X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fgeneric.py;h=ec43c5ae4086a769300ce9e550244cd9c13d6c00;hb=173190f5e3946173daea0539cf0e749cb14acd12;hp=83a31f3d3d67cc52cf1c1dbb0457e973c8b68e28;hpb=57c68ec4c303f471b2519db21b9b56c080d88338;p=youtube-dl diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 83a31f3d3..ec43c5ae4 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -32,7 +32,6 @@ from ..utils import ( unified_strdate, unsmuggle_url, UnsupportedError, - url_or_none, xpath_text, ) from .commonprotocols import RtmpIE @@ -48,7 +47,7 @@ from .nbc import NBCSportsVPlayerIE from .ooyala import OoyalaIE from .rutv import RUTVIE from .tvc import TVCIE -from .sportbox import SportBoxEmbedIE +from .sportbox import SportBoxIE from .smotri import SmotriIE from .myvi import MyviIE from .condenast import CondeNastIE @@ -78,7 +77,6 @@ from .instagram import InstagramIE from .liveleak import LiveLeakIE from .threeqsdn import ThreeQSDNIE from .theplatform import ThePlatformIE -from .vessel import VesselIE from .kaltura import KalturaIE from .eagleplatform import EaglePlatformIE from .facebook import FacebookIE @@ -90,7 +88,10 @@ from .piksel import PikselIE from .videa import VideaIE from .twentymin import TwentyMinutenIE from .ustream import UstreamIE -from .openload import OpenloadIE +from .openload import ( + OpenloadIE, + VerystreamIE, +) from .videopress import VideoPressIE from .rutube import RutubeIE from .limelight import LimelightBaseIE @@ -110,11 +111,13 @@ from .vice import ViceIE from .xfileshare import XFileShareIE from .cloudflarestream import CloudflareStreamIE from .peertube import PeerTubeIE +from .teachable import TeachableIE from .indavideo import IndavideoEmbedIE from .apa import APAIE from .foxnews import FoxNewsIE from .viqeo import ViqeoIE from .expressen import ExpressenIE +from .zype import ZypeIE class GenericIE(InfoExtractor): @@ -429,7 +432,7 @@ class GenericIE(InfoExtractor): }, }, { - # https://github.com/rg3/youtube-dl/issues/2253 + # https://github.com/ytdl-org/youtube-dl/issues/2253 'url': 'http://bcove.me/i6nfkrc3', 'md5': '0ba9446db037002366bab3b3eb30c88c', 'info_dict': { @@ -454,7 +457,7 @@ class GenericIE(InfoExtractor): }, }, { - # https://github.com/rg3/youtube-dl/issues/3541 + # https://github.com/ytdl-org/youtube-dl/issues/3541 'add_ie': ['BrightcoveLegacy'], 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1', 'info_dict': { @@ -918,7 +921,7 @@ class GenericIE(InfoExtractor): } }, # Multiple brightcove videos - # https://github.com/rg3/youtube-dl/issues/2283 + # https://github.com/ytdl-org/youtube-dl/issues/2283 { 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html', 'info_dict': { @@ -2071,6 +2074,68 @@ class GenericIE(InfoExtractor): }, 'playlist_count': 6, }, + { + # Squarespace video embed, 2019-08-28 + 'url': 'http://ootboxford.com', + 'info_dict': { + 'id': 'Tc7b_JGdZfw', + 'title': 'Out of the Blue, at Childish Things 10', + 'ext': 'mp4', + 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f', + 'uploader_id': 'helendouglashouse', + 'uploader': 'Helen & Douglas House', + 'upload_date': '20140328', + }, + 'params': { + 'skip_download': True, + }, + }, + { + # Zype embed + 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites', + 'info_dict': { + 'id': '5b400b834b32992a310622b9', + 'ext': 'mp4', + 'title': 'Smoky Barbecue Favorites', + 'thumbnail': r're:^https?://.*\.jpe?g', + }, + 'add_ie': [ZypeIE.ie_key()], + 'params': { + 'skip_download': True, + }, + }, + { + # videojs embed + 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904', + 'info_dict': { + 'id': 'shell', + 'ext': 'mp4', + 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано', + 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1', + 'thumbnail': r're:^https?://.*\.jpg$', + }, + 'params': { + 'skip_download': True, + }, + 'expected_warnings': ['Failed to download MPD manifest'], + }, + { + # DailyMotion embed with DM.player + 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804', + 'info_dict': { + 'id': 'k6aKkGHd9FJs4mtJN39', + 'ext': 'mp4', + 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final', + 'description': 'This video is private.', + 'uploader_id': 'x1jf30l', + 'uploader': 'beIN SPORTS USA', + 'upload_date': '20190528', + 'timestamp': 1559062971, + }, + 'params': { + 'skip_download': True, + }, + }, # { # # TODO: find another test # # http://schema.org/VideoObject @@ -2167,10 +2232,7 @@ class GenericIE(InfoExtractor): def _real_extract(self, url): if url.startswith('//'): - return { - '_type': 'url', - 'url': self.http_scheme() + url, - } + return self.url_result(self.http_scheme() + url) parsed_url = compat_urlparse.urlparse(url) if not parsed_url.scheme: @@ -2179,7 +2241,7 @@ class GenericIE(InfoExtractor): default_search = 'fixup_error' if default_search in ('auto', 'auto_warning', 'fixup_error'): - if '/' in url: + if re.match(r'^[^\s/]+\.[^\s/]+/', url): self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http') return self.url_result('http://' + url) elif default_search != 'fixup_error': @@ -2344,10 +2406,16 @@ class GenericIE(InfoExtractor): return camtasia_res # Sometimes embedded video player is hidden behind percent encoding - # (e.g. https://github.com/rg3/youtube-dl/issues/2448) + # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448) # Unescaping the whole page allows to handle those cases in a generic way webpage = compat_urllib_parse_unquote(webpage) + # Unescape squarespace embeds to be detected by generic extractor, + # see https://github.com/ytdl-org/youtube-dl/issues/21294 + webpage = re.sub( + r']+class=[^>]*?\bsqs-video-wrapper\b[^>]*>', + lambda x: unescapeHTML(x.group(0)), webpage) + # it's tempting to parse this further, but you would # have to take into account all the variations like # Video Title - Site Name @@ -2422,11 +2490,6 @@ class GenericIE(InfoExtractor): if tp_urls: return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform') - # Look for Vessel embeds - vessel_urls = VesselIE._extract_urls(webpage) - if vessel_urls: - return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key()) - # Look for embedded rtl.nl player matches = re.findall( r']+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"', @@ -2519,11 +2582,11 @@ class GenericIE(InfoExtractor): return self.url_result(mobj.group('url')) # Look for Ooyala videos - mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P[^"&]+)', webpage) or - re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P.{32})[\'"]', webpage) or - re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P.{32})[\'"]', webpage) or - re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P.{32})[\'"]\)', webpage) or - re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P.{32})[\'"]', webpage)) + mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P[^"&]+)', webpage) + or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P.{32})[\'"]', webpage) + or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P.{32})[\'"]', webpage) + or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P.{32})[\'"]\)', webpage) + or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P.{32})[\'"]', webpage)) if mobj is not None: embed_token = self._search_regex( r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)', @@ -2553,19 +2616,6 @@ class GenericIE(InfoExtractor): 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=(["\']) - (?Phttp://(?:(?: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 facebook_urls = FacebookIE._extract_urls(webpage) if facebook_urls: @@ -2622,9 +2672,9 @@ class GenericIE(InfoExtractor): return self.url_result(tvc_url, 'TVC') # Look for embedded SportBox player - sportbox_urls = SportBoxEmbedIE._extract_urls(webpage) + sportbox_urls = SportBoxIE._extract_urls(webpage) if sportbox_urls: - return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed') + return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key()) # Look for embedded XHamster player xhamster_urls = XHamsterEmbedIE._extract_urls(webpage) @@ -2990,6 +3040,12 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( openload_urls, video_id, video_title, ie=OpenloadIE.ie_key()) + # Look for Verystream embeds + verystream_urls = VerystreamIE._extract_urls(webpage) + if verystream_urls: + return self.playlist_from_matches( + verystream_urls, video_id, video_title, ie=VerystreamIE.ie_key()) + # Look for VideoPress embeds videopress_urls = VideoPressIE._extract_urls(webpage) if videopress_urls: @@ -3009,7 +3065,7 @@ class GenericIE(InfoExtractor): wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key()) # Look for Mediaset embeds - mediaset_urls = MediasetIE._extract_urls(webpage) + mediaset_urls = MediasetIE._extract_urls(self, webpage) if mediaset_urls: return self.playlist_from_matches( mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key()) @@ -3083,6 +3139,10 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key()) + teachable_url = TeachableIE._extract_url(webpage, url) + if teachable_url: + return self.url_result(teachable_url) + indavideo_urls = IndavideoEmbedIE._extract_urls(webpage) if indavideo_urls: return self.playlist_from_matches( @@ -3098,7 +3158,7 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key()) - sharevideos_urls = [mobj.group('url') for mobj in re.finditer( + sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer( r']+?\bsrc\s*=\s*(["\'])(?P(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1', webpage)] if sharevideos_urls: @@ -3115,6 +3175,11 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key()) + zype_urls = ZypeIE._extract_urls(webpage) + if zype_urls: + return self.playlist_from_matches( + zype_urls, video_id, video_title, ie=ZypeIE.ie_key()) + # Look for HTML5 media entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls') if entries: @@ -3136,9 +3201,13 @@ class GenericIE(InfoExtractor): jwplayer_data = self._find_jwplayer_data( webpage, video_id, transform_source=js_to_json) if jwplayer_data: - info = self._parse_jwplayer_data( - jwplayer_data, video_id, require_title=False, base_url=url) - return merge_dicts(info, info_dict) + try: + info = self._parse_jwplayer_data( + jwplayer_data, video_id, require_title=False, base_url=url) + return merge_dicts(info, info_dict) + except ExtractorError: + # See https://github.com/ytdl-org/youtube-dl/pull/16735 + pass # Video.js embed mobj = re.search( @@ -3152,8 +3221,8 @@ class GenericIE(InfoExtractor): sources = [sources] formats = [] for source in sources: - src = url_or_none(source.get('src')) - if not src: + src = source.get('src') + if not src or not isinstance(src, compat_str): continue src = compat_urlparse.urljoin(url, src) src_type = source.get('type') @@ -3172,8 +3241,8 @@ class GenericIE(InfoExtractor): else: formats.append({ 'url': src, - 'ext': (mimetype2ext(src_type) or - ext if ext in KNOWN_EXTENSIONS else 'mp4'), + 'ext': (mimetype2ext(src_type) + or ext if ext in KNOWN_EXTENSIONS else 'mp4'), }) if formats: self._sort_formats(formats)