 'add_ie': ['BrightcoveLegacy'],
419 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
420 'info_dict': {
421 'id': '3866516442001',
422 'ext': 'mp4',
423 'title': 'Leer mij vrouwen kennen: Aflevering 1',
424 'description': 'Leer mij vrouwen kennen: Aflevering 1',
425 'uploader': 'SBS Broadcasting',
426 },
427 'skip': 'Restricted to Netherlands',
428 'params': {
429 'skip_download': True, # m3u8 download
430 },
431 },
432 {
433 # Brightcove with alternative playerID key
434 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
435 'info_dict': {
436 'id': 'nmeth.2062_SV1',
437 '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',
438 },
439 'playlist': [{
440 'info_dict': {
441 'id': '2228375078001',
442 'ext': 'mp4',
443 'title': 'nmeth.2062-sv1',
444 'description': 'nmeth.2062-sv1',
445 'timestamp': 1363357591,
446 'upload_date': '20130315',
447 'uploader': 'Nature Publishing Group',
448 'uploader_id': '1964492299001',
449 },
450 }],
451 },
452 {
453 # Brightcove with UUID in videoPlayer
454 'url': 'http://www8.hp.com/cn/zh/home.html',
455 'info_dict': {
456 'id': '5255815316001',
457 'ext': 'mp4',
458 'title': 'Sprocket Video - China',
459 'description': 'Sprocket Video - China',
460 'uploader': 'HP-Video Gallery',
461 'timestamp': 1482263210,
462 'upload_date': '20161220',
463 'uploader_id': '1107601872001',
464 },
465 'params': {
466 'skip_download': True, # m3u8 download
467 },
468 },
469 # ooyala video
470 {
471 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
472 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
473 'info_dict': {
474 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
475 'ext': 'mp4',
476 'title': '2cc213299525360.mov', # that's what we get
477 'duration': 238.231,
478 },
479 'add_ie': ['Ooyala'],
480 },
481 {
482 # ooyala video embedded with http://player.ooyala.com/iframe.js
483 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
484 'info_dict': {
485 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
486 'ext': 'mp4',
487 'title': '"Steve Jobs: Man in the Machine" trailer',
488 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
489 'duration': 135.427,
490 },
491 'params': {
492 'skip_download': True,
493 },
494 'skip': 'movie expired',
495 },
496 # embed.ly video
497 {
498 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
499 'info_dict': {
500 'id': '9ODmcdjQcHQ',
501 'ext': 'mp4',
502 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
503 'upload_date': '20140225',
504 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
505 'uploader': 'Tested',
506 'uploader_id': 'testedcom',
507 },
508 # No need to test YoutubeIE here
509 'params': {
510 'skip_download': True,
511 },
512 },
513 # funnyordie embed
514 {
515 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
516 'info_dict': {
517 'id': '18e820ec3f',
518 'ext': 'mp4',
519 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
520 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
521 },
522 # HEAD requests lead to endless 301, while GET is OK
523 'expected_warnings': ['301'],
524 },
525 # RUTV embed
526 {
527 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
528 'info_dict': {
529 'id': '776940',
530 'ext': 'mp4',
531 'title': 'Охотское море стало целиком российским',
532 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
533 },
534 'params': {
535 # m3u8 download
536 'skip_download': True,
537 },
538 },
539 # TVC embed
540 {
541 '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/',
542 'info_dict': {
543 'id': '55304',
544 'ext': 'mp4',
545 'title': 'Дошкольное воспитание',
546 },
547 },
548 # SportBox embed
549 {
550 'url': 'http://www.vestifinance.ru/articles/25753',
551 'info_dict': {
552 'id': '25753',
553 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
554 },
555 'playlist': [{
556 'info_dict': {
557 'id': '370908',
558 'title': 'Госзаказ. День 3',
559 'ext': 'mp4',
560 }
561 }, {
562 'info_dict': {
563 'id': '370905',
564 'title': 'Госзаказ. День 2',
565 'ext': 'mp4',
566 }
567 }, {
568 'info_dict': {
569 'id': '370902',
570 'title': 'Госзаказ. День 1',
571 'ext': 'mp4',
572 }
573 }],
574 'params': {
575 # m3u8 download
576 'skip_download': True,
577 },
578 },
579 # Myvi.ru embed
580 {
581 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
582 'info_dict': {
583 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
584 'ext': 'mp4',
585 'title': 'Ужастики, русский трейлер (2015)',
586 'thumbnail': r're:^https?://.*\.jpg$',
587 'duration': 153,
588 }
589 },
590 # XHamster embed
591 {
592 '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',
593 'info_dict': {
594 'id': 'showthread',
595 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
596 },
597 'playlist_mincount': 7,
598 # This forum does not allow <iframe> syntaxes anymore
599 # Now HTML tags are displayed as-is
600 'skip': 'No videos on this page',
601 },
602 # Embedded TED video
603 {
604 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
605 'md5': '65fdff94098e4a607385a60c5177c638',
606 'info_dict': {
607 'id': '1969',
608 'ext': 'mp4',
609 'title': 'Hidden miracles of the natural world',
610 'uploader': 'Louie Schwartzberg',
611 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
612 }
613 },
614 # nowvideo embed hidden behind percent encoding
615 {
616 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
617 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
618 'info_dict': {
619 'id': '06e53103ca9aa',
620 'ext': 'flv',
621 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
622 'description': 'No description',
623 },
624 },
625 # arte embed
626 {
627 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
628 'md5': '7653032cbb25bf6c80d80f217055fa43',
629 'info_dict': {
630 'id': '048195-004_PLUS7-F',
631 'ext': 'flv',
632 'title': 'X:enius',
633 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
634 'upload_date': '20140320',
635 },
636 'params': {
637 'skip_download': 'Requires rtmpdump'
638 },
639 'skip': 'video gone',
640 },
641 # francetv embed
642 {
643 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
644 'info_dict': {
645 'id': 'EV_30231',
646 'ext': 'mp4',
647 'title': 'Alcaline, le concert avec Calogero',
648 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
649 'upload_date': '20150226',
650 'timestamp': 1424989860,
651 'duration': 5400,
652 },
653 'params': {
654 # m3u8 downloads
655 'skip_download': True,
656 },
657 'expected_warnings': [
658 'Forbidden'
659 ]
660 },
661 # Condé Nast embed
662 {
663 'url': 'http://www.wired.com/2014/04/honda-asimo/',
664 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
665 'info_dict': {
666 'id': '53501be369702d3275860000',
667 'ext': 'mp4',
668 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
669 }
670 },
671 # Dailymotion embed
672 {
673 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
674 'md5': '441aeeb82eb72c422c7f14ec533999cd',
675 'info_dict': {
676 'id': 'k2mm4bCdJ6CQ2i7c8o2',
677 'ext': 'mp4',
678 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
679 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
680 'uploader': 'Spi0n',
681 'uploader_id': 'xgditw',
682 'upload_date': '20140425',
683 'timestamp': 1398441542,
684 },
685 'add_ie': ['Dailymotion'],
686 },
687 # YouTube embed
688 {
689 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
690 'info_dict': {
691 'id': 'FXRb4ykk4S0',
692 'ext': 'mp4',
693 'title': 'The NBL Auction 2014',
694 'uploader': 'BADMINTON England',
695 'uploader_id': 'BADMINTONEvents',
696 'upload_date': '20140603',
697 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
698 },
699 'add_ie': ['Youtube'],
700 'params': {
701 'skip_download': True,
702 }
703 },
704 # MTVSercices embed
705 {
706 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
707 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
708 'info_dict': {
709 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
710 'ext': 'mp4',
711 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
712 'description': 'Two valets share their love for movie star Liam Neesons.',
713 'timestamp': 1349922600,
714 'upload_date': '20121011',
715 },
716 },
717 # YouTube embed via <data-embed-url="">
718 {
719 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
720 'info_dict': {
721 'id': '4vAffPZIT44',
722 'ext': 'mp4',
723 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
724 'uploader': 'Gameloft',
725 'uploader_id': 'gameloft',
726 'upload_date': '20140828',
727 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
728 },
729 'params': {
730 'skip_download': True,
731 }
732 },
733 # Camtasia studio
734 {
735 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
736 'playlist': [{
737 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
738 'info_dict': {
739 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
740 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
741 'ext': 'flv',
742 'duration': 2235.90,
743 }
744 }, {
745 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
746 'info_dict': {
747 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
748 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
749 'ext': 'flv',
750 'duration': 2235.93,
751 }
752 }],
753 'info_dict': {
754 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
755 }
756 },
757 # Flowplayer
758 {
759 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
760 'md5': '9d65602bf31c6e20014319c7d07fba27',
761 'info_dict': {
762 'id': '5123ea6d5e5a7',
763 'ext': 'mp4',
764 'age_limit': 18,
765 'uploader': 'www.handjobhub.com',
766 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
767 }
768 },
769 # Multiple brightcove videos
770 # https://github.com/rg3/youtube-dl/issues/2283
771 {
772 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
773 'info_dict': {
774 'id': 'always-never',
775 'title': 'Always / Never - The New Yorker',
776 },
777 'playlist_count': 3,
778 'params': {
779 'extract_flat': False,
780 'skip_download': True,
781 }
782 },
783 # MLB embed
784 {
785 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
786 'md5': '96f09a37e44da40dd083e12d9a683327',
787 'info_dict': {
788 'id': '33322633',
789 'ext': 'mp4',
790 'title': 'Ump changes call to ball',
791 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
792 'duration': 48,
793 'timestamp': 1401537900,
794 'upload_date': '20140531',
795 'thumbnail': r're:^https?://.*\.jpg$',
796 },
797 },
798 # Wistia embed
799 {
800 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
801 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
802 'info_dict': {
803 'id': '6e2wtrbdaf',
804 'ext': 'mov',
805 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
806 'description': 'a Paywall Videos video from Remilon',
807 'duration': 644.072,
808 'uploader': 'study.com',
809 'timestamp': 1459678540,
810 'upload_date': '20160403',
811 'filesize': 24687186,
812 },
813 },
814 {
815 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
816 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
817 'info_dict': {
818 'id': 'uxjb0lwrcz',
819 'ext': 'mp4',
820 'title': 'Conversation about Hexagonal Rails Part 1',
821 'description': 'a Martin Fowler video from ThoughtWorks',
822 'duration': 1715.0,
823 'uploader': 'thoughtworks.wistia.com',
824 'timestamp': 1401832161,
825 'upload_date': '20140603',
826 },
827 },
828 # Wistia standard embed (async)
829 {
830 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
831 'info_dict': {
832 'id': '807fafadvk',
833 'ext': 'mp4',
834 'title': 'Drip Brennan Dunn Workshop',
835 'description': 'a JV Webinars video from getdrip-1',
836 'duration': 4986.95,
837 'timestamp': 1463607249,
838 'upload_date': '20160518',
839 },
840 'params': {
841 'skip_download': True,
842 }
843 },
844 # Soundcloud embed
845 {
846 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
847 'info_dict': {
848 'id': '174391317',
849 'ext': 'mp3',
850 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
851 'uploader': 'Sophos Security',
852 'title': 'Chet Chat 171 - Oct 29, 2014',
853 'upload_date': '20141029',
854 }
855 },
856 # Soundcloud multiple embeds
857 {
858 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
859 'info_dict': {
860 'id': '52809',
861 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
862 },
863 'playlist_mincount': 7,
864 },
865 # TuneIn station embed
866 {
867 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
868 'info_dict': {
869 'id': '204146',
870 'ext': 'mp3',
871 'title': 'CNRV',
872 'location': 'Paris, France',
873 'is_live': True,
874 },
875 'params': {
876 # Live stream
877 'skip_download': True,
878 },
879 },
880 # Livestream embed
881 {
882 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
883 'info_dict': {
884 'id': '67864563',
885 'ext': 'flv',
886 'upload_date': '20141112',
887 'title': 'Rosetta #CometLanding webcast HL 10',
888 }
889 },
890 # Another Livestream embed, without 'new.' in URL
891 {
892 'url': 'https://www.freespeech.org/',
893 'info_dict': {
894 'id': '123537347',
895 'ext': 'mp4',
896 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
897 },
898 'params': {
899 # Live stream
900 'skip_download': True,
901 },
902 },
903 # LazyYT
904 {
905 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
906 'info_dict': {
907 'id': '1986',
908 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
909 },
910 'playlist_mincount': 2,
911 },
912 # Cinchcast embed
913 {
914 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
915 'info_dict': {
916 'id': '7141703',
917 'ext': 'mp3',
918 'upload_date': '20141126',
919 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
920 }
921 },
922 # Cinerama player
923 {
924 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
925 'info_dict': {
926 'id': '730m_DandD_1901_512k',
927 'ext': 'mp4',
928 'uploader': 'www.abc.net.au',
929 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
930 }
931 },
932 # embedded viddler video
933 {
934 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
935 'info_dict': {
936 'id': '4d03aad9',
937 'ext': 'mp4',
938 'uploader': 'deadspin',
939 'title': 'WALL-TO-GORTAT',
940 'timestamp': 1422285291,
941 'upload_date': '20150126',
942 },
943 'add_ie': ['Viddler'],
944 },
945 # Libsyn embed
946 {
947 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
948 'info_dict': {
949 'id': '3377616',
950 'ext': 'mp3',
951 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
952 'description': 'md5:601cb790edd05908957dae8aaa866465',
953 'upload_date': '20150220',
954 },
955 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
956 },
957 # jwplayer YouTube
958 {
959 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
960 'info_dict': {
961 'id': 'Mrj4DVp2zeA',
962 'ext': 'mp4',
963 'upload_date': '20150212',
964 'uploader': 'The National Archives UK',
965 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
966 'uploader_id': 'NationalArchives08',
967 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
968 },
969 },
970 # jwplayer rtmp
971 {
972 'url': 'http://www.suffolk.edu/sjc/',
973 'info_dict': {
974 'id': 'sjclive',
975 'ext': 'flv',
976 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
977 'uploader': 'www.suffolk.edu',
978 },
979 'params': {
980 'skip_download': True,
981 }
982 },
983 # Complex jwplayer
984 {
985 'url': 'http://www.indiedb.com/games/king-machine/videos',
986 'info_dict': {
987 'id': 'videos',
988 'ext': 'mp4',
989 'title': 'king machine trailer 1',
990 'thumbnail': r're:^https?://.*\.jpg$',
991 },
992 },
993 # rtl.nl embed
994 {
995 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
996 'playlist_mincount': 5,
997 'info_dict': {
998 'id': 'aanslagen-kopenhagen',
999 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1000 }
1001 },
1002 # Zapiks embed
1003 {
1004 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1005 'info_dict': {
1006 'id': '118046',
1007 'ext': 'mp4',
1008 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1009 }
1010 },
1011 # Kaltura embed (different embed code)
1012 {
1013 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1014 'info_dict': {
1015 'id': '1_a52wc67y',
1016 'ext': 'flv',
1017 'upload_date': '20150127',
1018 'uploader_id': 'PremierMedia',
1019 'timestamp': int,
1020 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1021 },
1022 },
1023 # Kaltura embed with single quotes
1024 {
1025 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1026 'info_dict': {
1027 'id': '0_izeg5utt',
1028 'ext': 'mp4',
1029 'title': '35871',
1030 'timestamp': 1355743100,
1031 'upload_date': '20121217',
1032 'uploader_id': 'batchUser',
1033 },
1034 'add_ie': ['Kaltura'],
1035 },
1036 {
1037 # Kaltura embedded via quoted entry_id
1038 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1039 'info_dict': {
1040 'id': '0_utuok90b',
1041 'ext': 'mp4',
1042 'title': '06_matthew_brender_raj_dutt',
1043 'timestamp': 1466638791,
1044 'upload_date': '20160622',
1045 },
1046 'add_ie': ['Kaltura'],
1047 'expected_warnings': [
1048 'Could not send HEAD request'
1049 ],
1050 'params': {
1051 'skip_download': True,
1052 }
1053 },
1054 {
1055 # Kaltura embedded, some fileExt broken (#11480)
1056 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1057 'info_dict': {
1058 'id': '1_sgtvehim',
1059 'ext': 'mp4',
1060 'title': 'Our "Standard Models" of particle physics and cosmology',
1061 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1062 'timestamp': 1321158993,
1063 'upload_date': '20111113',
1064 'uploader_id': 'kps1',
1065 },
1066 'add_ie': ['Kaltura'],
1067 },
1068 # Eagle.Platform embed (generic URL)
1069 {
1070 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1071 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1072 'info_dict': {
1073 'id': '227304',
1074 'ext': 'mp4',
1075 'title': 'Навальный вышел на свободу',
1076 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1077 'thumbnail': r're:^https?://.*\.jpg$',
1078 'duration': 87,
1079 'view_count': int,
1080 'age_limit': 0,
1081 },
1082 },
1083 # ClipYou (Eagle.Platform) embed (custom URL)
1084 {
1085 'url': 'http://muz-tv.ru/play/7129/',
1086 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1087 'info_dict': {
1088 'id': '12820',
1089 'ext': 'mp4',
1090 'title': "'O Sole Mio",
1091 'thumbnail': r're:^https?://.*\.jpg$',
1092 'duration': 216,
1093 'view_count': int,
1094 },
1095 },
1096 # Pladform embed
1097 {
1098 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1099 'info_dict': {
1100 'id': '100183293',
1101 'ext': 'mp4',
1102 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1103 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1104 'thumbnail': r're:^https?://.*\.jpg$',
1105 'duration': 694,
1106 'age_limit': 0,
1107 },
1108 },
1109 # Playwire embed
1110 {
1111 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1112 'info_dict': {
1113 'id': '3519514',
1114 'ext': 'mp4',
1115 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1116 'thumbnail': r're:^https?://.*\.png$',
1117 'duration': 45.115,
1118 },
1119 },
1120 # 5min embed
1121 {
1122 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1123 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1124 'info_dict': {
1125 'id': '518726732',
1126 'ext': 'mp4',
1127 'title': 'Facebook Creates "On This Day" | Crunch Report',
1128 },
1129 },
1130 # SVT embed
1131 {
1132 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1133 'info_dict': {
1134 'id': '2900353',
1135 'ext': 'flv',
1136 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1137 'duration': 27,
1138 'age_limit': 0,
1139 },
1140 },
1141 # Crooks and Liars embed
1142 {
1143 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1144 'info_dict': {
1145 'id': '8RUoRhRi',
1146 'ext': 'mp4',
1147 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1148 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1149 'timestamp': 1428207000,
1150 'upload_date': '20150405',
1151 'uploader': 'Heather',
1152 },
1153 },
1154 # Crooks and Liars external embed
1155 {
1156 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1157 'info_dict': {
1158 'id': 'MTE3MjUtMzQ2MzA',
1159 'ext': 'mp4',
1160 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1161 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1162 'timestamp': 1265032391,
1163 'upload_date': '20100201',
1164 'uploader': 'Heather',
1165 },
1166 },
1167 # NBC Sports vplayer embed
1168 {
1169 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1170 'info_dict': {
1171 'id': 'ln7x1qSThw4k',
1172 'ext': 'flv',
1173 'title': "PFT Live: New leader in the 'new-look' defense",
1174 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1175 'uploader': 'NBCU-SPORTS',
1176 'upload_date': '20140107',
1177 'timestamp': 1389118457,
1178 },
1179 },
1180 # NBC News embed
1181 {
1182 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1183 'md5': '1aa589c675898ae6d37a17913cf68d66',
1184 'info_dict': {
1185 'id': '701714499682',
1186 'ext': 'mp4',
1187 'title': 'PREVIEW: On Assignment: David Letterman',
1188 '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.',
1189 },
1190 },
1191 # UDN embed
1192 {
1193 'url': 'https://video.udn.com/news/300346',
1194 'md5': 'fd2060e988c326991037b9aff9df21a6',
1195 'info_dict': {
1196 'id': '300346',
1197 'ext': 'mp4',
1198 'title': '中一中男師變性 全校師生力挺',
1199 'thumbnail': r're:^https?://.*\.jpg$',
1200 },
1201 'params': {
1202 # m3u8 download
1203 'skip_download': True,
1204 },
1205 },
1206 # Ooyala embed
1207 {
1208 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1209 'info_dict': {
1210 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1211 'ext': 'mp4',
1212 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1213 'title': 'This is what separates the Excel masters from the wannabes',
1214 'duration': 191.933,
1215 },
1216 'params': {
1217 # m3u8 downloads
1218 'skip_download': True,
1219 }
1220 },
1221 # Brightcove URL in single quotes
1222 {
1223 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1224 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1225 'info_dict': {
1226 'id': '4255764656001',
1227 'ext': 'mp4',
1228 'title': 'SN Presents: Russell Martin, World Citizen',
1229 '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.',
1230 'uploader': 'Rogers Sportsnet',
1231 'uploader_id': '1704050871',
1232 'upload_date': '20150525',
1233 'timestamp': 1432570283,
1234 },
1235 },
1236 # Dailymotion Cloud video
1237 {
1238 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1239 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1240 'info_dict': {
1241 'id': 'x2uy8t3',
1242 'ext': 'mp4',
1243 'title': 'Sauvons les abeilles ! - Le débat',
1244 'description': 'md5:d9082128b1c5277987825d684939ca26',
1245 'thumbnail': r're:^https?://.*\.jpe?g$',
1246 'timestamp': 1434970506,
1247 'upload_date': '20150622',
1248 'uploader': 'Public Sénat',
1249 'uploader_id': 'xa9gza',
1250 }
1251 },
1252 # OnionStudios embed
1253 {
1254 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1255 'info_dict': {
1256 'id': '2855',
1257 'ext': 'mp4',
1258 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1259 'thumbnail': r're:^https?://.*\.jpe?g$',
1260 'uploader': 'ClickHole',
1261 'uploader_id': 'clickhole',
1262 }
1263 },
1264 # SnagFilms embed
1265 {
1266 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1267 'info_dict': {
1268 'id': '74849a00-85a9-11e1-9660-123139220831',
1269 'ext': 'mp4',
1270 'title': '#whilewewatch',
1271 }
1272 },
1273 # AdobeTVVideo embed
1274 {
1275 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1276 'md5': '43662b577c018ad707a63766462b1e87',
1277 'info_dict': {
1278 'id': '2456',
1279 'ext': 'mp4',
1280 'title': 'New experience with Acrobat DC',
1281 'description': 'New experience with Acrobat DC',
1282 'duration': 248.667,
1283 },
1284 },
1285 # BrightcoveInPageEmbed embed
1286 {
1287 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1288 'info_dict': {
1289 'id': '4238694884001',
1290 'ext': 'flv',
1291 'title': 'Tabletop: Dread, Last Thoughts',
1292 'description': 'Tabletop: Dread, Last Thoughts',
1293 'duration': 51690,
1294 },
1295 },
1296 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1297 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1298 {
1299 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1300 'info_dict': {
1301 'id': '4785848093001',
1302 'ext': 'mp4',
1303 'title': 'The Cardinal Pell Interview',
1304 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1305 'uploader': 'GlobeCast Australia - GlobeStream',
1306 'uploader_id': '2733773828001',
1307 'upload_date': '20160304',
1308 'timestamp': 1457083087,
1309 },
1310 'params': {
1311 # m3u8 downloads
1312 'skip_download': True,
1313 },
1314 },
1315 # Another form of arte.tv embed
1316 {
1317 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1318 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1319 'info_dict': {
1320 'id': '030273-562_PLUS7-F',
1321 'ext': 'mp4',
1322 'title': 'ARTE Reportage - Nulle part, en France',
1323 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1324 'upload_date': '20160409',
1325 },
1326 },
1327 # LiveLeak embed
1328 {
1329 'url': 'http://www.wykop.pl/link/3088787/',
1330 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1331 'info_dict': {
1332 'id': '874_1459135191',
1333 'ext': 'mp4',
1334 'title': 'Man shows poor quality of new apartment building',
1335 'description': 'The wall is like a sand pile.',
1336 'uploader': 'Lake8737',
1337 }
1338 },
1339 # Duplicated embedded video URLs
1340 {
1341 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1342 'info_dict': {
1343 'id': '149298443_480_16c25b74_2',
1344 'ext': 'mp4',
1345 'title': 'vs. Blue Orange Spring Game',
1346 'uploader': 'www.hudl.com',
1347 },
1348 },
1349 # twitter:player:stream embed
1350 {
1351 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1352 'info_dict': {
1353 'id': 'master',
1354 'ext': 'mp4',
1355 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1356 'uploader': 'www.rtl.be',
1357 },
1358 'params': {
1359 # m3u8 downloads
1360 'skip_download': True,
1361 },
1362 },
1363 # twitter:player embed
1364 {
1365 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1366 'md5': 'a3e0df96369831de324f0778e126653c',
1367 'info_dict': {
1368 'id': '4909620399001',
1369 'ext': 'mp4',
1370 'title': 'What Do Black Holes Sound Like?',
1371 'description': 'what do black holes sound like',
1372 'upload_date': '20160524',
1373 'uploader_id': '29913724001',
1374 'timestamp': 1464107587,
1375 'uploader': 'TheAtlantic',
1376 },
1377 'add_ie': ['BrightcoveLegacy'],
1378 },
1379 # Facebook <iframe> embed
1380 {
1381 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1382 'md5': 'fbcde74f534176ecb015849146dd3aee',
1383 'info_dict': {
1384 'id': '599637780109885',
1385 'ext': 'mp4',
1386 'title': 'Facebook video #599637780109885',
1387 },
1388 },
1389 # Facebook API embed
1390 {
1391 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1392 'md5': 'a47372ee61b39a7b90287094d447d94e',
1393 'info_dict': {
1394 'id': '10153467542406923',
1395 'ext': 'mp4',
1396 'title': 'Facebook video #10153467542406923',
1397 },
1398 },
1399 # Wordpress "YouTube Video Importer" plugin
1400 {
1401 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1402 'md5': 'd16797741b560b485194eddda8121b48',
1403 'info_dict': {
1404 'id': 'HNTXWDXV9Is',
1405 'ext': 'mp4',
1406 'title': 'Blue Devils Drumline Stanford lot 2016',
1407 'upload_date': '20160627',
1408 'uploader_id': 'GENOCIDE8GENERAL10',
1409 'uploader': 'cylus cyrus',
1410 },
1411 },
1412 {
1413 # video stored on custom kaltura server
1414 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1415 'md5': '537617d06e64dfed891fa1593c4b30cc',
1416 'info_dict': {
1417 'id': '0_1iotm5bh',
1418 'ext': 'mp4',
1419 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1420 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1421 'uploader_id': 'videos.expansion@el-mundo.net',
1422 'upload_date': '20150429',
1423 'timestamp': 1430303472,
1424 },
1425 'add_ie': ['Kaltura'],
1426 },
1427 {
1428 # Non-standard Vimeo embed
1429 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1430 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1431 'info_dict': {
1432 'id': '148867247',
1433 'ext': 'mp4',
1434 'title': 'Understanding the web - Teaser',
1435 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1436 'upload_date': '20151214',
1437 'uploader': 'OpenClassrooms',
1438 'uploader_id': 'openclassrooms',
1439 },
1440 'add_ie': ['Vimeo'],
1441 },
1442 {
1443 # generic vimeo embed that requires original URL passed as Referer
1444 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1445 'only_matching': True,
1446 },
1447 {
1448 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1449 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1450 'info_dict': {
1451 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1452 'ext': 'mp4',
1453 'title': 'Big Buck Bunny',
1454 'description': 'Royalty free test video',
1455 'timestamp': 1432816365,
1456 'upload_date': '20150528',
1457 'is_live': False,
1458 },
1459 'params': {
1460 'skip_download': True,
1461 },
1462 'add_ie': [ArkenaIE.ie_key()],
1463 },
1464 {
1465 '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/',
1466 'info_dict': {
1467 'id': '1c7141f46c',
1468 'ext': 'mp4',
1469 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1470 },
1471 'params': {
1472 'skip_download': True,
1473 },
1474 'add_ie': [Vbox7IE.ie_key()],
1475 },
1476 {
1477 # DBTV embeds
1478 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1479 'info_dict': {
1480 'id': '43254897',
1481 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1482 },
1483 'playlist_mincount': 3,
1484 },
1485 {
1486 # Videa embeds
1487 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1488 'info_dict': {
1489 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1490 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1491 },
1492 'playlist_mincount': 2,
1493 },
1494 {
1495 # 20 minuten embed
1496 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1497 'info_dict': {
1498 'id': '523629',
1499 'ext': 'mp4',
1500 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1501 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1502 },
1503 'params': {
1504 'skip_download': True,
1505 },
1506 'add_ie': [TwentyMinutenIE.ie_key()],
1507 },
1508 {
1509 # VideoPress embed
1510 'url': 'https://en.support.wordpress.com/videopress/',
1511 'info_dict': {
1512 'id': 'OcobLTqC',
1513 'ext': 'm4v',
1514 'title': 'IMG_5786',
1515 'timestamp': 1435711927,
1516 'upload_date': '20150701',
1517 },
1518 'params': {
1519 'skip_download': True,
1520 },
1521 'add_ie': [VideoPressIE.ie_key()],
1522 },
1523 {
1524 # Rutube embed
1525 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1526 'info_dict': {
1527 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1528 'ext': 'flv',
1529 'title': 'Магаззино: Казань 2',
1530 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1531 'uploader': 'Магаззино',
1532 'upload_date': '20170228',
1533 'uploader_id': '996642',
1534 },
1535 'params': {
1536 'skip_download': True,
1537 },
1538 'add_ie': [RutubeIE.ie_key()],
1539 },
1540 {
1541 # ThePlatform embedded with whitespaces in URLs
1542 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1543 'only_matching': True,
1544 },
1545 {
1546 # Senate ISVP iframe https
1547 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1548 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1549 'info_dict': {
1550 'id': 'govtaff020316',
1551 'ext': 'mp4',
1552 'title': 'Integrated Senate Video Player',
1553 },
1554 'add_ie': [SenateISVPIE.ie_key()],
1555 },
1556 # {
1557 # # TODO: find another test
1558 # # http://schema.org/VideoObject
1559 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1560 # 'md5': '888dcf08b7ea671381f00fab74692755',
1561 # 'info_dict': {
1562 # 'id': 'nyvTSJMKId',
1563 # 'ext': 'mp4',
1564 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1565 # 'description': '#love for cats.',
1566 # 'timestamp': 1461244995,
1567 # 'upload_date': '20160421',
1568 # },
1569 # 'params': {
1570 # 'force_generic_extractor': True,
1571 # },
1572 # }
1573 ]
1574
1575 def report_following_redirect(self, new_url):
1576 """Report information extraction."""
1577 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1578
1579 def _extract_rss(self, url, video_id, doc):
1580 playlist_title = doc.find('./channel/title').text
1581 playlist_desc_el = doc.find('./channel/description')
1582 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1583
1584 entries = []
1585 for it in doc.findall('./channel/item'):
1586 next_url = xpath_text(it, 'link', fatal=False)
1587 if not next_url:
1588 enclosure_nodes = it.findall('./enclosure')
1589 for e in enclosure_nodes:
1590 next_url = e.attrib.get('url')
1591 if next_url:
1592 break
1593
1594 if not next_url:
1595 continue
1596
1597 entries.append({
1598 '_type': 'url',
1599 'url': next_url,
1600 'title': it.find('title').text,
1601 })
1602
1603 return {
1604 '_type': 'playlist',
1605 'id': url,
1606 'title': playlist_title,
1607 'description': playlist_desc,
1608 'entries': entries,
1609 }
1610
1611 def _extract_camtasia(self, url, video_id, webpage):
1612 """ Returns None if no camtasia video can be found. """
1613
1614 camtasia_cfg = self._search_regex(
1615 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1616 webpage, 'camtasia configuration file', default=None)
1617 if camtasia_cfg is None:
1618 return None
1619
1620 title = self._html_search_meta('DC.title', webpage, fatal=True)
1621
1622 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1623 camtasia_cfg = self._download_xml(
1624 camtasia_url, video_id,
1625 note='Downloading camtasia configuration',
1626 errnote='Failed to download camtasia configuration')
1627 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1628
1629 entries = []
1630 for n in fileset_node.getchildren():
1631 url_n = n.find('./uri')
1632 if url_n is None:
1633 continue
1634
1635 entries.append({
1636 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1637 'title': '%s - %s' % (title, n.tag),
1638 'url': compat_urlparse.urljoin(url, url_n.text),
1639 'duration': float_or_none(n.find('./duration').text),
1640 })
1641
1642 return {
1643 '_type': 'playlist',
1644 'entries': entries,
1645 'title': title,
1646 }
1647
1648 def _real_extract(self, url):
1649 if url.startswith('//'):
1650 return {
1651 '_type': 'url',
1652 'url': self.http_scheme() + url,
1653 }
1654
1655 parsed_url = compat_urlparse.urlparse(url)
1656 if not parsed_url.scheme:
1657 default_search = self._downloader.params.get('default_search')
1658 if default_search is None:
1659 default_search = 'fixup_error'
1660
1661 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1662 if '/' in url:
1663 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1664 return self.url_result('http://' + url)
1665 elif default_search != 'fixup_error':
1666 if default_search == 'auto_warning':
1667 if re.match(r'^(?:url|URL)$', url):
1668 raise ExtractorError(
1669 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1670 expected=True)
1671 else:
1672 self._downloader.report_warning(
1673 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1674 return self.url_result('ytsearch:' + url)
1675
1676 if default_search in ('error', 'fixup_error'):
1677 raise ExtractorError(
1678 '%r is not a valid URL. '
1679 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1680 % (url, url), expected=True)
1681 else:
1682 if ':' not in default_search:
1683 default_search += ':'
1684 return self.url_result(default_search + url)
1685
1686 url, smuggled_data = unsmuggle_url(url)
1687 force_videoid = None
1688 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1689 if smuggled_data and 'force_videoid' in smuggled_data:
1690 force_videoid = smuggled_data['force_videoid']
1691 video_id = force_videoid
1692 else:
1693 video_id = self._generic_id(url)
1694
1695 self.to_screen('%s: Requesting header' % video_id)
1696
1697 head_req = HEADRequest(url)
1698 head_response = self._request_webpage(
1699 head_req, video_id,
1700 note=False, errnote='Could not send HEAD request to %s' % url,
1701 fatal=False)
1702
1703 if head_response is not False:
1704 # Check for redirect
1705 new_url = head_response.geturl()
1706 if url != new_url:
1707 self.report_following_redirect(new_url)
1708 if force_videoid:
1709 new_url = smuggle_url(
1710 new_url, {'force_videoid': force_videoid})
1711 return self.url_result(new_url)
1712
1713 full_response = None
1714 if head_response is False:
1715 request = sanitized_Request(url)
1716 request.add_header('Accept-Encoding', '*')
1717 full_response = self._request_webpage(request, video_id)
1718 head_response = full_response
1719
1720 info_dict = {
1721 'id': video_id,
1722 'title': self._generic_title(url),
1723 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1724 }
1725
1726 # Check for direct link to a video
1727 content_type = head_response.headers.get('Content-Type', '').lower()
1728 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1729 if m:
1730 format_id = m.group('format_id')
1731 if format_id.endswith('mpegurl'):
1732 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1733 elif format_id == 'f4m':
1734 formats = self._extract_f4m_formats(url, video_id)
1735 else:
1736 formats = [{
1737 'format_id': m.group('format_id'),
1738 'url': url,
1739 'vcodec': 'none' if m.group('type') == 'audio' else None
1740 }]
1741 info_dict['direct'] = True
1742 self._sort_formats(formats)
1743 info_dict['formats'] = formats
1744 return info_dict
1745
1746 if not self._downloader.params.get('test', False) and not is_intentional:
1747 force = self._downloader.params.get('force_generic_extractor', False)
1748 self._downloader.report_warning(
1749 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1750
1751 if not full_response:
1752 request = sanitized_Request(url)
1753 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1754 # making it impossible to download only chunk of the file (yet we need only 512kB to
1755 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1756 # that will always result in downloading the whole file that is not desirable.
1757 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1758 # to accept raw bytes and being able to download only a chunk.
1759 # It may probably better to solve this by checking Content-Type for application/octet-stream
1760 # after HEAD request finishes, but not sure if we can rely on this.
1761 request.add_header('Accept-Encoding', '*')
1762 full_response = self._request_webpage(request, video_id)
1763
1764 first_bytes = full_response.read(512)
1765
1766 # Is it an M3U playlist?
1767 if first_bytes.startswith(b'#EXTM3U'):
1768 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1769 self._sort_formats(info_dict['formats'])
1770 return info_dict
1771
1772 # Maybe it's a direct link to a video?
1773 # Be careful not to download the whole thing!
1774 if not is_html(first_bytes):
1775 self._downloader.report_warning(
1776 'URL could be a direct video link, returning it as such.')
1777 info_dict.update({
1778 'direct': True,
1779 'url': url,
1780 })
1781 return info_dict
1782
1783 webpage = self._webpage_read_content(
1784 full_response, url, video_id, prefix=first_bytes)
1785
1786 self.report_extraction(video_id)
1787
1788 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1789 try:
1790 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1791 if doc.tag == 'rss':
1792 return self._extract_rss(url, video_id, doc)
1793 elif doc.tag == 'SmoothStreamingMedia':
1794 info_dict['formats'] = self._parse_ism_formats(doc, url)
1795 self._sort_formats(info_dict['formats'])
1796 return info_dict
1797 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1798 smil = self._parse_smil(doc, url, video_id)
1799 self._sort_formats(smil['formats'])
1800 return smil
1801 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1802 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1803 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1804 info_dict['formats'] = self._parse_mpd_formats(
1805 doc, video_id,
1806 mpd_base_url=full_response.geturl().rpartition('/')[0],
1807 mpd_url=url)
1808 self._sort_formats(info_dict['formats'])
1809 return info_dict
1810 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1811 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1812 self._sort_formats(info_dict['formats'])
1813 return info_dict
1814 except compat_xml_parse_error:
1815 pass
1816
1817 # Is it a Camtasia project?
1818 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1819 if camtasia_res is not None:
1820 return camtasia_res
1821
1822 # Sometimes embedded video player is hidden behind percent encoding
1823 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1824 # Unescaping the whole page allows to handle those cases in a generic way
1825 webpage = compat_urllib_parse_unquote(webpage)
1826
1827 # it's tempting to parse this further, but you would
1828 # have to take into account all the variations like
1829 # Video Title - Site Name
1830 # Site Name | Video Title
1831 # Video Title - Tagline | Site Name
1832 # and so on and so forth; it's just not practical
1833 video_title = self._og_search_title(
1834 webpage, default=None) or self._html_search_regex(
1835 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1836 default='video')
1837
1838 # Try to detect age limit automatically
1839 age_limit = self._rta_search(webpage)
1840 # And then there are the jokers who advertise that they use RTA,
1841 # but actually don't.
1842 AGE_LIMIT_MARKERS = [
1843 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1844 ]
1845 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1846 age_limit = 18
1847
1848 # video uploader is domain name
1849 video_uploader = self._search_regex(
1850 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1851
1852 video_description = self._og_search_description(webpage, default=None)
1853 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1854
1855 # Look for Brightcove Legacy Studio embeds
1856 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1857 if bc_urls:
1858 self.to_screen('Brightcove video detected.')
1859 entries = [{
1860 '_type': 'url',
1861 'url': smuggle_url(bc_url, {'Referer': url}),
1862 'ie_key': 'BrightcoveLegacy'
1863 } for bc_url in bc_urls]
1864
1865 return {
1866 '_type': 'playlist',
1867 'title': video_title,
1868 'id': video_id,
1869 'entries': entries,
1870 }
1871
1872 # Look for Brightcove New Studio embeds
1873 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1874 if bc_urls:
1875 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
1876
1877 # Look for ThePlatform embeds
1878 tp_urls = ThePlatformIE._extract_urls(webpage)
1879 if tp_urls:
1880 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
1881
1882 # Look for Vessel embeds
1883 vessel_urls = VesselIE._extract_urls(webpage)
1884 if vessel_urls:
1885 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
1886
1887 # Look for embedded rtl.nl player
1888 matches = re.findall(
1889 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1890 webpage)
1891 if matches:
1892 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
1893
1894 vimeo_urls = VimeoIE._extract_urls(url, webpage)
1895 if vimeo_urls:
1896 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
1897
1898 vid_me_embed_url = self._search_regex(
1899 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1900 webpage, 'vid.me embed', default=None)
1901 if vid_me_embed_url is not None:
1902 return self.url_result(vid_me_embed_url, 'Vidme')
1903
1904 # Look for embedded YouTube player
1905 matches = re.findall(r'''(?x)
1906 (?:
1907 <iframe[^>]+?src=|
1908 data-video-url=|
1909 <embed[^>]+?src=|
1910 embedSWF\(?:\s*|
1911 new\s+SWFObject\(
1912 )
1913 (["\'])
1914 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1915 (?:embed|v|p)/.+?)
1916 \1''', webpage)
1917 if matches:
1918 return self.playlist_from_matches(
1919 matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
1920
1921 # Look for lazyYT YouTube embed
1922 matches = re.findall(
1923 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1924 if matches:
1925 return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
1926
1927 # Look for Wordpress "YouTube Video Importer" plugin
1928 matches = re.findall(r'''(?x)<div[^>]+
1929 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1930 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1931 if matches:
1932 return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
1933
1934 matches = DailymotionIE._extract_urls(webpage)
1935 if matches:
1936 return self.playlist_from_matches(matches, video_id, video_title)
1937
1938 # Look for embedded Dailymotion playlist player (#3822)
1939 m = re.search(
1940 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1941 if m:
1942 playlists = re.findall(
1943 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1944 if playlists:
1945 return self.playlist_from_matches(
1946 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
1947
1948 # Look for embedded Wistia player
1949 match = re.search(
1950 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1951 if match:
1952 embed_url = self._proto_relative_url(
1953 unescapeHTML(match.group('url')))
1954 return {
1955 '_type': 'url_transparent',
1956 'url': embed_url,
1957 'ie_key': 'Wistia',
1958 'uploader': video_uploader,
1959 }
1960
1961 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1962 if match:
1963 return {
1964 '_type': 'url_transparent',
1965 'url': 'wistia:%s' % match.group('id'),
1966 'ie_key': 'Wistia',
1967 'uploader': video_uploader,
1968 }
1969
1970 match = re.search(
1971 r'''(?sx)
1972 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1973 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1974 ''', webpage)
1975 if match:
1976 return self.url_result(self._proto_relative_url(
1977 'wistia:%s' % match.group('id')), 'Wistia')
1978
1979 # Look for SVT player
1980 svt_url = SVTIE._extract_url(webpage)
1981 if svt_url:
1982 return self.url_result(svt_url, 'SVT')
1983
1984 # Look for embedded condenast player
1985 matches = re.findall(
1986 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1987 webpage)
1988 if matches:
1989 return {
1990 '_type': 'playlist',
1991 'entries': [{
1992 '_type': 'url',
1993 'ie_key': 'CondeNast',
1994 'url': ma,
1995 } for ma in matches],
1996 'title': video_title,
1997 'id': video_id,
1998 }
1999
2000 # Look for Bandcamp pages with custom domain
2001 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2002 if mobj is not None:
2003 burl = unescapeHTML(mobj.group(1))
2004 # Don't set the extractor because it can be a track url or an album
2005 return self.url_result(burl)
2006
2007 # Look for embedded Vevo player
2008 mobj = re.search(
2009 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2010 if mobj is not None:
2011 return self.url_result(mobj.group('url'))
2012
2013 # Look for embedded Viddler player
2014 mobj = re.search(
2015 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2016 webpage)
2017 if mobj is not None:
2018 return self.url_result(mobj.group('url'))
2019
2020 # Look for NYTimes player
2021 mobj = re.search(
2022 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2023 webpage)
2024 if mobj is not None:
2025 return self.url_result(mobj.group('url'))
2026
2027 # Look for Libsyn player
2028 mobj = re.search(
2029 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2030 if mobj is not None:
2031 return self.url_result(mobj.group('url'))
2032
2033 # Look for Ooyala videos
2034 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2035 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2036 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2037 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2038 if mobj is not None:
2039 embed_token = self._search_regex(
2040 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2041 webpage, 'ooyala embed token', default=None)
2042 return OoyalaIE._build_url_result(smuggle_url(
2043 mobj.group('ec'), {
2044 'domain': url,
2045 'embed_token': embed_token,
2046 }))
2047
2048 # Look for multiple Ooyala embeds on SBN network websites
2049 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2050 if mobj is not None:
2051 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2052 if embeds:
2053 return self.playlist_from_matches(
2054 embeds, video_id, video_title,
2055 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2056
2057 # Look for Aparat videos
2058 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2059 if mobj is not None:
2060 return self.url_result(mobj.group(1), 'Aparat')
2061
2062 # Look for MPORA videos
2063 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2064 if mobj is not None:
2065 return self.url_result(mobj.group(1), 'Mpora')
2066
2067 # Look for embedded NovaMov-based player
2068 mobj = re.search(
2069 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2070 (?P<url>http://(?:(?:embed|www)\.)?
2071 (?:novamov\.com|
2072 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2073 videoweed\.(?:es|com)|
2074 movshare\.(?:net|sx|ag)|
2075 divxstage\.(?:eu|net|ch|co|at|ag))
2076 /embed\.php.+?)\1''', webpage)
2077 if mobj is not None:
2078 return self.url_result(mobj.group('url'))
2079
2080 # Look for embedded Facebook player
2081 facebook_url = FacebookIE._extract_url(webpage)
2082 if facebook_url is not None:
2083 return self.url_result(facebook_url, 'Facebook')
2084
2085 # Look for embedded VK player
2086 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2087 if mobj is not None:
2088 return self.url_result(mobj.group('url'), 'VK')
2089
2090 # Look for embedded Odnoklassniki player
2091 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2092 if mobj is not None:
2093 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2094
2095 # Look for embedded ivi player
2096 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2097 if mobj is not None:
2098 return self.url_result(mobj.group('url'), 'Ivi')
2099
2100 # Look for embedded Huffington Post player
2101 mobj = re.search(
2102 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2103 if mobj is not None:
2104 return self.url_result(mobj.group('url'), 'HuffPost')
2105
2106 # Look for embed.ly
2107 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2108 if mobj is not None:
2109 return self.url_result(mobj.group('url'))
2110 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2111 if mobj is not None:
2112 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2113
2114 # Look for funnyordie embed
2115 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2116 if matches:
2117 return self.playlist_from_matches(
2118 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2119
2120 # Look for BBC iPlayer embed
2121 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2122 if matches:
2123 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2124
2125 # Look for embedded RUTV player
2126 rutv_url = RUTVIE._extract_url(webpage)
2127 if rutv_url:
2128 return self.url_result(rutv_url, 'RUTV')
2129
2130 # Look for embedded TVC player
2131 tvc_url = TVCIE._extract_url(webpage)
2132 if tvc_url:
2133 return self.url_result(tvc_url, 'TVC')
2134
2135 # Look for embedded SportBox player
2136 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2137 if sportbox_urls:
2138 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2139
2140 # Look for embedded XHamster player
2141 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2142 if xhamster_urls:
2143 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2144
2145 # Look for embedded TNAFlixNetwork player
2146 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2147 if tnaflix_urls:
2148 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2149
2150 # Look for embedded PornHub player
2151 pornhub_urls = PornHubIE._extract_urls(webpage)
2152 if pornhub_urls:
2153 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2154
2155 # Look for embedded DrTuber player
2156 drtuber_urls = DrTuberIE._extract_urls(webpage)
2157 if drtuber_urls:
2158 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2159
2160 # Look for embedded RedTube player
2161 redtube_urls = RedTubeIE._extract_urls(webpage)
2162 if redtube_urls:
2163 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2164
2165 # Look for embedded Tvigle player
2166 mobj = re.search(
2167 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2168 if mobj is not None:
2169 return self.url_result(mobj.group('url'), 'Tvigle')
2170
2171 # Look for embedded TED player
2172 mobj = re.search(
2173 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2174 if mobj is not None:
2175 return self.url_result(mobj.group('url'), 'TED')
2176
2177 # Look for embedded Ustream videos
2178 ustream_url = UstreamIE._extract_url(webpage)
2179 if ustream_url:
2180 return self.url_result(ustream_url, UstreamIE.ie_key())
2181
2182 # Look for embedded arte.tv player
2183 mobj = re.search(
2184 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2185 webpage)
2186 if mobj is not None:
2187 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2188
2189 # Look for embedded francetv player
2190 mobj = re.search(
2191 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2192 webpage)
2193 if mobj is not None:
2194 return self.url_result(mobj.group('url'))
2195
2196 # Look for embedded smotri.com player
2197 smotri_url = SmotriIE._extract_url(webpage)
2198 if smotri_url:
2199 return self.url_result(smotri_url, 'Smotri')
2200
2201 # Look for embedded Myvi.ru player
2202 myvi_url = MyviIE._extract_url(webpage)
2203 if myvi_url:
2204 return self.url_result(myvi_url)
2205
2206 # Look for embedded soundcloud player
2207 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2208 if soundcloud_urls:
2209 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2210
2211 # Look for tunein player
2212 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2213 if tunein_urls:
2214 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2215
2216 # Look for embedded mtvservices player
2217 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2218 if mtvservices_url:
2219 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2220
2221 # Look for embedded yahoo player
2222 mobj = re.search(
2223 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2224 webpage)
2225 if mobj is not None:
2226 return self.url_result(mobj.group('url'), 'Yahoo')
2227
2228 # Look for embedded sbs.com.au player
2229 mobj = re.search(
2230 r'''(?x)
2231 (?:
2232 <meta\s+property="og:video"\s+content=|
2233 <iframe[^>]+?src=
2234 )
2235 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2236 webpage)
2237 if mobj is not None:
2238 return self.url_result(mobj.group('url'), 'SBS')
2239
2240 # Look for embedded Cinchcast player
2241 mobj = re.search(
2242 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2243 webpage)
2244 if mobj is not None:
2245 return self.url_result(mobj.group('url'), 'Cinchcast')
2246
2247 mobj = re.search(
2248 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2249 webpage)
2250 if not mobj:
2251 mobj = re.search(
2252 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2253 webpage)
2254 if mobj is not None:
2255 return self.url_result(mobj.group('url'), 'MLB')
2256
2257 mobj = re.search(
2258 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2259 webpage)
2260 if mobj is not None:
2261 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2262
2263 mobj = re.search(
2264 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2265 webpage)
2266 if mobj is not None:
2267 return self.url_result(mobj.group('url'), 'Livestream')
2268
2269 # Look for Zapiks embed
2270 mobj = re.search(
2271 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2272 if mobj is not None:
2273 return self.url_result(mobj.group('url'), 'Zapiks')
2274
2275 # Look for Kaltura embeds
2276 kaltura_url = KalturaIE._extract_url(webpage)
2277 if kaltura_url:
2278 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2279
2280 # Look for Eagle.Platform embeds
2281 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2282 if eagleplatform_url:
2283 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2284
2285 # Look for ClipYou (uses Eagle.Platform) embeds
2286 mobj = re.search(
2287 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2288 if mobj is not None:
2289 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2290
2291 # Look for Pladform embeds
2292 pladform_url = PladformIE._extract_url(webpage)
2293 if pladform_url:
2294 return self.url_result(pladform_url)
2295
2296 # Look for Videomore embeds
2297 videomore_url = VideomoreIE._extract_url(webpage)
2298 if videomore_url:
2299 return self.url_result(videomore_url)
2300
2301 # Look for Webcaster embeds
2302 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2303 if webcaster_url:
2304 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2305
2306 # Look for Playwire embeds
2307 mobj = re.search(
2308 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2309 if mobj is not None:
2310 return self.url_result(mobj.group('url'))
2311
2312 # Look for 5min embeds
2313 mobj = re.search(
2314 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2315 if mobj is not None:
2316 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2317
2318 # Look for Crooks and Liars embeds
2319 mobj = re.search(
2320 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2321 if mobj is not None:
2322 return self.url_result(mobj.group('url'))
2323
2324 # Look for NBC Sports VPlayer embeds
2325 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2326 if nbc_sports_url:
2327 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2328
2329 # Look for NBC News embeds
2330 nbc_news_embed_url = re.search(
2331 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2332 if nbc_news_embed_url:
2333 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2334
2335 # Look for Google Drive embeds
2336 google_drive_url = GoogleDriveIE._extract_url(webpage)
2337 if google_drive_url:
2338 return self.url_result(google_drive_url, 'GoogleDrive')
2339
2340 # Look for UDN embeds
2341 mobj = re.search(
2342 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2343 if mobj is not None:
2344 return self.url_result(
2345 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2346
2347 # Look for Senate ISVP iframe
2348 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2349 if senate_isvp_url:
2350 return self.url_result(senate_isvp_url, 'SenateISVP')
2351
2352 # Look for Dailymotion Cloud videos
2353 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2354 if dmcloud_url:
2355 return self.url_result(dmcloud_url, 'DailymotionCloud')
2356
2357 # Look for OnionStudios embeds
2358 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2359 if onionstudios_url:
2360 return self.url_result(onionstudios_url)
2361
2362 # Look for ViewLift embeds
2363 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2364 if viewlift_url:
2365 return self.url_result(viewlift_url)
2366
2367 # Look for JWPlatform embeds
2368 jwplatform_url = JWPlatformIE._extract_url(webpage)
2369 if jwplatform_url:
2370 return self.url_result(jwplatform_url, 'JWPlatform')
2371
2372 # Look for Digiteka embeds
2373 digiteka_url = DigitekaIE._extract_url(webpage)
2374 if digiteka_url:
2375 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2376
2377 # Look for Arkena embeds
2378 arkena_url = ArkenaIE._extract_url(webpage)
2379 if arkena_url:
2380 return self.url_result(arkena_url, ArkenaIE.ie_key())
2381
2382 # Look for Piksel embeds
2383 piksel_url = PikselIE._extract_url(webpage)
2384 if piksel_url:
2385 return self.url_result(piksel_url, PikselIE.ie_key())
2386
2387 # Look for Limelight embeds
2388 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2389 if mobj:
2390 lm = {
2391 'Media': 'media',
2392 'Channel': 'channel',
2393 'ChannelList': 'channel_list',
2394 }
2395 return self.url_result(smuggle_url('limelight:%s:%s' % (
2396 lm[mobj.group(1)], mobj.group(2)), {'source_url': url}),
2397 'Limelight%s' % mobj.group(1), mobj.group(2))
2398
2399 mobj = re.search(
2400 r'''(?sx)
2401 <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2402 <param[^>]+
2403 name=(["\'])flashVars\2[^>]+
2404 value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2405 ''', webpage)
2406 if mobj:
2407 return self.url_result(smuggle_url(
2408 'limelight:media:%s' % mobj.group('id'),
2409 {'source_url': url}), 'LimelightMedia', mobj.group('id'))
2410
2411 # Look for AdobeTVVideo embeds
2412 mobj = re.search(
2413 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2414 webpage)
2415 if mobj is not None:
2416 return self.url_result(
2417 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2418 'AdobeTVVideo')
2419
2420 # Look for Vine embeds
2421 mobj = re.search(
2422 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2423 webpage)
2424 if mobj is not None:
2425 return self.url_result(
2426 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2427
2428 # Look for VODPlatform embeds
2429 mobj = re.search(
2430 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2431 webpage)
2432 if mobj is not None:
2433 return self.url_result(
2434 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2435
2436 # Look for Mangomolo embeds
2437 mobj = re.search(
2438 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2439 (?:
2440 video\?.*?\bid=(?P<video_id>\d+)|
2441 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2442 ).+?)\1''', webpage)
2443 if mobj is not None:
2444 info = {
2445 '_type': 'url_transparent',
2446 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2447 'title': video_title,
2448 'description': video_description,
2449 'thumbnail': video_thumbnail,
2450 'uploader': video_uploader,
2451 }
2452 video_id = mobj.group('video_id')
2453 if video_id:
2454 info.update({
2455 'ie_key': 'MangomoloVideo',
2456 'id': video_id,
2457 })
2458 else:
2459 info.update({
2460 'ie_key': 'MangomoloLive',
2461 'id': mobj.group('channel_id'),
2462 })
2463 return info
2464
2465 # Look for Instagram embeds
2466 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2467 if instagram_embed_url is not None:
2468 return self.url_result(
2469 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2470
2471 # Look for LiveLeak embeds
2472 liveleak_url = LiveLeakIE._extract_url(webpage)
2473 if liveleak_url:
2474 return self.url_result(liveleak_url, 'LiveLeak')
2475
2476 # Look for 3Q SDN embeds
2477 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2478 if threeqsdn_url:
2479 return {
2480 '_type': 'url_transparent',
2481 'ie_key': ThreeQSDNIE.ie_key(),
2482 'url': self._proto_relative_url(threeqsdn_url),
2483 'title': video_title,
2484 'description': video_description,
2485 'thumbnail': video_thumbnail,
2486 'uploader': video_uploader,
2487 }
2488
2489 # Look for VBOX7 embeds
2490 vbox7_url = Vbox7IE._extract_url(webpage)
2491 if vbox7_url:
2492 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2493
2494 # Look for DBTV embeds
2495 dbtv_urls = DBTVIE._extract_urls(webpage)
2496 if dbtv_urls:
2497 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2498
2499 # Look for Videa embeds
2500 videa_urls = VideaIE._extract_urls(webpage)
2501 if videa_urls:
2502 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2503
2504 # Look for 20 minuten embeds
2505 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2506 if twentymin_urls:
2507 return self.playlist_from_matches(
2508 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2509
2510 # Look for Openload embeds
2511 openload_urls = OpenloadIE._extract_urls(webpage)
2512 if openload_urls:
2513 return self.playlist_from_matches(
2514 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2515
2516 # Look for VideoPress embeds
2517 videopress_urls = VideoPressIE._extract_urls(webpage)
2518 if videopress_urls:
2519 return self.playlist_from_matches(
2520 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2521
2522 # Look for Rutube embeds
2523 rutube_urls = RutubeIE._extract_urls(webpage)
2524 if rutube_urls:
2525 return self.playlist_from_matches(
2526 rutube_urls, ie=RutubeIE.ie_key())
2527
2528 # Looking for http://schema.org/VideoObject
2529 json_ld = self._search_json_ld(
2530 webpage, video_id, default={}, expected_type='VideoObject')
2531 if json_ld.get('url'):
2532 info_dict.update({
2533 'title': video_title or info_dict['title'],
2534 'description': video_description,
2535 'thumbnail': video_thumbnail,
2536 'age_limit': age_limit
2537 })
2538 info_dict.update(json_ld)
2539 return info_dict
2540
2541 # Look for HTML5 media
2542 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2543 if entries:
2544 for entry in entries:
2545 entry.update({
2546 'id': video_id,
2547 'title': video_title,
2548 })
2549 self._sort_formats(entry['formats'])
2550 return self.playlist_result(entries)
2551
2552 jwplayer_data_str = self._find_jwplayer_data(webpage)
2553 if jwplayer_data_str:
2554 try:
2555 jwplayer_data = self._parse_json(
2556 jwplayer_data_str, video_id, transform_source=js_to_json)
2557 info = self._parse_jwplayer_data(
2558 jwplayer_data, video_id, require_title=False)
2559 if not info.get('title'):
2560 info['title'] = video_title
2561 return info
2562 except ExtractorError:
2563 pass
2564
2565 def check_video(vurl):
2566 if YoutubeIE.suitable(vurl):
2567 return True
2568 if RtmpIE.suitable(vurl):
2569 return True
2570 vpath = compat_urlparse.urlparse(vurl).path
2571 vext = determine_ext(vpath)
2572 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
2573
2574 def filter_video(urls):
2575 return list(filter(check_video, urls))
2576
2577 # Start with something easy: JW Player in SWFObject
2578 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2579 if not found:
2580 # Look for gorilla-vid style embedding
2581 found = filter_video(re.findall(r'''(?sx)
2582 (?:
2583 jw_plugins|
2584 JWPlayerOptions|
2585 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2586 )
2587 .*?
2588 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2589 if not found:
2590 # Broaden the search a little bit
2591 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2592 if not found:
2593 # Broaden the findall a little bit: JWPlayer JS loader
2594 found = filter_video(re.findall(
2595 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2596 if not found:
2597 # Flow player
2598 found = filter_video(re.findall(r'''(?xs)
2599 flowplayer\("[^"]+",\s*
2600 \{[^}]+?\}\s*,
2601 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2602 ["']?url["']?\s*:\s*["']([^"']+)["']
2603 ''', webpage))
2604 if not found:
2605 # Cinerama player
2606 found = re.findall(
2607 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2608 if not found:
2609 # Try to find twitter cards info
2610 # twitter:player:stream should be checked before twitter:player since
2611 # it is expected to contain a raw stream (see
2612 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2613 found = filter_video(re.findall(
2614 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2615 if not found:
2616 # We look for Open Graph info:
2617 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2618 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2619 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2620 if m_video_type is not None:
2621 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2622 if not found:
2623 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2624 found = re.search(
2625 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2626 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2627 webpage)
2628 if not found:
2629 # Look also in Refresh HTTP header
2630 refresh_header = head_response.headers.get('Refresh')
2631 if refresh_header:
2632 # In python 2 response HTTP headers are bytestrings
2633 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2634 refresh_header = refresh_header.decode('iso-8859-1')
2635 found = re.search(REDIRECT_REGEX, refresh_header)
2636 if found:
2637 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2638 self.report_following_redirect(new_url)
2639 return {
2640 '_type': 'url',
2641 'url': new_url,
2642 }
2643
2644 if not found:
2645 # twitter:player is a https URL to iframe player that may or may not
2646 # be supported by youtube-dl thus this is checked the very last (see
2647 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2648 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2649 if embed_url:
2650 return self.url_result(embed_url)
2651
2652 if not found:
2653 raise UnsupportedError(url)
2654
2655 entries = []
2656 for video_url in orderedSet(found):
2657 video_url = unescapeHTML(video_url)
2658 video_url = video_url.replace('\\/', '/')
2659 video_url = compat_urlparse.urljoin(url, video_url)
2660 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2661
2662 # Sometimes, jwplayer extraction will result in a YouTube URL
2663 if YoutubeIE.suitable(video_url):
2664 entries.append(self.url_result(video_url, 'Youtube'))
2665 continue
2666
2667 # here's a fun little line of code for you:
2668 video_id = os.path.splitext(video_id)[0]
2669
2670 entry_info_dict = {
2671 'id': video_id,
2672 'uploader': video_uploader,
2673 'title': video_title,
2674 'age_limit': age_limit,
2675 }
2676
2677 if RtmpIE.suitable(video_url):
2678 entry_info_dict.update({
2679 '_type': 'url_transparent',
2680 'ie_key': RtmpIE.ie_key(),
2681 'url': video_url,
2682 })
2683 entries.append(entry_info_dict)
2684 continue
2685
2686 ext = determine_ext(video_url)
2687 if ext == 'smil':
2688 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2689 elif ext == 'xspf':
2690 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2691 elif ext == 'm3u8':
2692 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2693 elif ext == 'mpd':
2694 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2695 elif ext == 'f4m':
2696 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2697 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2698 # Just matching .ism/manifest is not enough to be reliably sure
2699 # whether it's actually an ISM manifest or some other streaming
2700 # manifest since there are various streaming URL formats
2701 # possible (see [1]) as well as some other shenanigans like
2702 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2703 # so on.
2704 # Thus the most reasonable way to solve this is to delegate
2705 # to generic extractor in order to look into the contents of
2706 # the manifest itself.
2707 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2708 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2709 entry_info_dict = self.url_result(
2710 smuggle_url(video_url, {'to_generic': True}),
2711 GenericIE.ie_key())
2712 else:
2713 entry_info_dict['url'] = video_url
2714
2715 if entry_info_dict.get('formats'):
2716 self._sort_formats(entry_info_dict['formats'])
2717
2718 entries.append(entry_info_dict)
2719
2720 if len(entries) == 1:
2721 return entries[0]
2722 else:
2723 for num, e in enumerate(entries, start=1):
2724 # 'url' results don't have a title
2725 if e.get('title') is not None:
2726 e['title'] = '%s (%d)' % (e['title'], num)
2727 return {
2728 '_type': 'playlist',
2729 'entries': entries,
2730 }