]> jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/generic.py
bc7c21f7a382003b9a5bede56fd10ea923a20d26
[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 'skip': 'video rotates...weekly?',
469 },
470 {
471 # Brightcove:new type [2].
472 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
473 'md5': '2b35148fcf48da41c9fb4591650784f3',
474 'info_dict': {
475 'id': '5348741021001',
476 'ext': 'mp4',
477 'upload_date': '20170306',
478 'uploader_id': '4191638492001',
479 'timestamp': 1488769918,
480 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
481
482 },
483 },
484 {
485 # Alternative brightcove <video> attributes
486 'url': 'http://www.programme-tv.net/videos/extraits/81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche/',
487 'info_dict': {
488 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
489 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
490 },
491 'playlist': [{
492 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
493 'info_dict': {
494 'id': '5311302538001',
495 'ext': 'mp4',
496 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
497 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
498 'timestamp': 1486321708,
499 'upload_date': '20170205',
500 'uploader_id': '800000640001',
501 },
502 'only_matching': True,
503 }],
504 },
505 {
506 # Brightcove with UUID in videoPlayer
507 'url': 'http://www8.hp.com/cn/zh/home.html',
508 'info_dict': {
509 'id': '5255815316001',
510 'ext': 'mp4',
511 'title': 'Sprocket Video - China',
512 'description': 'Sprocket Video - China',
513 'uploader': 'HP-Video Gallery',
514 'timestamp': 1482263210,
515 'upload_date': '20161220',
516 'uploader_id': '1107601872001',
517 },
518 'params': {
519 'skip_download': True, # m3u8 download
520 },
521 },
522 # ooyala video
523 {
524 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
525 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
526 'info_dict': {
527 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
528 'ext': 'mp4',
529 'title': '2cc213299525360.mov', # that's what we get
530 'duration': 238.231,
531 },
532 'add_ie': ['Ooyala'],
533 },
534 {
535 # ooyala video embedded with http://player.ooyala.com/iframe.js
536 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
537 'info_dict': {
538 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
539 'ext': 'mp4',
540 'title': '"Steve Jobs: Man in the Machine" trailer',
541 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
542 'duration': 135.427,
543 },
544 'params': {
545 'skip_download': True,
546 },
547 'skip': 'movie expired',
548 },
549 # embed.ly video
550 {
551 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
552 'info_dict': {
553 'id': '9ODmcdjQcHQ',
554 'ext': 'mp4',
555 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
556 'upload_date': '20140225',
557 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
558 'uploader': 'Tested',
559 'uploader_id': 'testedcom',
560 },
561 # No need to test YoutubeIE here
562 'params': {
563 'skip_download': True,
564 },
565 },
566 # funnyordie embed
567 {
568 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
569 'info_dict': {
570 'id': '18e820ec3f',
571 'ext': 'mp4',
572 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
573 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
574 },
575 # HEAD requests lead to endless 301, while GET is OK
576 'expected_warnings': ['301'],
577 },
578 # RUTV embed
579 {
580 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
581 'info_dict': {
582 'id': '776940',
583 'ext': 'mp4',
584 'title': 'Охотское море стало целиком российским',
585 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
586 },
587 'params': {
588 # m3u8 download
589 'skip_download': True,
590 },
591 },
592 # TVC embed
593 {
594 '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/',
595 'info_dict': {
596 'id': '55304',
597 'ext': 'mp4',
598 'title': 'Дошкольное воспитание',
599 },
600 },
601 # SportBox embed
602 {
603 'url': 'http://www.vestifinance.ru/articles/25753',
604 'info_dict': {
605 'id': '25753',
606 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
607 },
608 'playlist': [{
609 'info_dict': {
610 'id': '370908',
611 'title': 'Госзаказ. День 3',
612 'ext': 'mp4',
613 }
614 }, {
615 'info_dict': {
616 'id': '370905',
617 'title': 'Госзаказ. День 2',
618 'ext': 'mp4',
619 }
620 }, {
621 'info_dict': {
622 'id': '370902',
623 'title': 'Госзаказ. День 1',
624 'ext': 'mp4',
625 }
626 }],
627 'params': {
628 # m3u8 download
629 'skip_download': True,
630 },
631 },
632 # Myvi.ru embed
633 {
634 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
635 'info_dict': {
636 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
637 'ext': 'mp4',
638 'title': 'Ужастики, русский трейлер (2015)',
639 'thumbnail': r're:^https?://.*\.jpg$',
640 'duration': 153,
641 }
642 },
643 # XHamster embed
644 {
645 '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',
646 'info_dict': {
647 'id': 'showthread',
648 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
649 },
650 'playlist_mincount': 7,
651 # This forum does not allow <iframe> syntaxes anymore
652 # Now HTML tags are displayed as-is
653 'skip': 'No videos on this page',
654 },
655 # Embedded TED video
656 {
657 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
658 'md5': '65fdff94098e4a607385a60c5177c638',
659 'info_dict': {
660 'id': '1969',
661 'ext': 'mp4',
662 'title': 'Hidden miracles of the natural world',
663 'uploader': 'Louie Schwartzberg',
664 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
665 }
666 },
667 # nowvideo embed hidden behind percent encoding
668 {
669 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
670 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
671 'info_dict': {
672 'id': '06e53103ca9aa',
673 'ext': 'flv',
674 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
675 'description': 'No description',
676 },
677 },
678 # arte embed
679 {
680 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
681 'md5': '7653032cbb25bf6c80d80f217055fa43',
682 'info_dict': {
683 'id': '048195-004_PLUS7-F',
684 'ext': 'flv',
685 'title': 'X:enius',
686 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
687 'upload_date': '20140320',
688 },
689 'params': {
690 'skip_download': 'Requires rtmpdump'
691 },
692 'skip': 'video gone',
693 },
694 # francetv embed
695 {
696 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
697 'info_dict': {
698 'id': 'EV_30231',
699 'ext': 'mp4',
700 'title': 'Alcaline, le concert avec Calogero',
701 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
702 'upload_date': '20150226',
703 'timestamp': 1424989860,
704 'duration': 5400,
705 },
706 'params': {
707 # m3u8 downloads
708 'skip_download': True,
709 },
710 'expected_warnings': [
711 'Forbidden'
712 ]
713 },
714 # Condé Nast embed
715 {
716 'url': 'http://www.wired.com/2014/04/honda-asimo/',
717 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
718 'info_dict': {
719 'id': '53501be369702d3275860000',
720 'ext': 'mp4',
721 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
722 }
723 },
724 # Dailymotion embed
725 {
726 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
727 'md5': '441aeeb82eb72c422c7f14ec533999cd',
728 'info_dict': {
729 'id': 'k2mm4bCdJ6CQ2i7c8o2',
730 'ext': 'mp4',
731 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
732 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
733 'uploader': 'Spi0n',
734 'uploader_id': 'xgditw',
735 'upload_date': '20140425',
736 'timestamp': 1398441542,
737 },
738 'add_ie': ['Dailymotion'],
739 },
740 # YouTube embed
741 {
742 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
743 'info_dict': {
744 'id': 'FXRb4ykk4S0',
745 'ext': 'mp4',
746 'title': 'The NBL Auction 2014',
747 'uploader': 'BADMINTON England',
748 'uploader_id': 'BADMINTONEvents',
749 'upload_date': '20140603',
750 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
751 },
752 'add_ie': ['Youtube'],
753 'params': {
754 'skip_download': True,
755 }
756 },
757 # MTVSercices embed
758 {
759 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
760 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
761 'info_dict': {
762 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
763 'ext': 'mp4',
764 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
765 'description': 'Two valets share their love for movie star Liam Neesons.',
766 'timestamp': 1349922600,
767 'upload_date': '20121011',
768 },
769 },
770 # YouTube embed via <data-embed-url="">
771 {
772 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
773 'info_dict': {
774 'id': '4vAffPZIT44',
775 'ext': 'mp4',
776 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
777 'uploader': 'Gameloft',
778 'uploader_id': 'gameloft',
779 'upload_date': '20140828',
780 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
781 },
782 'params': {
783 'skip_download': True,
784 }
785 },
786 # YouTube <object> embed
787 {
788 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
789 'md5': '516718101ec834f74318df76259fb3cc',
790 'info_dict': {
791 'id': 'msN87y-iEx0',
792 'ext': 'webm',
793 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
794 'upload_date': '20080526',
795 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
796 'uploader': 'Christopher Sykes',
797 'uploader_id': 'ChristopherJSykes',
798 },
799 'add_ie': ['Youtube'],
800 },
801 # Camtasia studio
802 {
803 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
804 'playlist': [{
805 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
806 'info_dict': {
807 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
808 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
809 'ext': 'flv',
810 'duration': 2235.90,
811 }
812 }, {
813 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
814 'info_dict': {
815 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
816 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
817 'ext': 'flv',
818 'duration': 2235.93,
819 }
820 }],
821 'info_dict': {
822 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
823 }
824 },
825 # Flowplayer
826 {
827 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
828 'md5': '9d65602bf31c6e20014319c7d07fba27',
829 'info_dict': {
830 'id': '5123ea6d5e5a7',
831 'ext': 'mp4',
832 'age_limit': 18,
833 'uploader': 'www.handjobhub.com',
834 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
835 }
836 },
837 # Multiple brightcove videos
838 # https://github.com/rg3/youtube-dl/issues/2283
839 {
840 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
841 'info_dict': {
842 'id': 'always-never',
843 'title': 'Always / Never - The New Yorker',
844 },
845 'playlist_count': 3,
846 'params': {
847 'extract_flat': False,
848 'skip_download': True,
849 }
850 },
851 # MLB embed
852 {
853 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
854 'md5': '96f09a37e44da40dd083e12d9a683327',
855 'info_dict': {
856 'id': '33322633',
857 'ext': 'mp4',
858 'title': 'Ump changes call to ball',
859 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
860 'duration': 48,
861 'timestamp': 1401537900,
862 'upload_date': '20140531',
863 'thumbnail': r're:^https?://.*\.jpg$',
864 },
865 },
866 # Wistia embed
867 {
868 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
869 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
870 'info_dict': {
871 'id': '6e2wtrbdaf',
872 'ext': 'mov',
873 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
874 'description': 'a Paywall Videos video from Remilon',
875 'duration': 644.072,
876 'uploader': 'study.com',
877 'timestamp': 1459678540,
878 'upload_date': '20160403',
879 'filesize': 24687186,
880 },
881 },
882 {
883 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
884 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
885 'info_dict': {
886 'id': 'uxjb0lwrcz',
887 'ext': 'mp4',
888 'title': 'Conversation about Hexagonal Rails Part 1',
889 'description': 'a Martin Fowler video from ThoughtWorks',
890 'duration': 1715.0,
891 'uploader': 'thoughtworks.wistia.com',
892 'timestamp': 1401832161,
893 'upload_date': '20140603',
894 },
895 },
896 # Wistia standard embed (async)
897 {
898 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
899 'info_dict': {
900 'id': '807fafadvk',
901 'ext': 'mp4',
902 'title': 'Drip Brennan Dunn Workshop',
903 'description': 'a JV Webinars video from getdrip-1',
904 'duration': 4986.95,
905 'timestamp': 1463607249,
906 'upload_date': '20160518',
907 },
908 'params': {
909 'skip_download': True,
910 }
911 },
912 # Soundcloud embed
913 {
914 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
915 'info_dict': {
916 'id': '174391317',
917 'ext': 'mp3',
918 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
919 'uploader': 'Sophos Security',
920 'title': 'Chet Chat 171 - Oct 29, 2014',
921 'upload_date': '20141029',
922 }
923 },
924 # Soundcloud multiple embeds
925 {
926 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
927 'info_dict': {
928 'id': '52809',
929 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
930 },
931 'playlist_mincount': 7,
932 },
933 # TuneIn station embed
934 {
935 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
936 'info_dict': {
937 'id': '204146',
938 'ext': 'mp3',
939 'title': 'CNRV',
940 'location': 'Paris, France',
941 'is_live': True,
942 },
943 'params': {
944 # Live stream
945 'skip_download': True,
946 },
947 },
948 # Livestream embed
949 {
950 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
951 'info_dict': {
952 'id': '67864563',
953 'ext': 'flv',
954 'upload_date': '20141112',
955 'title': 'Rosetta #CometLanding webcast HL 10',
956 }
957 },
958 # Another Livestream embed, without 'new.' in URL
959 {
960 'url': 'https://www.freespeech.org/',
961 'info_dict': {
962 'id': '123537347',
963 'ext': 'mp4',
964 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
965 },
966 'params': {
967 # Live stream
968 'skip_download': True,
969 },
970 },
971 # LazyYT
972 {
973 'url': 'https://skiplagged.com/',
974 'info_dict': {
975 'id': 'skiplagged',
976 'title': 'Skiplagged: The smart way to find cheap flights',
977 },
978 'playlist_mincount': 1,
979 'add_ie': ['Youtube'],
980 },
981 # Cinchcast embed
982 {
983 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
984 'info_dict': {
985 'id': '7141703',
986 'ext': 'mp3',
987 'upload_date': '20141126',
988 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
989 }
990 },
991 # Cinerama player
992 {
993 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
994 'info_dict': {
995 'id': '730m_DandD_1901_512k',
996 'ext': 'mp4',
997 'uploader': 'www.abc.net.au',
998 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
999 }
1000 },
1001 # embedded viddler video
1002 {
1003 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1004 'info_dict': {
1005 'id': '4d03aad9',
1006 'ext': 'mp4',
1007 'uploader': 'deadspin',
1008 'title': 'WALL-TO-GORTAT',
1009 'timestamp': 1422285291,
1010 'upload_date': '20150126',
1011 },
1012 'add_ie': ['Viddler'],
1013 },
1014 # Libsyn embed
1015 {
1016 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1017 'info_dict': {
1018 'id': '3377616',
1019 'ext': 'mp3',
1020 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1021 'description': 'md5:601cb790edd05908957dae8aaa866465',
1022 'upload_date': '20150220',
1023 },
1024 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1025 },
1026 # jwplayer YouTube
1027 {
1028 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1029 'info_dict': {
1030 'id': 'Mrj4DVp2zeA',
1031 'ext': 'mp4',
1032 'upload_date': '20150212',
1033 'uploader': 'The National Archives UK',
1034 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1035 'uploader_id': 'NationalArchives08',
1036 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1037 },
1038 },
1039 # jwplayer rtmp
1040 {
1041 'url': 'http://www.suffolk.edu/sjc/',
1042 'info_dict': {
1043 'id': 'sjclive',
1044 'ext': 'flv',
1045 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1046 'uploader': 'www.suffolk.edu',
1047 },
1048 'params': {
1049 'skip_download': True,
1050 }
1051 },
1052 # Complex jwplayer
1053 {
1054 'url': 'http://www.indiedb.com/games/king-machine/videos',
1055 'info_dict': {
1056 'id': 'videos',
1057 'ext': 'mp4',
1058 'title': 'king machine trailer 1',
1059 'thumbnail': r're:^https?://.*\.jpg$',
1060 },
1061 },
1062 {
1063 # JWPlayer config passed as variable
1064 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1065 'info_dict': {
1066 'id': '3326530_hq',
1067 'ext': 'mp4',
1068 'title': 'ARIELE | Tube Cup',
1069 'uploader': 'www.txxx.com',
1070 'age_limit': 18,
1071 },
1072 'params': {
1073 'skip_download': True,
1074 }
1075 },
1076 # rtl.nl embed
1077 {
1078 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1079 'playlist_mincount': 5,
1080 'info_dict': {
1081 'id': 'aanslagen-kopenhagen',
1082 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1083 }
1084 },
1085 # Zapiks embed
1086 {
1087 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1088 'info_dict': {
1089 'id': '118046',
1090 'ext': 'mp4',
1091 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1092 }
1093 },
1094 # Kaltura embed (different embed code)
1095 {
1096 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1097 'info_dict': {
1098 'id': '1_a52wc67y',
1099 'ext': 'flv',
1100 'upload_date': '20150127',
1101 'uploader_id': 'PremierMedia',
1102 'timestamp': int,
1103 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1104 },
1105 },
1106 # Kaltura embed with single quotes
1107 {
1108 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1109 'info_dict': {
1110 'id': '0_izeg5utt',
1111 'ext': 'mp4',
1112 'title': '35871',
1113 'timestamp': 1355743100,
1114 'upload_date': '20121217',
1115 'uploader_id': 'batchUser',
1116 },
1117 'add_ie': ['Kaltura'],
1118 },
1119 {
1120 # Kaltura embedded via quoted entry_id
1121 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1122 'info_dict': {
1123 'id': '0_utuok90b',
1124 'ext': 'mp4',
1125 'title': '06_matthew_brender_raj_dutt',
1126 'timestamp': 1466638791,
1127 'upload_date': '20160622',
1128 },
1129 'add_ie': ['Kaltura'],
1130 'expected_warnings': [
1131 'Could not send HEAD request'
1132 ],
1133 'params': {
1134 'skip_download': True,
1135 }
1136 },
1137 {
1138 # Kaltura embedded, some fileExt broken (#11480)
1139 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1140 'info_dict': {
1141 'id': '1_sgtvehim',
1142 'ext': 'mp4',
1143 'title': 'Our "Standard Models" of particle physics and cosmology',
1144 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1145 'timestamp': 1321158993,
1146 'upload_date': '20111113',
1147 'uploader_id': 'kps1',
1148 },
1149 'add_ie': ['Kaltura'],
1150 },
1151 {
1152 # Kaltura iframe embed
1153 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1154 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1155 'info_dict': {
1156 'id': '0_f2cfbpwy',
1157 'ext': 'mp4',
1158 'title': 'I. M. Pei: A Centennial Celebration',
1159 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1160 'upload_date': '20170403',
1161 'uploader_id': 'batchUser',
1162 'timestamp': 1491232186,
1163 },
1164 'add_ie': ['Kaltura'],
1165 },
1166 # Eagle.Platform embed (generic URL)
1167 {
1168 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1169 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1170 'info_dict': {
1171 'id': '227304',
1172 'ext': 'mp4',
1173 'title': 'Навальный вышел на свободу',
1174 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1175 'thumbnail': r're:^https?://.*\.jpg$',
1176 'duration': 87,
1177 'view_count': int,
1178 'age_limit': 0,
1179 },
1180 },
1181 # ClipYou (Eagle.Platform) embed (custom URL)
1182 {
1183 'url': 'http://muz-tv.ru/play/7129/',
1184 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1185 'info_dict': {
1186 'id': '12820',
1187 'ext': 'mp4',
1188 'title': "'O Sole Mio",
1189 'thumbnail': r're:^https?://.*\.jpg$',
1190 'duration': 216,
1191 'view_count': int,
1192 },
1193 },
1194 # Pladform embed
1195 {
1196 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1197 'info_dict': {
1198 'id': '100183293',
1199 'ext': 'mp4',
1200 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1201 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1202 'thumbnail': r're:^https?://.*\.jpg$',
1203 'duration': 694,
1204 'age_limit': 0,
1205 },
1206 },
1207 # Playwire embed
1208 {
1209 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1210 'info_dict': {
1211 'id': '3519514',
1212 'ext': 'mp4',
1213 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1214 'thumbnail': r're:^https?://.*\.png$',
1215 'duration': 45.115,
1216 },
1217 },
1218 # 5min embed
1219 {
1220 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1221 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1222 'info_dict': {
1223 'id': '518726732',
1224 'ext': 'mp4',
1225 'title': 'Facebook Creates "On This Day" | Crunch Report',
1226 },
1227 },
1228 # SVT embed
1229 {
1230 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1231 'info_dict': {
1232 'id': '2900353',
1233 'ext': 'flv',
1234 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1235 'duration': 27,
1236 'age_limit': 0,
1237 },
1238 },
1239 # Crooks and Liars embed
1240 {
1241 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1242 'info_dict': {
1243 'id': '8RUoRhRi',
1244 'ext': 'mp4',
1245 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1246 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1247 'timestamp': 1428207000,
1248 'upload_date': '20150405',
1249 'uploader': 'Heather',
1250 },
1251 },
1252 # Crooks and Liars external embed
1253 {
1254 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1255 'info_dict': {
1256 'id': 'MTE3MjUtMzQ2MzA',
1257 'ext': 'mp4',
1258 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1259 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1260 'timestamp': 1265032391,
1261 'upload_date': '20100201',
1262 'uploader': 'Heather',
1263 },
1264 },
1265 # NBC Sports vplayer embed
1266 {
1267 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1268 'info_dict': {
1269 'id': 'ln7x1qSThw4k',
1270 'ext': 'flv',
1271 'title': "PFT Live: New leader in the 'new-look' defense",
1272 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1273 'uploader': 'NBCU-SPORTS',
1274 'upload_date': '20140107',
1275 'timestamp': 1389118457,
1276 },
1277 },
1278 # NBC News embed
1279 {
1280 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1281 'md5': '1aa589c675898ae6d37a17913cf68d66',
1282 'info_dict': {
1283 'id': '701714499682',
1284 'ext': 'mp4',
1285 'title': 'PREVIEW: On Assignment: David Letterman',
1286 '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.',
1287 },
1288 },
1289 # UDN embed
1290 {
1291 'url': 'https://video.udn.com/news/300346',
1292 'md5': 'fd2060e988c326991037b9aff9df21a6',
1293 'info_dict': {
1294 'id': '300346',
1295 'ext': 'mp4',
1296 'title': '中一中男師變性 全校師生力挺',
1297 'thumbnail': r're:^https?://.*\.jpg$',
1298 },
1299 'params': {
1300 # m3u8 download
1301 'skip_download': True,
1302 },
1303 },
1304 # Ooyala embed
1305 {
1306 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1307 'info_dict': {
1308 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1309 'ext': 'mp4',
1310 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1311 'title': 'This is what separates the Excel masters from the wannabes',
1312 'duration': 191.933,
1313 },
1314 'params': {
1315 # m3u8 downloads
1316 'skip_download': True,
1317 }
1318 },
1319 # Brightcove URL in single quotes
1320 {
1321 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1322 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1323 'info_dict': {
1324 'id': '4255764656001',
1325 'ext': 'mp4',
1326 'title': 'SN Presents: Russell Martin, World Citizen',
1327 '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.',
1328 'uploader': 'Rogers Sportsnet',
1329 'uploader_id': '1704050871',
1330 'upload_date': '20150525',
1331 'timestamp': 1432570283,
1332 },
1333 },
1334 # Dailymotion Cloud video
1335 {
1336 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1337 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1338 'info_dict': {
1339 'id': 'x2uy8t3',
1340 'ext': 'mp4',
1341 'title': 'Sauvons les abeilles ! - Le débat',
1342 'description': 'md5:d9082128b1c5277987825d684939ca26',
1343 'thumbnail': r're:^https?://.*\.jpe?g$',
1344 'timestamp': 1434970506,
1345 'upload_date': '20150622',
1346 'uploader': 'Public Sénat',
1347 'uploader_id': 'xa9gza',
1348 }
1349 },
1350 # OnionStudios embed
1351 {
1352 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1353 'info_dict': {
1354 'id': '2855',
1355 'ext': 'mp4',
1356 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1357 'thumbnail': r're:^https?://.*\.jpe?g$',
1358 'uploader': 'ClickHole',
1359 'uploader_id': 'clickhole',
1360 }
1361 },
1362 # SnagFilms embed
1363 {
1364 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1365 'info_dict': {
1366 'id': '74849a00-85a9-11e1-9660-123139220831',
1367 'ext': 'mp4',
1368 'title': '#whilewewatch',
1369 }
1370 },
1371 # AdobeTVVideo embed
1372 {
1373 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1374 'md5': '43662b577c018ad707a63766462b1e87',
1375 'info_dict': {
1376 'id': '2456',
1377 'ext': 'mp4',
1378 'title': 'New experience with Acrobat DC',
1379 'description': 'New experience with Acrobat DC',
1380 'duration': 248.667,
1381 },
1382 },
1383 # BrightcoveInPageEmbed embed
1384 {
1385 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1386 'info_dict': {
1387 'id': '4238694884001',
1388 'ext': 'flv',
1389 'title': 'Tabletop: Dread, Last Thoughts',
1390 'description': 'Tabletop: Dread, Last Thoughts',
1391 'duration': 51690,
1392 },
1393 },
1394 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1395 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1396 {
1397 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1398 'info_dict': {
1399 'id': '4785848093001',
1400 'ext': 'mp4',
1401 'title': 'The Cardinal Pell Interview',
1402 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1403 'uploader': 'GlobeCast Australia - GlobeStream',
1404 'uploader_id': '2733773828001',
1405 'upload_date': '20160304',
1406 'timestamp': 1457083087,
1407 },
1408 'params': {
1409 # m3u8 downloads
1410 'skip_download': True,
1411 },
1412 },
1413 # Another form of arte.tv embed
1414 {
1415 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1416 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1417 'info_dict': {
1418 'id': '030273-562_PLUS7-F',
1419 'ext': 'mp4',
1420 'title': 'ARTE Reportage - Nulle part, en France',
1421 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1422 'upload_date': '20160409',
1423 },
1424 },
1425 # LiveLeak embed
1426 {
1427 'url': 'http://www.wykop.pl/link/3088787/',
1428 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1429 'info_dict': {
1430 'id': '874_1459135191',
1431 'ext': 'mp4',
1432 'title': 'Man shows poor quality of new apartment building',
1433 'description': 'The wall is like a sand pile.',
1434 'uploader': 'Lake8737',
1435 }
1436 },
1437 # Duplicated embedded video URLs
1438 {
1439 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1440 'info_dict': {
1441 'id': '149298443_480_16c25b74_2',
1442 'ext': 'mp4',
1443 'title': 'vs. Blue Orange Spring Game',
1444 'uploader': 'www.hudl.com',
1445 },
1446 },
1447 # twitter:player:stream embed
1448 {
1449 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1450 'info_dict': {
1451 'id': 'master',
1452 'ext': 'mp4',
1453 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1454 'uploader': 'www.rtl.be',
1455 },
1456 'params': {
1457 # m3u8 downloads
1458 'skip_download': True,
1459 },
1460 },
1461 # twitter:player embed
1462 {
1463 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1464 'md5': 'a3e0df96369831de324f0778e126653c',
1465 'info_dict': {
1466 'id': '4909620399001',
1467 'ext': 'mp4',
1468 'title': 'What Do Black Holes Sound Like?',
1469 'description': 'what do black holes sound like',
1470 'upload_date': '20160524',
1471 'uploader_id': '29913724001',
1472 'timestamp': 1464107587,
1473 'uploader': 'TheAtlantic',
1474 },
1475 'add_ie': ['BrightcoveLegacy'],
1476 },
1477 # Facebook <iframe> embed
1478 {
1479 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1480 'md5': 'fbcde74f534176ecb015849146dd3aee',
1481 'info_dict': {
1482 'id': '599637780109885',
1483 'ext': 'mp4',
1484 'title': 'Facebook video #599637780109885',
1485 },
1486 },
1487 # Facebook API embed
1488 {
1489 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1490 'md5': 'a47372ee61b39a7b90287094d447d94e',
1491 'info_dict': {
1492 'id': '10153467542406923',
1493 'ext': 'mp4',
1494 'title': 'Facebook video #10153467542406923',
1495 },
1496 },
1497 # Wordpress "YouTube Video Importer" plugin
1498 {
1499 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1500 'md5': 'd16797741b560b485194eddda8121b48',
1501 'info_dict': {
1502 'id': 'HNTXWDXV9Is',
1503 'ext': 'mp4',
1504 'title': 'Blue Devils Drumline Stanford lot 2016',
1505 'upload_date': '20160627',
1506 'uploader_id': 'GENOCIDE8GENERAL10',
1507 'uploader': 'cylus cyrus',
1508 },
1509 },
1510 {
1511 # video stored on custom kaltura server
1512 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1513 'md5': '537617d06e64dfed891fa1593c4b30cc',
1514 'info_dict': {
1515 'id': '0_1iotm5bh',
1516 'ext': 'mp4',
1517 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1518 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1519 'uploader_id': 'videos.expansion@el-mundo.net',
1520 'upload_date': '20150429',
1521 'timestamp': 1430303472,
1522 },
1523 'add_ie': ['Kaltura'],
1524 },
1525 {
1526 # Non-standard Vimeo embed
1527 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1528 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1529 'info_dict': {
1530 'id': '148867247',
1531 'ext': 'mp4',
1532 'title': 'Understanding the web - Teaser',
1533 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1534 'upload_date': '20151214',
1535 'uploader': 'OpenClassrooms',
1536 'uploader_id': 'openclassrooms',
1537 },
1538 'add_ie': ['Vimeo'],
1539 },
1540 {
1541 # generic vimeo embed that requires original URL passed as Referer
1542 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1543 'only_matching': True,
1544 },
1545 {
1546 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1547 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1548 'info_dict': {
1549 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1550 'ext': 'mp4',
1551 'title': 'Big Buck Bunny',
1552 'description': 'Royalty free test video',
1553 'timestamp': 1432816365,
1554 'upload_date': '20150528',
1555 'is_live': False,
1556 },
1557 'params': {
1558 'skip_download': True,
1559 },
1560 'add_ie': [ArkenaIE.ie_key()],
1561 },
1562 {
1563 '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/',
1564 'info_dict': {
1565 'id': '1c7141f46c',
1566 'ext': 'mp4',
1567 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1568 },
1569 'params': {
1570 'skip_download': True,
1571 },
1572 'add_ie': [Vbox7IE.ie_key()],
1573 },
1574 {
1575 # DBTV embeds
1576 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1577 'info_dict': {
1578 'id': '43254897',
1579 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1580 },
1581 'playlist_mincount': 3,
1582 },
1583 {
1584 # Videa embeds
1585 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1586 'info_dict': {
1587 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1588 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1589 },
1590 'playlist_mincount': 2,
1591 },
1592 {
1593 # 20 minuten embed
1594 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1595 'info_dict': {
1596 'id': '523629',
1597 'ext': 'mp4',
1598 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1599 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1600 },
1601 'params': {
1602 'skip_download': True,
1603 },
1604 'add_ie': [TwentyMinutenIE.ie_key()],
1605 },
1606 {
1607 # VideoPress embed
1608 'url': 'https://en.support.wordpress.com/videopress/',
1609 'info_dict': {
1610 'id': 'OcobLTqC',
1611 'ext': 'm4v',
1612 'title': 'IMG_5786',
1613 'timestamp': 1435711927,
1614 'upload_date': '20150701',
1615 },
1616 'params': {
1617 'skip_download': True,
1618 },
1619 'add_ie': [VideoPressIE.ie_key()],
1620 },
1621 {
1622 # Rutube embed
1623 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1624 'info_dict': {
1625 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1626 'ext': 'flv',
1627 'title': 'Магаззино: Казань 2',
1628 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1629 'uploader': 'Магаззино',
1630 'upload_date': '20170228',
1631 'uploader_id': '996642',
1632 },
1633 'params': {
1634 'skip_download': True,
1635 },
1636 'add_ie': [RutubeIE.ie_key()],
1637 },
1638 {
1639 # ThePlatform embedded with whitespaces in URLs
1640 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1641 'only_matching': True,
1642 },
1643 {
1644 # Senate ISVP iframe https
1645 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1646 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1647 'info_dict': {
1648 'id': 'govtaff020316',
1649 'ext': 'mp4',
1650 'title': 'Integrated Senate Video Player',
1651 },
1652 'add_ie': [SenateISVPIE.ie_key()],
1653 },
1654 # {
1655 # # TODO: find another test
1656 # # http://schema.org/VideoObject
1657 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1658 # 'md5': '888dcf08b7ea671381f00fab74692755',
1659 # 'info_dict': {
1660 # 'id': 'nyvTSJMKId',
1661 # 'ext': 'mp4',
1662 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1663 # 'description': '#love for cats.',
1664 # 'timestamp': 1461244995,
1665 # 'upload_date': '20160421',
1666 # },
1667 # 'params': {
1668 # 'force_generic_extractor': True,
1669 # },
1670 # }
1671 ]
1672
1673 def report_following_redirect(self, new_url):
1674 """Report information extraction."""
1675 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1676
1677 def _extract_rss(self, url, video_id, doc):
1678 playlist_title = doc.find('./channel/title').text
1679 playlist_desc_el = doc.find('./channel/description')
1680 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1681
1682 entries = []
1683 for it in doc.findall('./channel/item'):
1684 next_url = xpath_text(it, 'link', fatal=False)
1685 if not next_url:
1686 enclosure_nodes = it.findall('./enclosure')
1687 for e in enclosure_nodes:
1688 next_url = e.attrib.get('url')
1689 if next_url:
1690 break
1691
1692 if not next_url:
1693 continue
1694
1695 entries.append({
1696 '_type': 'url',
1697 'url': next_url,
1698 'title': it.find('title').text,
1699 })
1700
1701 return {
1702 '_type': 'playlist',
1703 'id': url,
1704 'title': playlist_title,
1705 'description': playlist_desc,
1706 'entries': entries,
1707 }
1708
1709 def _extract_camtasia(self, url, video_id, webpage):
1710 """ Returns None if no camtasia video can be found. """
1711
1712 camtasia_cfg = self._search_regex(
1713 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1714 webpage, 'camtasia configuration file', default=None)
1715 if camtasia_cfg is None:
1716 return None
1717
1718 title = self._html_search_meta('DC.title', webpage, fatal=True)
1719
1720 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1721 camtasia_cfg = self._download_xml(
1722 camtasia_url, video_id,
1723 note='Downloading camtasia configuration',
1724 errnote='Failed to download camtasia configuration')
1725 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1726
1727 entries = []
1728 for n in fileset_node.getchildren():
1729 url_n = n.find('./uri')
1730 if url_n is None:
1731 continue
1732
1733 entries.append({
1734 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1735 'title': '%s - %s' % (title, n.tag),
1736 'url': compat_urlparse.urljoin(url, url_n.text),
1737 'duration': float_or_none(n.find('./duration').text),
1738 })
1739
1740 return {
1741 '_type': 'playlist',
1742 'entries': entries,
1743 'title': title,
1744 }
1745
1746 def _real_extract(self, url):
1747 if url.startswith('//'):
1748 return {
1749 '_type': 'url',
1750 'url': self.http_scheme() + url,
1751 }
1752
1753 parsed_url = compat_urlparse.urlparse(url)
1754 if not parsed_url.scheme:
1755 default_search = self._downloader.params.get('default_search')
1756 if default_search is None:
1757 default_search = 'fixup_error'
1758
1759 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1760 if '/' in url:
1761 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1762 return self.url_result('http://' + url)
1763 elif default_search != 'fixup_error':
1764 if default_search == 'auto_warning':
1765 if re.match(r'^(?:url|URL)$', url):
1766 raise ExtractorError(
1767 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1768 expected=True)
1769 else:
1770 self._downloader.report_warning(
1771 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1772 return self.url_result('ytsearch:' + url)
1773
1774 if default_search in ('error', 'fixup_error'):
1775 raise ExtractorError(
1776 '%r is not a valid URL. '
1777 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1778 % (url, url), expected=True)
1779 else:
1780 if ':' not in default_search:
1781 default_search += ':'
1782 return self.url_result(default_search + url)
1783
1784 url, smuggled_data = unsmuggle_url(url)
1785 force_videoid = None
1786 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1787 if smuggled_data and 'force_videoid' in smuggled_data:
1788 force_videoid = smuggled_data['force_videoid']
1789 video_id = force_videoid
1790 else:
1791 video_id = self._generic_id(url)
1792
1793 self.to_screen('%s: Requesting header' % video_id)
1794
1795 head_req = HEADRequest(url)
1796 head_response = self._request_webpage(
1797 head_req, video_id,
1798 note=False, errnote='Could not send HEAD request to %s' % url,
1799 fatal=False)
1800
1801 if head_response is not False:
1802 # Check for redirect
1803 new_url = head_response.geturl()
1804 if url != new_url:
1805 self.report_following_redirect(new_url)
1806 if force_videoid:
1807 new_url = smuggle_url(
1808 new_url, {'force_videoid': force_videoid})
1809 return self.url_result(new_url)
1810
1811 full_response = None
1812 if head_response is False:
1813 request = sanitized_Request(url)
1814 request.add_header('Accept-Encoding', '*')
1815 full_response = self._request_webpage(request, video_id)
1816 head_response = full_response
1817
1818 info_dict = {
1819 'id': video_id,
1820 'title': self._generic_title(url),
1821 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1822 }
1823
1824 # Check for direct link to a video
1825 content_type = head_response.headers.get('Content-Type', '').lower()
1826 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1827 if m:
1828 format_id = m.group('format_id')
1829 if format_id.endswith('mpegurl'):
1830 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1831 elif format_id == 'f4m':
1832 formats = self._extract_f4m_formats(url, video_id)
1833 else:
1834 formats = [{
1835 'format_id': m.group('format_id'),
1836 'url': url,
1837 'vcodec': 'none' if m.group('type') == 'audio' else None
1838 }]
1839 info_dict['direct'] = True
1840 self._sort_formats(formats)
1841 info_dict['formats'] = formats
1842 return info_dict
1843
1844 if not self._downloader.params.get('test', False) and not is_intentional:
1845 force = self._downloader.params.get('force_generic_extractor', False)
1846 self._downloader.report_warning(
1847 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1848
1849 if not full_response:
1850 request = sanitized_Request(url)
1851 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1852 # making it impossible to download only chunk of the file (yet we need only 512kB to
1853 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1854 # that will always result in downloading the whole file that is not desirable.
1855 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1856 # to accept raw bytes and being able to download only a chunk.
1857 # It may probably better to solve this by checking Content-Type for application/octet-stream
1858 # after HEAD request finishes, but not sure if we can rely on this.
1859 request.add_header('Accept-Encoding', '*')
1860 full_response = self._request_webpage(request, video_id)
1861
1862 first_bytes = full_response.read(512)
1863
1864 # Is it an M3U playlist?
1865 if first_bytes.startswith(b'#EXTM3U'):
1866 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1867 self._sort_formats(info_dict['formats'])
1868 return info_dict
1869
1870 # Maybe it's a direct link to a video?
1871 # Be careful not to download the whole thing!
1872 if not is_html(first_bytes):
1873 self._downloader.report_warning(
1874 'URL could be a direct video link, returning it as such.')
1875 info_dict.update({
1876 'direct': True,
1877 'url': url,
1878 })
1879 return info_dict
1880
1881 webpage = self._webpage_read_content(
1882 full_response, url, video_id, prefix=first_bytes)
1883
1884 self.report_extraction(video_id)
1885
1886 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1887 try:
1888 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1889 if doc.tag == 'rss':
1890 return self._extract_rss(url, video_id, doc)
1891 elif doc.tag == 'SmoothStreamingMedia':
1892 info_dict['formats'] = self._parse_ism_formats(doc, url)
1893 self._sort_formats(info_dict['formats'])
1894 return info_dict
1895 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1896 smil = self._parse_smil(doc, url, video_id)
1897 self._sort_formats(smil['formats'])
1898 return smil
1899 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1900 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1901 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1902 info_dict['formats'] = self._parse_mpd_formats(
1903 doc, video_id,
1904 mpd_base_url=full_response.geturl().rpartition('/')[0],
1905 mpd_url=url)
1906 self._sort_formats(info_dict['formats'])
1907 return info_dict
1908 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1909 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1910 self._sort_formats(info_dict['formats'])
1911 return info_dict
1912 except compat_xml_parse_error:
1913 pass
1914
1915 # Is it a Camtasia project?
1916 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1917 if camtasia_res is not None:
1918 return camtasia_res
1919
1920 # Sometimes embedded video player is hidden behind percent encoding
1921 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1922 # Unescaping the whole page allows to handle those cases in a generic way
1923 webpage = compat_urllib_parse_unquote(webpage)
1924
1925 # it's tempting to parse this further, but you would
1926 # have to take into account all the variations like
1927 # Video Title - Site Name
1928 # Site Name | Video Title
1929 # Video Title - Tagline | Site Name
1930 # and so on and so forth; it's just not practical
1931 video_title = self._og_search_title(
1932 webpage, default=None) or self._html_search_regex(
1933 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1934 default='video')
1935
1936 # Try to detect age limit automatically
1937 age_limit = self._rta_search(webpage)
1938 # And then there are the jokers who advertise that they use RTA,
1939 # but actually don't.
1940 AGE_LIMIT_MARKERS = [
1941 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1942 ]
1943 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1944 age_limit = 18
1945
1946 # video uploader is domain name
1947 video_uploader = self._search_regex(
1948 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1949
1950 video_description = self._og_search_description(webpage, default=None)
1951 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1952
1953 # Look for Brightcove Legacy Studio embeds
1954 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1955 if bc_urls:
1956 entries = [{
1957 '_type': 'url',
1958 'url': smuggle_url(bc_url, {'Referer': url}),
1959 'ie_key': 'BrightcoveLegacy'
1960 } for bc_url in bc_urls]
1961
1962 return {
1963 '_type': 'playlist',
1964 'title': video_title,
1965 'id': video_id,
1966 'entries': entries,
1967 }
1968
1969 # Look for Brightcove New Studio embeds
1970 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
1971 if bc_urls:
1972 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
1973
1974 # Look for ThePlatform embeds
1975 tp_urls = ThePlatformIE._extract_urls(webpage)
1976 if tp_urls:
1977 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
1978
1979 # Look for Vessel embeds
1980 vessel_urls = VesselIE._extract_urls(webpage)
1981 if vessel_urls:
1982 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
1983
1984 # Look for embedded rtl.nl player
1985 matches = re.findall(
1986 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1987 webpage)
1988 if matches:
1989 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
1990
1991 vimeo_urls = VimeoIE._extract_urls(url, webpage)
1992 if vimeo_urls:
1993 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
1994
1995 vid_me_embed_url = self._search_regex(
1996 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1997 webpage, 'vid.me embed', default=None)
1998 if vid_me_embed_url is not None:
1999 return self.url_result(vid_me_embed_url, 'Vidme')
2000
2001 # Look for embedded YouTube player
2002 matches = re.findall(r'''(?x)
2003 (?:
2004 <iframe[^>]+?src=|
2005 data-video-url=|
2006 <embed[^>]+?src=|
2007 embedSWF\(?:\s*|
2008 <object[^>]+data=|
2009 new\s+SWFObject\(
2010 )
2011 (["\'])
2012 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2013 (?:embed|v|p)/.+?)
2014 \1''', webpage)
2015 if matches:
2016 return self.playlist_from_matches(
2017 matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
2018
2019 # Look for lazyYT YouTube embed
2020 matches = re.findall(
2021 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
2022 if matches:
2023 return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
2024
2025 # Look for Wordpress "YouTube Video Importer" plugin
2026 matches = re.findall(r'''(?x)<div[^>]+
2027 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2028 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2029 if matches:
2030 return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
2031
2032 matches = DailymotionIE._extract_urls(webpage)
2033 if matches:
2034 return self.playlist_from_matches(matches, video_id, video_title)
2035
2036 # Look for embedded Dailymotion playlist player (#3822)
2037 m = re.search(
2038 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2039 if m:
2040 playlists = re.findall(
2041 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2042 if playlists:
2043 return self.playlist_from_matches(
2044 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2045
2046 # Look for embedded Wistia player
2047 match = re.search(
2048 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
2049 if match:
2050 embed_url = self._proto_relative_url(
2051 unescapeHTML(match.group('url')))
2052 return {
2053 '_type': 'url_transparent',
2054 'url': embed_url,
2055 'ie_key': 'Wistia',
2056 'uploader': video_uploader,
2057 }
2058
2059 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
2060 if match:
2061 return {
2062 '_type': 'url_transparent',
2063 'url': 'wistia:%s' % match.group('id'),
2064 'ie_key': 'Wistia',
2065 'uploader': video_uploader,
2066 }
2067
2068 match = re.search(
2069 r'''(?sx)
2070 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
2071 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
2072 ''', webpage)
2073 if match:
2074 return self.url_result(self._proto_relative_url(
2075 'wistia:%s' % match.group('id')), 'Wistia')
2076
2077 # Look for SVT player
2078 svt_url = SVTIE._extract_url(webpage)
2079 if svt_url:
2080 return self.url_result(svt_url, 'SVT')
2081
2082 # Look for embedded condenast player
2083 matches = re.findall(
2084 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
2085 webpage)
2086 if matches:
2087 return {
2088 '_type': 'playlist',
2089 'entries': [{
2090 '_type': 'url',
2091 'ie_key': 'CondeNast',
2092 'url': ma,
2093 } for ma in matches],
2094 'title': video_title,
2095 'id': video_id,
2096 }
2097
2098 # Look for Bandcamp pages with custom domain
2099 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2100 if mobj is not None:
2101 burl = unescapeHTML(mobj.group(1))
2102 # Don't set the extractor because it can be a track url or an album
2103 return self.url_result(burl)
2104
2105 # Look for embedded Vevo player
2106 mobj = re.search(
2107 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2108 if mobj is not None:
2109 return self.url_result(mobj.group('url'))
2110
2111 # Look for embedded Viddler player
2112 mobj = re.search(
2113 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2114 webpage)
2115 if mobj is not None:
2116 return self.url_result(mobj.group('url'))
2117
2118 # Look for NYTimes player
2119 mobj = re.search(
2120 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2121 webpage)
2122 if mobj is not None:
2123 return self.url_result(mobj.group('url'))
2124
2125 # Look for Libsyn player
2126 mobj = re.search(
2127 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2128 if mobj is not None:
2129 return self.url_result(mobj.group('url'))
2130
2131 # Look for Ooyala videos
2132 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2133 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2134 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2135 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2136 if mobj is not None:
2137 embed_token = self._search_regex(
2138 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2139 webpage, 'ooyala embed token', default=None)
2140 return OoyalaIE._build_url_result(smuggle_url(
2141 mobj.group('ec'), {
2142 'domain': url,
2143 'embed_token': embed_token,
2144 }))
2145
2146 # Look for multiple Ooyala embeds on SBN network websites
2147 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2148 if mobj is not None:
2149 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2150 if embeds:
2151 return self.playlist_from_matches(
2152 embeds, video_id, video_title,
2153 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2154
2155 # Look for Aparat videos
2156 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2157 if mobj is not None:
2158 return self.url_result(mobj.group(1), 'Aparat')
2159
2160 # Look for MPORA videos
2161 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2162 if mobj is not None:
2163 return self.url_result(mobj.group(1), 'Mpora')
2164
2165 # Look for embedded NovaMov-based player
2166 mobj = re.search(
2167 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2168 (?P<url>http://(?:(?:embed|www)\.)?
2169 (?:novamov\.com|
2170 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2171 videoweed\.(?:es|com)|
2172 movshare\.(?:net|sx|ag)|
2173 divxstage\.(?:eu|net|ch|co|at|ag))
2174 /embed\.php.+?)\1''', webpage)
2175 if mobj is not None:
2176 return self.url_result(mobj.group('url'))
2177
2178 # Look for embedded Facebook player
2179 facebook_url = FacebookIE._extract_url(webpage)
2180 if facebook_url is not None:
2181 return self.url_result(facebook_url, 'Facebook')
2182
2183 # Look for embedded VK player
2184 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2185 if mobj is not None:
2186 return self.url_result(mobj.group('url'), 'VK')
2187
2188 # Look for embedded Odnoklassniki player
2189 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2190 if mobj is not None:
2191 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2192
2193 # Look for embedded ivi player
2194 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2195 if mobj is not None:
2196 return self.url_result(mobj.group('url'), 'Ivi')
2197
2198 # Look for embedded Huffington Post player
2199 mobj = re.search(
2200 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2201 if mobj is not None:
2202 return self.url_result(mobj.group('url'), 'HuffPost')
2203
2204 # Look for embed.ly
2205 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2206 if mobj is not None:
2207 return self.url_result(mobj.group('url'))
2208 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2209 if mobj is not None:
2210 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2211
2212 # Look for funnyordie embed
2213 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2214 if matches:
2215 return self.playlist_from_matches(
2216 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2217
2218 # Look for BBC iPlayer embed
2219 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2220 if matches:
2221 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2222
2223 # Look for embedded RUTV player
2224 rutv_url = RUTVIE._extract_url(webpage)
2225 if rutv_url:
2226 return self.url_result(rutv_url, 'RUTV')
2227
2228 # Look for embedded TVC player
2229 tvc_url = TVCIE._extract_url(webpage)
2230 if tvc_url:
2231 return self.url_result(tvc_url, 'TVC')
2232
2233 # Look for embedded SportBox player
2234 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2235 if sportbox_urls:
2236 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2237
2238 # Look for embedded XHamster player
2239 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2240 if xhamster_urls:
2241 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2242
2243 # Look for embedded TNAFlixNetwork player
2244 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2245 if tnaflix_urls:
2246 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2247
2248 # Look for embedded PornHub player
2249 pornhub_urls = PornHubIE._extract_urls(webpage)
2250 if pornhub_urls:
2251 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2252
2253 # Look for embedded DrTuber player
2254 drtuber_urls = DrTuberIE._extract_urls(webpage)
2255 if drtuber_urls:
2256 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2257
2258 # Look for embedded RedTube player
2259 redtube_urls = RedTubeIE._extract_urls(webpage)
2260 if redtube_urls:
2261 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2262
2263 # Look for embedded Tvigle player
2264 mobj = re.search(
2265 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2266 if mobj is not None:
2267 return self.url_result(mobj.group('url'), 'Tvigle')
2268
2269 # Look for embedded TED player
2270 mobj = re.search(
2271 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2272 if mobj is not None:
2273 return self.url_result(mobj.group('url'), 'TED')
2274
2275 # Look for embedded Ustream videos
2276 ustream_url = UstreamIE._extract_url(webpage)
2277 if ustream_url:
2278 return self.url_result(ustream_url, UstreamIE.ie_key())
2279
2280 # Look for embedded arte.tv player
2281 mobj = re.search(
2282 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2283 webpage)
2284 if mobj is not None:
2285 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2286
2287 # Look for embedded francetv player
2288 mobj = re.search(
2289 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2290 webpage)
2291 if mobj is not None:
2292 return self.url_result(mobj.group('url'))
2293
2294 # Look for embedded smotri.com player
2295 smotri_url = SmotriIE._extract_url(webpage)
2296 if smotri_url:
2297 return self.url_result(smotri_url, 'Smotri')
2298
2299 # Look for embedded Myvi.ru player
2300 myvi_url = MyviIE._extract_url(webpage)
2301 if myvi_url:
2302 return self.url_result(myvi_url)
2303
2304 # Look for embedded soundcloud player
2305 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2306 if soundcloud_urls:
2307 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2308
2309 # Look for tunein player
2310 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2311 if tunein_urls:
2312 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2313
2314 # Look for embedded mtvservices player
2315 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2316 if mtvservices_url:
2317 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2318
2319 # Look for embedded yahoo player
2320 mobj = re.search(
2321 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2322 webpage)
2323 if mobj is not None:
2324 return self.url_result(mobj.group('url'), 'Yahoo')
2325
2326 # Look for embedded sbs.com.au player
2327 mobj = re.search(
2328 r'''(?x)
2329 (?:
2330 <meta\s+property="og:video"\s+content=|
2331 <iframe[^>]+?src=
2332 )
2333 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2334 webpage)
2335 if mobj is not None:
2336 return self.url_result(mobj.group('url'), 'SBS')
2337
2338 # Look for embedded Cinchcast player
2339 mobj = re.search(
2340 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2341 webpage)
2342 if mobj is not None:
2343 return self.url_result(mobj.group('url'), 'Cinchcast')
2344
2345 mobj = re.search(
2346 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2347 webpage)
2348 if not mobj:
2349 mobj = re.search(
2350 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2351 webpage)
2352 if mobj is not None:
2353 return self.url_result(mobj.group('url'), 'MLB')
2354
2355 mobj = re.search(
2356 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2357 webpage)
2358 if mobj is not None:
2359 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2360
2361 mobj = re.search(
2362 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2363 webpage)
2364 if mobj is not None:
2365 return self.url_result(mobj.group('url'), 'Livestream')
2366
2367 # Look for Zapiks embed
2368 mobj = re.search(
2369 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2370 if mobj is not None:
2371 return self.url_result(mobj.group('url'), 'Zapiks')
2372
2373 # Look for Kaltura embeds
2374 kaltura_url = KalturaIE._extract_url(webpage)
2375 if kaltura_url:
2376 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2377
2378 # Look for Eagle.Platform embeds
2379 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2380 if eagleplatform_url:
2381 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2382
2383 # Look for ClipYou (uses Eagle.Platform) embeds
2384 mobj = re.search(
2385 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2386 if mobj is not None:
2387 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2388
2389 # Look for Pladform embeds
2390 pladform_url = PladformIE._extract_url(webpage)
2391 if pladform_url:
2392 return self.url_result(pladform_url)
2393
2394 # Look for Videomore embeds
2395 videomore_url = VideomoreIE._extract_url(webpage)
2396 if videomore_url:
2397 return self.url_result(videomore_url)
2398
2399 # Look for Webcaster embeds
2400 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2401 if webcaster_url:
2402 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2403
2404 # Look for Playwire embeds
2405 mobj = re.search(
2406 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2407 if mobj is not None:
2408 return self.url_result(mobj.group('url'))
2409
2410 # Look for 5min embeds
2411 mobj = re.search(
2412 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2413 if mobj is not None:
2414 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2415
2416 # Look for Crooks and Liars embeds
2417 mobj = re.search(
2418 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2419 if mobj is not None:
2420 return self.url_result(mobj.group('url'))
2421
2422 # Look for NBC Sports VPlayer embeds
2423 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2424 if nbc_sports_url:
2425 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2426
2427 # Look for NBC News embeds
2428 nbc_news_embed_url = re.search(
2429 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2430 if nbc_news_embed_url:
2431 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2432
2433 # Look for Google Drive embeds
2434 google_drive_url = GoogleDriveIE._extract_url(webpage)
2435 if google_drive_url:
2436 return self.url_result(google_drive_url, 'GoogleDrive')
2437
2438 # Look for UDN embeds
2439 mobj = re.search(
2440 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2441 if mobj is not None:
2442 return self.url_result(
2443 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2444
2445 # Look for Senate ISVP iframe
2446 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2447 if senate_isvp_url:
2448 return self.url_result(senate_isvp_url, 'SenateISVP')
2449
2450 # Look for Dailymotion Cloud videos
2451 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2452 if dmcloud_url:
2453 return self.url_result(dmcloud_url, 'DailymotionCloud')
2454
2455 # Look for OnionStudios embeds
2456 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2457 if onionstudios_url:
2458 return self.url_result(onionstudios_url)
2459
2460 # Look for ViewLift embeds
2461 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2462 if viewlift_url:
2463 return self.url_result(viewlift_url)
2464
2465 # Look for JWPlatform embeds
2466 jwplatform_url = JWPlatformIE._extract_url(webpage)
2467 if jwplatform_url:
2468 return self.url_result(jwplatform_url, 'JWPlatform')
2469
2470 # Look for Digiteka embeds
2471 digiteka_url = DigitekaIE._extract_url(webpage)
2472 if digiteka_url:
2473 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2474
2475 # Look for Arkena embeds
2476 arkena_url = ArkenaIE._extract_url(webpage)
2477 if arkena_url:
2478 return self.url_result(arkena_url, ArkenaIE.ie_key())
2479
2480 # Look for Piksel embeds
2481 piksel_url = PikselIE._extract_url(webpage)
2482 if piksel_url:
2483 return self.url_result(piksel_url, PikselIE.ie_key())
2484
2485 # Look for Limelight embeds
2486 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2487 if mobj:
2488 lm = {
2489 'Media': 'media',
2490 'Channel': 'channel',
2491 'ChannelList': 'channel_list',
2492 }
2493 return self.url_result(smuggle_url('limelight:%s:%s' % (
2494 lm[mobj.group(1)], mobj.group(2)), {'source_url': url}),
2495 'Limelight%s' % mobj.group(1), mobj.group(2))
2496
2497 mobj = re.search(
2498 r'''(?sx)
2499 <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2500 <param[^>]+
2501 name=(["\'])flashVars\2[^>]+
2502 value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2503 ''', webpage)
2504 if mobj:
2505 return self.url_result(smuggle_url(
2506 'limelight:media:%s' % mobj.group('id'),
2507 {'source_url': url}), 'LimelightMedia', mobj.group('id'))
2508
2509 # Look for AdobeTVVideo embeds
2510 mobj = re.search(
2511 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2512 webpage)
2513 if mobj is not None:
2514 return self.url_result(
2515 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2516 'AdobeTVVideo')
2517
2518 # Look for Vine embeds
2519 mobj = re.search(
2520 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2521 webpage)
2522 if mobj is not None:
2523 return self.url_result(
2524 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2525
2526 # Look for VODPlatform embeds
2527 mobj = re.search(
2528 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2529 webpage)
2530 if mobj is not None:
2531 return self.url_result(
2532 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2533
2534 # Look for Mangomolo embeds
2535 mobj = re.search(
2536 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2537 (?:
2538 video\?.*?\bid=(?P<video_id>\d+)|
2539 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2540 ).+?)\1''', webpage)
2541 if mobj is not None:
2542 info = {
2543 '_type': 'url_transparent',
2544 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2545 'title': video_title,
2546 'description': video_description,
2547 'thumbnail': video_thumbnail,
2548 'uploader': video_uploader,
2549 }
2550 video_id = mobj.group('video_id')
2551 if video_id:
2552 info.update({
2553 'ie_key': 'MangomoloVideo',
2554 'id': video_id,
2555 })
2556 else:
2557 info.update({
2558 'ie_key': 'MangomoloLive',
2559 'id': mobj.group('channel_id'),
2560 })
2561 return info
2562
2563 # Look for Instagram embeds
2564 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2565 if instagram_embed_url is not None:
2566 return self.url_result(
2567 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2568
2569 # Look for LiveLeak embeds
2570 liveleak_url = LiveLeakIE._extract_url(webpage)
2571 if liveleak_url:
2572 return self.url_result(liveleak_url, 'LiveLeak')
2573
2574 # Look for 3Q SDN embeds
2575 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2576 if threeqsdn_url:
2577 return {
2578 '_type': 'url_transparent',
2579 'ie_key': ThreeQSDNIE.ie_key(),
2580 'url': self._proto_relative_url(threeqsdn_url),
2581 'title': video_title,
2582 'description': video_description,
2583 'thumbnail': video_thumbnail,
2584 'uploader': video_uploader,
2585 }
2586
2587 # Look for VBOX7 embeds
2588 vbox7_url = Vbox7IE._extract_url(webpage)
2589 if vbox7_url:
2590 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2591
2592 # Look for DBTV embeds
2593 dbtv_urls = DBTVIE._extract_urls(webpage)
2594 if dbtv_urls:
2595 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2596
2597 # Look for Videa embeds
2598 videa_urls = VideaIE._extract_urls(webpage)
2599 if videa_urls:
2600 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2601
2602 # Look for 20 minuten embeds
2603 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2604 if twentymin_urls:
2605 return self.playlist_from_matches(
2606 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2607
2608 # Look for Openload embeds
2609 openload_urls = OpenloadIE._extract_urls(webpage)
2610 if openload_urls:
2611 return self.playlist_from_matches(
2612 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2613
2614 # Look for VideoPress embeds
2615 videopress_urls = VideoPressIE._extract_urls(webpage)
2616 if videopress_urls:
2617 return self.playlist_from_matches(
2618 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2619
2620 # Look for Rutube embeds
2621 rutube_urls = RutubeIE._extract_urls(webpage)
2622 if rutube_urls:
2623 return self.playlist_from_matches(
2624 rutube_urls, ie=RutubeIE.ie_key())
2625
2626 # Looking for http://schema.org/VideoObject
2627 json_ld = self._search_json_ld(
2628 webpage, video_id, default={}, expected_type='VideoObject')
2629 if json_ld.get('url'):
2630 info_dict.update({
2631 'title': video_title or info_dict['title'],
2632 'description': video_description,
2633 'thumbnail': video_thumbnail,
2634 'age_limit': age_limit
2635 })
2636 info_dict.update(json_ld)
2637 return info_dict
2638
2639 # Look for HTML5 media
2640 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2641 if entries:
2642 for entry in entries:
2643 entry.update({
2644 'id': video_id,
2645 'title': video_title,
2646 })
2647 self._sort_formats(entry['formats'])
2648 return self.playlist_result(entries)
2649
2650 jwplayer_data = self._find_jwplayer_data(
2651 webpage, video_id, transform_source=js_to_json)
2652 if jwplayer_data:
2653 info = self._parse_jwplayer_data(
2654 jwplayer_data, video_id, require_title=False, base_url=url)
2655 if not info.get('title'):
2656 info['title'] = video_title
2657 return info
2658
2659 def check_video(vurl):
2660 if YoutubeIE.suitable(vurl):
2661 return True
2662 if RtmpIE.suitable(vurl):
2663 return True
2664 vpath = compat_urlparse.urlparse(vurl).path
2665 vext = determine_ext(vpath)
2666 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2667
2668 def filter_video(urls):
2669 return list(filter(check_video, urls))
2670
2671 # Start with something easy: JW Player in SWFObject
2672 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2673 if not found:
2674 # Look for gorilla-vid style embedding
2675 found = filter_video(re.findall(r'''(?sx)
2676 (?:
2677 jw_plugins|
2678 JWPlayerOptions|
2679 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2680 )
2681 .*?
2682 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2683 if not found:
2684 # Broaden the search a little bit
2685 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2686 if not found:
2687 # Broaden the findall a little bit: JWPlayer JS loader
2688 found = filter_video(re.findall(
2689 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2690 if not found:
2691 # Flow player
2692 found = filter_video(re.findall(r'''(?xs)
2693 flowplayer\("[^"]+",\s*
2694 \{[^}]+?\}\s*,
2695 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2696 ["']?url["']?\s*:\s*["']([^"']+)["']
2697 ''', webpage))
2698 if not found:
2699 # Cinerama player
2700 found = re.findall(
2701 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2702 if not found:
2703 # Try to find twitter cards info
2704 # twitter:player:stream should be checked before twitter:player since
2705 # it is expected to contain a raw stream (see
2706 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2707 found = filter_video(re.findall(
2708 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2709 if not found:
2710 # We look for Open Graph info:
2711 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2712 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2713 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2714 if m_video_type is not None:
2715 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2716 if not found:
2717 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2718 found = re.search(
2719 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2720 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2721 webpage)
2722 if not found:
2723 # Look also in Refresh HTTP header
2724 refresh_header = head_response.headers.get('Refresh')
2725 if refresh_header:
2726 # In python 2 response HTTP headers are bytestrings
2727 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2728 refresh_header = refresh_header.decode('iso-8859-1')
2729 found = re.search(REDIRECT_REGEX, refresh_header)
2730 if found:
2731 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2732 if new_url != url:
2733 self.report_following_redirect(new_url)
2734 return {
2735 '_type': 'url',
2736 'url': new_url,
2737 }
2738 else:
2739 found = None
2740
2741 if not found:
2742 # twitter:player is a https URL to iframe player that may or may not
2743 # be supported by youtube-dl thus this is checked the very last (see
2744 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2745 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2746 if embed_url:
2747 return self.url_result(embed_url)
2748
2749 if not found:
2750 raise UnsupportedError(url)
2751
2752 entries = []
2753 for video_url in orderedSet(found):
2754 video_url = unescapeHTML(video_url)
2755 video_url = video_url.replace('\\/', '/')
2756 video_url = compat_urlparse.urljoin(url, video_url)
2757 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2758
2759 # Sometimes, jwplayer extraction will result in a YouTube URL
2760 if YoutubeIE.suitable(video_url):
2761 entries.append(self.url_result(video_url, 'Youtube'))
2762 continue
2763
2764 # here's a fun little line of code for you:
2765 video_id = os.path.splitext(video_id)[0]
2766
2767 entry_info_dict = {
2768 'id': video_id,
2769 'uploader': video_uploader,
2770 'title': video_title,
2771 'age_limit': age_limit,
2772 }
2773
2774 if RtmpIE.suitable(video_url):
2775 entry_info_dict.update({
2776 '_type': 'url_transparent',
2777 'ie_key': RtmpIE.ie_key(),
2778 'url': video_url,
2779 })
2780 entries.append(entry_info_dict)
2781 continue
2782
2783 ext = determine_ext(video_url)
2784 if ext == 'smil':
2785 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2786 elif ext == 'xspf':
2787 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2788 elif ext == 'm3u8':
2789 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2790 elif ext == 'mpd':
2791 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2792 elif ext == 'f4m':
2793 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2794 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2795 # Just matching .ism/manifest is not enough to be reliably sure
2796 # whether it's actually an ISM manifest or some other streaming
2797 # manifest since there are various streaming URL formats
2798 # possible (see [1]) as well as some other shenanigans like
2799 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2800 # so on.
2801 # Thus the most reasonable way to solve this is to delegate
2802 # to generic extractor in order to look into the contents of
2803 # the manifest itself.
2804 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2805 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2806 entry_info_dict = self.url_result(
2807 smuggle_url(video_url, {'to_generic': True}),
2808 GenericIE.ie_key())
2809 else:
2810 entry_info_dict['url'] = video_url
2811
2812 if entry_info_dict.get('formats'):
2813 self._sort_formats(entry_info_dict['formats'])
2814
2815 entries.append(entry_info_dict)
2816
2817 if len(entries) == 1:
2818 return entries[0]
2819 else:
2820 for num, e in enumerate(entries, start=1):
2821 # 'url' results don't have a title
2822 if e.get('title') is not None:
2823 e['title'] = '%s (%d)' % (e['title'], num)
2824 return {
2825 '_type': 'playlist',
2826 'entries': entries,
2827 }