From 11fba1751d5a43491254a3f54fcd0903a40d1a35 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 4 Nov 2014 23:26:23 +0100 Subject: [PATCH] [imdb] Simplify --- youtube_dl/extractor/imdb.py | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py index 4536db3bf..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) @@ -73,9 +73,7 @@ class ImdbListIE(InfoExtractor): } 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')