3 from __future__ import unicode_literals
8 from .common import InfoExtractor
9 from .youtube import YoutubeIE
10 from ..compat import (
13 compat_xml_parse_error,
29 from .brightcove import BrightcoveIE
30 from .ooyala import OoyalaIE
31 from .rutv import RUTVIE
32 from .smotri import SmotriIE
33 from .condenast import CondeNastIE
36 class GenericIE(InfoExtractor):
37 IE_DESC = 'Generic downloader that works on some sites'
42 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
43 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
45 'id': '13601338388002',
47 'uploader': 'www.hodiho.fr',
48 'title': 'R\u00e9gis plante sa Jeep',
51 # bandcamp page with custom domain
53 'add_ie': ['Bandcamp'],
54 'url': 'http://bronyrock.com/track/the-pony-mash',
58 'title': 'The Pony Mash',
59 'uploader': 'M_Pallante',
61 'skip': 'There is a limit of 200 free downloads / month for the test song',
63 # embedded brightcove video
64 # it also tests brightcove videos that need to set the 'Referer' in the
67 'add_ie': ['Brightcove'],
68 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
70 'id': '2765128793001',
72 'title': 'Le cours de bourse : l’analyse technique',
73 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
74 'uploader': 'BFM BUSINESS',
77 'skip_download': True,
81 # https://github.com/rg3/youtube-dl/issues/2253
82 'url': 'http://bcove.me/i6nfkrc3',
83 'md5': '0ba9446db037002366bab3b3eb30c88c',
85 'id': '3101154703001',
87 'title': 'Still no power',
88 'uploader': 'thestar.com',
89 '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.',
91 'add_ie': ['Brightcove'],
94 'url': 'http://www.championat.com/video/football/v/87/87499.html',
95 'md5': 'fb973ecf6e4a78a67453647444222983',
97 'id': '3414141473001',
99 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
100 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
101 'uploader': 'Championat',
105 # https://github.com/rg3/youtube-dl/issues/3541
106 'add_ie': ['Brightcove'],
107 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
109 'id': '3866516442001',
111 'title': 'Leer mij vrouwen kennen: Aflevering 1',
112 'description': 'Leer mij vrouwen kennen: Aflevering 1',
113 'uploader': 'SBS Broadcasting',
115 'skip': 'Restricted to Netherlands',
117 'skip_download': True, # m3u8 download
120 # Direct link to a video
122 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
123 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
128 'upload_date': '20100513',
133 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
134 'md5': '5644c6ca5d5782c1d0d350dad9bd840c',
136 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
138 'title': '2cc213299525360.mov', # that's what we get
143 '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',
147 'upload_date': '20130224',
148 'uploader_id': 'TheVerge',
149 'description': 'Chris Ziegler takes a look at the Alcatel OneTouch Fire and the ZTE Open; two of the first Firefox OS handsets to be officially announced.',
150 'uploader': 'The Verge',
151 'title': 'First Firefox OS phones side-by-side',
154 'skip_download': False,
159 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
163 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
164 'upload_date': '20140225',
165 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
166 'uploader': 'Tested',
167 'uploader_id': 'testedcom',
169 # No need to test YoutubeIE here
171 'skip_download': True,
176 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
180 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
181 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
186 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
190 'title': 'Охотское море стало целиком российским',
191 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
195 'skip_download': True,
200 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
201 'md5': '65fdff94098e4a607385a60c5177c638',
205 'title': 'Hidden miracles of the natural world',
206 'uploader': 'Louie Schwartzberg',
207 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
210 # Embeded Ustream video
212 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
213 'md5': '27b99cdb639c9b12a79bca876a073417',
217 'uploader': 'AU SPA: The NSA and Privacy',
218 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
221 # nowvideo embed hidden behind percent encoding
223 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
224 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
226 'id': '06e53103ca9aa',
228 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
229 'description': 'No description',
234 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
235 'md5': '7653032cbb25bf6c80d80f217055fa43',
237 'id': '048195-004_PLUS7-F',
240 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
241 'upload_date': '20140320',
244 'skip_download': 'Requires rtmpdump'
249 'url': 'http://www.wired.com/2014/04/honda-asimo/',
250 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
252 'id': '53501be369702d3275860000',
254 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
259 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
260 'md5': '441aeeb82eb72c422c7f14ec533999cd',
262 'id': 'k2mm4bCdJ6CQ2i7c8o2',
264 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
267 'add_ie': ['Dailymotion'],
271 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
275 'title': 'The NBL Auction 2014',
276 'uploader': 'BADMINTON England',
277 'uploader_id': 'BADMINTONEvents',
278 'upload_date': '20140603',
279 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
281 'add_ie': ['Youtube'],
283 'skip_download': True,
288 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
289 'md5': '35727f82f58c76d996fc188f9755b0d5',
291 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
294 'description': 'Mario\'s life in the fast lane has never looked so good.',
297 # YouTube embed via <data-embed-url="">
299 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
303 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
304 'uploader': 'Gameloft',
305 'uploader_id': 'gameloft',
306 'upload_date': '20140828',
307 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
310 'skip_download': True,
315 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
317 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
319 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
320 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
325 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
327 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
328 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
334 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
339 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
340 'md5': '9d65602bf31c6e20014319c7d07fba27',
342 'id': '5123ea6d5e5a7',
345 'uploader': 'www.handjobhub.com',
346 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
351 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
353 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
354 'title': 'Zero Punctuation',
357 'playlist_mincount': 11,
359 # Multiple brightcove videos
360 # https://github.com/rg3/youtube-dl/issues/2283
362 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
364 'id': 'always-never',
365 'title': 'Always / Never - The New Yorker',
369 'extract_flat': False,
370 'skip_download': True,
375 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
376 'md5': '96f09a37e44da40dd083e12d9a683327',
380 'title': 'Ump changes call to ball',
381 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
383 'timestamp': 1401537900,
384 'upload_date': '20140531',
385 'thumbnail': 're:^https?://.*\.jpg$',
390 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
391 'md5': '8788b683c777a5cf25621eaf286d0c23',
395 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
397 'filesize': 182808282,
398 'uploader': 'education-portal.com',
402 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
403 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
407 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
409 'uploader': 'thoughtworks.wistia.com',
412 # Direct download with broken HEAD
414 'url': 'http://ai-radio.org:8000/radio.opus',
421 'skip_download': True, # infinite live stream
423 'expected_warnings': [
424 r'501.*Not Implemented'
429 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
433 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
434 'uploader': 'Sophos Security',
435 'title': 'Chet Chat 171 - Oct 29, 2014',
436 'upload_date': '20141029',
441 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
445 'upload_date': '20141112',
446 'title': 'Rosetta #CometLanding webcast HL 10',
451 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
453 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
455 'playlist_mincount': 2,
457 # Direct link with incorrect MIME type
459 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
460 'md5': '4ccbebe5f36706d85221f204d7eb5913',
462 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
463 'id': '5_Lennart_Poettering_-_Systemd',
465 'title': '5_Lennart_Poettering_-_Systemd',
466 'upload_date': '20141120',
468 'expected_warnings': [
469 'URL could be a direct video link, returning it as such.'
474 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
478 'upload_date': '20141126',
479 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
484 def report_following_redirect(self, new_url):
485 """Report information extraction."""
486 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
488 def _extract_rss(self, url, video_id, doc):
489 playlist_title = doc.find('./channel/title').text
490 playlist_desc_el = doc.find('./channel/description')
491 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
495 'url': e.find('link').text,
496 'title': e.find('title').text,
497 } for e in doc.findall('./channel/item')]
502 'title': playlist_title,
503 'description': playlist_desc,
507 def _extract_camtasia(self, url, video_id, webpage):
508 """ Returns None if no camtasia video can be found. """
510 camtasia_cfg = self._search_regex(
511 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
512 webpage, 'camtasia configuration file', default=None)
513 if camtasia_cfg is None:
516 title = self._html_search_meta('DC.title', webpage, fatal=True)
518 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
519 camtasia_cfg = self._download_xml(
520 camtasia_url, video_id,
521 note='Downloading camtasia configuration',
522 errnote='Failed to download camtasia configuration')
523 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
526 for n in fileset_node.getchildren():
527 url_n = n.find('./uri')
532 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
533 'title': '%s - %s' % (title, n.tag),
534 'url': compat_urlparse.urljoin(url, url_n.text),
535 'duration': float_or_none(n.find('./duration').text),
544 def _real_extract(self, url):
545 if url.startswith('//'):
548 'url': self.http_scheme() + url,
551 parsed_url = compat_urlparse.urlparse(url)
552 if not parsed_url.scheme:
553 default_search = self._downloader.params.get('default_search')
554 if default_search is None:
555 default_search = 'fixup_error'
557 if default_search in ('auto', 'auto_warning', 'fixup_error'):
559 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
560 return self.url_result('http://' + url)
561 elif default_search != 'fixup_error':
562 if default_search == 'auto_warning':
563 if re.match(r'^(?:url|URL)$', url):
564 raise ExtractorError(
565 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
568 self._downloader.report_warning(
569 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
570 return self.url_result('ytsearch:' + url)
572 if default_search in ('error', 'fixup_error'):
573 raise ExtractorError(
574 '%r is not a valid URL. '
575 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
576 % (url, url), expected=True)
578 if ':' not in default_search:
579 default_search += ':'
580 return self.url_result(default_search + url)
582 url, smuggled_data = unsmuggle_url(url)
584 is_intentional = smuggled_data and smuggled_data.get('to_generic')
585 if smuggled_data and 'force_videoid' in smuggled_data:
586 force_videoid = smuggled_data['force_videoid']
587 video_id = force_videoid
589 video_id = os.path.splitext(url.rstrip('/').split('/')[-1])[0]
591 self.to_screen('%s: Requesting header' % video_id)
593 head_req = HEADRequest(url)
594 head_response = self._request_webpage(
596 note=False, errnote='Could not send HEAD request to %s' % url,
599 if head_response is not False:
601 new_url = head_response.geturl()
603 self.report_following_redirect(new_url)
605 new_url = smuggle_url(
606 new_url, {'force_videoid': force_videoid})
607 return self.url_result(new_url)
610 if head_response is False:
611 full_response = self._request_webpage(url, video_id)
612 head_response = full_response
614 # Check for direct link to a video
615 content_type = head_response.headers.get('Content-Type', '')
616 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
618 upload_date = unified_strdate(
619 head_response.headers.get('Last-Modified'))
622 'title': os.path.splitext(url_basename(url))[0],
625 'format_id': m.group('format_id'),
627 'vcodec': 'none' if m.group('type') == 'audio' else None
629 'upload_date': upload_date,
632 if not self._downloader.params.get('test', False) and not is_intentional:
633 self._downloader.report_warning('Falling back on generic information extractor.')
635 if not full_response:
636 full_response = self._request_webpage(url, video_id)
638 # Maybe it's a direct link to a video?
639 # Be careful not to download the whole thing!
640 first_bytes = full_response.read(512)
641 if not re.match(r'^\s*<', first_bytes.decode('utf-8', 'replace')):
642 self._downloader.report_warning(
643 'URL could be a direct video link, returning it as such.')
644 upload_date = unified_strdate(
645 head_response.headers.get('Last-Modified'))
648 'title': os.path.splitext(url_basename(url))[0],
651 'upload_date': upload_date,
654 webpage = self._webpage_read_content(
655 full_response, url, video_id, prefix=first_bytes)
657 self.report_extraction(video_id)
661 doc = parse_xml(webpage)
663 return self._extract_rss(url, video_id, doc)
664 except compat_xml_parse_error:
667 # Is it a Camtasia project?
668 camtasia_res = self._extract_camtasia(url, video_id, webpage)
669 if camtasia_res is not None:
672 # Sometimes embedded video player is hidden behind percent encoding
673 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
674 # Unescaping the whole page allows to handle those cases in a generic way
675 webpage = compat_urllib_parse.unquote(webpage)
677 # it's tempting to parse this further, but you would
678 # have to take into account all the variations like
679 # Video Title - Site Name
680 # Site Name | Video Title
681 # Video Title - Tagline | Site Name
682 # and so on and so forth; it's just not practical
683 video_title = self._html_search_regex(
684 r'(?s)<title>(.*?)</title>', webpage, 'video title',
687 # Try to detect age limit automatically
688 age_limit = self._rta_search(webpage)
689 # And then there are the jokers who advertise that they use RTA,
690 # but actually don't.
691 AGE_LIMIT_MARKERS = [
692 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
694 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
697 # video uploader is domain name
698 video_uploader = self._search_regex(
699 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
702 def _playlist_from_matches(matches, getter=None, ie=None):
704 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
706 return self.playlist_result(
707 urlrs, playlist_id=video_id, playlist_title=video_title)
709 # Look for BrightCove:
710 bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
712 self.to_screen('Brightcove video detected.')
715 'url': smuggle_url(bc_url, {'Referer': url}),
716 'ie_key': 'Brightcove'
717 } for bc_url in bc_urls]
721 'title': video_title,
726 # Look for embedded (iframe) Vimeo player
728 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
730 player_url = unescapeHTML(mobj.group('url'))
731 surl = smuggle_url(player_url, {'Referer': url})
732 return self.url_result(surl)
734 # Look for embedded (swf embed) Vimeo player
736 r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
738 return self.url_result(mobj.group(1))
740 # Look for embedded YouTube player
741 matches = re.findall(r'''(?x)
750 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
754 return _playlist_from_matches(
755 matches, lambda m: unescapeHTML(m[1]))
757 # Look for lazyYT YouTube embed
758 matches = re.findall(
759 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
761 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
763 # Look for embedded Dailymotion player
764 matches = re.findall(
765 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
767 return _playlist_from_matches(
768 matches, lambda m: unescapeHTML(m[1]))
770 # Look for embedded Dailymotion playlist player (#3822)
772 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
774 playlists = re.findall(
775 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
777 return _playlist_from_matches(
778 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
780 # Look for embedded Wistia player
782 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
784 embed_url = self._proto_relative_url(
785 unescapeHTML(match.group('url')))
787 '_type': 'url_transparent',
790 'uploader': video_uploader,
791 'title': video_title,
795 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
798 '_type': 'url_transparent',
799 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
801 'uploader': video_uploader,
802 'title': video_title,
803 'id': match.group('id')
806 # Look for embedded blip.tv player
807 mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage)
809 return self.url_result('http://blip.tv/a/a-' + mobj.group(1), 'BlipTV')
810 mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage)
812 return self.url_result(mobj.group(1), 'BlipTV')
814 # Look for embedded condenast player
815 matches = re.findall(
816 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
823 'ie_key': 'CondeNast',
825 } for ma in matches],
826 'title': video_title,
830 # Look for Bandcamp pages with custom domain
831 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
833 burl = unescapeHTML(mobj.group(1))
834 # Don't set the extractor because it can be a track url or an album
835 return self.url_result(burl)
837 # Look for embedded Vevo player
839 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
841 return self.url_result(mobj.group('url'))
843 # Look for Ooyala videos
844 mobj = (re.search(r'player.ooyala.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
845 re.search(r'OO.Player.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage))
847 return OoyalaIE._build_url_result(mobj.group('ec'))
849 # Look for Aparat videos
850 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
852 return self.url_result(mobj.group(1), 'Aparat')
854 # Look for MPORA videos
855 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
857 return self.url_result(mobj.group(1), 'Mpora')
859 # Look for embedded NovaMov-based player
861 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
862 (?P<url>http://(?:(?:embed|www)\.)?
864 nowvideo\.(?:ch|sx|eu|at|ag|co)|
865 videoweed\.(?:es|com)|
866 movshare\.(?:net|sx|ag)|
867 divxstage\.(?:eu|net|ch|co|at|ag))
868 /embed\.php.+?)\1''', webpage)
870 return self.url_result(mobj.group('url'))
872 # Look for embedded Facebook player
874 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
876 return self.url_result(mobj.group('url'), 'Facebook')
878 # Look for embedded VK player
879 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
881 return self.url_result(mobj.group('url'), 'VK')
883 # Look for embedded ivi player
884 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
886 return self.url_result(mobj.group('url'), 'Ivi')
888 # Look for embedded Huffington Post player
890 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
892 return self.url_result(mobj.group('url'), 'HuffPost')
895 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
897 return self.url_result(mobj.group('url'))
898 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
900 return self.url_result(compat_urllib_parse.unquote(mobj.group('url')))
902 # Look for funnyordie embed
903 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
905 return _playlist_from_matches(
906 matches, getter=unescapeHTML, ie='FunnyOrDie')
908 # Look for BBC iPlayer embed
909 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
911 return self.playlist_result([self.url_result(video_url, ie='BBCCoUk') for video_url in matches])
913 # Look for embedded RUTV player
914 rutv_url = RUTVIE._extract_url(webpage)
916 return self.url_result(rutv_url, 'RUTV')
918 # Look for embedded TED player
920 r'<iframe[^>]+?src=(["\'])(?P<url>http://embed\.ted\.com/.+?)\1', webpage)
922 return self.url_result(mobj.group('url'), 'TED')
924 # Look for embedded Ustream videos
926 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
928 return self.url_result(mobj.group('url'), 'Ustream')
930 # Look for embedded arte.tv player
932 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
935 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
937 # Look for embedded smotri.com player
938 smotri_url = SmotriIE._extract_url(webpage)
940 return self.url_result(smotri_url, 'Smotri')
942 # Look for embeded soundcloud player
944 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
947 url = unescapeHTML(mobj.group('url'))
948 return self.url_result(url)
950 # Look for embedded vulture.com player
952 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
955 url = unescapeHTML(mobj.group('url'))
956 return self.url_result(url, ie='Vulture')
958 # Look for embedded mtvservices player
960 r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
963 url = unescapeHTML(mobj.group('url'))
964 return self.url_result(url, ie='MTVServicesEmbedded')
966 # Look for embedded yahoo player
968 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
971 return self.url_result(mobj.group('url'), 'Yahoo')
973 # Look for embedded sbs.com.au player
975 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:www\.)sbs\.com\.au/ondemand/video/single/.+?)\1',
978 return self.url_result(mobj.group('url'), 'SBS')
980 # Look for embedded Cinchcast player
982 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
985 return self.url_result(mobj.group('url'), 'Cinchcast')
988 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
991 return self.url_result(mobj.group('url'), 'MLB')
994 r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
997 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1000 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1002 if mobj is not None:
1003 return self.url_result(mobj.group('url'), 'Livestream')
1005 def check_video(vurl):
1006 vpath = compat_urlparse.urlparse(vurl).path
1007 vext = determine_ext(vpath)
1008 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1010 def filter_video(urls):
1011 return list(filter(check_video, urls))
1013 # Start with something easy: JW Player in SWFObject
1014 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1016 # Look for gorilla-vid style embedding
1017 found = filter_video(re.findall(r'''(?sx)
1021 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1023 .*?file\s*:\s*["\'](.*?)["\']''', webpage))
1025 # Broaden the search a little bit
1026 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1028 # Broaden the findall a little bit: JWPlayer JS loader
1029 found = filter_video(re.findall(
1030 r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1033 found = filter_video(re.findall(r'''(?xs)
1034 flowplayer\("[^"]+",\s*
1036 \s*{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1037 ["']?url["']?\s*:\s*["']([^"']+)["']
1040 # Try to find twitter cards info
1041 found = filter_video(re.findall(
1042 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1044 # We look for Open Graph info:
1045 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1046 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1047 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1048 if m_video_type is not None:
1049 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1052 found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1055 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1056 r'(?:[a-z-]+="[^"]+"\s+)*?content="[0-9]{,2};url=\'?([^\'"]+)',
1059 new_url = found.group(1)
1060 self.report_following_redirect(new_url)
1066 raise UnsupportedError(url)
1069 for video_url in found:
1070 video_url = compat_urlparse.urljoin(url, video_url)
1071 video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
1073 # Sometimes, jwplayer extraction will result in a YouTube URL
1074 if YoutubeIE.suitable(video_url):
1075 entries.append(self.url_result(video_url, 'Youtube'))
1078 # here's a fun little line of code for you:
1079 video_id = os.path.splitext(video_id)[0]
1084 'uploader': video_uploader,
1085 'title': video_title,
1086 'age_limit': age_limit,
1089 if len(entries) == 1:
1092 for num, e in enumerate(entries, start=1):
1093 e['title'] = '%s (%d)' % (e['title'], num)
1095 '_type': 'playlist',