X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fimdb.py;h=6108ed5526ba37f2e5b8d14b604974ca3c3f8273;hb=9908e0352872b252494747346589922358aa0375;hp=7cee505c085cd1601e0b8ce3ab689795b4f94dfd;hpb=c1e60cc2bf4d0130dac154e9014913e7d63d25ff;p=youtube-dl diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py index 7cee505c0..6108ed552 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) @@ -63,11 +63,17 @@ class ImdbListIE(InfoExtractor): IE_NAME = 'imdb:list' IE_DESC = 'Internet Movie Database lists' _VALID_URL = r'http://www\.imdb\.com/list/(?P[\da-zA-Z_-]{11})' + _TEST = { + 'url': 'http://www.imdb.com/list/JFs9NWw6XI0', + 'info_dict': { + 'id': 'JFs9NWw6XI0', + 'title': 'March 23, 2012 Releases', + }, + 'playlist_count': 7, + } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - list_id = mobj.group('id') - + list_id = self._match_id(url) webpage = self._download_webpage(url, list_id) entries = [ self.url_result('http://www.imdb.com' + m, 'Imdb')