[criterion] Rely on _match_id, improve regex and add thumbnail to test
authorDéstin Reed <trox1972@users.noreply.github.com>
Fri, 30 Sep 2016 18:06:08 +0000 (20:06 +0200)
committerDéstin Reed <trox1972@users.noreply.github.com>
Sat, 1 Oct 2016 11:46:48 +0000 (13:46 +0200)
youtube_dl/extractor/criterion.py

index ad32673a812f8bc529993c25feba87ffcf21b3e1..cf6a5d6cbe906443b1db592616cd89926860bbdd 100644 (file)
@@ -1,8 +1,6 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 
@@ -16,20 +14,20 @@ class CriterionIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Le Samouraï',
             'description': 'md5:a2b4b116326558149bef81f76dcbb93f',
+            'thumbnail': 're:^https?://.*\.jpg$',
         }
     }
 
     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(url, video_id)
 
         final_url = self._search_regex(
-            r'so.addVariable\("videoURL", "(.+?)"\)\;', webpage, 'video url')
+            r'so\.addVariable\("videoURL", "(.+?)"\)\;', webpage, 'video url')
         title = self._og_search_title(webpage)
         description = self._html_search_meta('description', webpage)
         thumbnail = self._search_regex(
-            r'so.addVariable\("thumbnailURL", "(.+?)"\)\;',
+            r'so\.addVariable\("thumbnailURL", "(.+?)"\)\;',
             webpage, 'thumbnail url')
 
         return {