]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/generic.py
1c233f038143bbdcda4630dc31c02faa0428bd6c
[youtubedl] / 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 orderedSet,
24 sanitized_Request,
25 smuggle_url,
26 unescapeHTML,
27 unified_strdate,
28 unsmuggle_url,
29 UnsupportedError,
30 xpath_text,
31 )
32 from .commonprotocols import RtmpIE
33 from .brightcove import (
34 BrightcoveLegacyIE,
35 BrightcoveNewIE,
36 )
37 from .nbc import NBCSportsVPlayerIE
38 from .ooyala import OoyalaIE
39 from .rutv import RUTVIE
40 from .tvc import TVCIE
41 from .sportbox import SportBoxEmbedIE
42 from .smotri import SmotriIE
43 from .myvi import MyviIE
44 from .condenast import CondeNastIE
45 from .udn import UDNEmbedIE
46 from .senateisvp import SenateISVPIE
47 from .svt import SVTIE
48 from .pornhub import PornHubIE
49 from .xhamster import XHamsterEmbedIE
50 from .tnaflix import TNAFlixNetworkEmbedIE
51 from .drtuber import DrTuberIE
52 from .redtube import RedTubeIE
53 from .vimeo import VimeoIE
54 from .dailymotion import (
55 DailymotionIE,
56 DailymotionCloudIE,
57 )
58 from .onionstudios import OnionStudiosIE
59 from .viewlift import ViewLiftEmbedIE
60 from .mtv import MTVServicesEmbeddedIE
61 from .pladform import PladformIE
62 from .videomore import VideomoreIE
63 from .webcaster import WebcasterFeedIE
64 from .googledrive import GoogleDriveIE
65 from .jwplatform import JWPlatformIE
66 from .digiteka import DigitekaIE
67 from .arkena import ArkenaIE
68 from .instagram import InstagramIE
69 from .liveleak import LiveLeakIE
70 from .threeqsdn import ThreeQSDNIE
71 from .theplatform import ThePlatformIE
72 from .vessel import VesselIE
73 from .kaltura import KalturaIE
74 from .eagleplatform import EaglePlatformIE
75 from .facebook import FacebookIE
76 from .soundcloud import SoundcloudIE
77 from .tunein import TuneInBaseIE
78 from .vbox7 import Vbox7IE
79 from .dbtv import DBTVIE
80 from .piksel import PikselIE
81 from .videa import VideaIE
82 from .twentymin import TwentyMinutenIE
83 from .ustream import UstreamIE
84 from .openload import OpenloadIE
85 from .videopress import VideoPressIE
86
87
88 class GenericIE(InfoExtractor):
89 IE_DESC = 'Generic downloader that works on some sites'
90 _VALID_URL = r'.*'
91 IE_NAME = 'generic'
92 _TESTS = [
93 # Direct link to a video
94 {
95 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
96 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
97 'info_dict': {
98 'id': 'trailer',
99 'ext': 'mp4',
100 'title': 'trailer',
101 'upload_date': '20100513',
102 }
103 },
104 # Direct link to media delivered compressed (until Accept-Encoding is *)
105 {
106 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
107 'md5': '128c42e68b13950268b648275386fc74',
108 'info_dict': {
109 'id': 'FictionJunction-Parallel_Hearts',
110 'ext': 'flac',
111 'title': 'FictionJunction-Parallel_Hearts',
112 'upload_date': '20140522',
113 },
114 'expected_warnings': [
115 'URL could be a direct video link, returning it as such.'
116 ],
117 'skip': 'URL invalid',
118 },
119 # Direct download with broken HEAD
120 {
121 'url': 'http://ai-radio.org:8000/radio.opus',
122 'info_dict': {
123 'id': 'radio',
124 'ext': 'opus',
125 'title': 'radio',
126 },
127 'params': {
128 'skip_download': True, # infinite live stream
129 },
130 'expected_warnings': [
131 r'501.*Not Implemented',
132 r'400.*Bad Request',
133 ],
134 },
135 # Direct link with incorrect MIME type
136 {
137 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
138 'md5': '4ccbebe5f36706d85221f204d7eb5913',
139 'info_dict': {
140 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
141 'id': '5_Lennart_Poettering_-_Systemd',
142 'ext': 'webm',
143 'title': '5_Lennart_Poettering_-_Systemd',
144 'upload_date': '20141120',
145 },
146 'expected_warnings': [
147 'URL could be a direct video link, returning it as such.'
148 ]
149 },
150 # RSS feed
151 {
152 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
153 'info_dict': {
154 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
155 'title': 'Zero Punctuation',
156 'description': 're:.*groundbreaking video review series.*'
157 },
158 'playlist_mincount': 11,
159 },
160 # RSS feed with enclosure
161 {
162 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
163 'info_dict': {
164 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
165 'ext': 'm4v',
166 'upload_date': '20150228',
167 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
168 }
169 },
170 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
171 {
172 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
173 'info_dict': {
174 'id': 'smil',
175 'ext': 'mp4',
176 'title': 'Automatics, robotics and biocybernetics',
177 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
178 'upload_date': '20130627',
179 'formats': 'mincount:16',
180 'subtitles': 'mincount:1',
181 },
182 'params': {
183 'force_generic_extractor': True,
184 'skip_download': True,
185 },
186 },
187 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
188 {
189 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
190 'info_dict': {
191 'id': 'hds',
192 'ext': 'flv',
193 'title': 'hds',
194 'formats': 'mincount:1',
195 },
196 'params': {
197 'skip_download': True,
198 },
199 },
200 # SMIL from https://www.restudy.dk/video/play/id/1637
201 {
202 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
203 'info_dict': {
204 'id': 'video_1637',
205 'ext': 'flv',
206 'title': 'video_1637',
207 'formats': 'mincount:3',
208 },
209 'params': {
210 'skip_download': True,
211 },
212 },
213 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
214 {
215 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
216 'info_dict': {
217 'id': 'smil-service',
218 'ext': 'flv',
219 'title': 'smil-service',
220 'formats': 'mincount:1',
221 },
222 'params': {
223 'skip_download': True,
224 },
225 },
226 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
227 {
228 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
229 'info_dict': {
230 'id': '4719370',
231 'ext': 'mp4',
232 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
233 'formats': 'mincount:3',
234 },
235 'params': {
236 'skip_download': True,
237 },
238 },
239 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
240 {
241 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
242 'info_dict': {
243 'id': 'mZlp2ctYIUEB',
244 'ext': 'mp4',
245 'title': 'Tikibad ontruimd wegens brand',
246 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
247 'thumbnail': r're:^https?://.*\.jpg$',
248 'duration': 33,
249 },
250 'params': {
251 'skip_download': True,
252 },
253 },
254 # MPD from http://dash-mse-test.appspot.com/media.html
255 {
256 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
257 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
258 'info_dict': {
259 'id': 'car-20120827-manifest',
260 'ext': 'mp4',
261 'title': 'car-20120827-manifest',
262 'formats': 'mincount:9',
263 'upload_date': '20130904',
264 },
265 'params': {
266 'format': 'bestvideo',
267 },
268 },
269 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
270 {
271 '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',
272 'info_dict': {
273 'id': 'content',
274 'ext': 'mp4',
275 'title': 'content',
276 'formats': 'mincount:8',
277 },
278 'params': {
279 # m3u8 downloads
280 'skip_download': True,
281 },
282 'skip': 'video gone',
283 },
284 # m3u8 served with Content-Type: text/plain
285 {
286 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
287 'info_dict': {
288 'id': 'index',
289 'ext': 'mp4',
290 'title': 'index',
291 'upload_date': '20140720',
292 'formats': 'mincount:11',
293 },
294 'params': {
295 # m3u8 downloads
296 'skip_download': True,
297 },
298 'skip': 'video gone',
299 },
300 # google redirect
301 {
302 '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',
303 'info_dict': {
304 'id': 'cmQHVoWB5FY',
305 'ext': 'mp4',
306 'upload_date': '20130224',
307 'uploader_id': 'TheVerge',
308 'description': r're:^Chris Ziegler takes a look at the\.*',
309 'uploader': 'The Verge',
310 'title': 'First Firefox OS phones side-by-side',
311 },
312 'params': {
313 'skip_download': False,
314 }
315 },
316 {
317 # redirect in Refresh HTTP header
318 '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',
319 'info_dict': {
320 'id': 'pO8h3EaFRdo',
321 'ext': 'mp4',
322 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
323 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
324 'upload_date': '20150917',
325 'uploader_id': 'brtvofficial',
326 'uploader': 'Boiler Room',
327 },
328 'params': {
329 'skip_download': False,
330 },
331 },
332 {
333 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
334 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
335 'info_dict': {
336 'id': '13601338388002',
337 'ext': 'mp4',
338 'uploader': 'www.hodiho.fr',
339 'title': 'R\u00e9gis plante sa Jeep',
340 }
341 },
342 # bandcamp page with custom domain
343 {
344 'add_ie': ['Bandcamp'],
345 'url': 'http://bronyrock.com/track/the-pony-mash',
346 'info_dict': {
347 'id': '3235767654',
348 'ext': 'mp3',
349 'title': 'The Pony Mash',
350 'uploader': 'M_Pallante',
351 },
352 'skip': 'There is a limit of 200 free downloads / month for the test song',
353 },
354 {
355 # embedded brightcove video
356 # it also tests brightcove videos that need to set the 'Referer'
357 # in the http requests
358 'add_ie': ['BrightcoveLegacy'],
359 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
360 'info_dict': {
361 'id': '2765128793001',
362 'ext': 'mp4',
363 'title': 'Le cours de bourse : lā€™analyse technique',
364 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
365 'uploader': 'BFM BUSINESS',
366 },
367 'params': {
368 'skip_download': True,
369 },
370 },
371 {
372 # embedded with itemprop embedURL and video id spelled as `idVideo`
373 'add_id': ['BrightcoveLegacy'],
374 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
375 'info_dict': {
376 'id': '5255628253001',
377 'ext': 'mp4',
378 'title': 'md5:37c519b1128915607601e75a87995fc0',
379 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
380 'uploader': 'BFM BUSINESS',
381 'uploader_id': '876450612001',
382 'timestamp': 1482255315,
383 'upload_date': '20161220',
384 },
385 'params': {
386 'skip_download': True,
387 },
388 },
389 {
390 # https://github.com/rg3/youtube-dl/issues/2253
391 'url': 'http://bcove.me/i6nfkrc3',
392 'md5': '0ba9446db037002366bab3b3eb30c88c',
393 'info_dict': {
394 'id': '3101154703001',
395 'ext': 'mp4',
396 'title': 'Still no power',
397 'uploader': 'thestar.com',
398 '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.',
399 },
400 'add_ie': ['BrightcoveLegacy'],
401 'skip': 'video gone',
402 },
403 {
404 'url': 'http://www.championat.com/video/football/v/87/87499.html',
405 'md5': 'fb973ecf6e4a78a67453647444222983',
406 'info_dict': {
407 'id': '3414141473001',
408 'ext': 'mp4',
409 'title': 'Š’ŠøŠ“ŠµŠ¾. Š£Š“Š°Š»ŠµŠ½ŠøŠµ Š”Š·Š°Š³Š¾ŠµŠ²Š° (Š¦Š”ŠšŠ)',
410 'description': 'ŠžŠ½Š»Š°Š¹Š½-трŠ°Š½ŃŠ»ŃŃ†Šøя Š¼Š°Ń‚чŠ° Š¦Š”ŠšŠ - "Š’Š¾Š»Š³Š°"',
411 'uploader': 'Championat',
412 },
413 },
414 {
415 # https://github.com/rg3/youtube-dl/issues/3541
416 'add_ie': ['BrightcoveLegacy'],
417 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
418 'info_dict': {
419 'id': '3866516442001',
420 'ext': 'mp4',
421 'title': 'Leer mij vrouwen kennen: Aflevering 1',
422 'description': 'Leer mij vrouwen kennen: Aflevering 1',
423 'uploader': 'SBS Broadcasting',
424 },
425 'skip': 'Restricted to Netherlands',
426 'params': {
427 'skip_download': True, # m3u8 download
428 },
429 },
430 {
431 # Brightcove with alternative playerID key
432 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
433 'info_dict': {
434 'id': 'nmeth.2062_SV1',
435 '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',
436 },
437 'playlist': [{
438 'info_dict': {
439 'id': '2228375078001',
440 'ext': 'mp4',
441 'title': 'nmeth.2062-sv1',
442 'description': 'nmeth.2062-sv1',
443 'timestamp': 1363357591,
444 'upload_date': '20130315',
445 'uploader': 'Nature Publishing Group',
446 'uploader_id': '1964492299001',
447 },
448 }],
449 },
450 # ooyala video
451 {
452 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
453 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
454 'info_dict': {
455 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
456 'ext': 'mp4',
457 'title': '2cc213299525360.mov', # that's what we get
458 'duration': 238.231,
459 },
460 'add_ie': ['Ooyala'],
461 },
462 {
463 # ooyala video embedded with http://player.ooyala.com/iframe.js
464 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
465 'info_dict': {
466 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
467 'ext': 'mp4',
468 'title': '"Steve Jobs: Man in the Machine" trailer',
469 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
470 'duration': 135.427,
471 },
472 'params': {
473 'skip_download': True,
474 },
475 'skip': 'movie expired',
476 },
477 # embed.ly video
478 {
479 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
480 'info_dict': {
481 'id': '9ODmcdjQcHQ',
482 'ext': 'mp4',
483 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
484 'upload_date': '20140225',
485 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
486 'uploader': 'Tested',
487 'uploader_id': 'testedcom',
488 },
489 # No need to test YoutubeIE here
490 'params': {
491 'skip_download': True,
492 },
493 },
494 # funnyordie embed
495 {
496 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
497 'info_dict': {
498 'id': '18e820ec3f',
499 'ext': 'mp4',
500 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
501 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
502 },
503 # HEAD requests lead to endless 301, while GET is OK
504 'expected_warnings': ['301'],
505 },
506 # RUTV embed
507 {
508 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
509 'info_dict': {
510 'id': '776940',
511 'ext': 'mp4',
512 'title': 'ŠžŃ…Š¾Ń‚сŠŗŠ¾Šµ Š¼Š¾Ń€Šµ стŠ°Š»Š¾ цŠµŠ»ŠøŠŗŠ¾Š¼ рŠ¾ŃŃŠøŠ¹ŃŠŗŠøŠ¼',
513 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
514 },
515 'params': {
516 # m3u8 download
517 'skip_download': True,
518 },
519 },
520 # TVC embed
521 {
522 '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/',
523 'info_dict': {
524 'id': '55304',
525 'ext': 'mp4',
526 'title': 'Š”Š¾ŃˆŠŗŠ¾Š»ŃŒŠ½Š¾Šµ Š²Š¾ŃŠæŠøтŠ°Š½ŠøŠµ',
527 },
528 },
529 # SportBox embed
530 {
531 'url': 'http://www.vestifinance.ru/articles/25753',
532 'info_dict': {
533 'id': '25753',
534 'title': 'ŠŸŃ€ŃŠ¼Ń‹Šµ трŠ°Š½ŃŠ»ŃŃ†ŠøŠø с Š¤Š¾Ń€ŃƒŠ¼Š°-Š²Ń‹ŃŃ‚Š°Š²ŠŗŠø "Š“Š¾ŃŠ·Š°ŠŗŠ°Š·-2013"',
535 },
536 'playlist': [{
537 'info_dict': {
538 'id': '370908',
539 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 3',
540 'ext': 'mp4',
541 }
542 }, {
543 'info_dict': {
544 'id': '370905',
545 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 2',
546 'ext': 'mp4',
547 }
548 }, {
549 'info_dict': {
550 'id': '370902',
551 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 1',
552 'ext': 'mp4',
553 }
554 }],
555 'params': {
556 # m3u8 download
557 'skip_download': True,
558 },
559 },
560 # Myvi.ru embed
561 {
562 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
563 'info_dict': {
564 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
565 'ext': 'mp4',
566 'title': 'Š£Š¶Š°ŃŃ‚ŠøŠŗŠø, руссŠŗŠøŠ¹ трŠµŠ¹Š»ŠµŃ€ (2015)',
567 'thumbnail': r're:^https?://.*\.jpg$',
568 'duration': 153,
569 }
570 },
571 # XHamster embed
572 {
573 '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',
574 'info_dict': {
575 'id': 'showthread',
576 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
577 },
578 'playlist_mincount': 7,
579 # This forum does not allow <iframe> syntaxes anymore
580 # Now HTML tags are displayed as-is
581 'skip': 'No videos on this page',
582 },
583 # Embedded TED video
584 {
585 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
586 'md5': '65fdff94098e4a607385a60c5177c638',
587 'info_dict': {
588 'id': '1969',
589 'ext': 'mp4',
590 'title': 'Hidden miracles of the natural world',
591 'uploader': 'Louie Schwartzberg',
592 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
593 }
594 },
595 # nowvideo embed hidden behind percent encoding
596 {
597 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
598 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
599 'info_dict': {
600 'id': '06e53103ca9aa',
601 'ext': 'flv',
602 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
603 'description': 'No description',
604 },
605 },
606 # arte embed
607 {
608 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
609 'md5': '7653032cbb25bf6c80d80f217055fa43',
610 'info_dict': {
611 'id': '048195-004_PLUS7-F',
612 'ext': 'flv',
613 'title': 'X:enius',
614 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
615 'upload_date': '20140320',
616 },
617 'params': {
618 'skip_download': 'Requires rtmpdump'
619 },
620 'skip': 'video gone',
621 },
622 # francetv embed
623 {
624 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
625 'info_dict': {
626 'id': 'EV_30231',
627 'ext': 'mp4',
628 'title': 'Alcaline, le concert avec Calogero',
629 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
630 'upload_date': '20150226',
631 'timestamp': 1424989860,
632 'duration': 5400,
633 },
634 'params': {
635 # m3u8 downloads
636 'skip_download': True,
637 },
638 'expected_warnings': [
639 'Forbidden'
640 ]
641 },
642 # CondƩ Nast embed
643 {
644 'url': 'http://www.wired.com/2014/04/honda-asimo/',
645 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
646 'info_dict': {
647 'id': '53501be369702d3275860000',
648 'ext': 'mp4',
649 'title': 'Hondaā€™s New Asimo Robot Is More Human Than Ever',
650 }
651 },
652 # Dailymotion embed
653 {
654 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
655 'md5': '441aeeb82eb72c422c7f14ec533999cd',
656 'info_dict': {
657 'id': 'k2mm4bCdJ6CQ2i7c8o2',
658 'ext': 'mp4',
659 'title': 'Le Zap de Spi0n nĀ°216 - Zapping du Web',
660 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
661 'uploader': 'Spi0n',
662 'uploader_id': 'xgditw',
663 'upload_date': '20140425',
664 'timestamp': 1398441542,
665 },
666 'add_ie': ['Dailymotion'],
667 },
668 # YouTube embed
669 {
670 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
671 'info_dict': {
672 'id': 'FXRb4ykk4S0',
673 'ext': 'mp4',
674 'title': 'The NBL Auction 2014',
675 'uploader': 'BADMINTON England',
676 'uploader_id': 'BADMINTONEvents',
677 'upload_date': '20140603',
678 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
679 },
680 'add_ie': ['Youtube'],
681 'params': {
682 'skip_download': True,
683 }
684 },
685 # MTVSercices embed
686 {
687 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
688 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
689 'info_dict': {
690 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
691 'ext': 'mp4',
692 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
693 'description': 'Two valets share their love for movie star Liam Neesons.',
694 'timestamp': 1349922600,
695 'upload_date': '20121011',
696 },
697 },
698 # YouTube embed via <data-embed-url="">
699 {
700 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
701 'info_dict': {
702 'id': '4vAffPZIT44',
703 'ext': 'mp4',
704 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
705 'uploader': 'Gameloft',
706 'uploader_id': 'gameloft',
707 'upload_date': '20140828',
708 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
709 },
710 'params': {
711 'skip_download': True,
712 }
713 },
714 # Camtasia studio
715 {
716 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
717 'playlist': [{
718 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
719 'info_dict': {
720 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
721 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
722 'ext': 'flv',
723 'duration': 2235.90,
724 }
725 }, {
726 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
727 'info_dict': {
728 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
729 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
730 'ext': 'flv',
731 'duration': 2235.93,
732 }
733 }],
734 'info_dict': {
735 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
736 }
737 },
738 # Flowplayer
739 {
740 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
741 'md5': '9d65602bf31c6e20014319c7d07fba27',
742 'info_dict': {
743 'id': '5123ea6d5e5a7',
744 'ext': 'mp4',
745 'age_limit': 18,
746 'uploader': 'www.handjobhub.com',
747 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
748 }
749 },
750 # Multiple brightcove videos
751 # https://github.com/rg3/youtube-dl/issues/2283
752 {
753 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
754 'info_dict': {
755 'id': 'always-never',
756 'title': 'Always / Never - The New Yorker',
757 },
758 'playlist_count': 3,
759 'params': {
760 'extract_flat': False,
761 'skip_download': True,
762 }
763 },
764 # MLB embed
765 {
766 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
767 'md5': '96f09a37e44da40dd083e12d9a683327',
768 'info_dict': {
769 'id': '33322633',
770 'ext': 'mp4',
771 'title': 'Ump changes call to ball',
772 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
773 'duration': 48,
774 'timestamp': 1401537900,
775 'upload_date': '20140531',
776 'thumbnail': r're:^https?://.*\.jpg$',
777 },
778 },
779 # Wistia embed
780 {
781 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
782 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
783 'info_dict': {
784 'id': '6e2wtrbdaf',
785 'ext': 'mov',
786 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
787 'description': 'a Paywall Videos video from Remilon',
788 'duration': 644.072,
789 'uploader': 'study.com',
790 'timestamp': 1459678540,
791 'upload_date': '20160403',
792 'filesize': 24687186,
793 },
794 },
795 {
796 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
797 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
798 'info_dict': {
799 'id': 'uxjb0lwrcz',
800 'ext': 'mp4',
801 'title': 'Conversation about Hexagonal Rails Part 1',
802 'description': 'a Martin Fowler video from ThoughtWorks',
803 'duration': 1715.0,
804 'uploader': 'thoughtworks.wistia.com',
805 'timestamp': 1401832161,
806 'upload_date': '20140603',
807 },
808 },
809 # Wistia standard embed (async)
810 {
811 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
812 'info_dict': {
813 'id': '807fafadvk',
814 'ext': 'mp4',
815 'title': 'Drip Brennan Dunn Workshop',
816 'description': 'a JV Webinars video from getdrip-1',
817 'duration': 4986.95,
818 'timestamp': 1463607249,
819 'upload_date': '20160518',
820 },
821 'params': {
822 'skip_download': True,
823 }
824 },
825 # Soundcloud embed
826 {
827 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
828 'info_dict': {
829 'id': '174391317',
830 'ext': 'mp3',
831 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
832 'uploader': 'Sophos Security',
833 'title': 'Chet Chat 171 - Oct 29, 2014',
834 'upload_date': '20141029',
835 }
836 },
837 # Soundcloud multiple embeds
838 {
839 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
840 'info_dict': {
841 'id': '52809',
842 'title': 'Guitar Essentials: Legato Workoutā€”One-Hour to Fluid Performance | TAB + AUDIO',
843 },
844 'playlist_mincount': 7,
845 },
846 # TuneIn station embed
847 {
848 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
849 'info_dict': {
850 'id': '204146',
851 'ext': 'mp3',
852 'title': 'CNRV',
853 'location': 'Paris, France',
854 'is_live': True,
855 },
856 'params': {
857 # Live stream
858 'skip_download': True,
859 },
860 },
861 # Livestream embed
862 {
863 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
864 'info_dict': {
865 'id': '67864563',
866 'ext': 'flv',
867 'upload_date': '20141112',
868 'title': 'Rosetta #CometLanding webcast HL 10',
869 }
870 },
871 # Another Livestream embed, without 'new.' in URL
872 {
873 'url': 'https://www.freespeech.org/',
874 'info_dict': {
875 'id': '123537347',
876 'ext': 'mp4',
877 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
878 },
879 'params': {
880 # Live stream
881 'skip_download': True,
882 },
883 },
884 # LazyYT
885 {
886 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
887 'info_dict': {
888 'id': '1986',
889 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
890 },
891 'playlist_mincount': 2,
892 },
893 # Cinchcast embed
894 {
895 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
896 'info_dict': {
897 'id': '7141703',
898 'ext': 'mp3',
899 'upload_date': '20141126',
900 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
901 }
902 },
903 # Cinerama player
904 {
905 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
906 'info_dict': {
907 'id': '730m_DandD_1901_512k',
908 'ext': 'mp4',
909 'uploader': 'www.abc.net.au',
910 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
911 }
912 },
913 # embedded viddler video
914 {
915 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
916 'info_dict': {
917 'id': '4d03aad9',
918 'ext': 'mp4',
919 'uploader': 'deadspin',
920 'title': 'WALL-TO-GORTAT',
921 'timestamp': 1422285291,
922 'upload_date': '20150126',
923 },
924 'add_ie': ['Viddler'],
925 },
926 # Libsyn embed
927 {
928 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
929 'info_dict': {
930 'id': '3377616',
931 'ext': 'mp3',
932 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
933 'description': 'md5:601cb790edd05908957dae8aaa866465',
934 'upload_date': '20150220',
935 },
936 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
937 },
938 # jwplayer YouTube
939 {
940 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
941 'info_dict': {
942 'id': 'Mrj4DVp2zeA',
943 'ext': 'mp4',
944 'upload_date': '20150212',
945 'uploader': 'The National Archives UK',
946 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
947 'uploader_id': 'NationalArchives08',
948 'title': 'Webinar: Using Discovery, The National Archivesā€™ online catalogue',
949 },
950 },
951 # jwplayer rtmp
952 {
953 'url': 'http://www.suffolk.edu/sjc/',
954 'info_dict': {
955 'id': 'sjclive',
956 'ext': 'flv',
957 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
958 'uploader': 'www.suffolk.edu',
959 },
960 'params': {
961 'skip_download': True,
962 }
963 },
964 # rtl.nl embed
965 {
966 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
967 'playlist_mincount': 5,
968 'info_dict': {
969 'id': 'aanslagen-kopenhagen',
970 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
971 }
972 },
973 # Zapiks embed
974 {
975 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
976 'info_dict': {
977 'id': '118046',
978 'ext': 'mp4',
979 'title': 'EP3S5 - Bon AppƩtit - Baqueira Mi Corazon !',
980 }
981 },
982 # Kaltura embed (different embed code)
983 {
984 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
985 'info_dict': {
986 'id': '1_a52wc67y',
987 'ext': 'flv',
988 'upload_date': '20150127',
989 'uploader_id': 'PremierMedia',
990 'timestamp': int,
991 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
992 },
993 },
994 # Kaltura embed protected with referrer
995 {
996 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
997 'info_dict': {
998 'id': '1_g4fbemnq',
999 'ext': 'mp4',
1000 'title': 'Violetta - Achter De Schermen - Ruggero',
1001 'description': 'Achter de schermen met Ruggero',
1002 'timestamp': 1435133761,
1003 'upload_date': '20150624',
1004 'uploader_id': 'echojecka',
1005 },
1006 },
1007 # Kaltura embed with single quotes
1008 {
1009 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1010 'info_dict': {
1011 'id': '0_izeg5utt',
1012 'ext': 'mp4',
1013 'title': '35871',
1014 'timestamp': 1355743100,
1015 'upload_date': '20121217',
1016 'uploader_id': 'batchUser',
1017 },
1018 'add_ie': ['Kaltura'],
1019 },
1020 {
1021 # Kaltura embedded via quoted entry_id
1022 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1023 'info_dict': {
1024 'id': '0_utuok90b',
1025 'ext': 'mp4',
1026 'title': '06_matthew_brender_raj_dutt',
1027 'timestamp': 1466638791,
1028 'upload_date': '20160622',
1029 },
1030 'add_ie': ['Kaltura'],
1031 'expected_warnings': [
1032 'Could not send HEAD request'
1033 ],
1034 'params': {
1035 'skip_download': True,
1036 }
1037 },
1038 {
1039 # Kaltura embedded, some fileExt broken (#11480)
1040 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1041 'info_dict': {
1042 'id': '1_sgtvehim',
1043 'ext': 'mp4',
1044 'title': 'Our "Standard Models" of particle physics and cosmology',
1045 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1046 'timestamp': 1321158993,
1047 'upload_date': '20111113',
1048 'uploader_id': 'kps1',
1049 },
1050 'add_ie': ['Kaltura'],
1051 },
1052 # Eagle.Platform embed (generic URL)
1053 {
1054 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1055 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1056 'info_dict': {
1057 'id': '227304',
1058 'ext': 'mp4',
1059 'title': 'ŠŠ°Š²Š°Š»ŃŒŠ½Ń‹Š¹ Š²Ń‹ŃˆŠµŠ» Š½Š° сŠ²Š¾Š±Š¾Š“у',
1060 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1061 'thumbnail': r're:^https?://.*\.jpg$',
1062 'duration': 87,
1063 'view_count': int,
1064 'age_limit': 0,
1065 },
1066 },
1067 # ClipYou (Eagle.Platform) embed (custom URL)
1068 {
1069 'url': 'http://muz-tv.ru/play/7129/',
1070 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1071 'info_dict': {
1072 'id': '12820',
1073 'ext': 'mp4',
1074 'title': "'O Sole Mio",
1075 'thumbnail': r're:^https?://.*\.jpg$',
1076 'duration': 216,
1077 'view_count': int,
1078 },
1079 },
1080 # Pladform embed
1081 {
1082 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1083 'info_dict': {
1084 'id': '100183293',
1085 'ext': 'mp4',
1086 'title': 'Š¢Š°Š¹Š½Ń‹ ŠæŠµŃ€ŠµŠ²Š°Š»Š° Š”ŃŃ‚Š»Š¾Š²Š° ā€¢ 1 сŠµŃ€Šøя 2 чŠ°ŃŃ‚ŃŒ',
1087 'description': 'Š”Š¾ŠŗуŠ¼ŠµŠ½Ń‚Š°Š»ŃŒŠ½Ń‹Š¹ сŠµŃ€ŠøŠ°Š»-рŠ°ŃŃŠ»ŠµŠ“Š¾Š²Š°Š½ŠøŠµ Š¾Š“Š½Š¾Š¹ ŠøŠ· сŠ°Š¼Ń‹Ń… Š¶ŃƒŃ‚ŠŗŠøх тŠ°Š¹Š½ Š„Š„ Š²ŠµŠŗŠ°',
1088 'thumbnail': r're:^https?://.*\.jpg$',
1089 'duration': 694,
1090 'age_limit': 0,
1091 },
1092 },
1093 # Playwire embed
1094 {
1095 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1096 'info_dict': {
1097 'id': '3519514',
1098 'ext': 'mp4',
1099 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1100 'thumbnail': r're:^https?://.*\.png$',
1101 'duration': 45.115,
1102 },
1103 },
1104 # 5min embed
1105 {
1106 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1107 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1108 'info_dict': {
1109 'id': '518726732',
1110 'ext': 'mp4',
1111 'title': 'Facebook Creates "On This Day" | Crunch Report',
1112 },
1113 },
1114 # SVT embed
1115 {
1116 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1117 'info_dict': {
1118 'id': '2900353',
1119 'ext': 'flv',
1120 'title': 'HƤr trycker Jagr till Giroux (under SVT-intervjun)',
1121 'duration': 27,
1122 'age_limit': 0,
1123 },
1124 },
1125 # Crooks and Liars embed
1126 {
1127 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1128 'info_dict': {
1129 'id': '8RUoRhRi',
1130 'ext': 'mp4',
1131 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1132 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1133 'timestamp': 1428207000,
1134 'upload_date': '20150405',
1135 'uploader': 'Heather',
1136 },
1137 },
1138 # Crooks and Liars external embed
1139 {
1140 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1141 'info_dict': {
1142 'id': 'MTE3MjUtMzQ2MzA',
1143 'ext': 'mp4',
1144 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1145 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1146 'timestamp': 1265032391,
1147 'upload_date': '20100201',
1148 'uploader': 'Heather',
1149 },
1150 },
1151 # NBC Sports vplayer embed
1152 {
1153 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1154 'info_dict': {
1155 'id': 'ln7x1qSThw4k',
1156 'ext': 'flv',
1157 'title': "PFT Live: New leader in the 'new-look' defense",
1158 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1159 'uploader': 'NBCU-SPORTS',
1160 'upload_date': '20140107',
1161 'timestamp': 1389118457,
1162 },
1163 },
1164 # NBC News embed
1165 {
1166 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1167 'md5': '1aa589c675898ae6d37a17913cf68d66',
1168 'info_dict': {
1169 'id': '701714499682',
1170 'ext': 'mp4',
1171 'title': 'PREVIEW: On Assignment: David Letterman',
1172 '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.',
1173 },
1174 },
1175 # UDN embed
1176 {
1177 'url': 'https://video.udn.com/news/300346',
1178 'md5': 'fd2060e988c326991037b9aff9df21a6',
1179 'info_dict': {
1180 'id': '300346',
1181 'ext': 'mp4',
1182 'title': 'äø­äø€äø­ē”·åø«č®Šę€§ å…Øę ”åø«ē”ŸåŠ›ęŒŗ',
1183 'thumbnail': r're:^https?://.*\.jpg$',
1184 },
1185 'params': {
1186 # m3u8 download
1187 'skip_download': True,
1188 },
1189 },
1190 # Ooyala embed
1191 {
1192 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1193 'info_dict': {
1194 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1195 'ext': 'mp4',
1196 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1197 'title': 'This is what separates the Excel masters from the wannabes',
1198 'duration': 191.933,
1199 },
1200 'params': {
1201 # m3u8 downloads
1202 'skip_download': True,
1203 }
1204 },
1205 # Brightcove URL in single quotes
1206 {
1207 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1208 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1209 'info_dict': {
1210 'id': '4255764656001',
1211 'ext': 'mp4',
1212 'title': 'SN Presents: Russell Martin, World Citizen',
1213 'description': 'To understand why he was the Toronto Blue Jaysā€™ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1214 'uploader': 'Rogers Sportsnet',
1215 'uploader_id': '1704050871',
1216 'upload_date': '20150525',
1217 'timestamp': 1432570283,
1218 },
1219 },
1220 # Dailymotion Cloud video
1221 {
1222 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1223 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1224 'info_dict': {
1225 'id': 'x2uy8t3',
1226 'ext': 'mp4',
1227 'title': 'Sauvons les abeilles ! - Le dƩbat',
1228 'description': 'md5:d9082128b1c5277987825d684939ca26',
1229 'thumbnail': r're:^https?://.*\.jpe?g$',
1230 'timestamp': 1434970506,
1231 'upload_date': '20150622',
1232 'uploader': 'Public SĆ©nat',
1233 'uploader_id': 'xa9gza',
1234 }
1235 },
1236 # OnionStudios embed
1237 {
1238 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1239 'info_dict': {
1240 'id': '2855',
1241 'ext': 'mp4',
1242 'title': 'Donā€™t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1243 'thumbnail': r're:^https?://.*\.jpe?g$',
1244 'uploader': 'ClickHole',
1245 'uploader_id': 'clickhole',
1246 }
1247 },
1248 # SnagFilms embed
1249 {
1250 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1251 'info_dict': {
1252 'id': '74849a00-85a9-11e1-9660-123139220831',
1253 'ext': 'mp4',
1254 'title': '#whilewewatch',
1255 }
1256 },
1257 # AdobeTVVideo embed
1258 {
1259 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1260 'md5': '43662b577c018ad707a63766462b1e87',
1261 'info_dict': {
1262 'id': '2456',
1263 'ext': 'mp4',
1264 'title': 'New experience with Acrobat DC',
1265 'description': 'New experience with Acrobat DC',
1266 'duration': 248.667,
1267 },
1268 },
1269 # BrightcoveInPageEmbed embed
1270 {
1271 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1272 'info_dict': {
1273 'id': '4238694884001',
1274 'ext': 'flv',
1275 'title': 'Tabletop: Dread, Last Thoughts',
1276 'description': 'Tabletop: Dread, Last Thoughts',
1277 'duration': 51690,
1278 },
1279 },
1280 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1281 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1282 {
1283 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1284 'info_dict': {
1285 'id': '4785848093001',
1286 'ext': 'mp4',
1287 'title': 'The Cardinal Pell Interview',
1288 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1289 'uploader': 'GlobeCast Australia - GlobeStream',
1290 'uploader_id': '2733773828001',
1291 'upload_date': '20160304',
1292 'timestamp': 1457083087,
1293 },
1294 'params': {
1295 # m3u8 downloads
1296 'skip_download': True,
1297 },
1298 },
1299 # Another form of arte.tv embed
1300 {
1301 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1302 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1303 'info_dict': {
1304 'id': '030273-562_PLUS7-F',
1305 'ext': 'mp4',
1306 'title': 'ARTE Reportage - Nulle part, en France',
1307 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1308 'upload_date': '20160409',
1309 },
1310 },
1311 # LiveLeak embed
1312 {
1313 'url': 'http://www.wykop.pl/link/3088787/',
1314 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1315 'info_dict': {
1316 'id': '874_1459135191',
1317 'ext': 'mp4',
1318 'title': 'Man shows poor quality of new apartment building',
1319 'description': 'The wall is like a sand pile.',
1320 'uploader': 'Lake8737',
1321 }
1322 },
1323 # Duplicated embedded video URLs
1324 {
1325 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1326 'info_dict': {
1327 'id': '149298443_480_16c25b74_2',
1328 'ext': 'mp4',
1329 'title': 'vs. Blue Orange Spring Game',
1330 'uploader': 'www.hudl.com',
1331 },
1332 },
1333 # twitter:player:stream embed
1334 {
1335 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1336 'info_dict': {
1337 'id': 'master',
1338 'ext': 'mp4',
1339 'title': 'Une nouvelle espĆØce de dinosaure dĆ©couverte en Argentine',
1340 'uploader': 'www.rtl.be',
1341 },
1342 'params': {
1343 # m3u8 downloads
1344 'skip_download': True,
1345 },
1346 },
1347 # twitter:player embed
1348 {
1349 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1350 'md5': 'a3e0df96369831de324f0778e126653c',
1351 'info_dict': {
1352 'id': '4909620399001',
1353 'ext': 'mp4',
1354 'title': 'What Do Black Holes Sound Like?',
1355 'description': 'what do black holes sound like',
1356 'upload_date': '20160524',
1357 'uploader_id': '29913724001',
1358 'timestamp': 1464107587,
1359 'uploader': 'TheAtlantic',
1360 },
1361 'add_ie': ['BrightcoveLegacy'],
1362 },
1363 # Facebook <iframe> embed
1364 {
1365 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1366 'md5': 'fbcde74f534176ecb015849146dd3aee',
1367 'info_dict': {
1368 'id': '599637780109885',
1369 'ext': 'mp4',
1370 'title': 'Facebook video #599637780109885',
1371 },
1372 },
1373 # Facebook API embed
1374 {
1375 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1376 'md5': 'a47372ee61b39a7b90287094d447d94e',
1377 'info_dict': {
1378 'id': '10153467542406923',
1379 'ext': 'mp4',
1380 'title': 'Facebook video #10153467542406923',
1381 },
1382 },
1383 # Wordpress "YouTube Video Importer" plugin
1384 {
1385 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1386 'md5': 'd16797741b560b485194eddda8121b48',
1387 'info_dict': {
1388 'id': 'HNTXWDXV9Is',
1389 'ext': 'mp4',
1390 'title': 'Blue Devils Drumline Stanford lot 2016',
1391 'upload_date': '20160627',
1392 'uploader_id': 'GENOCIDE8GENERAL10',
1393 'uploader': 'cylus cyrus',
1394 },
1395 },
1396 {
1397 # video stored on custom kaltura server
1398 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1399 'md5': '537617d06e64dfed891fa1593c4b30cc',
1400 'info_dict': {
1401 'id': '0_1iotm5bh',
1402 'ext': 'mp4',
1403 'title': 'Elecciones britƔnicas: 5 lecciones para Rajoy',
1404 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1405 'uploader_id': 'videos.expansion@el-mundo.net',
1406 'upload_date': '20150429',
1407 'timestamp': 1430303472,
1408 },
1409 'add_ie': ['Kaltura'],
1410 },
1411 {
1412 # Non-standard Vimeo embed
1413 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1414 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1415 'info_dict': {
1416 'id': '148867247',
1417 'ext': 'mp4',
1418 'title': 'Understanding the web - Teaser',
1419 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1420 'upload_date': '20151214',
1421 'uploader': 'OpenClassrooms',
1422 'uploader_id': 'openclassrooms',
1423 },
1424 'add_ie': ['Vimeo'],
1425 },
1426 {
1427 # generic vimeo embed that requires original URL passed as Referer
1428 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1429 'only_matching': True,
1430 },
1431 {
1432 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1433 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1434 'info_dict': {
1435 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1436 'ext': 'mp4',
1437 'title': 'Big Buck Bunny',
1438 'description': 'Royalty free test video',
1439 'timestamp': 1432816365,
1440 'upload_date': '20150528',
1441 'is_live': False,
1442 },
1443 'params': {
1444 'skip_download': True,
1445 },
1446 'add_ie': [ArkenaIE.ie_key()],
1447 },
1448 {
1449 '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/',
1450 'info_dict': {
1451 'id': '1c7141f46c',
1452 'ext': 'mp4',
1453 'title': 'ŠŠ ŠšŠžŠ”ŠŖŠœ ŠžŠ¢ Š’Š—Š Š˜Š’: Š˜Š·Ń‚ŠøчŠ°Š½Šµ Š½Š° Š³Š°Š· Š½Š° Š±ŠµŠ½Š·ŠøŠ½Š¾ŃŃ‚Š°Š½Ń†Šøя Š² ŠŸŠ»Š¾Š²Š“ŠøŠ²',
1454 },
1455 'params': {
1456 'skip_download': True,
1457 },
1458 'add_ie': [Vbox7IE.ie_key()],
1459 },
1460 {
1461 # DBTV embeds
1462 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1463 'info_dict': {
1464 'id': '43254897',
1465 'title': 'Etter ett Ƅrs planlegging, klaffet endelig alt: - Jeg mƄtte ta en liten dans',
1466 },
1467 'playlist_mincount': 3,
1468 },
1469 {
1470 # Videa embeds
1471 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1472 'info_dict': {
1473 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1474 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1475 },
1476 'playlist_mincount': 2,
1477 },
1478 {
1479 # 20 minuten embed
1480 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1481 'info_dict': {
1482 'id': '523629',
1483 'ext': 'mp4',
1484 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1485 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1486 },
1487 'params': {
1488 'skip_download': True,
1489 },
1490 'add_ie': [TwentyMinutenIE.ie_key()],
1491 },
1492 {
1493 # VideoPress embed
1494 'url': 'https://en.support.wordpress.com/videopress/',
1495 'info_dict': {
1496 'id': 'OcobLTqC',
1497 'ext': 'm4v',
1498 'title': 'IMG_5786',
1499 'timestamp': 1435711927,
1500 'upload_date': '20150701',
1501 },
1502 'params': {
1503 'skip_download': True,
1504 },
1505 'add_ie': [VideoPressIE.ie_key()],
1506 }
1507 # {
1508 # # TODO: find another test
1509 # # http://schema.org/VideoObject
1510 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1511 # 'md5': '888dcf08b7ea671381f00fab74692755',
1512 # 'info_dict': {
1513 # 'id': 'nyvTSJMKId',
1514 # 'ext': 'mp4',
1515 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1516 # 'description': '#love for cats.',
1517 # 'timestamp': 1461244995,
1518 # 'upload_date': '20160421',
1519 # },
1520 # 'params': {
1521 # 'force_generic_extractor': True,
1522 # },
1523 # }
1524 ]
1525
1526 def report_following_redirect(self, new_url):
1527 """Report information extraction."""
1528 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1529
1530 def _extract_rss(self, url, video_id, doc):
1531 playlist_title = doc.find('./channel/title').text
1532 playlist_desc_el = doc.find('./channel/description')
1533 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1534
1535 entries = []
1536 for it in doc.findall('./channel/item'):
1537 next_url = xpath_text(it, 'link', fatal=False)
1538 if not next_url:
1539 enclosure_nodes = it.findall('./enclosure')
1540 for e in enclosure_nodes:
1541 next_url = e.attrib.get('url')
1542 if next_url:
1543 break
1544
1545 if not next_url:
1546 continue
1547
1548 entries.append({
1549 '_type': 'url',
1550 'url': next_url,
1551 'title': it.find('title').text,
1552 })
1553
1554 return {
1555 '_type': 'playlist',
1556 'id': url,
1557 'title': playlist_title,
1558 'description': playlist_desc,
1559 'entries': entries,
1560 }
1561
1562 def _extract_camtasia(self, url, video_id, webpage):
1563 """ Returns None if no camtasia video can be found. """
1564
1565 camtasia_cfg = self._search_regex(
1566 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1567 webpage, 'camtasia configuration file', default=None)
1568 if camtasia_cfg is None:
1569 return None
1570
1571 title = self._html_search_meta('DC.title', webpage, fatal=True)
1572
1573 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1574 camtasia_cfg = self._download_xml(
1575 camtasia_url, video_id,
1576 note='Downloading camtasia configuration',
1577 errnote='Failed to download camtasia configuration')
1578 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1579
1580 entries = []
1581 for n in fileset_node.getchildren():
1582 url_n = n.find('./uri')
1583 if url_n is None:
1584 continue
1585
1586 entries.append({
1587 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1588 'title': '%s - %s' % (title, n.tag),
1589 'url': compat_urlparse.urljoin(url, url_n.text),
1590 'duration': float_or_none(n.find('./duration').text),
1591 })
1592
1593 return {
1594 '_type': 'playlist',
1595 'entries': entries,
1596 'title': title,
1597 }
1598
1599 def _real_extract(self, url):
1600 if url.startswith('//'):
1601 return {
1602 '_type': 'url',
1603 'url': self.http_scheme() + url,
1604 }
1605
1606 parsed_url = compat_urlparse.urlparse(url)
1607 if not parsed_url.scheme:
1608 default_search = self._downloader.params.get('default_search')
1609 if default_search is None:
1610 default_search = 'fixup_error'
1611
1612 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1613 if '/' in url:
1614 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1615 return self.url_result('http://' + url)
1616 elif default_search != 'fixup_error':
1617 if default_search == 'auto_warning':
1618 if re.match(r'^(?:url|URL)$', url):
1619 raise ExtractorError(
1620 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1621 expected=True)
1622 else:
1623 self._downloader.report_warning(
1624 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1625 return self.url_result('ytsearch:' + url)
1626
1627 if default_search in ('error', 'fixup_error'):
1628 raise ExtractorError(
1629 '%r is not a valid URL. '
1630 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1631 % (url, url), expected=True)
1632 else:
1633 if ':' not in default_search:
1634 default_search += ':'
1635 return self.url_result(default_search + url)
1636
1637 url, smuggled_data = unsmuggle_url(url)
1638 force_videoid = None
1639 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1640 if smuggled_data and 'force_videoid' in smuggled_data:
1641 force_videoid = smuggled_data['force_videoid']
1642 video_id = force_videoid
1643 else:
1644 video_id = self._generic_id(url)
1645
1646 self.to_screen('%s: Requesting header' % video_id)
1647
1648 head_req = HEADRequest(url)
1649 head_response = self._request_webpage(
1650 head_req, video_id,
1651 note=False, errnote='Could not send HEAD request to %s' % url,
1652 fatal=False)
1653
1654 if head_response is not False:
1655 # Check for redirect
1656 new_url = head_response.geturl()
1657 if url != new_url:
1658 self.report_following_redirect(new_url)
1659 if force_videoid:
1660 new_url = smuggle_url(
1661 new_url, {'force_videoid': force_videoid})
1662 return self.url_result(new_url)
1663
1664 full_response = None
1665 if head_response is False:
1666 request = sanitized_Request(url)
1667 request.add_header('Accept-Encoding', '*')
1668 full_response = self._request_webpage(request, video_id)
1669 head_response = full_response
1670
1671 info_dict = {
1672 'id': video_id,
1673 'title': self._generic_title(url),
1674 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1675 }
1676
1677 # Check for direct link to a video
1678 content_type = head_response.headers.get('Content-Type', '').lower()
1679 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1680 if m:
1681 format_id = m.group('format_id')
1682 if format_id.endswith('mpegurl'):
1683 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1684 elif format_id == 'f4m':
1685 formats = self._extract_f4m_formats(url, video_id)
1686 else:
1687 formats = [{
1688 'format_id': m.group('format_id'),
1689 'url': url,
1690 'vcodec': 'none' if m.group('type') == 'audio' else None
1691 }]
1692 info_dict['direct'] = True
1693 self._sort_formats(formats)
1694 info_dict['formats'] = formats
1695 return info_dict
1696
1697 if not self._downloader.params.get('test', False) and not is_intentional:
1698 force = self._downloader.params.get('force_generic_extractor', False)
1699 self._downloader.report_warning(
1700 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1701
1702 if not full_response:
1703 request = sanitized_Request(url)
1704 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1705 # making it impossible to download only chunk of the file (yet we need only 512kB to
1706 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1707 # that will always result in downloading the whole file that is not desirable.
1708 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1709 # to accept raw bytes and being able to download only a chunk.
1710 # It may probably better to solve this by checking Content-Type for application/octet-stream
1711 # after HEAD request finishes, but not sure if we can rely on this.
1712 request.add_header('Accept-Encoding', '*')
1713 full_response = self._request_webpage(request, video_id)
1714
1715 first_bytes = full_response.read(512)
1716
1717 # Is it an M3U playlist?
1718 if first_bytes.startswith(b'#EXTM3U'):
1719 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1720 self._sort_formats(info_dict['formats'])
1721 return info_dict
1722
1723 # Maybe it's a direct link to a video?
1724 # Be careful not to download the whole thing!
1725 if not is_html(first_bytes):
1726 self._downloader.report_warning(
1727 'URL could be a direct video link, returning it as such.')
1728 info_dict.update({
1729 'direct': True,
1730 'url': url,
1731 })
1732 return info_dict
1733
1734 webpage = self._webpage_read_content(
1735 full_response, url, video_id, prefix=first_bytes)
1736
1737 self.report_extraction(video_id)
1738
1739 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1740 try:
1741 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1742 if doc.tag == 'rss':
1743 return self._extract_rss(url, video_id, doc)
1744 elif doc.tag == 'SmoothStreamingMedia':
1745 info_dict['formats'] = self._parse_ism_formats(doc, url)
1746 self._sort_formats(info_dict['formats'])
1747 return info_dict
1748 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1749 smil = self._parse_smil(doc, url, video_id)
1750 self._sort_formats(smil['formats'])
1751 return smil
1752 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1753 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1754 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1755 info_dict['formats'] = self._parse_mpd_formats(
1756 doc, video_id,
1757 mpd_base_url=full_response.geturl().rpartition('/')[0],
1758 mpd_url=url)
1759 self._sort_formats(info_dict['formats'])
1760 return info_dict
1761 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1762 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1763 self._sort_formats(info_dict['formats'])
1764 return info_dict
1765 except compat_xml_parse_error:
1766 pass
1767
1768 # Is it a Camtasia project?
1769 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1770 if camtasia_res is not None:
1771 return camtasia_res
1772
1773 # Sometimes embedded video player is hidden behind percent encoding
1774 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1775 # Unescaping the whole page allows to handle those cases in a generic way
1776 webpage = compat_urllib_parse_unquote(webpage)
1777
1778 # it's tempting to parse this further, but you would
1779 # have to take into account all the variations like
1780 # Video Title - Site Name
1781 # Site Name | Video Title
1782 # Video Title - Tagline | Site Name
1783 # and so on and so forth; it's just not practical
1784 video_title = self._og_search_title(
1785 webpage, default=None) or self._html_search_regex(
1786 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1787 default='video')
1788
1789 # Try to detect age limit automatically
1790 age_limit = self._rta_search(webpage)
1791 # And then there are the jokers who advertise that they use RTA,
1792 # but actually don't.
1793 AGE_LIMIT_MARKERS = [
1794 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1795 ]
1796 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1797 age_limit = 18
1798
1799 # video uploader is domain name
1800 video_uploader = self._search_regex(
1801 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1802
1803 video_description = self._og_search_description(webpage, default=None)
1804 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1805
1806 # Helper method
1807 def _playlist_from_matches(matches, getter=None, ie=None):
1808 urlrs = orderedSet(
1809 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1810 for m in matches)
1811 return self.playlist_result(
1812 urlrs, playlist_id=video_id, playlist_title=video_title)
1813
1814 # Look for Brightcove Legacy Studio embeds
1815 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1816 if bc_urls:
1817 self.to_screen('Brightcove video detected.')
1818 entries = [{
1819 '_type': 'url',
1820 'url': smuggle_url(bc_url, {'Referer': url}),
1821 'ie_key': 'BrightcoveLegacy'
1822 } for bc_url in bc_urls]
1823
1824 return {
1825 '_type': 'playlist',
1826 'title': video_title,
1827 'id': video_id,
1828 'entries': entries,
1829 }
1830
1831 # Look for Brightcove New Studio embeds
1832 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1833 if bc_urls:
1834 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1835
1836 # Look for ThePlatform embeds
1837 tp_urls = ThePlatformIE._extract_urls(webpage)
1838 if tp_urls:
1839 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1840
1841 # Look for Vessel embeds
1842 vessel_urls = VesselIE._extract_urls(webpage)
1843 if vessel_urls:
1844 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1845
1846 # Look for embedded rtl.nl player
1847 matches = re.findall(
1848 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1849 webpage)
1850 if matches:
1851 return _playlist_from_matches(matches, ie='RtlNl')
1852
1853 vimeo_urls = VimeoIE._extract_urls(url, webpage)
1854 if vimeo_urls:
1855 return _playlist_from_matches(vimeo_urls, ie=VimeoIE.ie_key())
1856
1857 vid_me_embed_url = self._search_regex(
1858 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1859 webpage, 'vid.me embed', default=None)
1860 if vid_me_embed_url is not None:
1861 return self.url_result(vid_me_embed_url, 'Vidme')
1862
1863 # Look for embedded YouTube player
1864 matches = re.findall(r'''(?x)
1865 (?:
1866 <iframe[^>]+?src=|
1867 data-video-url=|
1868 <embed[^>]+?src=|
1869 embedSWF\(?:\s*|
1870 new\s+SWFObject\(
1871 )
1872 (["\'])
1873 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1874 (?:embed|v|p)/.+?)
1875 \1''', webpage)
1876 if matches:
1877 return _playlist_from_matches(
1878 matches, lambda m: unescapeHTML(m[1]))
1879
1880 # Look for lazyYT YouTube embed
1881 matches = re.findall(
1882 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1883 if matches:
1884 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1885
1886 # Look for Wordpress "YouTube Video Importer" plugin
1887 matches = re.findall(r'''(?x)<div[^>]+
1888 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1889 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1890 if matches:
1891 return _playlist_from_matches(matches, lambda m: m[-1])
1892
1893 matches = DailymotionIE._extract_urls(webpage)
1894 if matches:
1895 return _playlist_from_matches(matches)
1896
1897 # Look for embedded Dailymotion playlist player (#3822)
1898 m = re.search(
1899 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1900 if m:
1901 playlists = re.findall(
1902 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1903 if playlists:
1904 return _playlist_from_matches(
1905 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1906
1907 # Look for embedded Wistia player
1908 match = re.search(
1909 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1910 if match:
1911 embed_url = self._proto_relative_url(
1912 unescapeHTML(match.group('url')))
1913 return {
1914 '_type': 'url_transparent',
1915 'url': embed_url,
1916 'ie_key': 'Wistia',
1917 'uploader': video_uploader,
1918 }
1919
1920 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1921 if match:
1922 return {
1923 '_type': 'url_transparent',
1924 'url': 'wistia:%s' % match.group('id'),
1925 'ie_key': 'Wistia',
1926 'uploader': video_uploader,
1927 }
1928
1929 match = re.search(
1930 r'''(?sx)
1931 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1932 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1933 ''', webpage)
1934 if match:
1935 return self.url_result(self._proto_relative_url(
1936 'wistia:%s' % match.group('id')), 'Wistia')
1937
1938 # Look for SVT player
1939 svt_url = SVTIE._extract_url(webpage)
1940 if svt_url:
1941 return self.url_result(svt_url, 'SVT')
1942
1943 # Look for embedded condenast player
1944 matches = re.findall(
1945 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1946 webpage)
1947 if matches:
1948 return {
1949 '_type': 'playlist',
1950 'entries': [{
1951 '_type': 'url',
1952 'ie_key': 'CondeNast',
1953 'url': ma,
1954 } for ma in matches],
1955 'title': video_title,
1956 'id': video_id,
1957 }
1958
1959 # Look for Bandcamp pages with custom domain
1960 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1961 if mobj is not None:
1962 burl = unescapeHTML(mobj.group(1))
1963 # Don't set the extractor because it can be a track url or an album
1964 return self.url_result(burl)
1965
1966 # Look for embedded Vevo player
1967 mobj = re.search(
1968 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1969 if mobj is not None:
1970 return self.url_result(mobj.group('url'))
1971
1972 # Look for embedded Viddler player
1973 mobj = re.search(
1974 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1975 webpage)
1976 if mobj is not None:
1977 return self.url_result(mobj.group('url'))
1978
1979 # Look for NYTimes player
1980 mobj = re.search(
1981 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1982 webpage)
1983 if mobj is not None:
1984 return self.url_result(mobj.group('url'))
1985
1986 # Look for Libsyn player
1987 mobj = re.search(
1988 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1989 if mobj is not None:
1990 return self.url_result(mobj.group('url'))
1991
1992 # Look for Ooyala videos
1993 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1994 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1995 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1996 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1997 if mobj is not None:
1998 embed_token = self._search_regex(
1999 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2000 webpage, 'ooyala embed token', default=None)
2001 return OoyalaIE._build_url_result(smuggle_url(
2002 mobj.group('ec'), {
2003 'domain': url,
2004 'embed_token': embed_token,
2005 }))
2006
2007 # Look for multiple Ooyala embeds on SBN network websites
2008 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2009 if mobj is not None:
2010 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2011 if embeds:
2012 return _playlist_from_matches(
2013 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2014
2015 # Look for Aparat videos
2016 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2017 if mobj is not None:
2018 return self.url_result(mobj.group(1), 'Aparat')
2019
2020 # Look for MPORA videos
2021 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2022 if mobj is not None:
2023 return self.url_result(mobj.group(1), 'Mpora')
2024
2025 # Look for embedded NovaMov-based player
2026 mobj = re.search(
2027 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2028 (?P<url>http://(?:(?:embed|www)\.)?
2029 (?:novamov\.com|
2030 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2031 videoweed\.(?:es|com)|
2032 movshare\.(?:net|sx|ag)|
2033 divxstage\.(?:eu|net|ch|co|at|ag))
2034 /embed\.php.+?)\1''', webpage)
2035 if mobj is not None:
2036 return self.url_result(mobj.group('url'))
2037
2038 # Look for embedded Facebook player
2039 facebook_url = FacebookIE._extract_url(webpage)
2040 if facebook_url is not None:
2041 return self.url_result(facebook_url, 'Facebook')
2042
2043 # Look for embedded VK player
2044 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2045 if mobj is not None:
2046 return self.url_result(mobj.group('url'), 'VK')
2047
2048 # Look for embedded Odnoklassniki player
2049 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2050 if mobj is not None:
2051 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2052
2053 # Look for embedded ivi player
2054 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2055 if mobj is not None:
2056 return self.url_result(mobj.group('url'), 'Ivi')
2057
2058 # Look for embedded Huffington Post player
2059 mobj = re.search(
2060 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2061 if mobj is not None:
2062 return self.url_result(mobj.group('url'), 'HuffPost')
2063
2064 # Look for embed.ly
2065 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2066 if mobj is not None:
2067 return self.url_result(mobj.group('url'))
2068 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2069 if mobj is not None:
2070 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2071
2072 # Look for funnyordie embed
2073 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2074 if matches:
2075 return _playlist_from_matches(
2076 matches, getter=unescapeHTML, ie='FunnyOrDie')
2077
2078 # Look for BBC iPlayer embed
2079 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2080 if matches:
2081 return _playlist_from_matches(matches, ie='BBCCoUk')
2082
2083 # Look for embedded RUTV player
2084 rutv_url = RUTVIE._extract_url(webpage)
2085 if rutv_url:
2086 return self.url_result(rutv_url, 'RUTV')
2087
2088 # Look for embedded TVC player
2089 tvc_url = TVCIE._extract_url(webpage)
2090 if tvc_url:
2091 return self.url_result(tvc_url, 'TVC')
2092
2093 # Look for embedded SportBox player
2094 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2095 if sportbox_urls:
2096 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
2097
2098 # Look for embedded XHamster player
2099 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2100 if xhamster_urls:
2101 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
2102
2103 # Look for embedded TNAFlixNetwork player
2104 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2105 if tnaflix_urls:
2106 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
2107
2108 # Look for embedded PornHub player
2109 pornhub_urls = PornHubIE._extract_urls(webpage)
2110 if pornhub_urls:
2111 return _playlist_from_matches(pornhub_urls, ie=PornHubIE.ie_key())
2112
2113 # Look for embedded DrTuber player
2114 drtuber_urls = DrTuberIE._extract_urls(webpage)
2115 if drtuber_urls:
2116 return _playlist_from_matches(drtuber_urls, ie=DrTuberIE.ie_key())
2117
2118 # Look for embedded RedTube player
2119 redtube_urls = RedTubeIE._extract_urls(webpage)
2120 if redtube_urls:
2121 return _playlist_from_matches(redtube_urls, ie=RedTubeIE.ie_key())
2122
2123 # Look for embedded Tvigle player
2124 mobj = re.search(
2125 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2126 if mobj is not None:
2127 return self.url_result(mobj.group('url'), 'Tvigle')
2128
2129 # Look for embedded TED player
2130 mobj = re.search(
2131 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2132 if mobj is not None:
2133 return self.url_result(mobj.group('url'), 'TED')
2134
2135 # Look for embedded Ustream videos
2136 ustream_url = UstreamIE._extract_url(webpage)
2137 if ustream_url:
2138 return self.url_result(ustream_url, UstreamIE.ie_key())
2139
2140 # Look for embedded arte.tv player
2141 mobj = re.search(
2142 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2143 webpage)
2144 if mobj is not None:
2145 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2146
2147 # Look for embedded francetv player
2148 mobj = re.search(
2149 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2150 webpage)
2151 if mobj is not None:
2152 return self.url_result(mobj.group('url'))
2153
2154 # Look for embedded smotri.com player
2155 smotri_url = SmotriIE._extract_url(webpage)
2156 if smotri_url:
2157 return self.url_result(smotri_url, 'Smotri')
2158
2159 # Look for embedded Myvi.ru player
2160 myvi_url = MyviIE._extract_url(webpage)
2161 if myvi_url:
2162 return self.url_result(myvi_url)
2163
2164 # Look for embedded soundcloud player
2165 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2166 if soundcloud_urls:
2167 return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2168
2169 # Look for tunein player
2170 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2171 if tunein_urls:
2172 return _playlist_from_matches(tunein_urls)
2173
2174 # Look for embedded mtvservices player
2175 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2176 if mtvservices_url:
2177 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2178
2179 # Look for embedded yahoo player
2180 mobj = re.search(
2181 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2182 webpage)
2183 if mobj is not None:
2184 return self.url_result(mobj.group('url'), 'Yahoo')
2185
2186 # Look for embedded sbs.com.au player
2187 mobj = re.search(
2188 r'''(?x)
2189 (?:
2190 <meta\s+property="og:video"\s+content=|
2191 <iframe[^>]+?src=
2192 )
2193 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2194 webpage)
2195 if mobj is not None:
2196 return self.url_result(mobj.group('url'), 'SBS')
2197
2198 # Look for embedded Cinchcast player
2199 mobj = re.search(
2200 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2201 webpage)
2202 if mobj is not None:
2203 return self.url_result(mobj.group('url'), 'Cinchcast')
2204
2205 mobj = re.search(
2206 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2207 webpage)
2208 if not mobj:
2209 mobj = re.search(
2210 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2211 webpage)
2212 if mobj is not None:
2213 return self.url_result(mobj.group('url'), 'MLB')
2214
2215 mobj = re.search(
2216 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2217 webpage)
2218 if mobj is not None:
2219 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2220
2221 mobj = re.search(
2222 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2223 webpage)
2224 if mobj is not None:
2225 return self.url_result(mobj.group('url'), 'Livestream')
2226
2227 # Look for Zapiks embed
2228 mobj = re.search(
2229 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2230 if mobj is not None:
2231 return self.url_result(mobj.group('url'), 'Zapiks')
2232
2233 # Look for Kaltura embeds
2234 kaltura_url = KalturaIE._extract_url(webpage)
2235 if kaltura_url:
2236 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2237
2238 # Look for Eagle.Platform embeds
2239 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2240 if eagleplatform_url:
2241 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2242
2243 # Look for ClipYou (uses Eagle.Platform) embeds
2244 mobj = re.search(
2245 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2246 if mobj is not None:
2247 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2248
2249 # Look for Pladform embeds
2250 pladform_url = PladformIE._extract_url(webpage)
2251 if pladform_url:
2252 return self.url_result(pladform_url)
2253
2254 # Look for Videomore embeds
2255 videomore_url = VideomoreIE._extract_url(webpage)
2256 if videomore_url:
2257 return self.url_result(videomore_url)
2258
2259 # Look for Webcaster embeds
2260 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2261 if webcaster_url:
2262 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2263
2264 # Look for Playwire embeds
2265 mobj = re.search(
2266 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2267 if mobj is not None:
2268 return self.url_result(mobj.group('url'))
2269
2270 # Look for 5min embeds
2271 mobj = re.search(
2272 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2273 if mobj is not None:
2274 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2275
2276 # Look for Crooks and Liars embeds
2277 mobj = re.search(
2278 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2279 if mobj is not None:
2280 return self.url_result(mobj.group('url'))
2281
2282 # Look for NBC Sports VPlayer embeds
2283 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2284 if nbc_sports_url:
2285 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2286
2287 # Look for NBC News embeds
2288 nbc_news_embed_url = re.search(
2289 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2290 if nbc_news_embed_url:
2291 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2292
2293 # Look for Google Drive embeds
2294 google_drive_url = GoogleDriveIE._extract_url(webpage)
2295 if google_drive_url:
2296 return self.url_result(google_drive_url, 'GoogleDrive')
2297
2298 # Look for UDN embeds
2299 mobj = re.search(
2300 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2301 if mobj is not None:
2302 return self.url_result(
2303 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2304
2305 # Look for Senate ISVP iframe
2306 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2307 if senate_isvp_url:
2308 return self.url_result(senate_isvp_url, 'SenateISVP')
2309
2310 # Look for Dailymotion Cloud videos
2311 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2312 if dmcloud_url:
2313 return self.url_result(dmcloud_url, 'DailymotionCloud')
2314
2315 # Look for OnionStudios embeds
2316 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2317 if onionstudios_url:
2318 return self.url_result(onionstudios_url)
2319
2320 # Look for ViewLift embeds
2321 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2322 if viewlift_url:
2323 return self.url_result(viewlift_url)
2324
2325 # Look for JWPlatform embeds
2326 jwplatform_url = JWPlatformIE._extract_url(webpage)
2327 if jwplatform_url:
2328 return self.url_result(jwplatform_url, 'JWPlatform')
2329
2330 # Look for Digiteka embeds
2331 digiteka_url = DigitekaIE._extract_url(webpage)
2332 if digiteka_url:
2333 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2334
2335 # Look for Arkena embeds
2336 arkena_url = ArkenaIE._extract_url(webpage)
2337 if arkena_url:
2338 return self.url_result(arkena_url, ArkenaIE.ie_key())
2339
2340 # Look for Piksel embeds
2341 piksel_url = PikselIE._extract_url(webpage)
2342 if piksel_url:
2343 return self.url_result(piksel_url, PikselIE.ie_key())
2344
2345 # Look for Limelight embeds
2346 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2347 if mobj:
2348 lm = {
2349 'Media': 'media',
2350 'Channel': 'channel',
2351 'ChannelList': 'channel_list',
2352 }
2353 return self.url_result('limelight:%s:%s' % (
2354 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2355
2356 mobj = re.search(
2357 r'''(?sx)
2358 <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2359 <param[^>]+
2360 name=(["\'])flashVars\2[^>]+
2361 value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2362 ''', webpage)
2363 if mobj:
2364 return self.url_result('limelight:media:%s' % mobj.group('id'))
2365
2366 # Look for AdobeTVVideo embeds
2367 mobj = re.search(
2368 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2369 webpage)
2370 if mobj is not None:
2371 return self.url_result(
2372 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2373 'AdobeTVVideo')
2374
2375 # Look for Vine embeds
2376 mobj = re.search(
2377 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2378 webpage)
2379 if mobj is not None:
2380 return self.url_result(
2381 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2382
2383 # Look for VODPlatform embeds
2384 mobj = re.search(
2385 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2386 webpage)
2387 if mobj is not None:
2388 return self.url_result(
2389 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2390
2391 # Look for Mangomolo embeds
2392 mobj = re.search(
2393 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2394 (?:
2395 video\?.*?\bid=(?P<video_id>\d+)|
2396 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2397 ).+?)\1''', webpage)
2398 if mobj is not None:
2399 info = {
2400 '_type': 'url_transparent',
2401 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2402 'title': video_title,
2403 'description': video_description,
2404 'thumbnail': video_thumbnail,
2405 'uploader': video_uploader,
2406 }
2407 video_id = mobj.group('video_id')
2408 if video_id:
2409 info.update({
2410 'ie_key': 'MangomoloVideo',
2411 'id': video_id,
2412 })
2413 else:
2414 info.update({
2415 'ie_key': 'MangomoloLive',
2416 'id': mobj.group('channel_id'),
2417 })
2418 return info
2419
2420 # Look for Instagram embeds
2421 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2422 if instagram_embed_url is not None:
2423 return self.url_result(
2424 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2425
2426 # Look for LiveLeak embeds
2427 liveleak_url = LiveLeakIE._extract_url(webpage)
2428 if liveleak_url:
2429 return self.url_result(liveleak_url, 'LiveLeak')
2430
2431 # Look for 3Q SDN embeds
2432 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2433 if threeqsdn_url:
2434 return {
2435 '_type': 'url_transparent',
2436 'ie_key': ThreeQSDNIE.ie_key(),
2437 'url': self._proto_relative_url(threeqsdn_url),
2438 'title': video_title,
2439 'description': video_description,
2440 'thumbnail': video_thumbnail,
2441 'uploader': video_uploader,
2442 }
2443
2444 # Look for VBOX7 embeds
2445 vbox7_url = Vbox7IE._extract_url(webpage)
2446 if vbox7_url:
2447 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2448
2449 # Look for DBTV embeds
2450 dbtv_urls = DBTVIE._extract_urls(webpage)
2451 if dbtv_urls:
2452 return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
2453
2454 # Look for Videa embeds
2455 videa_urls = VideaIE._extract_urls(webpage)
2456 if videa_urls:
2457 return _playlist_from_matches(videa_urls, ie=VideaIE.ie_key())
2458
2459 # Look for 20 minuten embeds
2460 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2461 if twentymin_urls:
2462 return _playlist_from_matches(
2463 twentymin_urls, ie=TwentyMinutenIE.ie_key())
2464
2465 # Look for Openload embeds
2466 openload_urls = OpenloadIE._extract_urls(webpage)
2467 if openload_urls:
2468 return _playlist_from_matches(
2469 openload_urls, ie=OpenloadIE.ie_key())
2470
2471 # Look for VideoPress embeds
2472 videopress_urls = VideoPressIE._extract_urls(webpage)
2473 if videopress_urls:
2474 return _playlist_from_matches(
2475 videopress_urls, ie=VideoPressIE.ie_key())
2476
2477 # Looking for http://schema.org/VideoObject
2478 json_ld = self._search_json_ld(
2479 webpage, video_id, default={}, expected_type='VideoObject')
2480 if json_ld.get('url'):
2481 info_dict.update({
2482 'title': video_title or info_dict['title'],
2483 'description': video_description,
2484 'thumbnail': video_thumbnail,
2485 'age_limit': age_limit
2486 })
2487 info_dict.update(json_ld)
2488 return info_dict
2489
2490 # Look for HTML5 media
2491 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2492 if entries:
2493 for entry in entries:
2494 entry.update({
2495 'id': video_id,
2496 'title': video_title,
2497 })
2498 self._sort_formats(entry['formats'])
2499 return self.playlist_result(entries)
2500
2501 def check_video(vurl):
2502 if YoutubeIE.suitable(vurl):
2503 return True
2504 if RtmpIE.suitable(vurl):
2505 return True
2506 vpath = compat_urlparse.urlparse(vurl).path
2507 vext = determine_ext(vpath)
2508 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
2509
2510 def filter_video(urls):
2511 return list(filter(check_video, urls))
2512
2513 # Start with something easy: JW Player in SWFObject
2514 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2515 if not found:
2516 # Look for gorilla-vid style embedding
2517 found = filter_video(re.findall(r'''(?sx)
2518 (?:
2519 jw_plugins|
2520 JWPlayerOptions|
2521 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2522 )
2523 .*?
2524 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2525 if not found:
2526 # Broaden the search a little bit
2527 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2528 if not found:
2529 # Broaden the findall a little bit: JWPlayer JS loader
2530 found = filter_video(re.findall(
2531 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2532 if not found:
2533 # Flow player
2534 found = filter_video(re.findall(r'''(?xs)
2535 flowplayer\("[^"]+",\s*
2536 \{[^}]+?\}\s*,
2537 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2538 ["']?url["']?\s*:\s*["']([^"']+)["']
2539 ''', webpage))
2540 if not found:
2541 # Cinerama player
2542 found = re.findall(
2543 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2544 if not found:
2545 # Try to find twitter cards info
2546 # twitter:player:stream should be checked before twitter:player since
2547 # it is expected to contain a raw stream (see
2548 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2549 found = filter_video(re.findall(
2550 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2551 if not found:
2552 # We look for Open Graph info:
2553 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2554 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2555 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2556 if m_video_type is not None:
2557 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2558 if not found:
2559 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2560 found = re.search(
2561 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2562 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2563 webpage)
2564 if not found:
2565 # Look also in Refresh HTTP header
2566 refresh_header = head_response.headers.get('Refresh')
2567 if refresh_header:
2568 # In python 2 response HTTP headers are bytestrings
2569 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2570 refresh_header = refresh_header.decode('iso-8859-1')
2571 found = re.search(REDIRECT_REGEX, refresh_header)
2572 if found:
2573 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2574 self.report_following_redirect(new_url)
2575 return {
2576 '_type': 'url',
2577 'url': new_url,
2578 }
2579
2580 if not found:
2581 # twitter:player is a https URL to iframe player that may or may not
2582 # be supported by youtube-dl thus this is checked the very last (see
2583 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2584 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2585 if embed_url:
2586 return self.url_result(embed_url)
2587
2588 if not found:
2589 raise UnsupportedError(url)
2590
2591 entries = []
2592 for video_url in orderedSet(found):
2593 video_url = unescapeHTML(video_url)
2594 video_url = video_url.replace('\\/', '/')
2595 video_url = compat_urlparse.urljoin(url, video_url)
2596 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2597
2598 # Sometimes, jwplayer extraction will result in a YouTube URL
2599 if YoutubeIE.suitable(video_url):
2600 entries.append(self.url_result(video_url, 'Youtube'))
2601 continue
2602
2603 # here's a fun little line of code for you:
2604 video_id = os.path.splitext(video_id)[0]
2605
2606 entry_info_dict = {
2607 'id': video_id,
2608 'uploader': video_uploader,
2609 'title': video_title,
2610 'age_limit': age_limit,
2611 }
2612
2613 if RtmpIE.suitable(video_url):
2614 entry_info_dict.update({
2615 '_type': 'url_transparent',
2616 'ie_key': RtmpIE.ie_key(),
2617 'url': video_url,
2618 })
2619 entries.append(entry_info_dict)
2620 continue
2621
2622 ext = determine_ext(video_url)
2623 if ext == 'smil':
2624 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2625 elif ext == 'xspf':
2626 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2627 elif ext == 'm3u8':
2628 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2629 elif ext == 'mpd':
2630 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2631 elif ext == 'f4m':
2632 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2633 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2634 # Just matching .ism/manifest is not enough to be reliably sure
2635 # whether it's actually an ISM manifest or some other streaming
2636 # manifest since there are various streaming URL formats
2637 # possible (see [1]) as well as some other shenanigans like
2638 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2639 # so on.
2640 # Thus the most reasonable way to solve this is to delegate
2641 # to generic extractor in order to look into the contents of
2642 # the manifest itself.
2643 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2644 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2645 entry_info_dict = self.url_result(
2646 smuggle_url(video_url, {'to_generic': True}),
2647 GenericIE.ie_key())
2648 else:
2649 entry_info_dict['url'] = video_url
2650
2651 if entry_info_dict.get('formats'):
2652 self._sort_formats(entry_info_dict['formats'])
2653
2654 entries.append(entry_info_dict)
2655
2656 if len(entries) == 1:
2657 return entries[0]
2658 else:
2659 for num, e in enumerate(entries, start=1):
2660 # 'url' results don't have a title
2661 if e.get('title') is not None:
2662 e['title'] = '%s (%d)' % (e['title'], num)
2663 return {
2664 '_type': 'playlist',
2665 'entries': entries,
2666 }