X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fgeneric.py;h=d09e856652e2536fd475ad5fb75bae0854ab725e;hb=8001607e903a5ccaff76908f23bece08818743c0;hp=ec4d0c210431a9afe772241dea2384cff8526985;hpb=2fe1b5bd2add12d70717878704cd3f811af5d22c;p=youtube-dl diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index ec4d0c210..d09e85665 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -36,6 +36,7 @@ from .smotri import SmotriIE from .condenast import CondeNastIE from .udn import UDNEmbedIE from .senateisvp import SenateISVPIE +from .bliptv import BlipTVIE class GenericIE(InfoExtractor): @@ -412,6 +413,19 @@ class GenericIE(InfoExtractor): 'thumbnail': 're:^https?://.*\.jpg$', }, }, + # MLB articles + { + 'url': 'http://m.mlb.com/news/article/118550098/blue-jays-kevin-pillar-goes-spidey-up-the-wall-to-rob-tim-beckham-of-a-homer', + 'md5': 'b190e70141fb9a1552a85426b4da1b5d', + 'info_dict': { + 'id': '75609783', + 'ext': 'mp4', + 'title': 'Must C: Pillar climbs for catch', + 'description': '4/15/15: Blue Jays outfielder Kevin Pillar continues his defensive dominance by climbing the wall in left to rob Tim Beckham of a home run', + 'timestamp': 1429124820, + 'upload_date': '20150415', + } + }, # Wistia embed { 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson', @@ -1073,12 +1087,9 @@ class GenericIE(InfoExtractor): } # Look for embedded blip.tv player - mobj = re.search(r']*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') + bliptv_url = BlipTVIE._extract_url(webpage) + if bliptv_url: + return self.url_result(bliptv_url, 'BlipTV') # Look for embedded condenast player matches = re.findall( @@ -1291,6 +1302,10 @@ class GenericIE(InfoExtractor): mobj = re.search( r']+?src=(["\'])(?Phttps?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1', webpage) + if not mobj: + mobj = re.search( + r'data-video-link=["\'](?Phttp://m.mlb.com/video/[^"\']+)', + webpage) if mobj is not None: return self.url_result(mobj.group('url'), 'MLB')