X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fgeneric.py;h=43218c3a43eef6afc1ea00431c4a398624007e79;hb=b65e3b0636c4b992f3187bff7d5268c6891023a6;hp=0292e0458ac8ccd28f1c4853973f2852c281644f;hpb=aee36ca832ec3a5696c40707098d97be0353e997;p=youtube-dl diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 0292e0458..43218c3a4 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -32,6 +32,7 @@ from ..utils import ( unified_strdate, unsmuggle_url, UnsupportedError, + url_or_none, xpath_text, ) from .commonprotocols import RtmpIE @@ -110,6 +111,9 @@ from .xfileshare import XFileShareIE from .cloudflarestream import CloudflareStreamIE from .peertube import PeerTubeIE from .indavideo import IndavideoEmbedIE +from .apa import APAIE +from .foxnews import FoxNewsIE +from .viqeo import ViqeoIE class GenericIE(InfoExtractor): @@ -1393,17 +1397,6 @@ class GenericIE(InfoExtractor): 'skip_download': True, }, }, - # SVT embed - { - 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun', - 'info_dict': { - 'id': '2900353', - 'ext': 'flv', - 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)', - 'duration': 27, - 'age_limit': 0, - }, - }, # Crooks and Liars embed { 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists', @@ -2041,6 +2034,23 @@ class GenericIE(InfoExtractor): 'skip_download': True, }, }, + { + # APA embed via JWPlatform embed + 'url': 'http://www.vol.at/blue-man-group/5593454', + 'info_dict': { + 'id': 'jjv85FdZ', + 'ext': 'mp4', + 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview', + 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', + 'thumbnail': r're:^https?://.*\.jpg$', + 'duration': 254, + 'timestamp': 1519211149, + 'upload_date': '20180221', + }, + 'params': { + 'skip_download': True, + }, + }, { 'url': 'http://share-videos.se/auto/video/83645793?uid=13', 'md5': 'b68d276de422ab07ee1d49388103f457', @@ -2051,6 +2061,15 @@ class GenericIE(InfoExtractor): }, 'skip': 'TODO: fix nested playlists processing in tests', }, + { + # Viqeo embeds + 'url': 'https://viqeo.tv/', + 'info_dict': { + 'id': 'viqeo', + 'title': 'All-new video platform', + }, + 'playlist_count': 6, + }, # { # # TODO: find another test # # http://schema.org/VideoObject @@ -3058,7 +3077,7 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key()) - peertube_urls = PeerTubeIE._extract_urls(webpage) + peertube_urls = PeerTubeIE._extract_urls(webpage, url) if peertube_urls: return self.playlist_from_matches( peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key()) @@ -3068,6 +3087,16 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key()) + apa_urls = APAIE._extract_urls(webpage) + if apa_urls: + return self.playlist_from_matches( + apa_urls, video_id, video_title, ie=APAIE.ie_key()) + + foxnews_urls = FoxNewsIE._extract_urls(webpage) + if foxnews_urls: + 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( r']+?\bsrc\s*=\s*(["\'])(?P(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1', webpage)] @@ -3075,6 +3104,11 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( sharevideos_urls, video_id, video_title) + viqeo_urls = ViqeoIE._extract_urls(webpage) + if viqeo_urls: + return self.playlist_from_matches( + viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key()) + # Look for HTML5 media entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls') if entries: @@ -3112,8 +3146,8 @@ class GenericIE(InfoExtractor): sources = [sources] formats = [] for source in sources: - src = source.get('src') - if not src or not isinstance(src, compat_str): + src = url_or_none(source.get('src')) + if not src: continue src = compat_urlparse.urljoin(url, src) src_type = source.get('type')