X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fyahoo.py;h=34e6afb20fb6833ab21501785deb54cf5f0a0e24;hb=a56f9de156c7cca29dfa45de1dadc66e10a265f2;hp=e6d5d7969f27cf4f78768958ea4f0ece53b53b46;hpb=466880f53106a2604235d82f38a9f2f82827c268;p=youtube-dl diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index e6d5d7969..34e6afb20 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -17,7 +17,7 @@ class YahooIE(InfoExtractor): _TESTS = [ { u'url': u'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', - u'file': u'214727115.mp4', + u'file': u'214727115.flv', u'info_dict': { u'title': u'Julian Smith & Travis Legg Watch Julian Smith', u'description': u'Julian and Travis watch Julian Smith', @@ -31,7 +31,7 @@ class YahooIE(InfoExtractor): u'url': u'http://screen.yahoo.com/wired/codefellas-s1-ep12-cougar-lies-103000935.html', u'file': u'103000935.flv', u'info_dict': { - u'title': u'The Cougar Lies with Spanish Moss', + u'title': u'Codefellas - The Cougar Lies with Spanish Moss', u'description': u'Agent Topple\'s mustache does its dirty work, and Nicole brokers a deal for peace. But why is the NSA collecting millions of Instagram brunch photos? And if your waffles have nothing to hide, what are they so worried about?', }, u'params': { @@ -50,6 +50,21 @@ class YahooIE(InfoExtractor): webpage, u'items', flags=re.MULTILINE) items = json.loads(items_json) info = items['mediaItems']['query']['results']['mediaObj'][0] + # The 'meta' field is not always in the video webpage, we request it + # from another page + long_id = info['id'] + query = ('SELECT * FROM yahoo.media.video.streams WHERE id="%s"' + ' AND plrs="86Gj0vCaSzV_Iuf6hNylf2"' % long_id) + data = compat_urllib_parse.urlencode({ + 'q': query, + 'env': 'prod', + 'format': 'json', + }) + query_result_json = self._download_webpage( + 'http://video.query.yahoo.com/v1/public/yql?' + data, + video_id, u'Downloading video info') + query_result = json.loads(query_result_json) + info = query_result['query']['results']['mediaObj'][0] meta = info['meta'] formats = [] @@ -117,7 +132,7 @@ class YahooSearchIE(SearchInfoExtractor): mobj = re.search(r'(?Pscreen\.yahoo\.com/.*?-\d*?\.html)"', r) e = self.url_result('http://' + mobj.group('url'), 'Yahoo') res['entries'].append(e) - if (pagenum * 30 +i >= n) or (m[u'last'] >= (m[u'total'] -1 )): + if (pagenum * 30 +i >= n) or (m[u'last'] >= (m[u'total'] -1)): break return res