]> jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/generic.py
[extractor/generic] Add forgotten return for jwplayer formats
[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 # # TODO: find another test
1547 # # http://schema.org/VideoObject
1548 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1549 # 'md5': '888dcf08b7ea671381f00fab74692755',
1550 # 'info_dict': {
1551 # 'id': 'nyvTSJMKId',
1552 # 'ext': 'mp4',
1553 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1554 # 'description': '#love for cats.',
1555 # 'timestamp': 1461244995,
1556 # 'upload_date': '20160421',
1557 # },
1558 # 'params': {
1559 # 'force_generic_extractor': True,
1560 # },
1561 # }
1562 ]
1563
1564 def report_following_redirect(self, new_url):
1565 """Report information extraction."""
1566 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1567
1568 def _extract_rss(self, url, video_id, doc):
1569 playlist_title = doc.find('./channel/title').text
1570 playlist_desc_el = doc.find('./channel/description')
1571 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1572
1573 entries = []
1574 for it in doc.findall('./channel/item'):
1575 next_url = xpath_text(it, 'link', fatal=False)
1576 if not next_url:
1577 enclosure_nodes = it.findall('./enclosure')
1578 for e in enclosure_nodes:
1579 next_url = e.attrib.get('url')
1580 if next_url:
1581 break
1582
1583 if not next_url:
1584 continue
1585
1586 entries.append({
1587 '_type': 'url',
1588 'url': next_url,
1589 'title': it.find('title').text,
1590 })
1591
1592 return {
1593 '_type': 'playlist',
1594 'id': url,
1595 'title': playlist_title,
1596 'description': playlist_desc,
1597 'entries': entries,
1598 }
1599
1600 def _extract_camtasia(self, url, video_id, webpage):
1601 """ Returns None if no camtasia video can be found. """
1602
1603 camtasia_cfg = self._search_regex(
1604 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1605 webpage, 'camtasia configuration file', default=None)
1606 if camtasia_cfg is None:
1607 return None
1608
1609 title = self._html_search_meta('DC.title', webpage, fatal=True)
1610
1611 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1612 camtasia_cfg = self._download_xml(
1613 camtasia_url, video_id,
1614 note='Downloading camtasia configuration',
1615 errnote='Failed to download camtasia configuration')
1616 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1617
1618 entries = []
1619 for n in fileset_node.getchildren():
1620 url_n = n.find('./uri')
1621 if url_n is None:
1622 continue
1623
1624 entries.append({
1625 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1626 'title': '%s - %s' % (title, n.tag),
1627 'url': compat_urlparse.urljoin(url, url_n.text),
1628 'duration': float_or_none(n.find('./duration').text),
1629 })
1630
1631 return {
1632 '_type': 'playlist',
1633 'entries': entries,
1634 'title': title,
1635 }
1636
1637 def _real_extract(self, url):
1638 if url.startswith('//'):
1639 return {
1640 '_type': 'url',
1641 'url': self.http_scheme() + url,
1642 }
1643
1644 parsed_url = compat_urlparse.urlparse(url)
1645 if not parsed_url.scheme:
1646 default_search = self._downloader.params.get('default_search')
1647 if default_search is None:
1648 default_search = 'fixup_error'
1649
1650 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1651 if '/' in url:
1652 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1653 return self.url_result('http://' + url)
1654 elif default_search != 'fixup_error':
1655 if default_search == 'auto_warning':
1656 if re.match(r'^(?:url|URL)$', url):
1657 raise ExtractorError(
1658 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1659 expected=True)
1660 else:
1661 self._downloader.report_warning(
1662 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1663 return self.url_result('ytsearch:' + url)
1664
1665 if default_search in ('error', 'fixup_error'):
1666 raise ExtractorError(
1667 '%r is not a valid URL. '
1668 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1669 % (url, url), expected=True)
1670 else:
1671 if ':' not in default_search:
1672 default_search += ':'
1673 return self.url_result(default_search + url)
1674
1675 url, smuggled_data = unsmuggle_url(url)
1676 force_videoid = None
1677 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1678 if smuggled_data and 'force_videoid' in smuggled_data:
1679 force_videoid = smuggled_data['force_videoid']
1680 video_id = force_videoid
1681 else:
1682 video_id = self._generic_id(url)
1683
1684 self.to_screen('%s: Requesting header' % video_id)
1685
1686 head_req = HEADRequest(url)
1687 head_response = self._request_webpage(
1688 head_req, video_id,
1689 note=False, errnote='Could not send HEAD request to %s' % url,
1690 fatal=False)
1691
1692 if head_response is not False:
1693 # Check for redirect
1694 new_url = head_response.geturl()
1695 if url != new_url:
1696 self.report_following_redirect(new_url)
1697 if force_videoid:
1698 new_url = smuggle_url(
1699 new_url, {'force_videoid': force_videoid})
1700 return self.url_result(new_url)
1701
1702 full_response = None
1703 if head_response is False:
1704 request = sanitized_Request(url)
1705 request.add_header('Accept-Encoding', '*')
1706 full_response = self._request_webpage(request, video_id)
1707 head_response = full_response
1708
1709 info_dict = {
1710 'id': video_id,
1711 'title': self._generic_title(url),
1712 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1713 }
1714
1715 # Check for direct link to a video
1716 content_type = head_response.headers.get('Content-Type', '').lower()
1717 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1718 if m:
1719 format_id = m.group('format_id')
1720 if format_id.endswith('mpegurl'):
1721 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1722 elif format_id == 'f4m':
1723 formats = self._extract_f4m_formats(url, video_id)
1724 else:
1725 formats = [{
1726 'format_id': m.group('format_id'),
1727 'url': url,
1728 'vcodec': 'none' if m.group('type') == 'audio' else None
1729 }]
1730 info_dict['direct'] = True
1731 self._sort_formats(formats)
1732 info_dict['formats'] = formats
1733 return info_dict
1734
1735 if not self._downloader.params.get('test', False) and not is_intentional:
1736 force = self._downloader.params.get('force_generic_extractor', False)
1737 self._downloader.report_warning(
1738 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1739
1740 if not full_response:
1741 request = sanitized_Request(url)
1742 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1743 # making it impossible to download only chunk of the file (yet we need only 512kB to
1744 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1745 # that will always result in downloading the whole file that is not desirable.
1746 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1747 # to accept raw bytes and being able to download only a chunk.
1748 # It may probably better to solve this by checking Content-Type for application/octet-stream
1749 # after HEAD request finishes, but not sure if we can rely on this.
1750 request.add_header('Accept-Encoding', '*')
1751 full_response = self._request_webpage(request, video_id)
1752
1753 first_bytes = full_response.read(512)
1754
1755 # Is it an M3U playlist?
1756 if first_bytes.startswith(b'#EXTM3U'):
1757 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1758 self._sort_formats(info_dict['formats'])
1759 return info_dict
1760
1761 # Maybe it's a direct link to a video?
1762 # Be careful not to download the whole thing!
1763 if not is_html(first_bytes):
1764 self._downloader.report_warning(
1765 'URL could be a direct video link, returning it as such.')
1766 info_dict.update({
1767 'direct': True,
1768 'url': url,
1769 })
1770 return info_dict
1771
1772 webpage = self._webpage_read_content(
1773 full_response, url, video_id, prefix=first_bytes)
1774
1775 self.report_extraction(video_id)
1776
1777 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1778 try:
1779 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1780 if doc.tag == 'rss':
1781 return self._extract_rss(url, video_id, doc)
1782 elif doc.tag == 'SmoothStreamingMedia':
1783 info_dict['formats'] = self._parse_ism_formats(doc, url)
1784 self._sort_formats(info_dict['formats'])
1785 return info_dict
1786 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1787 smil = self._parse_smil(doc, url, video_id)
1788 self._sort_formats(smil['formats'])
1789 return smil
1790 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1791 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1792 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1793 info_dict['formats'] = self._parse_mpd_formats(
1794 doc, video_id,
1795 mpd_base_url=full_response.geturl().rpartition('/')[0],
1796 mpd_url=url)
1797 self._sort_formats(info_dict['formats'])
1798 return info_dict
1799 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1800 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1801 self._sort_formats(info_dict['formats'])
1802 return info_dict
1803 except compat_xml_parse_error:
1804 pass
1805
1806 # Is it a Camtasia project?
1807 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1808 if camtasia_res is not None:
1809 return camtasia_res
1810
1811 # Sometimes embedded video player is hidden behind percent encoding
1812 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1813 # Unescaping the whole page allows to handle those cases in a generic way
1814 webpage = compat_urllib_parse_unquote(webpage)
1815
1816 # it's tempting to parse this further, but you would
1817 # have to take into account all the variations like
1818 # Video Title - Site Name
1819 # Site Name | Video Title
1820 # Video Title - Tagline | Site Name
1821 # and so on and so forth; it's just not practical
1822 video_title = self._og_search_title(
1823 webpage, default=None) or self._html_search_regex(
1824 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1825 default='video')
1826
1827 # Try to detect age limit automatically
1828 age_limit = self._rta_search(webpage)
1829 # And then there are the jokers who advertise that they use RTA,
1830 # but actually don't.
1831 AGE_LIMIT_MARKERS = [
1832 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1833 ]
1834 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1835 age_limit = 18
1836
1837 # video uploader is domain name
1838 video_uploader = self._search_regex(
1839 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1840
1841 video_description = self._og_search_description(webpage, default=None)
1842 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1843
1844 # Helper method
1845 def _playlist_from_matches(matches, getter=None, ie=None):
1846 urlrs = orderedSet(
1847 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1848 for m in matches)
1849 return self.playlist_result(
1850 urlrs, playlist_id=video_id, playlist_title=video_title)
1851
1852 # Look for Brightcove Legacy Studio embeds
1853 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1854 if bc_urls:
1855 self.to_screen('Brightcove video detected.')
1856 entries = [{
1857 '_type': 'url',
1858 'url': smuggle_url(bc_url, {'Referer': url}),
1859 'ie_key': 'BrightcoveLegacy'
1860 } for bc_url in bc_urls]
1861
1862 return {
1863 '_type': 'playlist',
1864 'title': video_title,
1865 'id': video_id,
1866 'entries': entries,
1867 }
1868
1869 # Look for Brightcove New Studio embeds
1870 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1871 if bc_urls:
1872 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1873
1874 # Look for ThePlatform embeds
1875 tp_urls = ThePlatformIE._extract_urls(webpage)
1876 if tp_urls:
1877 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1878
1879 # Look for Vessel embeds
1880 vessel_urls = VesselIE._extract_urls(webpage)
1881 if vessel_urls:
1882 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1883
1884 # Look for embedded rtl.nl player
1885 matches = re.findall(
1886 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1887 webpage)
1888 if matches:
1889 return _playlist_from_matches(matches, ie='RtlNl')
1890
1891 vimeo_urls = VimeoIE._extract_urls(url, webpage)
1892 if vimeo_urls:
1893 return _playlist_from_matches(vimeo_urls, ie=VimeoIE.ie_key())
1894
1895 vid_me_embed_url = self._search_regex(
1896 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1897 webpage, 'vid.me embed', default=None)
1898 if vid_me_embed_url is not None:
1899 return self.url_result(vid_me_embed_url, 'Vidme')
1900
1901 # Look for embedded YouTube player
1902 matches = re.findall(r'''(?x)
1903 (?:
1904 <iframe[^>]+?src=|
1905 data-video-url=|
1906 <embed[^>]+?src=|
1907 embedSWF\(?:\s*|
1908 new\s+SWFObject\(
1909 )
1910 (["\'])
1911 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1912 (?:embed|v|p)/.+?)
1913 \1''', webpage)
1914 if matches:
1915 return _playlist_from_matches(
1916 matches, lambda m: unescapeHTML(m[1]))
1917
1918 # Look for lazyYT YouTube embed
1919 matches = re.findall(
1920 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1921 if matches:
1922 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1923
1924 # Look for Wordpress "YouTube Video Importer" plugin
1925 matches = re.findall(r'''(?x)<div[^>]+
1926 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1927 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1928 if matches:
1929 return _playlist_from_matches(matches, lambda m: m[-1])
1930
1931 matches = DailymotionIE._extract_urls(webpage)
1932 if matches:
1933 return _playlist_from_matches(matches)
1934
1935 # Look for embedded Dailymotion playlist player (#3822)
1936 m = re.search(
1937 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1938 if m:
1939 playlists = re.findall(
1940 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1941 if playlists:
1942 return _playlist_from_matches(
1943 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1944
1945 # Look for embedded Wistia player
1946 match = re.search(
1947 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1948 if match:
1949 embed_url = self._proto_relative_url(
1950 unescapeHTML(match.group('url')))
1951 return {
1952 '_type': 'url_transparent',
1953 'url': embed_url,
1954 'ie_key': 'Wistia',
1955 'uploader': video_uploader,
1956 }
1957
1958 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1959 if match:
1960 return {
1961 '_type': 'url_transparent',
1962 'url': 'wistia:%s' % match.group('id'),
1963 'ie_key': 'Wistia',
1964 'uploader': video_uploader,
1965 }
1966
1967 match = re.search(
1968 r'''(?sx)
1969 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1970 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1971 ''', webpage)
1972 if match:
1973 return self.url_result(self._proto_relative_url(
1974 'wistia:%s' % match.group('id')), 'Wistia')
1975
1976 # Look for SVT player
1977 svt_url = SVTIE._extract_url(webpage)
1978 if svt_url:
1979 return self.url_result(svt_url, 'SVT')
1980
1981 # Look for embedded condenast player
1982 matches = re.findall(
1983 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1984 webpage)
1985 if matches:
1986 return {
1987 '_type': 'playlist',
1988 'entries': [{
1989 '_type': 'url',
1990 'ie_key': 'CondeNast',
1991 'url': ma,
1992 } for ma in matches],
1993 'title': video_title,
1994 'id': video_id,
1995 }
1996
1997 # Look for Bandcamp pages with custom domain
1998 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1999 if mobj is not None:
2000 burl = unescapeHTML(mobj.group(1))
2001 # Don't set the extractor because it can be a track url or an album
2002 return self.url_result(burl)
2003
2004 # Look for embedded Vevo player
2005 mobj = re.search(
2006 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2007 if mobj is not None:
2008 return self.url_result(mobj.group('url'))
2009
2010 # Look for embedded Viddler player
2011 mobj = re.search(
2012 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2013 webpage)
2014 if mobj is not None:
2015 return self.url_result(mobj.group('url'))
2016
2017 # Look for NYTimes player
2018 mobj = re.search(
2019 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2020 webpage)
2021 if mobj is not None:
2022 return self.url_result(mobj.group('url'))
2023
2024 # Look for Libsyn player
2025 mobj = re.search(
2026 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2027 if mobj is not None:
2028 return self.url_result(mobj.group('url'))
2029
2030 # Look for Ooyala videos
2031 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2032 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2033 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2034 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2035 if mobj is not None:
2036 embed_token = self._search_regex(
2037 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2038 webpage, 'ooyala embed token', default=None)
2039 return OoyalaIE._build_url_result(smuggle_url(
2040 mobj.group('ec'), {
2041 'domain': url,
2042 'embed_token': embed_token,
2043 }))
2044
2045 # Look for multiple Ooyala embeds on SBN network websites
2046 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2047 if mobj is not None:
2048 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2049 if embeds:
2050 return _playlist_from_matches(
2051 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2052
2053 # Look for Aparat videos
2054 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2055 if mobj is not None:
2056 return self.url_result(mobj.group(1), 'Aparat')
2057
2058 # Look for MPORA videos
2059 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2060 if mobj is not None:
2061 return self.url_result(mobj.group(1), 'Mpora')
2062
2063 # Look for embedded NovaMov-based player
2064 mobj = re.search(
2065 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2066 (?P<url>http://(?:(?:embed|www)\.)?
2067 (?:novamov\.com|
2068 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2069 videoweed\.(?:es|com)|
2070 movshare\.(?:net|sx|ag)|
2071 divxstage\.(?:eu|net|ch|co|at|ag))
2072 /embed\.php.+?)\1''', webpage)
2073 if mobj is not None:
2074 return self.url_result(mobj.group('url'))
2075
2076 # Look for embedded Facebook player
2077 facebook_url = FacebookIE._extract_url(webpage)
2078 if facebook_url is not None:
2079 return self.url_result(facebook_url, 'Facebook')
2080
2081 # Look for embedded VK player
2082 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2083 if mobj is not None:
2084 return self.url_result(mobj.group('url'), 'VK')
2085
2086 # Look for embedded Odnoklassniki player
2087 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2088 if mobj is not None:
2089 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2090
2091 # Look for embedded ivi player
2092 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2093 if mobj is not None:
2094 return self.url_result(mobj.group('url'), 'Ivi')
2095
2096 # Look for embedded Huffington Post player
2097 mobj = re.search(
2098 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2099 if mobj is not None:
2100 return self.url_result(mobj.group('url'), 'HuffPost')
2101
2102 # Look for embed.ly
2103 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2104 if mobj is not None:
2105 return self.url_result(mobj.group('url'))
2106 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2107 if mobj is not None:
2108 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2109
2110 # Look for funnyordie embed
2111 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2112 if matches:
2113 return _playlist_from_matches(
2114 matches, getter=unescapeHTML, ie='FunnyOrDie')
2115
2116 # Look for BBC iPlayer embed
2117 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2118 if matches:
2119 return _playlist_from_matches(matches, ie='BBCCoUk')
2120
2121 # Look for embedded RUTV player
2122 rutv_url = RUTVIE._extract_url(webpage)
2123 if rutv_url:
2124 return self.url_result(rutv_url, 'RUTV')
2125
2126 # Look for embedded TVC player
2127 tvc_url = TVCIE._extract_url(webpage)
2128 if tvc_url:
2129 return self.url_result(tvc_url, 'TVC')
2130
2131 # Look for embedded SportBox player
2132 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2133 if sportbox_urls:
2134 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
2135
2136 # Look for embedded XHamster player
2137 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2138 if xhamster_urls:
2139 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
2140
2141 # Look for embedded TNAFlixNetwork player
2142 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2143 if tnaflix_urls:
2144 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
2145
2146 # Look for embedded PornHub player
2147 pornhub_urls = PornHubIE._extract_urls(webpage)
2148 if pornhub_urls:
2149 return _playlist_from_matches(pornhub_urls, ie=PornHubIE.ie_key())
2150
2151 # Look for embedded DrTuber player
2152 drtuber_urls = DrTuberIE._extract_urls(webpage)
2153 if drtuber_urls:
2154 return _playlist_from_matches(drtuber_urls, ie=DrTuberIE.ie_key())
2155
2156 # Look for embedded RedTube player
2157 redtube_urls = RedTubeIE._extract_urls(webpage)
2158 if redtube_urls:
2159 return _playlist_from_matches(redtube_urls, ie=RedTubeIE.ie_key())
2160
2161 # Look for embedded Tvigle player
2162 mobj = re.search(
2163 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2164 if mobj is not None:
2165 return self.url_result(mobj.group('url'), 'Tvigle')
2166
2167 # Look for embedded TED player
2168 mobj = re.search(
2169 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2170 if mobj is not None:
2171 return self.url_result(mobj.group('url'), 'TED')
2172
2173 # Look for embedded Ustream videos
2174 ustream_url = UstreamIE._extract_url(webpage)
2175 if ustream_url:
2176 return self.url_result(ustream_url, UstreamIE.ie_key())
2177
2178 # Look for embedded arte.tv player
2179 mobj = re.search(
2180 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2181 webpage)
2182 if mobj is not None:
2183 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2184
2185 # Look for embedded francetv player
2186 mobj = re.search(
2187 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2188 webpage)
2189 if mobj is not None:
2190 return self.url_result(mobj.group('url'))
2191
2192 # Look for embedded smotri.com player
2193 smotri_url = SmotriIE._extract_url(webpage)
2194 if smotri_url:
2195 return self.url_result(smotri_url, 'Smotri')
2196
2197 # Look for embedded Myvi.ru player
2198 myvi_url = MyviIE._extract_url(webpage)
2199 if myvi_url:
2200 return self.url_result(myvi_url)
2201
2202 # Look for embedded soundcloud player
2203 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2204 if soundcloud_urls:
2205 return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2206
2207 # Look for tunein player
2208 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2209 if tunein_urls:
2210 return _playlist_from_matches(tunein_urls)
2211
2212 # Look for embedded mtvservices player
2213 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2214 if mtvservices_url:
2215 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2216
2217 # Look for embedded yahoo player
2218 mobj = re.search(
2219 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2220 webpage)
2221 if mobj is not None:
2222 return self.url_result(mobj.group('url'), 'Yahoo')
2223
2224 # Look for embedded sbs.com.au player
2225 mobj = re.search(
2226 r'''(?x)
2227 (?:
2228 <meta\s+property="og:video"\s+content=|
2229 <iframe[^>]+?src=
2230 )
2231 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2232 webpage)
2233 if mobj is not None:
2234 return self.url_result(mobj.group('url'), 'SBS')
2235
2236 # Look for embedded Cinchcast player
2237 mobj = re.search(
2238 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2239 webpage)
2240 if mobj is not None:
2241 return self.url_result(mobj.group('url'), 'Cinchcast')
2242
2243 mobj = re.search(
2244 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2245 webpage)
2246 if not mobj:
2247 mobj = re.search(
2248 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2249 webpage)
2250 if mobj is not None:
2251 return self.url_result(mobj.group('url'), 'MLB')
2252
2253 mobj = re.search(
2254 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2255 webpage)
2256 if mobj is not None:
2257 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2258
2259 mobj = re.search(
2260 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2261 webpage)
2262 if mobj is not None:
2263 return self.url_result(mobj.group('url'), 'Livestream')
2264
2265 # Look for Zapiks embed
2266 mobj = re.search(
2267 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2268 if mobj is not None:
2269 return self.url_result(mobj.group('url'), 'Zapiks')
2270
2271 # Look for Kaltura embeds
2272 kaltura_url = KalturaIE._extract_url(webpage)
2273 if kaltura_url:
2274 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2275
2276 # Look for Eagle.Platform embeds
2277 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2278 if eagleplatform_url:
2279 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2280
2281 # Look for ClipYou (uses Eagle.Platform) embeds
2282 mobj = re.search(
2283 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2284 if mobj is not None:
2285 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2286
2287 # Look for Pladform embeds
2288 pladform_url = PladformIE._extract_url(webpage)
2289 if pladform_url:
2290 return self.url_result(pladform_url)
2291
2292 # Look for Videomore embeds
2293 videomore_url = VideomoreIE._extract_url(webpage)
2294 if videomore_url:
2295 return self.url_result(videomore_url)
2296
2297 # Look for Webcaster embeds
2298 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2299 if webcaster_url:
2300 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2301
2302 # Look for Playwire embeds
2303 mobj = re.search(
2304 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2305 if mobj is not None:
2306 return self.url_result(mobj.group('url'))
2307
2308 # Look for 5min embeds
2309 mobj = re.search(
2310 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2311 if mobj is not None:
2312 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2313
2314 # Look for Crooks and Liars embeds
2315 mobj = re.search(
2316 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2317 if mobj is not None:
2318 return self.url_result(mobj.group('url'))
2319
2320 # Look for NBC Sports VPlayer embeds
2321 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2322 if nbc_sports_url:
2323 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2324
2325 # Look for NBC News embeds
2326 nbc_news_embed_url = re.search(
2327 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2328 if nbc_news_embed_url:
2329 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2330
2331 # Look for Google Drive embeds
2332 google_drive_url = GoogleDriveIE._extract_url(webpage)
2333 if google_drive_url:
2334 return self.url_result(google_drive_url, 'GoogleDrive')
2335
2336 # Look for UDN embeds
2337 mobj = re.search(
2338 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2339 if mobj is not None:
2340 return self.url_result(
2341 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2342
2343 # Look for Senate ISVP iframe
2344 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2345 if senate_isvp_url:
2346 return self.url_result(senate_isvp_url, 'SenateISVP')
2347
2348 # Look for Dailymotion Cloud videos
2349 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2350 if dmcloud_url:
2351 return self.url_result(dmcloud_url, 'DailymotionCloud')
2352
2353 # Look for OnionStudios embeds
2354 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2355 if onionstudios_url:
2356 return self.url_result(onionstudios_url)
2357
2358 # Look for ViewLift embeds
2359 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2360 if viewlift_url:
2361 return self.url_result(viewlift_url)
2362
2363 # Look for JWPlatform embeds
2364 jwplatform_url = JWPlatformIE._extract_url(webpage)
2365 if jwplatform_url:
2366 return self.url_result(jwplatform_url, 'JWPlatform')
2367
2368 # Look for Digiteka embeds
2369 digiteka_url = DigitekaIE._extract_url(webpage)
2370 if digiteka_url:
2371 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2372
2373 # Look for Arkena embeds
2374 arkena_url = ArkenaIE._extract_url(webpage)
2375 if arkena_url:
2376 return self.url_result(arkena_url, ArkenaIE.ie_key())
2377
2378 # Look for Piksel embeds
2379 piksel_url = PikselIE._extract_url(webpage)
2380 if piksel_url:
2381 return self.url_result(piksel_url, PikselIE.ie_key())
2382
2383 # Look for Limelight embeds
2384 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2385 if mobj:
2386 lm = {
2387 'Media': 'media',
2388 'Channel': 'channel',
2389 'ChannelList': 'channel_list',
2390 }
2391 return self.url_result(smuggle_url('limelight:%s:%s' % (
2392 lm[mobj.group(1)], mobj.group(2)), {'source_url': url}),
2393 'Limelight%s' % mobj.group(1), mobj.group(2))
2394
2395 mobj = re.search(
2396 r'''(?sx)
2397 <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2398 <param[^>]+
2399 name=(["\'])flashVars\2[^>]+
2400 value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2401 ''', webpage)
2402 if mobj:
2403 return self.url_result(smuggle_url(
2404 'limelight:media:%s' % mobj.group('id'),
2405 {'source_url': url}), 'LimelightMedia', mobj.group('id'))
2406
2407 # Look for AdobeTVVideo embeds
2408 mobj = re.search(
2409 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2410 webpage)
2411 if mobj is not None:
2412 return self.url_result(
2413 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2414 'AdobeTVVideo')
2415
2416 # Look for Vine embeds
2417 mobj = re.search(
2418 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2419 webpage)
2420 if mobj is not None:
2421 return self.url_result(
2422 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2423
2424 # Look for VODPlatform embeds
2425 mobj = re.search(
2426 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2427 webpage)
2428 if mobj is not None:
2429 return self.url_result(
2430 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2431
2432 # Look for Mangomolo embeds
2433 mobj = re.search(
2434 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2435 (?:
2436 video\?.*?\bid=(?P<video_id>\d+)|
2437 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2438 ).+?)\1''', webpage)
2439 if mobj is not None:
2440 info = {
2441 '_type': 'url_transparent',
2442 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2443 'title': video_title,
2444 'description': video_description,
2445 'thumbnail': video_thumbnail,
2446 'uploader': video_uploader,
2447 }
2448 video_id = mobj.group('video_id')
2449 if video_id:
2450 info.update({
2451 'ie_key': 'MangomoloVideo',
2452 'id': video_id,
2453 })
2454 else:
2455 info.update({
2456 'ie_key': 'MangomoloLive',
2457 'id': mobj.group('channel_id'),
2458 })
2459 return info
2460
2461 # Look for Instagram embeds
2462 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2463 if instagram_embed_url is not None:
2464 return self.url_result(
2465 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2466
2467 # Look for LiveLeak embeds
2468 liveleak_url = LiveLeakIE._extract_url(webpage)
2469 if liveleak_url:
2470 return self.url_result(liveleak_url, 'LiveLeak')
2471
2472 # Look for 3Q SDN embeds
2473 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2474 if threeqsdn_url:
2475 return {
2476 '_type': 'url_transparent',
2477 'ie_key': ThreeQSDNIE.ie_key(),
2478 'url': self._proto_relative_url(threeqsdn_url),
2479 'title': video_title,
2480 'description': video_description,
2481 'thumbnail': video_thumbnail,
2482 'uploader': video_uploader,
2483 }
2484
2485 # Look for VBOX7 embeds
2486 vbox7_url = Vbox7IE._extract_url(webpage)
2487 if vbox7_url:
2488 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2489
2490 # Look for DBTV embeds
2491 dbtv_urls = DBTVIE._extract_urls(webpage)
2492 if dbtv_urls:
2493 return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
2494
2495 # Look for Videa embeds
2496 videa_urls = VideaIE._extract_urls(webpage)
2497 if videa_urls:
2498 return _playlist_from_matches(videa_urls, ie=VideaIE.ie_key())
2499
2500 # Look for 20 minuten embeds
2501 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2502 if twentymin_urls:
2503 return _playlist_from_matches(
2504 twentymin_urls, ie=TwentyMinutenIE.ie_key())
2505
2506 # Look for Openload embeds
2507 openload_urls = OpenloadIE._extract_urls(webpage)
2508 if openload_urls:
2509 return _playlist_from_matches(
2510 openload_urls, ie=OpenloadIE.ie_key())
2511
2512 # Look for VideoPress embeds
2513 videopress_urls = VideoPressIE._extract_urls(webpage)
2514 if videopress_urls:
2515 return _playlist_from_matches(
2516 videopress_urls, ie=VideoPressIE.ie_key())
2517
2518 # Look for Rutube embeds
2519 rutube_urls = RutubeIE._extract_urls(webpage)
2520 if rutube_urls:
2521 return _playlist_from_matches(
2522 rutube_urls, ie=RutubeIE.ie_key())
2523
2524 # Looking for http://schema.org/VideoObject
2525 json_ld = self._search_json_ld(
2526 webpage, video_id, default={}, expected_type='VideoObject')
2527 if json_ld.get('url'):
2528 info_dict.update({
2529 'title': video_title or info_dict['title'],
2530 'description': video_description,
2531 'thumbnail': video_thumbnail,
2532 'age_limit': age_limit
2533 })
2534 info_dict.update(json_ld)
2535 return info_dict
2536
2537 # Look for HTML5 media
2538 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2539 if entries:
2540 for entry in entries:
2541 entry.update({
2542 'id': video_id,
2543 'title': video_title,
2544 })
2545 self._sort_formats(entry['formats'])
2546 return self.playlist_result(entries)
2547
2548 jwplayer_data_str = self._find_jwplayer_data(webpage)
2549 if jwplayer_data_str:
2550 try:
2551 jwplayer_data = self._parse_json(
2552 jwplayer_data_str, video_id, transform_source=js_to_json)
2553 info = self._parse_jwplayer_data(
2554 jwplayer_data, video_id, require_title=False)
2555 if not info.get('title'):
2556 info['title'] = video_title
2557 return info
2558 except ExtractorError:
2559 pass
2560
2561 def check_video(vurl):
2562 if YoutubeIE.suitable(vurl):
2563 return True
2564 if RtmpIE.suitable(vurl):
2565 return True
2566 vpath = compat_urlparse.urlparse(vurl).path
2567 vext = determine_ext(vpath)
2568 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
2569
2570 def filter_video(urls):
2571 return list(filter(check_video, urls))
2572
2573 # Start with something easy: JW Player in SWFObject
2574 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2575 if not found:
2576 # Look for gorilla-vid style embedding
2577 found = filter_video(re.findall(r'''(?sx)
2578 (?:
2579 jw_plugins|
2580 JWPlayerOptions|
2581 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2582 )
2583 .*?
2584 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2585 if not found:
2586 # Broaden the search a little bit
2587 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2588 if not found:
2589 # Broaden the findall a little bit: JWPlayer JS loader
2590 found = filter_video(re.findall(
2591 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2592 if not found:
2593 # Flow player
2594 found = filter_video(re.findall(r'''(?xs)
2595 flowplayer\("[^"]+",\s*
2596 \{[^}]+?\}\s*,
2597 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2598 ["']?url["']?\s*:\s*["']([^"']+)["']
2599 ''', webpage))
2600 if not found:
2601 # Cinerama player
2602 found = re.findall(
2603 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2604 if not found:
2605 # Try to find twitter cards info
2606 # twitter:player:stream should be checked before twitter:player since
2607 # it is expected to contain a raw stream (see
2608 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2609 found = filter_video(re.findall(
2610 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2611 if not found:
2612 # We look for Open Graph info:
2613 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2614 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2615 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2616 if m_video_type is not None:
2617 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2618 if not found:
2619 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2620 found = re.search(
2621 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2622 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2623 webpage)
2624 if not found:
2625 # Look also in Refresh HTTP header
2626 refresh_header = head_response.headers.get('Refresh')
2627 if refresh_header:
2628 # In python 2 response HTTP headers are bytestrings
2629 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2630 refresh_header = refresh_header.decode('iso-8859-1')
2631 found = re.search(REDIRECT_REGEX, refresh_header)
2632 if found:
2633 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2634 self.report_following_redirect(new_url)
2635 return {
2636 '_type': 'url',
2637 'url': new_url,
2638 }
2639
2640 if not found:
2641 # twitter:player is a https URL to iframe player that may or may not
2642 # be supported by youtube-dl thus this is checked the very last (see
2643 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2644 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2645 if embed_url:
2646 return self.url_result(embed_url)
2647
2648 if not found:
2649 raise UnsupportedError(url)
2650
2651 entries = []
2652 for video_url in orderedSet(found):
2653 video_url = unescapeHTML(video_url)
2654 video_url = video_url.replace('\\/', '/')
2655 video_url = compat_urlparse.urljoin(url, video_url)
2656 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2657
2658 # Sometimes, jwplayer extraction will result in a YouTube URL
2659 if YoutubeIE.suitable(video_url):
2660 entries.append(self.url_result(video_url, 'Youtube'))
2661 continue
2662
2663 # here's a fun little line of code for you:
2664 video_id = os.path.splitext(video_id)[0]
2665
2666 entry_info_dict = {
2667 'id': video_id,
2668 'uploader': video_uploader,
2669 'title': video_title,
2670 'age_limit': age_limit,
2671 }
2672
2673 if RtmpIE.suitable(video_url):
2674 entry_info_dict.update({
2675 '_type': 'url_transparent',
2676 'ie_key': RtmpIE.ie_key(),
2677 'url': video_url,
2678 })
2679 entries.append(entry_info_dict)
2680 continue
2681
2682 ext = determine_ext(video_url)
2683 if ext == 'smil':
2684 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2685 elif ext == 'xspf':
2686 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2687 elif ext == 'm3u8':
2688 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2689 elif ext == 'mpd':
2690 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2691 elif ext == 'f4m':
2692 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2693 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2694 # Just matching .ism/manifest is not enough to be reliably sure
2695 # whether it's actually an ISM manifest or some other streaming
2696 # manifest since there are various streaming URL formats
2697 # possible (see [1]) as well as some other shenanigans like
2698 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2699 # so on.
2700 # Thus the most reasonable way to solve this is to delegate
2701 # to generic extractor in order to look into the contents of
2702 # the manifest itself.
2703 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2704 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2705 entry_info_dict = self.url_result(
2706 smuggle_url(video_url, {'to_generic': True}),
2707 GenericIE.ie_key())
2708 else:
2709 entry_info_dict['url'] = video_url
2710
2711 if entry_info_dict.get('formats'):
2712 self._sort_formats(entry_info_dict['formats'])
2713
2714 entries.append(entry_info_dict)
2715
2716 if len(entries) == 1:
2717 return entries[0]
2718 else:
2719 for num, e in enumerate(entries, start=1):
2720 # 'url' results don't have a title
2721 if e.get('title') is not None:
2722 e['title'] = '%s (%d)' % (e['title'], num)
2723 return {
2724 '_type': 'playlist',
2725 'entries': entries,
2726 }