X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fcriterion.py;h=f7815b905d13910e0a931f2609fa015c9ac3f00a;hb=a61ce71468cb222338ccd8039dc631f3619dc585;hp=a149d29007982e60463ec3c85bf8e239dbc882c0;hpb=7fd930c0c8a33d452027f3844962ab83ee08d807;p=youtube-dl

diff --git a/youtube_dl/extractor/criterion.py b/youtube_dl/extractor/criterion.py
index a149d2900..f7815b905 100644
--- a/youtube_dl/extractor/criterion.py
+++ b/youtube_dl/extractor/criterion.py
@@ -1,40 +1,39 @@
-# -*- coding: utf-8 -*-
-
-import re
+# coding: utf-8
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
 
+
 class CriterionIE(InfoExtractor):
-    _VALID_URL = r'http://www.criterion.com/films/(.*)'
+    _VALID_URL = r'https?://(?:www\.)?criterion\.com/films/(?P<id>[0-9]+)-.+'
     _TEST = {
-        u'url': u'http://www.criterion.com/films/184-le-samourai',
-        u'file': u'184.mp4',
-        u'md5': u'bc51beba55685509883a9a7830919ec3',
-        u'info_dict': {
-            u"title": u"Le Samouraï",
-            u"description" : u"In a career-defining performance, Alain Delon plays a contract killer with samurai instincts. A razor-sharp cocktail of 1940s American gangster cinema and 1960s French pop culture, maverick director Jean-Pierre Melville&#x27;s masterpiece _Le Samouraï_ defines cool. "
+        'url': 'http://www.criterion.com/films/184-le-samourai',
+        'md5': 'bc51beba55685509883a9a7830919ec3',
+        'info_dict': {
+            'id': '184',
+            'ext': 'mp4',
+            'title': 'Le Samouraï',
+            'description': 'md5:a2b4b116326558149bef81f76dcbb93f',
+            'thumbnail': r're:^https?://.*\.jpg$',
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1).split('-')[0]
+        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')
-        title = self._search_regex(r'<meta content="(.+?)" property="og:title" />',
-                                webpage, 'video title')
-        description = self._search_regex(r'<meta name="description" content="(.+?)" />',
-                                webpage, 'video description')
-        thumbnail = self._search_regex(r'so.addVariable\("thumbnailURL", "(.+?)"\)\;',
-                                webpage, 'thumbnail url')
-        ext = final_url.split('.')[-1]
+        final_url = self._search_regex(
+            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\("thumbnailURL", "(.+?)"\)\;',
+            webpage, 'thumbnail url')
 
-        return {'id': video_id,
-                'url' : final_url,
-                'title': title,
-                'ext': ext,
-                'description': description,
-                'thumbnail': thumbnail,
-                }
+        return {
+            'id': video_id,
+            'url': final_url,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+        }