X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fcriterion.py;h=31fe3d57b31ccddccadbbcbb66244ef6aea63cd2;hb=948bcc60df48415ddbf3d7ea03bc3af53a9d928d;hp=d1fe7fc3c10485fa167eb4c556955afb05b3bbfe;hpb=159736c1b81e2897e91369f399eceacaa09192b4;p=youtube-dl

diff --git a/youtube_dl/extractor/criterion.py b/youtube_dl/extractor/criterion.py
index d1fe7fc3c..31fe3d57b 100644
--- a/youtube_dl/extractor/criterion.py
+++ b/youtube_dl/extractor/criterion.py
@@ -3,29 +3,38 @@
 import re
 
 from .common import InfoExtractor
+from ..utils import determine_ext
 
 class CriterionIE(InfoExtractor):
-    _VALID_URL = r'http://www.criterion.com/films/(.*)'
+    _VALID_URL = r'https?://www\.criterion\.com/films/(\d*)-.+'
+    _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'md5:a2b4b116326558149bef81f76dcbb93f',
+        }
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1).split('-')[0]
+        video_id = mobj.group(1)
         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" />',
+        title = self._html_search_regex(r'<meta content="(.+?)" property="og:title" />',
                                 webpage, 'video title')
-        description = self._search_regex(r'<meta name="description" content="(.+?)" />',
+        description = self._html_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]
 
         return {'id': video_id,
                 'url' : final_url,
                 'title': title,
-                'ext': ext,
+                'ext': determine_ext(final_url),
                 'description': description,
                 'thumbnail': thumbnail,
                 }