X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fimdb.py;h=f2c1c10f5c1dec44129ea4cd7d4cff69c7c07206;hb=1139a54d9bb9d214a8451301a44af6d03dd450b7;hp=4536db3bfca1e1244e70089bea30de9687d923f0;hpb=2eebf060af9fe284cbcb839886b27030553fb48d;p=youtube-dl diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py index 4536db3bf..f2c1c10f5 100644 --- a/youtube_dl/extractor/imdb.py +++ b/youtube_dl/extractor/imdb.py @@ -6,7 +6,6 @@ import json from .common import InfoExtractor from ..utils import ( compat_urlparse, - get_element_by_attribute, ) @@ -27,10 +26,11 @@ class ImdbIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage('http://www.imdb.com/video/imdb/vi%s' % video_id, video_id) - descr = get_element_by_attribute('itemprop', 'description', webpage) + descr = self._html_search_regex( + r'(?s)(.*?)', + webpage, 'description', fatal=False) available_formats = re.findall( r'case \'(?P.*?)\' :$\s+url = \'(?P.*?)\'', webpage, flags=re.MULTILINE) @@ -71,11 +71,9 @@ class ImdbListIE(InfoExtractor): }, 'playlist_count': 7, } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - list_id = mobj.group('id') + def _real_extract(self, url): + list_id = self._match_id(url) webpage = self._download_webpage(url, list_id) entries = [ self.url_result('http://www.imdb.com' + m, 'Imdb')