Unify coding cookie
[youtube-dl] / youtube_dl / extractor / xnxx.py
index 7a73b243080406b29b6c4a17d50a3e4d1ac023cb..e0a6255dc4df8f2a2bd56ffcf1363089a08e6aea 100644 (file)
@@ -1,43 +1,42 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..utils import (
-    compat_urllib_parse,
-)
+from ..compat import compat_urllib_parse_unquote
 
 
 class XNXXIE(InfoExtractor):
-    _VALID_URL = r'^https?://(?:video|www)\.xnxx\.com/video(?P<id>[0-9]+)/(.*)'
-    _TEST = {
-        'url': 'http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_',
-        'md5': '0831677e2b4761795f68d417e0b7b445',
+    _VALID_URL = r'https?://(?:video|www)\.xnxx\.com/video-?(?P<id>[0-9a-z]+)/'
+    _TESTS = [{
+        'url': 'http://www.xnxx.com/video-55awb78/skyrim_test_video',
+        'md5': 'ef7ecee5af78f8b03dca2cf31341d3a0',
         'info_dict': {
-            'id': '1135332',
+            'id': '55awb78',
             'ext': 'flv',
-            'title': 'lida ยป Naked Funny Actress  (5)',
+            'title': 'Skyrim Test Video',
             'age_limit': 18,
-        }
-    }
+        },
+    }, {
+        'url': 'http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.xnxx.com/video-55awb78/',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
-        # Get webpage content
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         video_url = self._search_regex(r'flv_url=(.*?)&amp;',
-            webpage, 'video URL')
-        video_url = compat_urllib_parse.unquote(video_url)
+                                       webpage, 'video URL')
+        video_url = compat_urllib_parse_unquote(video_url)
 
         video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XNXX.COM',
-            webpage, 'title')
+                                              webpage, 'title')
 
         video_thumbnail = self._search_regex(r'url_bigthumb=(.*?)&amp;',
-            webpage, 'thumbnail', fatal=False)
+                                             webpage, 'thumbnail', fatal=False)
 
         return {
             'id': video_id,