]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/generic.py
274f817384d65a6287427ad35f97d3126cea7cd0
[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 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 : lā€™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': 'Š’ŠøŠ“ŠµŠ¾. Š£Š“Š°Š»ŠµŠ½ŠøŠµ Š”Š·Š°Š³Š¾ŠµŠ²Š° (Š¦Š”ŠšŠ)',
412 'description': 'ŠžŠ½Š»Š°Š¹Š½-трŠ°Š½ŃŠ»ŃŃ†Šøя Š¼Š°Ń‚чŠ° Š¦Š”ŠšŠ - "Š’Š¾Š»Š³Š°"',
413 'uploader': 'Championat',
414 },
415 },
416 {
417 # https://github.com/rg3/youtube-dl/issues/3541
418 'add_ie': ['BrightcoveLegacy'],
419 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
420 'info_dict': {
421 'id': '3866516442001',
422 'ext': 'mp4',
423 'title': 'Leer mij vrouwen kennen: Aflevering 1',
424 'description': 'Leer mij vrouwen kennen: Aflevering 1',
425 'uploader': 'SBS Broadcasting',
426 },
427 'skip': 'Restricted to Netherlands',
428 'params': {
429 'skip_download': True, # m3u8 download
430 },
431 },
432 {
433 # Brightcove with alternative playerID key
434 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
435 'info_dict': {
436 'id': 'nmeth.2062_SV1',
437 'title': 'Simultaneous multiview imaging of the Drosophila syncytial blastoderm : Quantitative high-speed imaging of entire developing embryos with simultaneous multiview light-sheet microscopy : Nature Methods : Nature Research',
438 },
439 'playlist': [{
440 'info_dict': {
441 'id': '2228375078001',
442 'ext': 'mp4',
443 'title': 'nmeth.2062-sv1',
444 'description': 'nmeth.2062-sv1',
445 'timestamp': 1363357591,
446 'upload_date': '20130315',
447 'uploader': 'Nature Publishing Group',
448 'uploader_id': '1964492299001',
449 },
450 }],
451 },
452 {
453 # Brightcove with UUID in videoPlayer
454 'url': 'http://www8.hp.com/cn/zh/home.html',
455 'info_dict': {
456 'id': '5255815316001',
457 'ext': 'mp4',
458 'title': 'Sprocket Video - China',
459 'description': 'Sprocket Video - China',
460 'uploader': 'HP-Video Gallery',
461 'timestamp': 1482263210,
462 'upload_date': '20161220',
463 'uploader_id': '1107601872001',
464 },
465 'params': {
466 'skip_download': True, # m3u8 download
467 },
468 },
469 # ooyala video
470 {
471 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
472 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
473 'info_dict': {
474 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
475 'ext': 'mp4',
476 'title': '2cc213299525360.mov', # that's what we get
477 'duration': 238.231,
478 },
479 'add_ie': ['Ooyala'],
480 },
481 {
482 # ooyala video embedded with http://player.ooyala.com/iframe.js
483 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
484 'info_dict': {
485 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
486 'ext': 'mp4',
487 'title': '"Steve Jobs: Man in the Machine" trailer',
488 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
489 'duration': 135.427,
490 },
491 'params': {
492 'skip_download': True,
493 },
494 'skip': 'movie expired',
495 },
496 # embed.ly video
497 {
498 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
499 'info_dict': {
500 'id': '9ODmcdjQcHQ',
501 'ext': 'mp4',
502 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
503 'upload_date': '20140225',
504 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
505 'uploader': 'Tested',
506 'uploader_id': 'testedcom',
507 },
508 # No need to test YoutubeIE here
509 'params': {
510 'skip_download': True,
511 },
512 },
513 # funnyordie embed
514 {
515 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
516 'info_dict': {
517 'id': '18e820ec3f',
518 'ext': 'mp4',
519 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
520 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
521 },
522 # HEAD requests lead to endless 301, while GET is OK
523 'expected_warnings': ['301'],
524 },
525 # RUTV embed
526 {
527 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
528 'info_dict': {
529 'id': '776940',
530 'ext': 'mp4',
531 'title': 'ŠžŃ…Š¾Ń‚сŠŗŠ¾Šµ Š¼Š¾Ń€Šµ стŠ°Š»Š¾ цŠµŠ»ŠøŠŗŠ¾Š¼ рŠ¾ŃŃŠøŠ¹ŃŠŗŠøŠ¼',
532 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
533 },
534 'params': {
535 # m3u8 download
536 'skip_download': True,
537 },
538 },
539 # TVC embed
540 {
541 'url': 'http://sch1298sz.mskobr.ru/dou_edu/karamel_ki/filial_galleries/video/iframe_src_http_tvc_ru_video_iframe_id_55304_isplay_false_acc_video_id_channel_brand_id_11_show_episodes_episode_id_32307_frameb/',
542 'info_dict': {
543 'id': '55304',
544 'ext': 'mp4',
545 'title': 'Š”Š¾ŃˆŠŗŠ¾Š»ŃŒŠ½Š¾Šµ Š²Š¾ŃŠæŠøтŠ°Š½ŠøŠµ',
546 },
547 },
548 # SportBox embed
549 {
550 'url': 'http://www.vestifinance.ru/articles/25753',
551 'info_dict': {
552 'id': '25753',
553 '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"',
554 },
555 'playlist': [{
556 'info_dict': {
557 'id': '370908',
558 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 3',
559 'ext': 'mp4',
560 }
561 }, {
562 'info_dict': {
563 'id': '370905',
564 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 2',
565 'ext': 'mp4',
566 }
567 }, {
568 'info_dict': {
569 'id': '370902',
570 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 1',
571 'ext': 'mp4',
572 }
573 }],
574 'params': {
575 # m3u8 download
576 'skip_download': True,
577 },
578 },
579 # Myvi.ru embed
580 {
581 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
582 'info_dict': {
583 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
584 'ext': 'mp4',
585 'title': 'Š£Š¶Š°ŃŃ‚ŠøŠŗŠø, руссŠŗŠøŠ¹ трŠµŠ¹Š»ŠµŃ€ (2015)',
586 'thumbnail': r're:^https?://.*\.jpg$',
587 'duration': 153,
588 }
589 },
590 # XHamster embed
591 {
592 'url': 'http://www.numisc.com/forum/showthread.php?11696-FM15-which-pumiscer-was-this-%28-vid-%29-%28-alfa-as-fuck-srx-%29&s=711f5db534502e22260dec8c5e2d66d8',
593 'info_dict': {
594 'id': 'showthread',
595 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
596 },
597 'playlist_mincount': 7,
598 # This forum does not allow <iframe> syntaxes anymore
599 # Now HTML tags are displayed as-is
600 'skip': 'No videos on this page',
601 },
602 # Embedded TED video
603 {
604 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
605 'md5': '65fdff94098e4a607385a60c5177c638',
606 'info_dict': {
607 'id': '1969',
608 'ext': 'mp4',
609 'title': 'Hidden miracles of the natural world',
610 'uploader': 'Louie Schwartzberg',
611 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
612 }
613 },
614 # nowvideo embed hidden behind percent encoding
615 {
616 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
617 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
618 'info_dict': {
619 'id': '06e53103ca9aa',
620 'ext': 'flv',
621 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
622 'description': 'No description',
623 },
624 },
625 # arte embed
626 {
627 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
628 'md5': '7653032cbb25bf6c80d80f217055fa43',
629 'info_dict': {
630 'id': '048195-004_PLUS7-F',
631 'ext': 'flv',
632 'title': 'X:enius',
633 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
634 'upload_date': '20140320',
635 },
636 'params': {
637 'skip_download': 'Requires rtmpdump'
638 },
639 'skip': 'video gone',
640 },
641 # francetv embed
642 {
643 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
644 'info_dict': {
645 'id': 'EV_30231',
646 'ext': 'mp4',
647 'title': 'Alcaline, le concert avec Calogero',
648 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
649 'upload_date': '20150226',
650 'timestamp': 1424989860,
651 'duration': 5400,
652 },
653 'params': {
654 # m3u8 downloads
655 'skip_download': True,
656 },
657 'expected_warnings': [
658 'Forbidden'
659 ]
660 },
661 # CondƩ Nast embed
662 {
663 'url': 'http://www.wired.com/2014/04/honda-asimo/',
664 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
665 'info_dict': {
666 'id': '53501be369702d3275860000',
667 'ext': 'mp4',
668 'title': 'Hondaā€™s New Asimo Robot Is More Human Than Ever',
669 }
670 },
671 # Dailymotion embed
672 {
673 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
674 'md5': '441aeeb82eb72c422c7f14ec533999cd',
675 'info_dict': {
676 'id': 'k2mm4bCdJ6CQ2i7c8o2',
677 'ext': 'mp4',
678 'title': 'Le Zap de Spi0n nĀ°216 - Zapping du Web',
679 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
680 'uploader': 'Spi0n',
681 'uploader_id': 'xgditw',
682 'upload_date': '20140425',
683 'timestamp': 1398441542,
684 },
685 'add_ie': ['Dailymotion'],
686 },
687 # YouTube embed
688 {
689 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
690 'info_dict': {
691 'id': 'FXRb4ykk4S0',
692 'ext': 'mp4',
693 'title': 'The NBL Auction 2014',
694 'uploader': 'BADMINTON England',
695 'uploader_id': 'BADMINTONEvents',
696 'upload_date': '20140603',
697 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
698 },
699 'add_ie': ['Youtube'],
700 'params': {
701 'skip_download': True,
702 }
703 },
704 # MTVSercices embed
705 {
706 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
707 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
708 'info_dict': {
709 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
710 'ext': 'mp4',
711 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
712 'description': 'Two valets share their love for movie star Liam Neesons.',
713 'timestamp': 1349922600,
714 'upload_date': '20121011',
715 },
716 },
717 # YouTube embed via <data-embed-url="">
718 {
719 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
720 'info_dict': {
721 'id': '4vAffPZIT44',
722 'ext': 'mp4',
723 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
724 'uploader': 'Gameloft',
725 'uploader_id': 'gameloft',
726 'upload_date': '20140828',
727 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
728 },
729 'params': {
730 'skip_download': True,
731 }
732 },
733 # Camtasia studio
734 {
735 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
736 'playlist': [{
737 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
738 'info_dict': {
739 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
740 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
741 'ext': 'flv',
742 'duration': 2235.90,
743 }
744 }, {
745 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
746 'info_dict': {
747 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
748 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
749 'ext': 'flv',
750 'duration': 2235.93,
751 }
752 }],
753 'info_dict': {
754 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
755 }
756 },
757 # Flowplayer
758 {
759 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
760 'md5': '9d65602bf31c6e20014319c7d07fba27',
761 'info_dict': {
762 'id': '5123ea6d5e5a7',
763 'ext': 'mp4',
764 'age_limit': 18,
765 'uploader': 'www.handjobhub.com',
766 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
767 }
768 },
769 # Multiple brightcove videos
770 # https://github.com/rg3/youtube-dl/issues/2283
771 {
772 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
773 'info_dict': {
774 'id': 'always-never',
775 'title': 'Always / Never - The New Yorker',
776 },
777 'playlist_count': 3,
778 'params': {
779 'extract_flat': False,
780 'skip_download': True,
781 }
782 },
783 # MLB embed
784 {
785 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
786 'md5': '96f09a37e44da40dd083e12d9a683327',
787 'info_dict': {
788 'id': '33322633',
789 'ext': 'mp4',
790 'title': 'Ump changes call to ball',
791 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
792 'duration': 48,
793 'timestamp': 1401537900,
794 'upload_date': '20140531',
795 'thumbnail': r're:^https?://.*\.jpg$',
796 },
797 },
798 # Wistia embed
799 {
800 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
801 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
802 'info_dict': {
803 'id': '6e2wtrbdaf',
804 'ext': 'mov',
805 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
806 'description': 'a Paywall Videos video from Remilon',
807 'duration': 644.072,
808 'uploader': 'study.com',
809 'timestamp': 1459678540,
810 'upload_date': '20160403',
811 'filesize': 24687186,
812 },
813 },
814 {
815 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
816 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
817 'info_dict': {
818 'id': 'uxjb0lwrcz',
819 'ext': 'mp4',
820 'title': 'Conversation about Hexagonal Rails Part 1',
821 'description': 'a Martin Fowler video from ThoughtWorks',
822 'duration': 1715.0,
823 'uploader': 'thoughtworks.wistia.com',
824 'timestamp': 1401832161,
825 'upload_date': '20140603',
826 },
827 },
828 # Wistia standard embed (async)
829 {
830 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
831 'info_dict': {
832 'id': '807fafadvk',
833 'ext': 'mp4',
834 'title': 'Drip Brennan Dunn Workshop',
835 'description': 'a JV Webinars video from getdrip-1',
836 'duration': 4986.95,
837 'timestamp': 1463607249,
838 'upload_date': '20160518',
839 },
840 'params': {
841 'skip_download': True,
842 }
843 },
844 # Soundcloud embed
845 {
846 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
847 'info_dict': {
848 'id': '174391317',
849 'ext': 'mp3',
850 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
851 'uploader': 'Sophos Security',
852 'title': 'Chet Chat 171 - Oct 29, 2014',
853 'upload_date': '20141029',
854 }
855 },
856 # Soundcloud multiple embeds
857 {
858 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
859 'info_dict': {
860 'id': '52809',
861 'title': 'Guitar Essentials: Legato Workoutā€”One-Hour to Fluid Performance | TAB + AUDIO',
862 },
863 'playlist_mincount': 7,
864 },
865 # TuneIn station embed
866 {
867 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
868 'info_dict': {
869 'id': '204146',
870 'ext': 'mp3',
871 'title': 'CNRV',
872 'location': 'Paris, France',
873 'is_live': True,
874 },
875 'params': {
876 # Live stream
877 'skip_download': True,
878 },
879 },
880 # Livestream embed
881 {
882 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
883 'info_dict': {
884 'id': '67864563',
885 'ext': 'flv',
886 'upload_date': '20141112',
887 'title': 'Rosetta #CometLanding webcast HL 10',
888 }
889 },
890 # Another Livestream embed, without 'new.' in URL
891 {
892 'url': 'https://www.freespeech.org/',
893 'info_dict': {
894 'id': '123537347',
895 'ext': 'mp4',
896 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
897 },
898 'params': {
899 # Live stream
900 'skip_download': True,
901 },
902 },
903 # LazyYT
904 {
905 'url': 'https://skiplagged.com/',
906 'info_dict': {
907 'id': 'skiplagged',
908 'title': 'Skiplagged: The smart way to find cheap flights',
909 },
910 'playlist_mincount': 1,
911 'add_ie': ['Youtube'],
912 },
913 # Cinchcast embed
914 {
915 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
916 'info_dict': {
917 'id': '7141703',
918 'ext': 'mp3',
919 'upload_date': '20141126',
920 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
921 }
922 },
923 # Cinerama player
924 {
925 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
926 'info_dict': {
927 'id': '730m_DandD_1901_512k',
928 'ext': 'mp4',
929 'uploader': 'www.abc.net.au',
930 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
931 }
932 },
933 # embedded viddler video
934 {
935 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
936 'info_dict': {
937 'id': '4d03aad9',
938 'ext': 'mp4',
939 'uploader': 'deadspin',
940 'title': 'WALL-TO-GORTAT',
941 'timestamp': 1422285291,
942 'upload_date': '20150126',
943 },
944 'add_ie': ['Viddler'],
945 },
946 # Libsyn embed
947 {
948 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
949 'info_dict': {
950 'id': '3377616',
951 'ext': 'mp3',
952 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
953 'description': 'md5:601cb790edd05908957dae8aaa866465',
954 'upload_date': '20150220',
955 },
956 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
957 },
958 # jwplayer YouTube
959 {
960 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
961 'info_dict': {
962 'id': 'Mrj4DVp2zeA',
963 'ext': 'mp4',
964 'upload_date': '20150212',
965 'uploader': 'The National Archives UK',
966 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
967 'uploader_id': 'NationalArchives08',
968 'title': 'Webinar: Using Discovery, The National Archivesā€™ online catalogue',
969 },
970 },
971 # jwplayer rtmp
972 {
973 'url': 'http://www.suffolk.edu/sjc/',
974 'info_dict': {
975 'id': 'sjclive',
976 'ext': 'flv',
977 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
978 'uploader': 'www.suffolk.edu',
979 },
980 'params': {
981 'skip_download': True,
982 }
983 },
984 # Complex jwplayer
985 {
986 'url': 'http://www.indiedb.com/games/king-machine/videos',
987 'info_dict': {
988 'id': 'videos',
989 'ext': 'mp4',
990 'title': 'king machine trailer 1',
991 'thumbnail': r're:^https?://.*\.jpg$',
992 },
993 },
994 {
995 # JWPlayer config passed as variable
996 'url': 'http://www.txxx.com/videos/3326530/ariele/',
997 'info_dict': {
998 'id': '3326530_hq',
999 'ext': 'mp4',
1000 'title': 'ARIELE | Tube Cup',
1001 'uploader': 'www.txxx.com',
1002 'age_limit': 18,
1003 },
1004 'params': {
1005 'skip_download': True,
1006 }
1007 },
1008 # rtl.nl embed
1009 {
1010 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1011 'playlist_mincount': 5,
1012 'info_dict': {
1013 'id': 'aanslagen-kopenhagen',
1014 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1015 }
1016 },
1017 # Zapiks embed
1018 {
1019 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1020 'info_dict': {
1021 'id': '118046',
1022 'ext': 'mp4',
1023 'title': 'EP3S5 - Bon AppƩtit - Baqueira Mi Corazon !',
1024 }
1025 },
1026 # Kaltura embed (different embed code)
1027 {
1028 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1029 'info_dict': {
1030 'id': '1_a52wc67y',
1031 'ext': 'flv',
1032 'upload_date': '20150127',
1033 'uploader_id': 'PremierMedia',
1034 'timestamp': int,
1035 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1036 },
1037 },
1038 # Kaltura embed with single quotes
1039 {
1040 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1041 'info_dict': {
1042 'id': '0_izeg5utt',
1043 'ext': 'mp4',
1044 'title': '35871',
1045 'timestamp': 1355743100,
1046 'upload_date': '20121217',
1047 'uploader_id': 'batchUser',
1048 },
1049 'add_ie': ['Kaltura'],
1050 },
1051 {
1052 # Kaltura embedded via quoted entry_id
1053 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1054 'info_dict': {
1055 'id': '0_utuok90b',
1056 'ext': 'mp4',
1057 'title': '06_matthew_brender_raj_dutt',
1058 'timestamp': 1466638791,
1059 'upload_date': '20160622',
1060 },
1061 'add_ie': ['Kaltura'],
1062 'expected_warnings': [
1063 'Could not send HEAD request'
1064 ],
1065 'params': {
1066 'skip_download': True,
1067 }
1068 },
1069 {
1070 # Kaltura embedded, some fileExt broken (#11480)
1071 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1072 'info_dict': {
1073 'id': '1_sgtvehim',
1074 'ext': 'mp4',
1075 'title': 'Our "Standard Models" of particle physics and cosmology',
1076 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1077 'timestamp': 1321158993,
1078 'upload_date': '20111113',
1079 'uploader_id': 'kps1',
1080 },
1081 'add_ie': ['Kaltura'],
1082 },
1083 # Eagle.Platform embed (generic URL)
1084 {
1085 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1086 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1087 'info_dict': {
1088 'id': '227304',
1089 'ext': 'mp4',
1090 'title': 'ŠŠ°Š²Š°Š»ŃŒŠ½Ń‹Š¹ Š²Ń‹ŃˆŠµŠ» Š½Š° сŠ²Š¾Š±Š¾Š“у',
1091 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1092 'thumbnail': r're:^https?://.*\.jpg$',
1093 'duration': 87,
1094 'view_count': int,
1095 'age_limit': 0,
1096 },
1097 },
1098 # ClipYou (Eagle.Platform) embed (custom URL)
1099 {
1100 'url': 'http://muz-tv.ru/play/7129/',
1101 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1102 'info_dict': {
1103 'id': '12820',
1104 'ext': 'mp4',
1105 'title': "'O Sole Mio",
1106 'thumbnail': r're:^https?://.*\.jpg$',
1107 'duration': 216,
1108 'view_count': int,
1109 },
1110 },
1111 # Pladform embed
1112 {
1113 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1114 'info_dict': {
1115 'id': '100183293',
1116 'ext': 'mp4',
1117 'title': 'Š¢Š°Š¹Š½Ń‹ ŠæŠµŃ€ŠµŠ²Š°Š»Š° Š”ŃŃ‚Š»Š¾Š²Š° ā€¢ 1 сŠµŃ€Šøя 2 чŠ°ŃŃ‚ŃŒ',
1118 'description': 'Š”Š¾ŠŗуŠ¼ŠµŠ½Ń‚Š°Š»ŃŒŠ½Ń‹Š¹ сŠµŃ€ŠøŠ°Š»-рŠ°ŃŃŠ»ŠµŠ“Š¾Š²Š°Š½ŠøŠµ Š¾Š“Š½Š¾Š¹ ŠøŠ· сŠ°Š¼Ń‹Ń… Š¶ŃƒŃ‚ŠŗŠøх тŠ°Š¹Š½ Š„Š„ Š²ŠµŠŗŠ°',
1119 'thumbnail': r're:^https?://.*\.jpg$',
1120 'duration': 694,
1121 'age_limit': 0,
1122 },
1123 },
1124 # Playwire embed
1125 {
1126 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1127 'info_dict': {
1128 'id': '3519514',
1129 'ext': 'mp4',
1130 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1131 'thumbnail': r're:^https?://.*\.png$',
1132 'duration': 45.115,
1133 },
1134 },
1135 # 5min embed
1136 {
1137 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1138 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1139 'info_dict': {
1140 'id': '518726732',
1141 'ext': 'mp4',
1142 'title': 'Facebook Creates "On This Day" | Crunch Report',
1143 },
1144 },
1145 # SVT embed
1146 {
1147 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1148 'info_dict': {
1149 'id': '2900353',
1150 'ext': 'flv',
1151 'title': 'HƤr trycker Jagr till Giroux (under SVT-intervjun)',
1152 'duration': 27,
1153 'age_limit': 0,
1154 },
1155 },
1156 # Crooks and Liars embed
1157 {
1158 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1159 'info_dict': {
1160 'id': '8RUoRhRi',
1161 'ext': 'mp4',
1162 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1163 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1164 'timestamp': 1428207000,
1165 'upload_date': '20150405',
1166 'uploader': 'Heather',
1167 },
1168 },
1169 # Crooks and Liars external embed
1170 {
1171 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1172 'info_dict': {
1173 'id': 'MTE3MjUtMzQ2MzA',
1174 'ext': 'mp4',
1175 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1176 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1177 'timestamp': 1265032391,
1178 'upload_date': '20100201',
1179 'uploader': 'Heather',
1180 },
1181 },
1182 # NBC Sports vplayer embed
1183 {
1184 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1185 'info_dict': {
1186 'id': 'ln7x1qSThw4k',
1187 'ext': 'flv',
1188 'title': "PFT Live: New leader in the 'new-look' defense",
1189 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1190 'uploader': 'NBCU-SPORTS',
1191 'upload_date': '20140107',
1192 'timestamp': 1389118457,
1193 },
1194 },
1195 # NBC News embed
1196 {
1197 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1198 'md5': '1aa589c675898ae6d37a17913cf68d66',
1199 'info_dict': {
1200 'id': '701714499682',
1201 'ext': 'mp4',
1202 'title': 'PREVIEW: On Assignment: David Letterman',
1203 '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.',
1204 },
1205 },
1206 # UDN embed
1207 {
1208 'url': 'https://video.udn.com/news/300346',
1209 'md5': 'fd2060e988c326991037b9aff9df21a6',
1210 'info_dict': {
1211 'id': '300346',
1212 'ext': 'mp4',
1213 'title': 'äø­äø€äø­ē”·åø«č®Šę€§ å…Øę ”åø«ē”ŸåŠ›ęŒŗ',
1214 'thumbnail': r're:^https?://.*\.jpg$',
1215 },
1216 'params': {
1217 # m3u8 download
1218 'skip_download': True,
1219 },
1220 },
1221 # Ooyala embed
1222 {
1223 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1224 'info_dict': {
1225 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1226 'ext': 'mp4',
1227 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1228 'title': 'This is what separates the Excel masters from the wannabes',
1229 'duration': 191.933,
1230 },
1231 'params': {
1232 # m3u8 downloads
1233 'skip_download': True,
1234 }
1235 },
1236 # Brightcove URL in single quotes
1237 {
1238 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1239 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1240 'info_dict': {
1241 'id': '4255764656001',
1242 'ext': 'mp4',
1243 'title': 'SN Presents: Russell Martin, World Citizen',
1244 '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.',
1245 'uploader': 'Rogers Sportsnet',
1246 'uploader_id': '1704050871',
1247 'upload_date': '20150525',
1248 'timestamp': 1432570283,
1249 },
1250 },
1251 # Dailymotion Cloud video
1252 {
1253 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1254 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1255 'info_dict': {
1256 'id': 'x2uy8t3',
1257 'ext': 'mp4',
1258 'title': 'Sauvons les abeilles ! - Le dƩbat',
1259 'description': 'md5:d9082128b1c5277987825d684939ca26',
1260 'thumbnail': r're:^https?://.*\.jpe?g$',
1261 'timestamp': 1434970506,
1262 'upload_date': '20150622',
1263 'uploader': 'Public SĆ©nat',
1264 'uploader_id': 'xa9gza',
1265 }
1266 },
1267 # OnionStudios embed
1268 {
1269 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1270 'info_dict': {
1271 'id': '2855',
1272 'ext': 'mp4',
1273 'title': 'Donā€™t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1274 'thumbnail': r're:^https?://.*\.jpe?g$',
1275 'uploader': 'ClickHole',
1276 'uploader_id': 'clickhole',
1277 }
1278 },
1279 # SnagFilms embed
1280 {
1281 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1282 'info_dict': {
1283 'id': '74849a00-85a9-11e1-9660-123139220831',
1284 'ext': 'mp4',
1285 'title': '#whilewewatch',
1286 }
1287 },
1288 # AdobeTVVideo embed
1289 {
1290 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1291 'md5': '43662b577c018ad707a63766462b1e87',
1292 'info_dict': {
1293 'id': '2456',
1294 'ext': 'mp4',
1295 'title': 'New experience with Acrobat DC',
1296 'description': 'New experience with Acrobat DC',
1297 'duration': 248.667,
1298 },
1299 },
1300 # BrightcoveInPageEmbed embed
1301 {
1302 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1303 'info_dict': {
1304 'id': '4238694884001',
1305 'ext': 'flv',
1306 'title': 'Tabletop: Dread, Last Thoughts',
1307 'description': 'Tabletop: Dread, Last Thoughts',
1308 'duration': 51690,
1309 },
1310 },
1311 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1312 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1313 {
1314 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1315 'info_dict': {
1316 'id': '4785848093001',
1317 'ext': 'mp4',
1318 'title': 'The Cardinal Pell Interview',
1319 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1320 'uploader': 'GlobeCast Australia - GlobeStream',
1321 'uploader_id': '2733773828001',
1322 'upload_date': '20160304',
1323 'timestamp': 1457083087,
1324 },
1325 'params': {
1326 # m3u8 downloads
1327 'skip_download': True,
1328 },
1329 },
1330 # Another form of arte.tv embed
1331 {
1332 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1333 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1334 'info_dict': {
1335 'id': '030273-562_PLUS7-F',
1336 'ext': 'mp4',
1337 'title': 'ARTE Reportage - Nulle part, en France',
1338 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1339 'upload_date': '20160409',
1340 },
1341 },
1342 # LiveLeak embed
1343 {
1344 'url': 'http://www.wykop.pl/link/3088787/',
1345 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1346 'info_dict': {
1347 'id': '874_1459135191',
1348 'ext': 'mp4',
1349 'title': 'Man shows poor quality of new apartment building',
1350 'description': 'The wall is like a sand pile.',
1351 'uploader': 'Lake8737',
1352 }
1353 },
1354 # Duplicated embedded video URLs
1355 {
1356 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1357 'info_dict': {
1358 'id': '149298443_480_16c25b74_2',
1359 'ext': 'mp4',
1360 'title': 'vs. Blue Orange Spring Game',
1361 'uploader': 'www.hudl.com',
1362 },
1363 },
1364 # twitter:player:stream embed
1365 {
1366 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1367 'info_dict': {
1368 'id': 'master',
1369 'ext': 'mp4',
1370 'title': 'Une nouvelle espĆØce de dinosaure dĆ©couverte en Argentine',
1371 'uploader': 'www.rtl.be',
1372 },
1373 'params': {
1374 # m3u8 downloads
1375 'skip_download': True,
1376 },
1377 },
1378 # twitter:player embed
1379 {
1380 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1381 'md5': 'a3e0df96369831de324f0778e126653c',
1382 'info_dict': {
1383 'id': '4909620399001',
1384 'ext': 'mp4',
1385 'title': 'What Do Black Holes Sound Like?',
1386 'description': 'what do black holes sound like',
1387 'upload_date': '20160524',
1388 'uploader_id': '29913724001',
1389 'timestamp': 1464107587,
1390 'uploader': 'TheAtlantic',
1391 },
1392 'add_ie': ['BrightcoveLegacy'],
1393 },
1394 # Facebook <iframe> embed
1395 {
1396 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1397 'md5': 'fbcde74f534176ecb015849146dd3aee',
1398 'info_dict': {
1399 'id': '599637780109885',
1400 'ext': 'mp4',
1401 'title': 'Facebook video #599637780109885',
1402 },
1403 },
1404 # Facebook API embed
1405 {
1406 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1407 'md5': 'a47372ee61b39a7b90287094d447d94e',
1408 'info_dict': {
1409 'id': '10153467542406923',
1410 'ext': 'mp4',
1411 'title': 'Facebook video #10153467542406923',
1412 },
1413 },
1414 # Wordpress "YouTube Video Importer" plugin
1415 {
1416 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1417 'md5': 'd16797741b560b485194eddda8121b48',
1418 'info_dict': {
1419 'id': 'HNTXWDXV9Is',
1420 'ext': 'mp4',
1421 'title': 'Blue Devils Drumline Stanford lot 2016',
1422 'upload_date': '20160627',
1423 'uploader_id': 'GENOCIDE8GENERAL10',
1424 'uploader': 'cylus cyrus',
1425 },
1426 },
1427 {
1428 # video stored on custom kaltura server
1429 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1430 'md5': '537617d06e64dfed891fa1593c4b30cc',
1431 'info_dict': {
1432 'id': '0_1iotm5bh',
1433 'ext': 'mp4',
1434 'title': 'Elecciones britƔnicas: 5 lecciones para Rajoy',
1435 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1436 'uploader_id': 'videos.expansion@el-mundo.net',
1437 'upload_date': '20150429',
1438 'timestamp': 1430303472,
1439 },
1440 'add_ie': ['Kaltura'],
1441 },
1442 {
1443 # Non-standard Vimeo embed
1444 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1445 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1446 'info_dict': {
1447 'id': '148867247',
1448 'ext': 'mp4',
1449 'title': 'Understanding the web - Teaser',
1450 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1451 'upload_date': '20151214',
1452 'uploader': 'OpenClassrooms',
1453 'uploader_id': 'openclassrooms',
1454 },
1455 'add_ie': ['Vimeo'],
1456 },
1457 {
1458 # generic vimeo embed that requires original URL passed as Referer
1459 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1460 'only_matching': True,
1461 },
1462 {
1463 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1464 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1465 'info_dict': {
1466 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1467 'ext': 'mp4',
1468 'title': 'Big Buck Bunny',
1469 'description': 'Royalty free test video',
1470 'timestamp': 1432816365,
1471 'upload_date': '20150528',
1472 'is_live': False,
1473 },
1474 'params': {
1475 'skip_download': True,
1476 },
1477 'add_ie': [ArkenaIE.ie_key()],
1478 },
1479 {
1480 '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/',
1481 'info_dict': {
1482 'id': '1c7141f46c',
1483 'ext': 'mp4',
1484 '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',
1485 },
1486 'params': {
1487 'skip_download': True,
1488 },
1489 'add_ie': [Vbox7IE.ie_key()],
1490 },
1491 {
1492 # DBTV embeds
1493 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1494 'info_dict': {
1495 'id': '43254897',
1496 'title': 'Etter ett Ƅrs planlegging, klaffet endelig alt: - Jeg mƄtte ta en liten dans',
1497 },
1498 'playlist_mincount': 3,
1499 },
1500 {
1501 # Videa embeds
1502 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1503 'info_dict': {
1504 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1505 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1506 },
1507 'playlist_mincount': 2,
1508 },
1509 {
1510 # 20 minuten embed
1511 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1512 'info_dict': {
1513 'id': '523629',
1514 'ext': 'mp4',
1515 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1516 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1517 },
1518 'params': {
1519 'skip_download': True,
1520 },
1521 'add_ie': [TwentyMinutenIE.ie_key()],
1522 },
1523 {
1524 # VideoPress embed
1525 'url': 'https://en.support.wordpress.com/videopress/',
1526 'info_dict': {
1527 'id': 'OcobLTqC',
1528 'ext': 'm4v',
1529 'title': 'IMG_5786',
1530 'timestamp': 1435711927,
1531 'upload_date': '20150701',
1532 },
1533 'params': {
1534 'skip_download': True,
1535 },
1536 'add_ie': [VideoPressIE.ie_key()],
1537 },
1538 {
1539 # Rutube embed
1540 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1541 'info_dict': {
1542 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1543 'ext': 'flv',
1544 'title': 'ŠœŠ°Š³Š°Š·Š·ŠøŠ½Š¾: ŠšŠ°Š·Š°Š½ŃŒ 2',
1545 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1546 'uploader': 'ŠœŠ°Š³Š°Š·Š·ŠøŠ½Š¾',
1547 'upload_date': '20170228',
1548 'uploader_id': '996642',
1549 },
1550 'params': {
1551 'skip_download': True,
1552 },
1553 'add_ie': [RutubeIE.ie_key()],
1554 },
1555 {
1556 # ThePlatform embedded with whitespaces in URLs
1557 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1558 'only_matching': True,
1559 },
1560 {
1561 # Senate ISVP iframe https
1562 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1563 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1564 'info_dict': {
1565 'id': 'govtaff020316',
1566 'ext': 'mp4',
1567 'title': 'Integrated Senate Video Player',
1568 },
1569 'add_ie': [SenateISVPIE.ie_key()],
1570 },
1571 # {
1572 # # TODO: find another test
1573 # # http://schema.org/VideoObject
1574 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1575 # 'md5': '888dcf08b7ea671381f00fab74692755',
1576 # 'info_dict': {
1577 # 'id': 'nyvTSJMKId',
1578 # 'ext': 'mp4',
1579 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1580 # 'description': '#love for cats.',
1581 # 'timestamp': 1461244995,
1582 # 'upload_date': '20160421',
1583 # },
1584 # 'params': {
1585 # 'force_generic_extractor': True,
1586 # },
1587 # }
1588 ]
1589
1590 def report_following_redirect(self, new_url):
1591 """Report information extraction."""
1592 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1593
1594 def _extract_rss(self, url, video_id, doc):
1595 playlist_title = doc.find('./channel/title').text
1596 playlist_desc_el = doc.find('./channel/description')
1597 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1598
1599 entries = []
1600 for it in doc.findall('./channel/item'):
1601 next_url = xpath_text(it, 'link', fatal=False)
1602 if not next_url:
1603 enclosure_nodes = it.findall('./enclosure')
1604 for e in enclosure_nodes:
1605 next_url = e.attrib.get('url')
1606 if next_url:
1607 break
1608
1609 if not next_url:
1610 continue
1611
1612 entries.append({
1613 '_type': 'url',
1614 'url': next_url,
1615 'title': it.find('title').text,
1616 })
1617
1618 return {
1619 '_type': 'playlist',
1620 'id': url,
1621 'title': playlist_title,
1622 'description': playlist_desc,
1623 'entries': entries,
1624 }
1625
1626 def _extract_camtasia(self, url, video_id, webpage):
1627 """ Returns None if no camtasia video can be found. """
1628
1629 camtasia_cfg = self._search_regex(
1630 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1631 webpage, 'camtasia configuration file', default=None)
1632 if camtasia_cfg is None:
1633 return None
1634
1635 title = self._html_search_meta('DC.title', webpage, fatal=True)
1636
1637 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1638 camtasia_cfg = self._download_xml(
1639 camtasia_url, video_id,
1640 note='Downloading camtasia configuration',
1641 errnote='Failed to download camtasia configuration')
1642 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1643
1644 entries = []
1645 for n in fileset_node.getchildren():
1646 url_n = n.find('./uri')
1647 if url_n is None:
1648 continue
1649
1650 entries.append({
1651 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1652 'title': '%s - %s' % (title, n.tag),
1653 'url': compat_urlparse.urljoin(url, url_n.text),
1654 'duration': float_or_none(n.find('./duration').text),
1655 })
1656
1657 return {
1658 '_type': 'playlist',
1659 'entries': entries,
1660 'title': title,
1661 }
1662
1663 def _real_extract(self, url):
1664 if url.startswith('//'):
1665 return {
1666 '_type': 'url',
1667 'url': self.http_scheme() + url,
1668 }
1669
1670 parsed_url = compat_urlparse.urlparse(url)
1671 if not parsed_url.scheme:
1672 default_search = self._downloader.params.get('default_search')
1673 if default_search is None:
1674 default_search = 'fixup_error'
1675
1676 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1677 if '/' in url:
1678 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1679 return self.url_result('http://' + url)
1680 elif default_search != 'fixup_error':
1681 if default_search == 'auto_warning':
1682 if re.match(r'^(?:url|URL)$', url):
1683 raise ExtractorError(
1684 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1685 expected=True)
1686 else:
1687 self._downloader.report_warning(
1688 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1689 return self.url_result('ytsearch:' + url)
1690
1691 if default_search in ('error', 'fixup_error'):
1692 raise ExtractorError(
1693 '%r is not a valid URL. '
1694 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1695 % (url, url), expected=True)
1696 else:
1697 if ':' not in default_search:
1698 default_search += ':'
1699 return self.url_result(default_search + url)
1700
1701 url, smuggled_data = unsmuggle_url(url)
1702 force_videoid = None
1703 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1704 if smuggled_data and 'force_videoid' in smuggled_data:
1705 force_videoid = smuggled_data['force_videoid']
1706 video_id = force_videoid
1707 else:
1708 video_id = self._generic_id(url)
1709
1710 self.to_screen('%s: Requesting header' % video_id)
1711
1712 head_req = HEADRequest(url)
1713 head_response = self._request_webpage(
1714 head_req, video_id,
1715 note=False, errnote='Could not send HEAD request to %s' % url,
1716 fatal=False)
1717
1718 if head_response is not False:
1719 # Check for redirect
1720 new_url = head_response.geturl()
1721 if url != new_url:
1722 self.report_following_redirect(new_url)
1723 if force_videoid:
1724 new_url = smuggle_url(
1725 new_url, {'force_videoid': force_videoid})
1726 return self.url_result(new_url)
1727
1728 full_response = None
1729 if head_response is False:
1730 request = sanitized_Request(url)
1731 request.add_header('Accept-Encoding', '*')
1732 full_response = self._request_webpage(request, video_id)
1733 head_response = full_response
1734
1735 info_dict = {
1736 'id': video_id,
1737 'title': self._generic_title(url),
1738 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1739 }
1740
1741 # Check for direct link to a video
1742 content_type = head_response.headers.get('Content-Type', '').lower()
1743 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1744 if m:
1745 format_id = m.group('format_id')
1746 if format_id.endswith('mpegurl'):
1747 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1748 elif format_id == 'f4m':
1749 formats = self._extract_f4m_formats(url, video_id)
1750 else:
1751 formats = [{
1752 'format_id': m.group('format_id'),
1753 'url': url,
1754 'vcodec': 'none' if m.group('type') == 'audio' else None
1755 }]
1756 info_dict['direct'] = True
1757 self._sort_formats(formats)
1758 info_dict['formats'] = formats
1759 return info_dict
1760
1761 if not self._downloader.params.get('test', False) and not is_intentional:
1762 force = self._downloader.params.get('force_generic_extractor', False)
1763 self._downloader.report_warning(
1764 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1765
1766 if not full_response:
1767 request = sanitized_Request(url)
1768 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1769 # making it impossible to download only chunk of the file (yet we need only 512kB to
1770 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1771 # that will always result in downloading the whole file that is not desirable.
1772 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1773 # to accept raw bytes and being able to download only a chunk.
1774 # It may probably better to solve this by checking Content-Type for application/octet-stream
1775 # after HEAD request finishes, but not sure if we can rely on this.
1776 request.add_header('Accept-Encoding', '*')
1777 full_response = self._request_webpage(request, video_id)
1778
1779 first_bytes = full_response.read(512)
1780
1781 # Is it an M3U playlist?
1782 if first_bytes.startswith(b'#EXTM3U'):
1783 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1784 self._sort_formats(info_dict['formats'])
1785 return info_dict
1786
1787 # Maybe it's a direct link to a video?
1788 # Be careful not to download the whole thing!
1789 if not is_html(first_bytes):
1790 self._downloader.report_warning(
1791 'URL could be a direct video link, returning it as such.')
1792 info_dict.update({
1793 'direct': True,
1794 'url': url,
1795 })
1796 return info_dict
1797
1798 webpage = self._webpage_read_content(
1799 full_response, url, video_id, prefix=first_bytes)
1800
1801 self.report_extraction(video_id)
1802
1803 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1804 try:
1805 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1806 if doc.tag == 'rss':
1807 return self._extract_rss(url, video_id, doc)
1808 elif doc.tag == 'SmoothStreamingMedia':
1809 info_dict['formats'] = self._parse_ism_formats(doc, url)
1810 self._sort_formats(info_dict['formats'])
1811 return info_dict
1812 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1813 smil = self._parse_smil(doc, url, video_id)
1814 self._sort_formats(smil['formats'])
1815 return smil
1816 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1817 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1818 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1819 info_dict['formats'] = self._parse_mpd_formats(
1820 doc, video_id,
1821 mpd_base_url=full_response.geturl().rpartition('/')[0],
1822 mpd_url=url)
1823 self._sort_formats(info_dict['formats'])
1824 return info_dict
1825 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1826 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1827 self._sort_formats(info_dict['formats'])
1828 return info_dict
1829 except compat_xml_parse_error:
1830 pass
1831
1832 # Is it a Camtasia project?
1833 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1834 if camtasia_res is not None:
1835 return camtasia_res
1836
1837 # Sometimes embedded video player is hidden behind percent encoding
1838 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1839 # Unescaping the whole page allows to handle those cases in a generic way
1840 webpage = compat_urllib_parse_unquote(webpage)
1841
1842 # it's tempting to parse this further, but you would
1843 # have to take into account all the variations like
1844 # Video Title - Site Name
1845 # Site Name | Video Title
1846 # Video Title - Tagline | Site Name
1847 # and so on and so forth; it's just not practical
1848 video_title = self._og_search_title(
1849 webpage, default=None) or self._html_search_regex(
1850 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1851 default='video')
1852
1853 # Try to detect age limit automatically
1854 age_limit = self._rta_search(webpage)
1855 # And then there are the jokers who advertise that they use RTA,
1856 # but actually don't.
1857 AGE_LIMIT_MARKERS = [
1858 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1859 ]
1860 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1861 age_limit = 18
1862
1863 # video uploader is domain name
1864 video_uploader = self._search_regex(
1865 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1866
1867 video_description = self._og_search_description(webpage, default=None)
1868 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1869
1870 # Look for Brightcove Legacy Studio embeds
1871 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1872 if bc_urls:
1873 self.to_screen('Brightcove video detected.')
1874 entries = [{
1875 '_type': 'url',
1876 'url': smuggle_url(bc_url, {'Referer': url}),
1877 'ie_key': 'BrightcoveLegacy'
1878 } for bc_url in bc_urls]
1879
1880 return {
1881 '_type': 'playlist',
1882 'title': video_title,
1883 'id': video_id,
1884 'entries': entries,
1885 }
1886
1887 # Look for Brightcove New Studio embeds
1888 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1889 if bc_urls:
1890 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
1891
1892 # Look for ThePlatform embeds
1893 tp_urls = ThePlatformIE._extract_urls(webpage)
1894 if tp_urls:
1895 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
1896
1897 # Look for Vessel embeds
1898 vessel_urls = VesselIE._extract_urls(webpage)
1899 if vessel_urls:
1900 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
1901
1902 # Look for embedded rtl.nl player
1903 matches = re.findall(
1904 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1905 webpage)
1906 if matches:
1907 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
1908
1909 vimeo_urls = VimeoIE._extract_urls(url, webpage)
1910 if vimeo_urls:
1911 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
1912
1913 vid_me_embed_url = self._search_regex(
1914 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1915 webpage, 'vid.me embed', default=None)
1916 if vid_me_embed_url is not None:
1917 return self.url_result(vid_me_embed_url, 'Vidme')
1918
1919 # Look for embedded YouTube player
1920 matches = re.findall(r'''(?x)
1921 (?:
1922 <iframe[^>]+?src=|
1923 data-video-url=|
1924 <embed[^>]+?src=|
1925 embedSWF\(?:\s*|
1926 new\s+SWFObject\(
1927 )
1928 (["\'])
1929 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1930 (?:embed|v|p)/.+?)
1931 \1''', webpage)
1932 if matches:
1933 return self.playlist_from_matches(
1934 matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
1935
1936 # Look for lazyYT YouTube embed
1937 matches = re.findall(
1938 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1939 if matches:
1940 return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
1941
1942 # Look for Wordpress "YouTube Video Importer" plugin
1943 matches = re.findall(r'''(?x)<div[^>]+
1944 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1945 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1946 if matches:
1947 return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
1948
1949 matches = DailymotionIE._extract_urls(webpage)
1950 if matches:
1951 return self.playlist_from_matches(matches, video_id, video_title)
1952
1953 # Look for embedded Dailymotion playlist player (#3822)
1954 m = re.search(
1955 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1956 if m:
1957 playlists = re.findall(
1958 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1959 if playlists:
1960 return self.playlist_from_matches(
1961 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
1962
1963 # Look for embedded Wistia player
1964 match = re.search(
1965 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1966 if match:
1967 embed_url = self._proto_relative_url(
1968 unescapeHTML(match.group('url')))
1969 return {
1970 '_type': 'url_transparent',
1971 'url': embed_url,
1972 'ie_key': 'Wistia',
1973 'uploader': video_uploader,
1974 }
1975
1976 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1977 if match:
1978 return {
1979 '_type': 'url_transparent',
1980 'url': 'wistia:%s' % match.group('id'),
1981 'ie_key': 'Wistia',
1982 'uploader': video_uploader,
1983 }
1984
1985 match = re.search(
1986 r'''(?sx)
1987 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1988 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1989 ''', webpage)
1990 if match:
1991 return self.url_result(self._proto_relative_url(
1992 'wistia:%s' % match.group('id')), 'Wistia')
1993
1994 # Look for SVT player
1995 svt_url = SVTIE._extract_url(webpage)
1996 if svt_url:
1997 return self.url_result(svt_url, 'SVT')
1998
1999 # Look for embedded condenast player
2000 matches = re.findall(
2001 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
2002 webpage)
2003 if matches:
2004 return {
2005 '_type': 'playlist',
2006 'entries': [{
2007 '_type': 'url',
2008 'ie_key': 'CondeNast',
2009 'url': ma,
2010 } for ma in matches],
2011 'title': video_title,
2012 'id': video_id,
2013 }
2014
2015 # Look for Bandcamp pages with custom domain
2016 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2017 if mobj is not None:
2018 burl = unescapeHTML(mobj.group(1))
2019 # Don't set the extractor because it can be a track url or an album
2020 return self.url_result(burl)
2021
2022 # Look for embedded Vevo player
2023 mobj = re.search(
2024 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2025 if mobj is not None:
2026 return self.url_result(mobj.group('url'))
2027
2028 # Look for embedded Viddler player
2029 mobj = re.search(
2030 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2031 webpage)
2032 if mobj is not None:
2033 return self.url_result(mobj.group('url'))
2034
2035 # Look for NYTimes player
2036 mobj = re.search(
2037 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2038 webpage)
2039 if mobj is not None:
2040 return self.url_result(mobj.group('url'))
2041
2042 # Look for Libsyn player
2043 mobj = re.search(
2044 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2045 if mobj is not None:
2046 return self.url_result(mobj.group('url'))
2047
2048 # Look for Ooyala videos
2049 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2050 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2051 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2052 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2053 if mobj is not None:
2054 embed_token = self._search_regex(
2055 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2056 webpage, 'ooyala embed token', default=None)
2057 return OoyalaIE._build_url_result(smuggle_url(
2058 mobj.group('ec'), {
2059 'domain': url,
2060 'embed_token': embed_token,
2061 }))
2062
2063 # Look for multiple Ooyala embeds on SBN network websites
2064 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2065 if mobj is not None:
2066 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2067 if embeds:
2068 return self.playlist_from_matches(
2069 embeds, video_id, video_title,
2070 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2071
2072 # Look for Aparat videos
2073 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2074 if mobj is not None:
2075 return self.url_result(mobj.group(1), 'Aparat')
2076
2077 # Look for MPORA videos
2078 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2079 if mobj is not None:
2080 return self.url_result(mobj.group(1), 'Mpora')
2081
2082 # Look for embedded NovaMov-based player
2083 mobj = re.search(
2084 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2085 (?P<url>http://(?:(?:embed|www)\.)?
2086 (?:novamov\.com|
2087 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2088 videoweed\.(?:es|com)|
2089 movshare\.(?:net|sx|ag)|
2090 divxstage\.(?:eu|net|ch|co|at|ag))
2091 /embed\.php.+?)\1''', webpage)
2092 if mobj is not None:
2093 return self.url_result(mobj.group('url'))
2094
2095 # Look for embedded Facebook player
2096 facebook_url = FacebookIE._extract_url(webpage)
2097 if facebook_url is not None:
2098 return self.url_result(facebook_url, 'Facebook')
2099
2100 # Look for embedded VK player
2101 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2102 if mobj is not None:
2103 return self.url_result(mobj.group('url'), 'VK')
2104
2105 # Look for embedded Odnoklassniki player
2106 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2107 if mobj is not None:
2108 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2109
2110 # Look for embedded ivi player
2111 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2112 if mobj is not None:
2113 return self.url_result(mobj.group('url'), 'Ivi')
2114
2115 # Look for embedded Huffington Post player
2116 mobj = re.search(
2117 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2118 if mobj is not None:
2119 return self.url_result(mobj.group('url'), 'HuffPost')
2120
2121 # Look for embed.ly
2122 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2123 if mobj is not None:
2124 return self.url_result(mobj.group('url'))
2125 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2126 if mobj is not None:
2127 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2128
2129 # Look for funnyordie embed
2130 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2131 if matches:
2132 return self.playlist_from_matches(
2133 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2134
2135 # Look for BBC iPlayer embed
2136 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2137 if matches:
2138 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2139
2140 # Look for embedded RUTV player
2141 rutv_url = RUTVIE._extract_url(webpage)
2142 if rutv_url:
2143 return self.url_result(rutv_url, 'RUTV')
2144
2145 # Look for embedded TVC player
2146 tvc_url = TVCIE._extract_url(webpage)
2147 if tvc_url:
2148 return self.url_result(tvc_url, 'TVC')
2149
2150 # Look for embedded SportBox player
2151 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2152 if sportbox_urls:
2153 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2154
2155 # Look for embedded XHamster player
2156 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2157 if xhamster_urls:
2158 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2159
2160 # Look for embedded TNAFlixNetwork player
2161 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2162 if tnaflix_urls:
2163 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2164
2165 # Look for embedded PornHub player
2166 pornhub_urls = PornHubIE._extract_urls(webpage)
2167 if pornhub_urls:
2168 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2169
2170 # Look for embedded DrTuber player
2171 drtuber_urls = DrTuberIE._extract_urls(webpage)
2172 if drtuber_urls:
2173 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2174
2175 # Look for embedded RedTube player
2176 redtube_urls = RedTubeIE._extract_urls(webpage)
2177 if redtube_urls:
2178 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2179
2180 # Look for embedded Tvigle player
2181 mobj = re.search(
2182 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2183 if mobj is not None:
2184 return self.url_result(mobj.group('url'), 'Tvigle')
2185
2186 # Look for embedded TED player
2187 mobj = re.search(
2188 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2189 if mobj is not None:
2190 return self.url_result(mobj.group('url'), 'TED')
2191
2192 # Look for embedded Ustream videos
2193 ustream_url = UstreamIE._extract_url(webpage)
2194 if ustream_url:
2195 return self.url_result(ustream_url, UstreamIE.ie_key())
2196
2197 # Look for embedded arte.tv player
2198 mobj = re.search(
2199 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2200 webpage)
2201 if mobj is not None:
2202 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2203
2204 # Look for embedded francetv player
2205 mobj = re.search(
2206 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2207 webpage)
2208 if mobj is not None:
2209 return self.url_result(mobj.group('url'))
2210
2211 # Look for embedded smotri.com player
2212 smotri_url = SmotriIE._extract_url(webpage)
2213 if smotri_url:
2214 return self.url_result(smotri_url, 'Smotri')
2215
2216 # Look for embedded Myvi.ru player
2217 myvi_url = MyviIE._extract_url(webpage)
2218 if myvi_url:
2219 return self.url_result(myvi_url)
2220
2221 # Look for embedded soundcloud player
2222 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2223 if soundcloud_urls:
2224 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2225
2226 # Look for tunein player
2227 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2228 if tunein_urls:
2229 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2230
2231 # Look for embedded mtvservices player
2232 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2233 if mtvservices_url:
2234 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2235
2236 # Look for embedded yahoo player
2237 mobj = re.search(
2238 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2239 webpage)
2240 if mobj is not None:
2241 return self.url_result(mobj.group('url'), 'Yahoo')
2242
2243 # Look for embedded sbs.com.au player
2244 mobj = re.search(
2245 r'''(?x)
2246 (?:
2247 <meta\s+property="og:video"\s+content=|
2248 <iframe[^>]+?src=
2249 )
2250 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2251 webpage)
2252 if mobj is not None:
2253 return self.url_result(mobj.group('url'), 'SBS')
2254
2255 # Look for embedded Cinchcast player
2256 mobj = re.search(
2257 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2258 webpage)
2259 if mobj is not None:
2260 return self.url_result(mobj.group('url'), 'Cinchcast')
2261
2262 mobj = re.search(
2263 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2264 webpage)
2265 if not mobj:
2266 mobj = re.search(
2267 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2268 webpage)
2269 if mobj is not None:
2270 return self.url_result(mobj.group('url'), 'MLB')
2271
2272 mobj = re.search(
2273 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2274 webpage)
2275 if mobj is not None:
2276 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2277
2278 mobj = re.search(
2279 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2280 webpage)
2281 if mobj is not None:
2282 return self.url_result(mobj.group('url'), 'Livestream')
2283
2284 # Look for Zapiks embed
2285 mobj = re.search(
2286 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2287 if mobj is not None:
2288 return self.url_result(mobj.group('url'), 'Zapiks')
2289
2290 # Look for Kaltura embeds
2291 kaltura_url = KalturaIE._extract_url(webpage)
2292 if kaltura_url:
2293 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2294
2295 # Look for Eagle.Platform embeds
2296 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2297 if eagleplatform_url:
2298 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2299
2300 # Look for ClipYou (uses Eagle.Platform) embeds
2301 mobj = re.search(
2302 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2303 if mobj is not None:
2304 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2305
2306 # Look for Pladform embeds
2307 pladform_url = PladformIE._extract_url(webpage)
2308 if pladform_url:
2309 return self.url_result(pladform_url)
2310
2311 # Look for Videomore embeds
2312 videomore_url = VideomoreIE._extract_url(webpage)
2313 if videomore_url:
2314 return self.url_result(videomore_url)
2315
2316 # Look for Webcaster embeds
2317 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2318 if webcaster_url:
2319 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2320
2321 # Look for Playwire embeds
2322 mobj = re.search(
2323 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2324 if mobj is not None:
2325 return self.url_result(mobj.group('url'))
2326
2327 # Look for 5min embeds
2328 mobj = re.search(
2329 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2330 if mobj is not None:
2331 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2332
2333 # Look for Crooks and Liars embeds
2334 mobj = re.search(
2335 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2336 if mobj is not None:
2337 return self.url_result(mobj.group('url'))
2338
2339 # Look for NBC Sports VPlayer embeds
2340 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2341 if nbc_sports_url:
2342 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2343
2344 # Look for NBC News embeds
2345 nbc_news_embed_url = re.search(
2346 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2347 if nbc_news_embed_url:
2348 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2349
2350 # Look for Google Drive embeds
2351 google_drive_url = GoogleDriveIE._extract_url(webpage)
2352 if google_drive_url:
2353 return self.url_result(google_drive_url, 'GoogleDrive')
2354
2355 # Look for UDN embeds
2356 mobj = re.search(
2357 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2358 if mobj is not None:
2359 return self.url_result(
2360 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2361
2362 # Look for Senate ISVP iframe
2363 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2364 if senate_isvp_url:
2365 return self.url_result(senate_isvp_url, 'SenateISVP')
2366
2367 # Look for Dailymotion Cloud videos
2368 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2369 if dmcloud_url:
2370 return self.url_result(dmcloud_url, 'DailymotionCloud')
2371
2372 # Look for OnionStudios embeds
2373 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2374 if onionstudios_url:
2375 return self.url_result(onionstudios_url)
2376
2377 # Look for ViewLift embeds
2378 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2379 if viewlift_url:
2380 return self.url_result(viewlift_url)
2381
2382 # Look for JWPlatform embeds
2383 jwplatform_url = JWPlatformIE._extract_url(webpage)
2384 if jwplatform_url:
2385 return self.url_result(jwplatform_url, 'JWPlatform')
2386
2387 # Look for Digiteka embeds
2388 digiteka_url = DigitekaIE._extract_url(webpage)
2389 if digiteka_url:
2390 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2391
2392 # Look for Arkena embeds
2393 arkena_url = ArkenaIE._extract_url(webpage)
2394 if arkena_url:
2395 return self.url_result(arkena_url, ArkenaIE.ie_key())
2396
2397 # Look for Piksel embeds
2398 piksel_url = PikselIE._extract_url(webpage)
2399 if piksel_url:
2400 return self.url_result(piksel_url, PikselIE.ie_key())
2401
2402 # Look for Limelight embeds
2403 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2404 if mobj:
2405 lm = {
2406 'Media': 'media',
2407 'Channel': 'channel',
2408 'ChannelList': 'channel_list',
2409 }
2410 return self.url_result(smuggle_url('limelight:%s:%s' % (
2411 lm[mobj.group(1)], mobj.group(2)), {'source_url': url}),
2412 'Limelight%s' % mobj.group(1), mobj.group(2))
2413
2414 mobj = re.search(
2415 r'''(?sx)
2416 <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2417 <param[^>]+
2418 name=(["\'])flashVars\2[^>]+
2419 value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2420 ''', webpage)
2421 if mobj:
2422 return self.url_result(smuggle_url(
2423 'limelight:media:%s' % mobj.group('id'),
2424 {'source_url': url}), 'LimelightMedia', mobj.group('id'))
2425
2426 # Look for AdobeTVVideo embeds
2427 mobj = re.search(
2428 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2429 webpage)
2430 if mobj is not None:
2431 return self.url_result(
2432 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2433 'AdobeTVVideo')
2434
2435 # Look for Vine embeds
2436 mobj = re.search(
2437 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2438 webpage)
2439 if mobj is not None:
2440 return self.url_result(
2441 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2442
2443 # Look for VODPlatform embeds
2444 mobj = re.search(
2445 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2446 webpage)
2447 if mobj is not None:
2448 return self.url_result(
2449 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2450
2451 # Look for Mangomolo embeds
2452 mobj = re.search(
2453 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2454 (?:
2455 video\?.*?\bid=(?P<video_id>\d+)|
2456 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2457 ).+?)\1''', webpage)
2458 if mobj is not None:
2459 info = {
2460 '_type': 'url_transparent',
2461 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2462 'title': video_title,
2463 'description': video_description,
2464 'thumbnail': video_thumbnail,
2465 'uploader': video_uploader,
2466 }
2467 video_id = mobj.group('video_id')
2468 if video_id:
2469 info.update({
2470 'ie_key': 'MangomoloVideo',
2471 'id': video_id,
2472 })
2473 else:
2474 info.update({
2475 'ie_key': 'MangomoloLive',
2476 'id': mobj.group('channel_id'),
2477 })
2478 return info
2479
2480 # Look for Instagram embeds
2481 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2482 if instagram_embed_url is not None:
2483 return self.url_result(
2484 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2485
2486 # Look for LiveLeak embeds
2487 liveleak_url = LiveLeakIE._extract_url(webpage)
2488 if liveleak_url:
2489 return self.url_result(liveleak_url, 'LiveLeak')
2490
2491 # Look for 3Q SDN embeds
2492 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2493 if threeqsdn_url:
2494 return {
2495 '_type': 'url_transparent',
2496 'ie_key': ThreeQSDNIE.ie_key(),
2497 'url': self._proto_relative_url(threeqsdn_url),
2498 'title': video_title,
2499 'description': video_description,
2500 'thumbnail': video_thumbnail,
2501 'uploader': video_uploader,
2502 }
2503
2504 # Look for VBOX7 embeds
2505 vbox7_url = Vbox7IE._extract_url(webpage)
2506 if vbox7_url:
2507 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2508
2509 # Look for DBTV embeds
2510 dbtv_urls = DBTVIE._extract_urls(webpage)
2511 if dbtv_urls:
2512 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2513
2514 # Look for Videa embeds
2515 videa_urls = VideaIE._extract_urls(webpage)
2516 if videa_urls:
2517 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2518
2519 # Look for 20 minuten embeds
2520 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2521 if twentymin_urls:
2522 return self.playlist_from_matches(
2523 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2524
2525 # Look for Openload embeds
2526 openload_urls = OpenloadIE._extract_urls(webpage)
2527 if openload_urls:
2528 return self.playlist_from_matches(
2529 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2530
2531 # Look for VideoPress embeds
2532 videopress_urls = VideoPressIE._extract_urls(webpage)
2533 if videopress_urls:
2534 return self.playlist_from_matches(
2535 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2536
2537 # Look for Rutube embeds
2538 rutube_urls = RutubeIE._extract_urls(webpage)
2539 if rutube_urls:
2540 return self.playlist_from_matches(
2541 rutube_urls, ie=RutubeIE.ie_key())
2542
2543 # Looking for http://schema.org/VideoObject
2544 json_ld = self._search_json_ld(
2545 webpage, video_id, default={}, expected_type='VideoObject')
2546 if json_ld.get('url'):
2547 info_dict.update({
2548 'title': video_title or info_dict['title'],
2549 'description': video_description,
2550 'thumbnail': video_thumbnail,
2551 'age_limit': age_limit
2552 })
2553 info_dict.update(json_ld)
2554 return info_dict
2555
2556 # Look for HTML5 media
2557 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2558 if entries:
2559 for entry in entries:
2560 entry.update({
2561 'id': video_id,
2562 'title': video_title,
2563 })
2564 self._sort_formats(entry['formats'])
2565 return self.playlist_result(entries)
2566
2567 jwplayer_data = self._find_jwplayer_data(
2568 webpage, video_id, transform_source=js_to_json)
2569 if jwplayer_data:
2570 info = self._parse_jwplayer_data(
2571 jwplayer_data, video_id, require_title=False)
2572 if not info.get('title'):
2573 info['title'] = video_title
2574 return info
2575
2576 def check_video(vurl):
2577 if YoutubeIE.suitable(vurl):
2578 return True
2579 if RtmpIE.suitable(vurl):
2580 return True
2581 vpath = compat_urlparse.urlparse(vurl).path
2582 vext = determine_ext(vpath)
2583 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
2584
2585 def filter_video(urls):
2586 return list(filter(check_video, urls))
2587
2588 # Start with something easy: JW Player in SWFObject
2589 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2590 if not found:
2591 # Look for gorilla-vid style embedding
2592 found = filter_video(re.findall(r'''(?sx)
2593 (?:
2594 jw_plugins|
2595 JWPlayerOptions|
2596 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2597 )
2598 .*?
2599 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2600 if not found:
2601 # Broaden the search a little bit
2602 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2603 if not found:
2604 # Broaden the findall a little bit: JWPlayer JS loader
2605 found = filter_video(re.findall(
2606 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2607 if not found:
2608 # Flow player
2609 found = filter_video(re.findall(r'''(?xs)
2610 flowplayer\("[^"]+",\s*
2611 \{[^}]+?\}\s*,
2612 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2613 ["']?url["']?\s*:\s*["']([^"']+)["']
2614 ''', webpage))
2615 if not found:
2616 # Cinerama player
2617 found = re.findall(
2618 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2619 if not found:
2620 # Try to find twitter cards info
2621 # twitter:player:stream should be checked before twitter:player since
2622 # it is expected to contain a raw stream (see
2623 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2624 found = filter_video(re.findall(
2625 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2626 if not found:
2627 # We look for Open Graph info:
2628 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2629 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2630 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2631 if m_video_type is not None:
2632 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2633 if not found:
2634 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2635 found = re.search(
2636 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2637 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2638 webpage)
2639 if not found:
2640 # Look also in Refresh HTTP header
2641 refresh_header = head_response.headers.get('Refresh')
2642 if refresh_header:
2643 # In python 2 response HTTP headers are bytestrings
2644 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2645 refresh_header = refresh_header.decode('iso-8859-1')
2646 found = re.search(REDIRECT_REGEX, refresh_header)
2647 if found:
2648 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2649 if new_url != url:
2650 self.report_following_redirect(new_url)
2651 return {
2652 '_type': 'url',
2653 'url': new_url,
2654 }
2655 else:
2656 found = None
2657
2658 if not found:
2659 # twitter:player is a https URL to iframe player that may or may not
2660 # be supported by youtube-dl thus this is checked the very last (see
2661 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2662 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2663 if embed_url:
2664 return self.url_result(embed_url)
2665
2666 if not found:
2667 raise UnsupportedError(url)
2668
2669 entries = []
2670 for video_url in orderedSet(found):
2671 video_url = unescapeHTML(video_url)
2672 video_url = video_url.replace('\\/', '/')
2673 video_url = compat_urlparse.urljoin(url, video_url)
2674 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2675
2676 # Sometimes, jwplayer extraction will result in a YouTube URL
2677 if YoutubeIE.suitable(video_url):
2678 entries.append(self.url_result(video_url, 'Youtube'))
2679 continue
2680
2681 # here's a fun little line of code for you:
2682 video_id = os.path.splitext(video_id)[0]
2683
2684 entry_info_dict = {
2685 'id': video_id,
2686 'uploader': video_uploader,
2687 'title': video_title,
2688 'age_limit': age_limit,
2689 }
2690
2691 if RtmpIE.suitable(video_url):
2692 entry_info_dict.update({
2693 '_type': 'url_transparent',
2694 'ie_key': RtmpIE.ie_key(),
2695 'url': video_url,
2696 })
2697 entries.append(entry_info_dict)
2698 continue
2699
2700 ext = determine_ext(video_url)
2701 if ext == 'smil':
2702 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2703 elif ext == 'xspf':
2704 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2705 elif ext == 'm3u8':
2706 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2707 elif ext == 'mpd':
2708 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2709 elif ext == 'f4m':
2710 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2711 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2712 # Just matching .ism/manifest is not enough to be reliably sure
2713 # whether it's actually an ISM manifest or some other streaming
2714 # manifest since there are various streaming URL formats
2715 # possible (see [1]) as well as some other shenanigans like
2716 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2717 # so on.
2718 # Thus the most reasonable way to solve this is to delegate
2719 # to generic extractor in order to look into the contents of
2720 # the manifest itself.
2721 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2722 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2723 entry_info_dict = self.url_result(
2724 smuggle_url(video_url, {'to_generic': True}),
2725 GenericIE.ie_key())
2726 else:
2727 entry_info_dict['url'] = video_url
2728
2729 if entry_info_dict.get('formats'):
2730 self._sort_formats(entry_info_dict['formats'])
2731
2732 entries.append(entry_info_dict)
2733
2734 if len(entries) == 1:
2735 return entries[0]
2736 else:
2737 for num, e in enumerate(entries, start=1):
2738 # 'url' results don't have a title
2739 if e.get('title') is not None:
2740 e['title'] = '%s (%d)' % (e['title'], num)
2741 return {
2742 '_type': 'playlist',
2743 'entries': entries,
2744 }