[imdb] Simplify
authorPhilipp Hagemeister <phihag@phihag.de>
Tue, 4 Nov 2014 22:26:23 +0000 (23:26 +0100)
committerPhilipp Hagemeister <phihag@phihag.de>
Tue, 4 Nov 2014 22:26:23 +0000 (23:26 +0100)
youtube_dl/extractor/imdb.py

index 4536db3bfca1e1244e70089bea30de9687d923f0..6108ed5526ba37f2e5b8d14b604974ca3c3f8273 100644 (file)
@@ -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)<span itemprop="description">(.*?)</span>',
+            webpage, 'description', fatal=False)
         available_formats = re.findall(
             r'case \'(?P<f_id>.*?)\' :$\s+url = \'(?P<path>.*?)\'', 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')