Merge tag 'upstream/2017.02.24.1'

[youtubedl] / youtube_dl / extractor / xnxx.py

diff --git a/youtube_dl/extractor/xnxx.py b/youtube_dl/extractor/xnxx.py
index 1177a4b14ec04748bebb5ab17db2f0a29c68ca5c..e0a6255dc4df8f2a2bd56ffcf1363089a08e6aea 100644 (file)
--- a/youtube_dl/extractor/xnxx.py
+++ b/youtube_dl/extractor/xnxx.py
@@ -1,55 +1,48 @@
-import re
+# coding: utf-8
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import (
-    compat_urllib_parse,
-
-    ExtractorError,
-)
+from ..compat import compat_urllib_parse_unquote
 
 
 class XNXXIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:video|www)\.xnxx\.com/video([0-9]+)/(.*)'
-    VIDEO_URL_RE = r'flv_url=(.*?)&'
-    VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM'
-    VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&amp;'
-    _TEST = {
-        u'url': u'http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_',
-        u'file': u'1135332.flv',
-        u'md5': u'0831677e2b4761795f68d417e0b7b445',
-        u'info_dict': {
-            u"title": u"lida \u00bb Naked Funny Actress  (5)",
-            u"age_limit": 18,
-        }
-    }
+    _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': '55awb78',
+            'ext': 'flv',
+            '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)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
-        video_id = mobj.group(1)
-
-        # Get webpage content
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        video_url = self._search_regex(self.VIDEO_URL_RE,
-            webpage, u'video URL')
-        video_url = compat_urllib_parse.unquote(video_url)
+        video_url = self._search_regex(r'flv_url=(.*?)&amp;',
+                                       webpage, 'video URL')
+        video_url = compat_urllib_parse_unquote(video_url)
 
-        video_title = self._html_search_regex(self.VIDEO_TITLE_RE,
-            webpage, u'title')
+        video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XNXX.COM',
+                                              webpage, 'title')
 
-        video_thumbnail = self._search_regex(self.VIDEO_THUMB_RE,
-            webpage, u'thumbnail', fatal=False)
+        video_thumbnail = self._search_regex(r'url_bigthumb=(.*?)&amp;',
+                                             webpage, 'thumbnail', fatal=False)
 
-        return [{
+        return {
             'id': video_id,
             'url': video_url,
-            'uploader': None,
-            'upload_date': None,
             'title': video_title,
             'ext': 'flv',
             'thumbnail': video_thumbnail,
-            'description': None,
             'age_limit': 18,
-        }]
+        }