+
+ # Is it an RSS feed?
+ try:
+ doc = parse_xml(webpage)
+ if doc.tag == 'rss':
+ return self._extract_rss(url, video_id, doc)
+ except compat_xml_parse_error:
+ pass
+
+ # Is it a Camtasia project?
+ camtasia_res = self._extract_camtasia(url, video_id, webpage)
+ if camtasia_res is not None:
+ return camtasia_res
+
+ # Sometimes embedded video player is hidden behind percent encoding
+ # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
+ # Unescaping the whole page allows to handle those cases in a generic way
+ webpage = compat_urllib_parse.unquote(webpage)
+
+ # it's tempting to parse this further, but you would
+ # have to take into account all the variations like
+ # Video Title - Site Name
+ # Site Name | Video Title
+ # Video Title - Tagline | Site Name
+ # and so on and so forth; it's just not practical
+ video_title = self._html_search_regex(
+ r'(?s)<title>(.*?)</title>', webpage, 'video title',
+ default='video')
+
+ # Try to detect age limit automatically
+ age_limit = self._rta_search(webpage)
+ # And then there are the jokers who advertise that they use RTA,
+ # but actually don't.
+ AGE_LIMIT_MARKERS = [
+ r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
+ ]
+ if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
+ age_limit = 18
+
+ # video uploader is domain name
+ video_uploader = self._search_regex(
+ r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
+
+ # Helper method
+ def _playlist_from_matches(matches, getter=None, ie=None):
+ urlrs = orderedSet(
+ self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
+ for m in matches)
+ return self.playlist_result(
+ urlrs, playlist_id=video_id, playlist_title=video_title)
+
+ # Look for BrightCove:
+ bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
+ if bc_urls:
+ self.to_screen('Brightcove video detected.')
+ entries = [{
+ '_type': 'url',
+ 'url': smuggle_url(bc_url, {'Referer': url}),
+ 'ie_key': 'Brightcove'
+ } for bc_url in bc_urls]
+
+ return {
+ '_type': 'playlist',
+ 'title': video_title,
+ 'id': video_id,
+ 'entries': entries,
+ }
+
+ # Look for embedded (iframe) Vimeo player
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
+ if mobj:
+ player_url = unescapeHTML(mobj.group('url'))
+ surl = smuggle_url(player_url, {'Referer': url})
+ return self.url_result(surl)
+
+ # Look for embedded (swf embed) Vimeo player
+ mobj = re.search(
+ r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
+ if mobj:
+ return self.url_result(mobj.group(1))
+
+ # Look for embedded YouTube player
+ matches = re.findall(r'''(?x)
+ (?:
+ <iframe[^>]+?src=|
+ data-video-url=|
+ <embed[^>]+?src=|
+ embedSWF\(?:\s*|
+ new\s+SWFObject\(
+ )
+ (["\'])
+ (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
+ (?:embed|v|p)/.+?)
+ \1''', webpage)
+ if matches:
+ return _playlist_from_matches(
+ matches, lambda m: unescapeHTML(m[1]))
+
+ # Look for lazyYT YouTube embed
+ matches = re.findall(
+ r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
+ if matches:
+ return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
+
+ # Look for embedded Dailymotion player
+ matches = re.findall(
+ r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
+ if matches:
+ return _playlist_from_matches(
+ matches, lambda m: unescapeHTML(m[1]))
+
+ # Look for embedded Dailymotion playlist player (#3822)
+ m = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
+ if m:
+ playlists = re.findall(
+ r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
+ if playlists:
+ return _playlist_from_matches(
+ playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
+
+ # Look for embedded Wistia player
+ match = re.search(
+ r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
+ if match:
+ embed_url = self._proto_relative_url(
+ unescapeHTML(match.group('url')))
+ return {
+ '_type': 'url_transparent',
+ 'url': embed_url,
+ 'ie_key': 'Wistia',
+ 'uploader': video_uploader,
+ 'title': video_title,
+ 'id': video_id,
+ }
+
+ match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
+ if match:
+ return {
+ '_type': 'url_transparent',
+ 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
+ 'ie_key': 'Wistia',
+ 'uploader': video_uploader,
+ 'title': video_title,
+ 'id': match.group('id')
+ }
+
+ # Look for embedded blip.tv player
+ mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage)
+ if mobj:
+ return self.url_result('http://blip.tv/a/a-' + mobj.group(1), 'BlipTV')
+ mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage)
+ if mobj:
+ return self.url_result(mobj.group(1), 'BlipTV')
+
+ # Look for embedded condenast player
+ matches = re.findall(
+ r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
+ webpage)
+ if matches:
+ return {
+ '_type': 'playlist',
+ 'entries': [{
+ '_type': 'url',
+ 'ie_key': 'CondeNast',
+ 'url': ma,
+ } for ma in matches],
+ 'title': video_title,
+ 'id': video_id,
+ }
+
+ # Look for Bandcamp pages with custom domain
+ mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
+ if mobj is not None:
+ burl = unescapeHTML(mobj.group(1))
+ # Don't set the extractor because it can be a track url or an album
+ return self.url_result(burl)
+
+ # Look for embedded Vevo player
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'))
+
+ # Look for embedded Viddler player
+ mobj = re.search(
+ r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
+ webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'))
+
+ # Look for Ooyala videos
+ mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
+ re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
+ re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage))
+ if mobj is not None:
+ return OoyalaIE._build_url_result(mobj.group('ec'))
+
+ # Look for multiple Ooyala embeds on SBN network websites
+ mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
+ if mobj is not None:
+ embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
+ if embeds:
+ return _playlist_from_matches(
+ embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
+
+ # Look for Aparat videos
+ mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group(1), 'Aparat')
+
+ # Look for MPORA videos
+ mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group(1), 'Mpora')
+
+ # Look for embedded NovaMov-based player
+ mobj = re.search(
+ r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
+ (?P<url>http://(?:(?:embed|www)\.)?
+ (?:novamov\.com|
+ nowvideo\.(?:ch|sx|eu|at|ag|co)|
+ videoweed\.(?:es|com)|
+ movshare\.(?:net|sx|ag)|
+ divxstage\.(?:eu|net|ch|co|at|ag))
+ /embed\.php.+?)\1''', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'))
+
+ # Look for embedded Facebook player
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'), 'Facebook')
+
+ # Look for embedded VK player
+ mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'), 'VK')
+
+ # Look for embedded ivi player
+ mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'), 'Ivi')
+
+ # Look for embedded Huffington Post player
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'), 'HuffPost')
+
+ # Look for embed.ly
+ mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'))
+ mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
+ if mobj is not None:
+ return self.url_result(compat_urllib_parse.unquote(mobj.group('url')))
+
+ # Look for funnyordie embed
+ matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
+ if matches:
+ return _playlist_from_matches(
+ matches, getter=unescapeHTML, ie='FunnyOrDie')
+
+ # Look for BBC iPlayer embed
+ matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
+ if matches:
+ return _playlist_from_matches(matches, ie='BBCCoUk')
+
+ # Look for embedded RUTV player
+ rutv_url = RUTVIE._extract_url(webpage)
+ if rutv_url:
+ return self.url_result(rutv_url, 'RUTV')
+
+ # Look for embedded TED player
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'), 'TED')
+
+ # Look for embedded Ustream videos
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'), 'Ustream')
+
+ # Look for embedded arte.tv player
+ mobj = re.search(
+ r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
+ webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'), 'ArteTVEmbed')
+
+ # Look for embedded smotri.com player
+ smotri_url = SmotriIE._extract_url(webpage)
+ if smotri_url:
+ return self.url_result(smotri_url, 'Smotri')
+
+ # Look for embeded soundcloud player
+ mobj = re.search(
+ r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
+ webpage)
+ if mobj is not None:
+ url = unescapeHTML(mobj.group('url'))
+ return self.url_result(url)
+
+ # Look for embedded vulture.com player
+ mobj = re.search(
+ r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
+ webpage)
+ if mobj is not None:
+ url = unescapeHTML(mobj.group('url'))
+ return self.url_result(url, ie='Vulture')
+
+ # Look for embedded mtvservices player
+ mobj = re.search(
+ r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
+ webpage)
+ if mobj is not None:
+ url = unescapeHTML(mobj.group('url'))
+ return self.url_result(url, ie='MTVServicesEmbedded')
+
+ # Look for embedded yahoo player
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
+ webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'), 'Yahoo')
+
+ # Look for embedded sbs.com.au player
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:www\.)sbs\.com\.au/ondemand/video/single/.+?)\1',
+ webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'), 'SBS')
+
+ # Look for embedded Cinchcast player
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
+ webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'), 'Cinchcast')
+
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
+ webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'), 'MLB')
+
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
+ webpage)
+ if mobj is not None:
+ return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
+
+ mobj = re.search(
+ r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
+ webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'), 'Livestream')
+
+ def check_video(vurl):
+ vpath = compat_urlparse.urlparse(vurl).path
+ vext = determine_ext(vpath)
+ return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
+
+ def filter_video(urls):
+ return list(filter(check_video, urls))
Rapsys Git / youtubedl / blobdiff