[criterion] Simplify and modernize

youtube_dl/extractor/criterion.py

@@ -1,40 +1,43 @@
 # -*- coding: utf-8 -*-
+from __future__ import unicode_literals
 
 import re
 
 from .common import InfoExtractor
-from ..utils import determine_ext
+
 
 class CriterionIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.criterion\.com/films/(\d*)-.+'
+    _VALID_URL = r'https?://www\.criterion\.com/films/(?P<id>[0-9]+)-.+'
     _TEST = {
-        u'url': u'http://www.criterion.com/films/184-le-samourai',
+        'url': 'http://www.criterion.com/films/184-le-samourai',
-        u'file': u'184.mp4',
+        'md5': 'bc51beba55685509883a9a7830919ec3',
-        u'md5': u'bc51beba55685509883a9a7830919ec3',
+        'info_dict': {
-        u'info_dict': {
+            'id': '184',
-            u"title": u"Le Samouraï",
+            'ext': 'mp4',
-            u"description" : u'md5:a2b4b116326558149bef81f76dcbb93f',
+            'title': 'Le Samouraï',
+            'description': 'md5:a2b4b116326558149bef81f76dcbb93f',
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
+        video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
 
-        final_url = self._search_regex(r'so.addVariable\("videoURL", "(.+?)"\)\;',
+        final_url = self._search_regex(
-                                webpage, 'video url')
+            r'so.addVariable\("videoURL", "(.+?)"\)\;', webpage, 'video url')
-        title = self._html_search_regex(r'<meta content="(.+?)" property="og:title" />',
+        title = self._og_search_title(webpage)
-                                webpage, 'video title')
+        description = self._html_search_regex(
-        description = self._html_search_regex(r'<meta name="description" content="(.+?)" />',
+            r'<meta name="description" content="(.+?)" />',
-                                webpage, 'video description')
+            webpage, 'video description')
-        thumbnail = self._search_regex(r'so.addVariable\("thumbnailURL", "(.+?)"\)\;',
+        thumbnail = self._search_regex(
-                                webpage, 'thumbnail url')
+            r'so.addVariable\("thumbnailURL", "(.+?)"\)\;',
+            webpage, 'thumbnail url')
 
-        return {'id': video_id,
+        return {
-                'url' : final_url,
+            'id': video_id,
-                'title': title,
+            'url': final_url,
-                'ext': determine_ext(final_url),
+            'title': title,
-                'description': description,
+            'description': description,
-                'thumbnail': thumbnail,
+            'thumbnail': thumbnail,
-                }
+        }