X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;ds=sidebyside;f=youtube_dl%2Fextractor%2Fyahoo.py;h=221341c138c76f09186dc06bf19025bdb85e6d87;hb=e80f40e5ca32f2396a034965af86a9b507fad411;hp=1815224944987f6d110ef27a1a10b896143fb00b;hpb=fb6a5b965b9c2ba1c263036d6b353d5ff0a80b05;p=youtube-dl diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index 181522494..221341c13 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -15,7 +15,7 @@ from ..utils import ( class YahooIE(InfoExtractor): IE_DESC = 'Yahoo screen and movies' - _VALID_URL = r'https?://(?:screen|movies)\.yahoo\.com/.*?-(?P[0-9]+)(?:-[a-z]+)?\.html' + _VALID_URL = r'(?Phttps?://(?:screen|movies)\.yahoo\.com/.*?-(?P[0-9]+)(?:-[a-z]+)?\.html)' _TESTS = [ { 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', @@ -38,20 +38,21 @@ class YahooIE(InfoExtractor): }, }, { - 'url': 'https://movies.yahoo.com/video/world-loves-spider-man-190819223.html', - 'md5': '410b7104aa9893b765bc22787a22f3d9', + 'url': 'https://screen.yahoo.com/community/community-sizzle-reel-203225340.html?format=embed', + 'md5': '60e8ac193d8fb71997caa8fce54c6460', 'info_dict': { - 'id': '516ed8e2-2c4f-339f-a211-7a8b49d30845', + 'id': '4fe78544-8d48-39d8-97cd-13f205d9fcdb', 'ext': 'mp4', - 'title': 'The World Loves Spider-Man', - 'description': '''People all over the world are celebrating the release of \"The Amazing Spider-Man 2.\" We're taking a look at the enthusiastic response Spider-Man has received from viewers all over the world.''', + 'title': "Yahoo Saves 'Community'", + 'description': 'md5:4d4145af2fd3de00cbb6c1d664105053', } - } + }, ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + url = mobj.group('url') webpage = self._download_webpage(url, video_id) items_json = self._search_regex( @@ -60,7 +61,8 @@ class YahooIE(InfoExtractor): if items_json is None: CONTENT_ID_REGEXES = [ r'YUI\.namespace\("Media"\)\.CONTENT_ID\s*=\s*"([^"]+)"', - r'root\.App\.Cache\.context\.videoCache\.curVideo = \{"([^"]+)"' + r'root\.App\.Cache\.context\.videoCache\.curVideo = \{"([^"]+)"', + r'"first_videoid"\s*:\s*"([^"]+)"', ] long_id = self._search_regex(CONTENT_ID_REGEXES, webpage, 'content ID') video_id = long_id @@ -70,9 +72,9 @@ class YahooIE(InfoExtractor): # The 'meta' field is not always in the video webpage, we request it # from another page long_id = info['id'] - return self._get_info(long_id, video_id) + return self._get_info(long_id, video_id, webpage) - def _get_info(self, long_id, video_id): + def _get_info(self, long_id, video_id, webpage): query = ('SELECT * FROM yahoo.media.video.streams WHERE id="%s"' ' AND plrs="86Gj0vCaSzV_Iuf6hNylf2" AND region="US"' ' AND protocol="http"' % long_id) @@ -115,7 +117,7 @@ class YahooIE(InfoExtractor): 'title': meta['title'], 'formats': formats, 'description': clean_html(meta['description']), - 'thumbnail': meta.get('thumbnail'), + 'thumbnail': meta['thumbnail'] if meta.get('thumbnail') else self._og_search_thumbnail(webpage), } @@ -139,7 +141,7 @@ class YahooNewsIE(YahooIE): video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) long_id = self._search_regex(r'contentId: \'(.+?)\',', webpage, 'long id') - return self._get_info(long_id, video_id) + return self._get_info(long_id, video_id, webpage) class YahooSearchIE(SearchInfoExtractor):