]> jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/generic.py
[generic] Replace LazyYT test with skiplagged
[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': 'https://skiplagged.com/',
906 'info_dict': {
907 'id': 'skiplagged',
908 'title': 'Skiplagged: The smart way to find cheap flights',
909 },
910 'playlist_mincount': 1,
911 'add_ie': ['Youtube'],
912 },
913 # Cinchcast embed
914 {
915 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
916 'info_dict': {
917 'id': '7141703',
918 'ext': 'mp3',
919 'upload_date': '20141126',
920 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
921 }
922 },
923 # Cinerama player
924 {
925 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
926 'info_dict': {
927 'id': '730m_DandD_1901_512k',
928 'ext': 'mp4',
929 'uploader': 'www.abc.net.au',
930 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
931 }
932 },
933 # embedded viddler video
934 {
935 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
936 'info_dict': {
937 'id': '4d03aad9',
938 'ext': 'mp4',
939 'uploader': 'deadspin',
940 'title': 'WALL-TO-GORTAT',
941 'timestamp': 1422285291,
942 'upload_date': '20150126',
943 },
944 'add_ie': ['Viddler'],
945 },
946 # Libsyn embed
947 {
948 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
949 'info_dict': {
950 'id': '3377616',
951 'ext': 'mp3',
952 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
953 'description': 'md5:601cb790edd05908957dae8aaa866465',
954 'upload_date': '20150220',
955 },
956 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
957 },
958 # jwplayer YouTube
959 {
960 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
961 'info_dict': {
962 'id': 'Mrj4DVp2zeA',
963 'ext': 'mp4',
964 'upload_date': '20150212',
965 'uploader': 'The National Archives UK',
966 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
967 'uploader_id': 'NationalArchives08',
968 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
969 },
970 },
971 # jwplayer rtmp
972 {
973 'url': 'http://www.suffolk.edu/sjc/',
974 'info_dict': {
975 'id': 'sjclive',
976 'ext': 'flv',
977 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
978 'uploader': 'www.suffolk.edu',
979 },
980 'params': {
981 'skip_download': True,
982 }
983 },
984 # Complex jwplayer
985 {
986 'url': 'http://www.indiedb.com/games/king-machine/videos',
987 'info_dict': {
988 'id': 'videos',
989 'ext': 'mp4',
990 'title': 'king machine trailer 1',
991 'thumbnail': r're:^https?://.*\.jpg$',
992 },
993 },
994 # rtl.nl embed
995 {
996 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
997 'playlist_mincount': 5,
998 'info_dict': {
999 'id': 'aanslagen-kopenhagen',
1000 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1001 }
1002 },
1003 # Zapiks embed
1004 {
1005 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1006 'info_dict': {
1007 'id': '118046',
1008 'ext': 'mp4',
1009 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1010 }
1011 },
1012 # Kaltura embed (different embed code)
1013 {
1014 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1015 'info_dict': {
1016 'id': '1_a52wc67y',
1017 'ext': 'flv',
1018 'upload_date': '20150127',
1019 'uploader_id': 'PremierMedia',
1020 'timestamp': int,
1021 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1022 },
1023 },
1024 # Kaltura embed with single quotes
1025 {
1026 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1027 'info_dict': {
1028 'id': '0_izeg5utt',
1029 'ext': 'mp4',
1030 'title': '35871',
1031 'timestamp': 1355743100,
1032 'upload_date': '20121217',
1033 'uploader_id': 'batchUser',
1034 },
1035 'add_ie': ['Kaltura'],
1036 },
1037 {
1038 # Kaltura embedded via quoted entry_id
1039 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1040 'info_dict': {
1041 'id': '0_utuok90b',
1042 'ext': 'mp4',
1043 'title': '06_matthew_brender_raj_dutt',
1044 'timestamp': 1466638791,
1045 'upload_date': '20160622',
1046 },
1047 'add_ie': ['Kaltura'],
1048 'expected_warnings': [
1049 'Could not send HEAD request'
1050 ],
1051 'params': {
1052 'skip_download': True,
1053 }
1054 },
1055 {
1056 # Kaltura embedded, some fileExt broken (#11480)
1057 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1058 'info_dict': {
1059 'id': '1_sgtvehim',
1060 'ext': 'mp4',
1061 'title': 'Our "Standard Models" of particle physics and cosmology',
1062 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1063 'timestamp': 1321158993,
1064 'upload_date': '20111113',
1065 'uploader_id': 'kps1',
1066 },
1067 'add_ie': ['Kaltura'],
1068 },
1069 # Eagle.Platform embed (generic URL)
1070 {
1071 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1072 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1073 'info_dict': {
1074 'id': '227304',
1075 'ext': 'mp4',
1076 'title': 'Навальный вышел на свободу',
1077 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1078 'thumbnail': r're:^https?://.*\.jpg$',
1079 'duration': 87,
1080 'view_count': int,
1081 'age_limit': 0,
1082 },
1083 },
1084 # ClipYou (Eagle.Platform) embed (custom URL)
1085 {
1086 'url': 'http://muz-tv.ru/play/7129/',
1087 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1088 'info_dict': {
1089 'id': '12820',
1090 'ext': 'mp4',
1091 'title': "'O Sole Mio",
1092 'thumbnail': r're:^https?://.*\.jpg$',
1093 'duration': 216,
1094 'view_count': int,
1095 },
1096 },
1097 # Pladform embed
1098 {
1099 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1100 'info_dict': {
1101 'id': '100183293',
1102 'ext': 'mp4',
1103 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1104 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1105 'thumbnail': r're:^https?://.*\.jpg$',
1106 'duration': 694,
1107 'age_limit': 0,
1108 },
1109 },
1110 # Playwire embed
1111 {
1112 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1113 'info_dict': {
1114 'id': '3519514',
1115 'ext': 'mp4',
1116 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1117 'thumbnail': r're:^https?://.*\.png$',
1118 'duration': 45.115,
1119 },
1120 },
1121 # 5min embed
1122 {
1123 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1124 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1125 'info_dict': {
1126 'id': '518726732',
1127 'ext': 'mp4',
1128 'title': 'Facebook Creates "On This Day" | Crunch Report',
1129 },
1130 },
1131 # SVT embed
1132 {
1133 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1134 'info_dict': {
1135 'id': '2900353',
1136 'ext': 'flv',
1137 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1138 'duration': 27,
1139 'age_limit': 0,
1140 },
1141 },
1142 # Crooks and Liars embed
1143 {
1144 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1145 'info_dict': {
1146 'id': '8RUoRhRi',
1147 'ext': 'mp4',
1148 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1149 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1150 'timestamp': 1428207000,
1151 'upload_date': '20150405',
1152 'uploader': 'Heather',
1153 },
1154 },
1155 # Crooks and Liars external embed
1156 {
1157 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1158 'info_dict': {
1159 'id': 'MTE3MjUtMzQ2MzA',
1160 'ext': 'mp4',
1161 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1162 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1163 'timestamp': 1265032391,
1164 'upload_date': '20100201',
1165 'uploader': 'Heather',
1166 },
1167 },
1168 # NBC Sports vplayer embed
1169 {
1170 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1171 'info_dict': {
1172 'id': 'ln7x1qSThw4k',
1173 'ext': 'flv',
1174 'title': "PFT Live: New leader in the 'new-look' defense",
1175 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1176 'uploader': 'NBCU-SPORTS',
1177 'upload_date': '20140107',
1178 'timestamp': 1389118457,
1179 },
1180 },
1181 # NBC News embed
1182 {
1183 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1184 'md5': '1aa589c675898ae6d37a17913cf68d66',
1185 'info_dict': {
1186 'id': '701714499682',
1187 'ext': 'mp4',
1188 'title': 'PREVIEW: On Assignment: David Letterman',
1189 '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.',
1190 },
1191 },
1192 # UDN embed
1193 {
1194 'url': 'https://video.udn.com/news/300346',
1195 'md5': 'fd2060e988c326991037b9aff9df21a6',
1196 'info_dict': {
1197 'id': '300346',
1198 'ext': 'mp4',
1199 'title': '中一中男師變性 全校師生力挺',
1200 'thumbnail': r're:^https?://.*\.jpg$',
1201 },
1202 'params': {
1203 # m3u8 download
1204 'skip_download': True,
1205 },
1206 },
1207 # Ooyala embed
1208 {
1209 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1210 'info_dict': {
1211 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1212 'ext': 'mp4',
1213 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1214 'title': 'This is what separates the Excel masters from the wannabes',
1215 'duration': 191.933,
1216 },
1217 'params': {
1218 # m3u8 downloads
1219 'skip_download': True,
1220 }
1221 },
1222 # Brightcove URL in single quotes
1223 {
1224 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1225 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1226 'info_dict': {
1227 'id': '4255764656001',
1228 'ext': 'mp4',
1229 'title': 'SN Presents: Russell Martin, World Citizen',
1230 '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.',
1231 'uploader': 'Rogers Sportsnet',
1232 'uploader_id': '1704050871',
1233 'upload_date': '20150525',
1234 'timestamp': 1432570283,
1235 },
1236 },
1237 # Dailymotion Cloud video
1238 {
1239 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1240 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1241 'info_dict': {
1242 'id': 'x2uy8t3',
1243 'ext': 'mp4',
1244 'title': 'Sauvons les abeilles ! - Le débat',
1245 'description': 'md5:d9082128b1c5277987825d684939ca26',
1246 'thumbnail': r're:^https?://.*\.jpe?g$',
1247 'timestamp': 1434970506,
1248 'upload_date': '20150622',
1249 'uploader': 'Public Sénat',
1250 'uploader_id': 'xa9gza',
1251 }
1252 },
1253 # OnionStudios embed
1254 {
1255 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1256 'info_dict': {
1257 'id': '2855',
1258 'ext': 'mp4',
1259 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1260 'thumbnail': r're:^https?://.*\.jpe?g$',
1261 'uploader': 'ClickHole',
1262 'uploader_id': 'clickhole',
1263 }
1264 },
1265 # SnagFilms embed
1266 {
1267 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1268 'info_dict': {
1269 'id': '74849a00-85a9-11e1-9660-123139220831',
1270 'ext': 'mp4',
1271 'title': '#whilewewatch',
1272 }
1273 },
1274 # AdobeTVVideo embed
1275 {
1276 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1277 'md5': '43662b577c018ad707a63766462b1e87',
1278 'info_dict': {
1279 'id': '2456',
1280 'ext': 'mp4',
1281 'title': 'New experience with Acrobat DC',
1282 'description': 'New experience with Acrobat DC',
1283 'duration': 248.667,
1284 },
1285 },
1286 # BrightcoveInPageEmbed embed
1287 {
1288 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1289 'info_dict': {
1290 'id': '4238694884001',
1291 'ext': 'flv',
1292 'title': 'Tabletop: Dread, Last Thoughts',
1293 'description': 'Tabletop: Dread, Last Thoughts',
1294 'duration': 51690,
1295 },
1296 },
1297 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1298 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1299 {
1300 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1301 'info_dict': {
1302 'id': '4785848093001',
1303 'ext': 'mp4',
1304 'title': 'The Cardinal Pell Interview',
1305 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1306 'uploader': 'GlobeCast Australia - GlobeStream',
1307 'uploader_id': '2733773828001',
1308 'upload_date': '20160304',
1309 'timestamp': 1457083087,
1310 },
1311 'params': {
1312 # m3u8 downloads
1313 'skip_download': True,
1314 },
1315 },
1316 # Another form of arte.tv embed
1317 {
1318 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1319 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1320 'info_dict': {
1321 'id': '030273-562_PLUS7-F',
1322 'ext': 'mp4',
1323 'title': 'ARTE Reportage - Nulle part, en France',
1324 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1325 'upload_date': '20160409',
1326 },
1327 },
1328 # LiveLeak embed
1329 {
1330 'url': 'http://www.wykop.pl/link/3088787/',
1331 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1332 'info_dict': {
1333 'id': '874_1459135191',
1334 'ext': 'mp4',
1335 'title': 'Man shows poor quality of new apartment building',
1336 'description': 'The wall is like a sand pile.',
1337 'uploader': 'Lake8737',
1338 }
1339 },
1340 # Duplicated embedded video URLs
1341 {
1342 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1343 'info_dict': {
1344 'id': '149298443_480_16c25b74_2',
1345 'ext': 'mp4',
1346 'title': 'vs. Blue Orange Spring Game',
1347 'uploader': 'www.hudl.com',
1348 },
1349 },
1350 # twitter:player:stream embed
1351 {
1352 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1353 'info_dict': {
1354 'id': 'master',
1355 'ext': 'mp4',
1356 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1357 'uploader': 'www.rtl.be',
1358 },
1359 'params': {
1360 # m3u8 downloads
1361 'skip_download': True,
1362 },
1363 },
1364 # twitter:player embed
1365 {
1366 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1367 'md5': 'a3e0df96369831de324f0778e126653c',
1368 'info_dict': {
1369 'id': '4909620399001',
1370 'ext': 'mp4',
1371 'title': 'What Do Black Holes Sound Like?',
1372 'description': 'what do black holes sound like',
1373 'upload_date': '20160524',
1374 'uploader_id': '29913724001',
1375 'timestamp': 1464107587,
1376 'uploader': 'TheAtlantic',
1377 },
1378 'add_ie': ['BrightcoveLegacy'],
1379 },
1380 # Facebook <iframe> embed
1381 {
1382 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1383 'md5': 'fbcde74f534176ecb015849146dd3aee',
1384 'info_dict': {
1385 'id': '599637780109885',
1386 'ext': 'mp4',
1387 'title': 'Facebook video #599637780109885',
1388 },
1389 },
1390 # Facebook API embed
1391 {
1392 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1393 'md5': 'a47372ee61b39a7b90287094d447d94e',
1394 'info_dict': {
1395 'id': '10153467542406923',
1396 'ext': 'mp4',
1397 'title': 'Facebook video #10153467542406923',
1398 },
1399 },
1400 # Wordpress "YouTube Video Importer" plugin
1401 {
1402 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1403 'md5': 'd16797741b560b485194eddda8121b48',
1404 'info_dict': {
1405 'id': 'HNTXWDXV9Is',
1406 'ext': 'mp4',
1407 'title': 'Blue Devils Drumline Stanford lot 2016',
1408 'upload_date': '20160627',
1409 'uploader_id': 'GENOCIDE8GENERAL10',
1410 'uploader': 'cylus cyrus',
1411 },
1412 },
1413 {
1414 # video stored on custom kaltura server
1415 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1416 'md5': '537617d06e64dfed891fa1593c4b30cc',
1417 'info_dict': {
1418 'id': '0_1iotm5bh',
1419 'ext': 'mp4',
1420 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1421 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1422 'uploader_id': 'videos.expansion@el-mundo.net',
1423 'upload_date': '20150429',
1424 'timestamp': 1430303472,
1425 },
1426 'add_ie': ['Kaltura'],
1427 },
1428 {
1429 # Non-standard Vimeo embed
1430 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1431 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1432 'info_dict': {
1433 'id': '148867247',
1434 'ext': 'mp4',
1435 'title': 'Understanding the web - Teaser',
1436 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1437 'upload_date': '20151214',
1438 'uploader': 'OpenClassrooms',
1439 'uploader_id': 'openclassrooms',
1440 },
1441 'add_ie': ['Vimeo'],
1442 },
1443 {
1444 # generic vimeo embed that requires original URL passed as Referer
1445 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1446 'only_matching': True,
1447 },
1448 {
1449 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1450 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1451 'info_dict': {
1452 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1453 'ext': 'mp4',
1454 'title': 'Big Buck Bunny',
1455 'description': 'Royalty free test video',
1456 'timestamp': 1432816365,
1457 'upload_date': '20150528',
1458 'is_live': False,
1459 },
1460 'params': {
1461 'skip_download': True,
1462 },
1463 'add_ie': [ArkenaIE.ie_key()],
1464 },
1465 {
1466 '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/',
1467 'info_dict': {
1468 'id': '1c7141f46c',
1469 'ext': 'mp4',
1470 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1471 },
1472 'params': {
1473 'skip_download': True,
1474 },
1475 'add_ie': [Vbox7IE.ie_key()],
1476 },
1477 {
1478 # DBTV embeds
1479 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1480 'info_dict': {
1481 'id': '43254897',
1482 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1483 },
1484 'playlist_mincount': 3,
1485 },
1486 {
1487 # Videa embeds
1488 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1489 'info_dict': {
1490 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1491 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1492 },
1493 'playlist_mincount': 2,
1494 },
1495 {
1496 # 20 minuten embed
1497 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1498 'info_dict': {
1499 'id': '523629',
1500 'ext': 'mp4',
1501 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1502 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1503 },
1504 'params': {
1505 'skip_download': True,
1506 },
1507 'add_ie': [TwentyMinutenIE.ie_key()],
1508 },
1509 {
1510 # VideoPress embed
1511 'url': 'https://en.support.wordpress.com/videopress/',
1512 'info_dict': {
1513 'id': 'OcobLTqC',
1514 'ext': 'm4v',
1515 'title': 'IMG_5786',
1516 'timestamp': 1435711927,
1517 'upload_date': '20150701',
1518 },
1519 'params': {
1520 'skip_download': True,
1521 },
1522 'add_ie': [VideoPressIE.ie_key()],
1523 },
1524 {
1525 # Rutube embed
1526 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1527 'info_dict': {
1528 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1529 'ext': 'flv',
1530 'title': 'Магаззино: Казань 2',
1531 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1532 'uploader': 'Магаззино',
1533 'upload_date': '20170228',
1534 'uploader_id': '996642',
1535 },
1536 'params': {
1537 'skip_download': True,
1538 },
1539 'add_ie': [RutubeIE.ie_key()],
1540 },
1541 {
1542 # ThePlatform embedded with whitespaces in URLs
1543 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1544 'only_matching': True,
1545 },
1546 {
1547 # Senate ISVP iframe https
1548 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1549 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1550 'info_dict': {
1551 'id': 'govtaff020316',
1552 'ext': 'mp4',
1553 'title': 'Integrated Senate Video Player',
1554 },
1555 'add_ie': [SenateISVPIE.ie_key()],
1556 },
1557 # {
1558 # # TODO: find another test
1559 # # http://schema.org/VideoObject
1560 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1561 # 'md5': '888dcf08b7ea671381f00fab74692755',
1562 # 'info_dict': {
1563 # 'id': 'nyvTSJMKId',
1564 # 'ext': 'mp4',
1565 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1566 # 'description': '#love for cats.',
1567 # 'timestamp': 1461244995,
1568 # 'upload_date': '20160421',
1569 # },
1570 # 'params': {
1571 # 'force_generic_extractor': True,
1572 # },
1573 # }
1574 ]
1575
1576 def report_following_redirect(self, new_url):
1577 """Report information extraction."""
1578 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1579
1580 def _extract_rss(self, url, video_id, doc):
1581 playlist_title = doc.find('./channel/title').text
1582 playlist_desc_el = doc.find('./channel/description')
1583 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1584
1585 entries = []
1586 for it in doc.findall('./channel/item'):
1587 next_url = xpath_text(it, 'link', fatal=False)
1588 if not next_url:
1589 enclosure_nodes = it.findall('./enclosure')
1590 for e in enclosure_nodes:
1591 next_url = e.attrib.get('url')
1592 if next_url:
1593 break
1594
1595 if not next_url:
1596 continue
1597
1598 entries.append({
1599 '_type': 'url',
1600 'url': next_url,
1601 'title': it.find('title').text,
1602 })
1603
1604 return {
1605 '_type': 'playlist',
1606 'id': url,
1607 'title': playlist_title,
1608 'description': playlist_desc,
1609 'entries': entries,
1610 }
1611
1612 def _extract_camtasia(self, url, video_id, webpage):
1613 """ Returns None if no camtasia video can be found. """
1614
1615 camtasia_cfg = self._search_regex(
1616 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1617 webpage, 'camtasia configuration file', default=None)
1618 if camtasia_cfg is None:
1619 return None
1620
1621 title = self._html_search_meta('DC.title', webpage, fatal=True)
1622
1623 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1624 camtasia_cfg = self._download_xml(
1625 camtasia_url, video_id,
1626 note='Downloading camtasia configuration',
1627 errnote='Failed to download camtasia configuration')
1628 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1629
1630 entries = []
1631 for n in fileset_node.getchildren():
1632 url_n = n.find('./uri')
1633 if url_n is None:
1634 continue
1635
1636 entries.append({
1637 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1638 'title': '%s - %s' % (title, n.tag),
1639 'url': compat_urlparse.urljoin(url, url_n.text),
1640 'duration': float_or_none(n.find('./duration').text),
1641 })
1642
1643 return {
1644 '_type': 'playlist',
1645 'entries': entries,
1646 'title': title,
1647 }
1648
1649 def _real_extract(self, url):
1650 if url.startswith('//'):
1651 return {
1652 '_type': 'url',
1653 'url': self.http_scheme() + url,
1654 }
1655
1656 parsed_url = compat_urlparse.urlparse(url)
1657 if not parsed_url.scheme:
1658 default_search = self._downloader.params.get('default_search')
1659 if default_search is None:
1660 default_search = 'fixup_error'
1661
1662 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1663 if '/' in url:
1664 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1665 return self.url_result('http://' + url)
1666 elif default_search != 'fixup_error':
1667 if default_search == 'auto_warning':
1668 if re.match(r'^(?:url|URL)$', url):
1669 raise ExtractorError(
1670 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1671 expected=True)
1672 else:
1673 self._downloader.report_warning(
1674 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1675 return self.url_result('ytsearch:' + url)
1676
1677 if default_search in ('error', 'fixup_error'):
1678 raise ExtractorError(
1679 '%r is not a valid URL. '
1680 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1681 % (url, url), expected=True)
1682 else:
1683 if ':' not in default_search:
1684 default_search += ':'
1685 return self.url_result(default_search + url)
1686
1687 url, smuggled_data = unsmuggle_url(url)
1688 force_videoid = None
1689 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1690 if smuggled_data and 'force_videoid' in smuggled_data:
1691 force_videoid = smuggled_data['force_videoid']
1692 video_id = force_videoid
1693 else:
1694 video_id = self._generic_id(url)
1695
1696 self.to_screen('%s: Requesting header' % video_id)
1697
1698 head_req = HEADRequest(url)
1699 head_response = self._request_webpage(
1700 head_req, video_id,
1701 note=False, errnote='Could not send HEAD request to %s' % url,
1702 fatal=False)
1703
1704 if head_response is not False:
1705 # Check for redirect
1706 new_url = head_response.geturl()
1707 if url != new_url:
1708 self.report_following_redirect(new_url)
1709 if force_videoid:
1710 new_url = smuggle_url(
1711 new_url, {'force_videoid': force_videoid})
1712 return self.url_result(new_url)
1713
1714 full_response = None
1715 if head_response is False:
1716 request = sanitized_Request(url)
1717 request.add_header('Accept-Encoding', '*')
1718 full_response = self._request_webpage(request, video_id)
1719 head_response = full_response
1720
1721 info_dict = {
1722 'id': video_id,
1723 'title': self._generic_title(url),
1724 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1725 }
1726
1727 # Check for direct link to a video
1728 content_type = head_response.headers.get('Content-Type', '').lower()
1729 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1730 if m:
1731 format_id = m.group('format_id')
1732 if format_id.endswith('mpegurl'):
1733 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1734 elif format_id == 'f4m':
1735 formats = self._extract_f4m_formats(url, video_id)
1736 else:
1737 formats = [{
1738 'format_id': m.group('format_id'),
1739 'url': url,
1740 'vcodec': 'none' if m.group('type') == 'audio' else None
1741 }]
1742 info_dict['direct'] = True
1743 self._sort_formats(formats)
1744 info_dict['formats'] = formats
1745 return info_dict
1746
1747 if not self._downloader.params.get('test', False) and not is_intentional:
1748 force = self._downloader.params.get('force_generic_extractor', False)
1749 self._downloader.report_warning(
1750 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1751
1752 if not full_response:
1753 request = sanitized_Request(url)
1754 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1755 # making it impossible to download only chunk of the file (yet we need only 512kB to
1756 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1757 # that will always result in downloading the whole file that is not desirable.
1758 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1759 # to accept raw bytes and being able to download only a chunk.
1760 # It may probably better to solve this by checking Content-Type for application/octet-stream
1761 # after HEAD request finishes, but not sure if we can rely on this.
1762 request.add_header('Accept-Encoding', '*')
1763 full_response = self._request_webpage(request, video_id)
1764
1765 first_bytes = full_response.read(512)
1766
1767 # Is it an M3U playlist?
1768 if first_bytes.startswith(b'#EXTM3U'):
1769 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1770 self._sort_formats(info_dict['formats'])
1771 return info_dict
1772
1773 # Maybe it's a direct link to a video?
1774 # Be careful not to download the whole thing!
1775 if not is_html(first_bytes):
1776 self._downloader.report_warning(
1777 'URL could be a direct video link, returning it as such.')
1778 info_dict.update({
1779 'direct': True,
1780 'url': url,
1781 })
1782 return info_dict
1783
1784 webpage = self._webpage_read_content(
1785 full_response, url, video_id, prefix=first_bytes)
1786
1787 self.report_extraction(video_id)
1788
1789 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1790 try:
1791 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1792 if doc.tag == 'rss':
1793 return self._extract_rss(url, video_id, doc)
1794 elif doc.tag == 'SmoothStreamingMedia':
1795 info_dict['formats'] = self._parse_ism_formats(doc, url)
1796 self._sort_formats(info_dict['formats'])
1797 return info_dict
1798 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1799 smil = self._parse_smil(doc, url, video_id)
1800 self._sort_formats(smil['formats'])
1801 return smil
1802 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1803 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1804 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1805 info_dict['formats'] = self._parse_mpd_formats(
1806 doc, video_id,
1807 mpd_base_url=full_response.geturl().rpartition('/')[0],
1808 mpd_url=url)
1809 self._sort_formats(info_dict['formats'])
1810 return info_dict
1811 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1812 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1813 self._sort_formats(info_dict['formats'])
1814 return info_dict
1815 except compat_xml_parse_error:
1816 pass
1817
1818 # Is it a Camtasia project?
1819 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1820 if camtasia_res is not None:
1821 return camtasia_res
1822
1823 # Sometimes embedded video player is hidden behind percent encoding
1824 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1825 # Unescaping the whole page allows to handle those cases in a generic way
1826 webpage = compat_urllib_parse_unquote(webpage)
1827
1828 # it's tempting to parse this further, but you would
1829 # have to take into account all the variations like
1830 # Video Title - Site Name
1831 # Site Name | Video Title
1832 # Video Title - Tagline | Site Name
1833 # and so on and so forth; it's just not practical
1834 video_title = self._og_search_title(
1835 webpage, default=None) or self._html_search_regex(
1836 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1837 default='video')
1838
1839 # Try to detect age limit automatically
1840 age_limit = self._rta_search(webpage)
1841 # And then there are the jokers who advertise that they use RTA,
1842 # but actually don't.
1843 AGE_LIMIT_MARKERS = [
1844 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1845 ]
1846 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1847 age_limit = 18
1848
1849 # video uploader is domain name
1850 video_uploader = self._search_regex(
1851 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1852
1853 video_description = self._og_search_description(webpage, default=None)
1854 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1855
1856 # Look for Brightcove Legacy Studio embeds
1857 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1858 if bc_urls:
1859 self.to_screen('Brightcove video detected.')
1860 entries = [{
1861 '_type': 'url',
1862 'url': smuggle_url(bc_url, {'Referer': url}),
1863 'ie_key': 'BrightcoveLegacy'
1864 } for bc_url in bc_urls]
1865
1866 return {
1867 '_type': 'playlist',
1868 'title': video_title,
1869 'id': video_id,
1870 'entries': entries,
1871 }
1872
1873 # Look for Brightcove New Studio embeds
1874 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1875 if bc_urls:
1876 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
1877
1878 # Look for ThePlatform embeds
1879 tp_urls = ThePlatformIE._extract_urls(webpage)
1880 if tp_urls:
1881 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
1882
1883 # Look for Vessel embeds
1884 vessel_urls = VesselIE._extract_urls(webpage)
1885 if vessel_urls:
1886 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
1887
1888 # Look for embedded rtl.nl player
1889 matches = re.findall(
1890 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1891 webpage)
1892 if matches:
1893 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
1894
1895 vimeo_urls = VimeoIE._extract_urls(url, webpage)
1896 if vimeo_urls:
1897 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
1898
1899 vid_me_embed_url = self._search_regex(
1900 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1901 webpage, 'vid.me embed', default=None)
1902 if vid_me_embed_url is not None:
1903 return self.url_result(vid_me_embed_url, 'Vidme')
1904
1905 # Look for embedded YouTube player
1906 matches = re.findall(r'''(?x)
1907 (?:
1908 <iframe[^>]+?src=|
1909 data-video-url=|
1910 <embed[^>]+?src=|
1911 embedSWF\(?:\s*|
1912 new\s+SWFObject\(
1913 )
1914 (["\'])
1915 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1916 (?:embed|v|p)/.+?)
1917 \1''', webpage)
1918 if matches:
1919 return self.playlist_from_matches(
1920 matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
1921
1922 # Look for lazyYT YouTube embed
1923 matches = re.findall(
1924 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1925 if matches:
1926 return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
1927
1928 # Look for Wordpress "YouTube Video Importer" plugin
1929 matches = re.findall(r'''(?x)<div[^>]+
1930 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1931 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1932 if matches:
1933 return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
1934
1935 matches = DailymotionIE._extract_urls(webpage)
1936 if matches:
1937 return self.playlist_from_matches(matches, video_id, video_title)
1938
1939 # Look for embedded Dailymotion playlist player (#3822)
1940 m = re.search(
1941 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1942 if m:
1943 playlists = re.findall(
1944 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1945 if playlists:
1946 return self.playlist_from_matches(
1947 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
1948
1949 # Look for embedded Wistia player
1950 match = re.search(
1951 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1952 if match:
1953 embed_url = self._proto_relative_url(
1954 unescapeHTML(match.group('url')))
1955 return {
1956 '_type': 'url_transparent',
1957 'url': embed_url,
1958 'ie_key': 'Wistia',
1959 'uploader': video_uploader,
1960 }
1961
1962 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1963 if match:
1964 return {
1965 '_type': 'url_transparent',
1966 'url': 'wistia:%s' % match.group('id'),
1967 'ie_key': 'Wistia',
1968 'uploader': video_uploader,
1969 }
1970
1971 match = re.search(
1972 r'''(?sx)
1973 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1974 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1975 ''', webpage)
1976 if match:
1977 return self.url_result(self._proto_relative_url(
1978 'wistia:%s' % match.group('id')), 'Wistia')
1979
1980 # Look for SVT player
1981 svt_url = SVTIE._extract_url(webpage)
1982 if svt_url:
1983 return self.url_result(svt_url, 'SVT')
1984
1985 # Look for embedded condenast player
1986 matches = re.findall(
1987 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1988 webpage)
1989 if matches:
1990 return {
1991 '_type': 'playlist',
1992 'entries': [{
1993 '_type': 'url',
1994 'ie_key': 'CondeNast',
1995 'url': ma,
1996 } for ma in matches],
1997 'title': video_title,
1998 'id': video_id,
1999 }
2000
2001 # Look for Bandcamp pages with custom domain
2002 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2003 if mobj is not None:
2004 burl = unescapeHTML(mobj.group(1))
2005 # Don't set the extractor because it can be a track url or an album
2006 return self.url_result(burl)
2007
2008 # Look for embedded Vevo player
2009 mobj = re.search(
2010 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2011 if mobj is not None:
2012 return self.url_result(mobj.group('url'))
2013
2014 # Look for embedded Viddler player
2015 mobj = re.search(
2016 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2017 webpage)
2018 if mobj is not None:
2019 return self.url_result(mobj.group('url'))
2020
2021 # Look for NYTimes player
2022 mobj = re.search(
2023 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2024 webpage)
2025 if mobj is not None:
2026 return self.url_result(mobj.group('url'))
2027
2028 # Look for Libsyn player
2029 mobj = re.search(
2030 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2031 if mobj is not None:
2032 return self.url_result(mobj.group('url'))
2033
2034 # Look for Ooyala videos
2035 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2036 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2037 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2038 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2039 if mobj is not None:
2040 embed_token = self._search_regex(
2041 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2042 webpage, 'ooyala embed token', default=None)
2043 return OoyalaIE._build_url_result(smuggle_url(
2044 mobj.group('ec'), {
2045 'domain': url,
2046 'embed_token': embed_token,
2047 }))
2048
2049 # Look for multiple Ooyala embeds on SBN network websites
2050 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2051 if mobj is not None:
2052 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2053 if embeds:
2054 return self.playlist_from_matches(
2055 embeds, video_id, video_title,
2056 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2057
2058 # Look for Aparat videos
2059 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2060 if mobj is not None:
2061 return self.url_result(mobj.group(1), 'Aparat')
2062
2063 # Look for MPORA videos
2064 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2065 if mobj is not None:
2066 return self.url_result(mobj.group(1), 'Mpora')
2067
2068 # Look for embedded NovaMov-based player
2069 mobj = re.search(
2070 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2071 (?P<url>http://(?:(?:embed|www)\.)?
2072 (?:novamov\.com|
2073 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2074 videoweed\.(?:es|com)|
2075 movshare\.(?:net|sx|ag)|
2076 divxstage\.(?:eu|net|ch|co|at|ag))
2077 /embed\.php.+?)\1''', webpage)
2078 if mobj is not None:
2079 return self.url_result(mobj.group('url'))
2080
2081 # Look for embedded Facebook player
2082 facebook_url = FacebookIE._extract_url(webpage)
2083 if facebook_url is not None:
2084 return self.url_result(facebook_url, 'Facebook')
2085
2086 # Look for embedded VK player
2087 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2088 if mobj is not None:
2089 return self.url_result(mobj.group('url'), 'VK')
2090
2091 # Look for embedded Odnoklassniki player
2092 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2093 if mobj is not None:
2094 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2095
2096 # Look for embedded ivi player
2097 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2098 if mobj is not None:
2099 return self.url_result(mobj.group('url'), 'Ivi')
2100
2101 # Look for embedded Huffington Post player
2102 mobj = re.search(
2103 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2104 if mobj is not None:
2105 return self.url_result(mobj.group('url'), 'HuffPost')
2106
2107 # Look for embed.ly
2108 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2109 if mobj is not None:
2110 return self.url_result(mobj.group('url'))
2111 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2112 if mobj is not None:
2113 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2114
2115 # Look for funnyordie embed
2116 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2117 if matches:
2118 return self.playlist_from_matches(
2119 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2120
2121 # Look for BBC iPlayer embed
2122 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2123 if matches:
2124 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2125
2126 # Look for embedded RUTV player
2127 rutv_url = RUTVIE._extract_url(webpage)
2128 if rutv_url:
2129 return self.url_result(rutv_url, 'RUTV')
2130
2131 # Look for embedded TVC player
2132 tvc_url = TVCIE._extract_url(webpage)
2133 if tvc_url:
2134 return self.url_result(tvc_url, 'TVC')
2135
2136 # Look for embedded SportBox player
2137 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2138 if sportbox_urls:
2139 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2140
2141 # Look for embedded XHamster player
2142 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2143 if xhamster_urls:
2144 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2145
2146 # Look for embedded TNAFlixNetwork player
2147 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2148 if tnaflix_urls:
2149 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2150
2151 # Look for embedded PornHub player
2152 pornhub_urls = PornHubIE._extract_urls(webpage)
2153 if pornhub_urls:
2154 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2155
2156 # Look for embedded DrTuber player
2157 drtuber_urls = DrTuberIE._extract_urls(webpage)
2158 if drtuber_urls:
2159 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2160
2161 # Look for embedded RedTube player
2162 redtube_urls = RedTubeIE._extract_urls(webpage)
2163 if redtube_urls:
2164 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2165
2166 # Look for embedded Tvigle player
2167 mobj = re.search(
2168 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2169 if mobj is not None:
2170 return self.url_result(mobj.group('url'), 'Tvigle')
2171
2172 # Look for embedded TED player
2173 mobj = re.search(
2174 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2175 if mobj is not None:
2176 return self.url_result(mobj.group('url'), 'TED')
2177
2178 # Look for embedded Ustream videos
2179 ustream_url = UstreamIE._extract_url(webpage)
2180 if ustream_url:
2181 return self.url_result(ustream_url, UstreamIE.ie_key())
2182
2183 # Look for embedded arte.tv player
2184 mobj = re.search(
2185 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2186 webpage)
2187 if mobj is not None:
2188 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2189
2190 # Look for embedded francetv player
2191 mobj = re.search(
2192 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2193 webpage)
2194 if mobj is not None:
2195 return self.url_result(mobj.group('url'))
2196
2197 # Look for embedded smotri.com player
2198 smotri_url = SmotriIE._extract_url(webpage)
2199 if smotri_url:
2200 return self.url_result(smotri_url, 'Smotri')
2201
2202 # Look for embedded Myvi.ru player
2203 myvi_url = MyviIE._extract_url(webpage)
2204 if myvi_url:
2205 return self.url_result(myvi_url)
2206
2207 # Look for embedded soundcloud player
2208 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2209 if soundcloud_urls:
2210 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2211
2212 # Look for tunein player
2213 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2214 if tunein_urls:
2215 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2216
2217 # Look for embedded mtvservices player
2218 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2219 if mtvservices_url:
2220 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2221
2222 # Look for embedded yahoo player
2223 mobj = re.search(
2224 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2225 webpage)
2226 if mobj is not None:
2227 return self.url_result(mobj.group('url'), 'Yahoo')
2228
2229 # Look for embedded sbs.com.au player
2230 mobj = re.search(
2231 r'''(?x)
2232 (?:
2233 <meta\s+property="og:video"\s+content=|
2234 <iframe[^>]+?src=
2235 )
2236 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2237 webpage)
2238 if mobj is not None:
2239 return self.url_result(mobj.group('url'), 'SBS')
2240
2241 # Look for embedded Cinchcast player
2242 mobj = re.search(
2243 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2244 webpage)
2245 if mobj is not None:
2246 return self.url_result(mobj.group('url'), 'Cinchcast')
2247
2248 mobj = re.search(
2249 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2250 webpage)
2251 if not mobj:
2252 mobj = re.search(
2253 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2254 webpage)
2255 if mobj is not None:
2256 return self.url_result(mobj.group('url'), 'MLB')
2257
2258 mobj = re.search(
2259 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2260 webpage)
2261 if mobj is not None:
2262 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2263
2264 mobj = re.search(
2265 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2266 webpage)
2267 if mobj is not None:
2268 return self.url_result(mobj.group('url'), 'Livestream')
2269
2270 # Look for Zapiks embed
2271 mobj = re.search(
2272 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2273 if mobj is not None:
2274 return self.url_result(mobj.group('url'), 'Zapiks')
2275
2276 # Look for Kaltura embeds
2277 kaltura_url = KalturaIE._extract_url(webpage)
2278 if kaltura_url:
2279 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2280
2281 # Look for Eagle.Platform embeds
2282 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2283 if eagleplatform_url:
2284 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2285
2286 # Look for ClipYou (uses Eagle.Platform) embeds
2287 mobj = re.search(
2288 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2289 if mobj is not None:
2290 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2291
2292 # Look for Pladform embeds
2293 pladform_url = PladformIE._extract_url(webpage)
2294 if pladform_url:
2295 return self.url_result(pladform_url)
2296
2297 # Look for Videomore embeds
2298 videomore_url = VideomoreIE._extract_url(webpage)
2299 if videomore_url:
2300 return self.url_result(videomore_url)
2301
2302 # Look for Webcaster embeds
2303 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2304 if webcaster_url:
2305 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2306
2307 # Look for Playwire embeds
2308 mobj = re.search(
2309 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2310 if mobj is not None:
2311 return self.url_result(mobj.group('url'))
2312
2313 # Look for 5min embeds
2314 mobj = re.search(
2315 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2316 if mobj is not None:
2317 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2318
2319 # Look for Crooks and Liars embeds
2320 mobj = re.search(
2321 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2322 if mobj is not None:
2323 return self.url_result(mobj.group('url'))
2324
2325 # Look for NBC Sports VPlayer embeds
2326 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2327 if nbc_sports_url:
2328 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2329
2330 # Look for NBC News embeds
2331 nbc_news_embed_url = re.search(
2332 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2333 if nbc_news_embed_url:
2334 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2335
2336 # Look for Google Drive embeds
2337 google_drive_url = GoogleDriveIE._extract_url(webpage)
2338 if google_drive_url:
2339 return self.url_result(google_drive_url, 'GoogleDrive')
2340
2341 # Look for UDN embeds
2342 mobj = re.search(
2343 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2344 if mobj is not None:
2345 return self.url_result(
2346 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2347
2348 # Look for Senate ISVP iframe
2349 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2350 if senate_isvp_url:
2351 return self.url_result(senate_isvp_url, 'SenateISVP')
2352
2353 # Look for Dailymotion Cloud videos
2354 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2355 if dmcloud_url:
2356 return self.url_result(dmcloud_url, 'DailymotionCloud')
2357
2358 # Look for OnionStudios embeds
2359 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2360 if onionstudios_url:
2361 return self.url_result(onionstudios_url)
2362
2363 # Look for ViewLift embeds
2364 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2365 if viewlift_url:
2366 return self.url_result(viewlift_url)
2367
2368 # Look for JWPlatform embeds
2369 jwplatform_url = JWPlatformIE._extract_url(webpage)
2370 if jwplatform_url:
2371 return self.url_result(jwplatform_url, 'JWPlatform')
2372
2373 # Look for Digiteka embeds
2374 digiteka_url = DigitekaIE._extract_url(webpage)
2375 if digiteka_url:
2376 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2377
2378 # Look for Arkena embeds
2379 arkena_url = ArkenaIE._extract_url(webpage)
2380 if arkena_url:
2381 return self.url_result(arkena_url, ArkenaIE.ie_key())
2382
2383 # Look for Piksel embeds
2384 piksel_url = PikselIE._extract_url(webpage)
2385 if piksel_url:
2386 return self.url_result(piksel_url, PikselIE.ie_key())
2387
2388 # Look for Limelight embeds
2389 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2390 if mobj:
2391 lm = {
2392 'Media': 'media',
2393 'Channel': 'channel',
2394 'ChannelList': 'channel_list',
2395 }
2396 return self.url_result(smuggle_url('limelight:%s:%s' % (
2397 lm[mobj.group(1)], mobj.group(2)), {'source_url': url}),
2398 'Limelight%s' % mobj.group(1), mobj.group(2))
2399
2400 mobj = re.search(
2401 r'''(?sx)
2402 <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2403 <param[^>]+
2404 name=(["\'])flashVars\2[^>]+
2405 value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2406 ''', webpage)
2407 if mobj:
2408 return self.url_result(smuggle_url(
2409 'limelight:media:%s' % mobj.group('id'),
2410 {'source_url': url}), 'LimelightMedia', mobj.group('id'))
2411
2412 # Look for AdobeTVVideo embeds
2413 mobj = re.search(
2414 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2415 webpage)
2416 if mobj is not None:
2417 return self.url_result(
2418 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2419 'AdobeTVVideo')
2420
2421 # Look for Vine embeds
2422 mobj = re.search(
2423 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2424 webpage)
2425 if mobj is not None:
2426 return self.url_result(
2427 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2428
2429 # Look for VODPlatform embeds
2430 mobj = re.search(
2431 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2432 webpage)
2433 if mobj is not None:
2434 return self.url_result(
2435 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2436
2437 # Look for Mangomolo embeds
2438 mobj = re.search(
2439 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2440 (?:
2441 video\?.*?\bid=(?P<video_id>\d+)|
2442 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2443 ).+?)\1''', webpage)
2444 if mobj is not None:
2445 info = {
2446 '_type': 'url_transparent',
2447 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2448 'title': video_title,
2449 'description': video_description,
2450 'thumbnail': video_thumbnail,
2451 'uploader': video_uploader,
2452 }
2453 video_id = mobj.group('video_id')
2454 if video_id:
2455 info.update({
2456 'ie_key': 'MangomoloVideo',
2457 'id': video_id,
2458 })
2459 else:
2460 info.update({
2461 'ie_key': 'MangomoloLive',
2462 'id': mobj.group('channel_id'),
2463 })
2464 return info
2465
2466 # Look for Instagram embeds
2467 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2468 if instagram_embed_url is not None:
2469 return self.url_result(
2470 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2471
2472 # Look for LiveLeak embeds
2473 liveleak_url = LiveLeakIE._extract_url(webpage)
2474 if liveleak_url:
2475 return self.url_result(liveleak_url, 'LiveLeak')
2476
2477 # Look for 3Q SDN embeds
2478 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2479 if threeqsdn_url:
2480 return {
2481 '_type': 'url_transparent',
2482 'ie_key': ThreeQSDNIE.ie_key(),
2483 'url': self._proto_relative_url(threeqsdn_url),
2484 'title': video_title,
2485 'description': video_description,
2486 'thumbnail': video_thumbnail,
2487 'uploader': video_uploader,
2488 }
2489
2490 # Look for VBOX7 embeds
2491 vbox7_url = Vbox7IE._extract_url(webpage)
2492 if vbox7_url:
2493 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2494
2495 # Look for DBTV embeds
2496 dbtv_urls = DBTVIE._extract_urls(webpage)
2497 if dbtv_urls:
2498 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2499
2500 # Look for Videa embeds
2501 videa_urls = VideaIE._extract_urls(webpage)
2502 if videa_urls:
2503 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2504
2505 # Look for 20 minuten embeds
2506 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2507 if twentymin_urls:
2508 return self.playlist_from_matches(
2509 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2510
2511 # Look for Openload embeds
2512 openload_urls = OpenloadIE._extract_urls(webpage)
2513 if openload_urls:
2514 return self.playlist_from_matches(
2515 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2516
2517 # Look for VideoPress embeds
2518 videopress_urls = VideoPressIE._extract_urls(webpage)
2519 if videopress_urls:
2520 return self.playlist_from_matches(
2521 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2522
2523 # Look for Rutube embeds
2524 rutube_urls = RutubeIE._extract_urls(webpage)
2525 if rutube_urls:
2526 return self.playlist_from_matches(
2527 rutube_urls, ie=RutubeIE.ie_key())
2528
2529 # Looking for http://schema.org/VideoObject
2530 json_ld = self._search_json_ld(
2531 webpage, video_id, default={}, expected_type='VideoObject')
2532 if json_ld.get('url'):
2533 info_dict.update({
2534 'title': video_title or info_dict['title'],
2535 'description': video_description,
2536 'thumbnail': video_thumbnail,
2537 'age_limit': age_limit
2538 })
2539 info_dict.update(json_ld)
2540 return info_dict
2541
2542 # Look for HTML5 media
2543 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2544 if entries:
2545 for entry in entries:
2546 entry.update({
2547 'id': video_id,
2548 'title': video_title,
2549 })
2550 self._sort_formats(entry['formats'])
2551 return self.playlist_result(entries)
2552
2553 jwplayer_data_str = self._find_jwplayer_data(webpage)
2554 if jwplayer_data_str:
2555 try:
2556 jwplayer_data = self._parse_json(
2557 jwplayer_data_str, video_id, transform_source=js_to_json)
2558 info = self._parse_jwplayer_data(
2559 jwplayer_data, video_id, require_title=False)
2560 if not info.get('title'):
2561 info['title'] = video_title
2562 return info
2563 except ExtractorError:
2564 pass
2565
2566 def check_video(vurl):
2567 if YoutubeIE.suitable(vurl):
2568 return True
2569 if RtmpIE.suitable(vurl):
2570 return True
2571 vpath = compat_urlparse.urlparse(vurl).path
2572 vext = determine_ext(vpath)
2573 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
2574
2575 def filter_video(urls):
2576 return list(filter(check_video, urls))
2577
2578 # Start with something easy: JW Player in SWFObject
2579 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2580 if not found:
2581 # Look for gorilla-vid style embedding
2582 found = filter_video(re.findall(r'''(?sx)
2583 (?:
2584 jw_plugins|
2585 JWPlayerOptions|
2586 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2587 )
2588 .*?
2589 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2590 if not found:
2591 # Broaden the search a little bit
2592 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2593 if not found:
2594 # Broaden the findall a little bit: JWPlayer JS loader
2595 found = filter_video(re.findall(
2596 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2597 if not found:
2598 # Flow player
2599 found = filter_video(re.findall(r'''(?xs)
2600 flowplayer\("[^"]+",\s*
2601 \{[^}]+?\}\s*,
2602 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2603 ["']?url["']?\s*:\s*["']([^"']+)["']
2604 ''', webpage))
2605 if not found:
2606 # Cinerama player
2607 found = re.findall(
2608 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2609 if not found:
2610 # Try to find twitter cards info
2611 # twitter:player:stream should be checked before twitter:player since
2612 # it is expected to contain a raw stream (see
2613 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2614 found = filter_video(re.findall(
2615 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2616 if not found:
2617 # We look for Open Graph info:
2618 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2619 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2620 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2621 if m_video_type is not None:
2622 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2623 if not found:
2624 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2625 found = re.search(
2626 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2627 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2628 webpage)
2629 if not found:
2630 # Look also in Refresh HTTP header
2631 refresh_header = head_response.headers.get('Refresh')
2632 if refresh_header:
2633 # In python 2 response HTTP headers are bytestrings
2634 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2635 refresh_header = refresh_header.decode('iso-8859-1')
2636 found = re.search(REDIRECT_REGEX, refresh_header)
2637 if found:
2638 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2639 if new_url != url:
2640 self.report_following_redirect(new_url)
2641 return {
2642 '_type': 'url',
2643 'url': new_url,
2644 }
2645 else:
2646 found = None
2647
2648 if not found:
2649 # twitter:player is a https URL to iframe player that may or may not
2650 # be supported by youtube-dl thus this is checked the very last (see
2651 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2652 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2653 if embed_url:
2654 return self.url_result(embed_url)
2655
2656 if not found:
2657 raise UnsupportedError(url)
2658
2659 entries = []
2660 for video_url in orderedSet(found):
2661 video_url = unescapeHTML(video_url)
2662 video_url = video_url.replace('\\/', '/')
2663 video_url = compat_urlparse.urljoin(url, video_url)
2664 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2665
2666 # Sometimes, jwplayer extraction will result in a YouTube URL
2667 if YoutubeIE.suitable(video_url):
2668 entries.append(self.url_result(video_url, 'Youtube'))
2669 continue
2670
2671 # here's a fun little line of code for you:
2672 video_id = os.path.splitext(video_id)[0]
2673
2674 entry_info_dict = {
2675 'id': video_id,
2676 'uploader': video_uploader,
2677 'title': video_title,
2678 'age_limit': age_limit,
2679 }
2680
2681 if RtmpIE.suitable(video_url):
2682 entry_info_dict.update({
2683 '_type': 'url_transparent',
2684 'ie_key': RtmpIE.ie_key(),
2685 'url': video_url,
2686 })
2687 entries.append(entry_info_dict)
2688 continue
2689
2690 ext = determine_ext(video_url)
2691 if ext == 'smil':
2692 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2693 elif ext == 'xspf':
2694 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2695 elif ext == 'm3u8':
2696 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2697 elif ext == 'mpd':
2698 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2699 elif ext == 'f4m':
2700 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2701 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2702 # Just matching .ism/manifest is not enough to be reliably sure
2703 # whether it's actually an ISM manifest or some other streaming
2704 # manifest since there are various streaming URL formats
2705 # possible (see [1]) as well as some other shenanigans like
2706 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2707 # so on.
2708 # Thus the most reasonable way to solve this is to delegate
2709 # to generic extractor in order to look into the contents of
2710 # the manifest itself.
2711 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2712 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2713 entry_info_dict = self.url_result(
2714 smuggle_url(video_url, {'to_generic': True}),
2715 GenericIE.ie_key())
2716 else:
2717 entry_info_dict['url'] = video_url
2718
2719 if entry_info_dict.get('formats'):
2720 self._sort_formats(entry_info_dict['formats'])
2721
2722 entries.append(entry_info_dict)
2723
2724 if len(entries) == 1:
2725 return entries[0]
2726 else:
2727 for num, e in enumerate(entries, start=1):
2728 # 'url' results don't have a title
2729 if e.get('title') is not None:
2730 e['title'] = '%s (%d)' % (e['title'], num)
2731 return {
2732 '_type': 'playlist',
2733 'entries': entries,
2734 }