- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('videoid')
- url = 'http://www.' + mobj.group('url')
-
- req = compat_urllib_request.Request(url)
- req.add_header('Cookie', 'age_verified=1')
- webpage = self._download_webpage(req, video_id)
-
- video_title = self._html_search_regex(r'videotitle ="([^"]+)', webpage, u'title')
- video_description = self._html_search_regex(r'>Description:</strong>(.+?)<', webpage, u'description', fatal=False)
- video_uploader = self._html_search_regex(r'>Submitted by:</strong>(?:\w|<[^>]*>)*(.+?)<', webpage, u'uploader', fatal=False)
- thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, u'thumbnail', fatal=False)
- if thumbnail:
- thumbnail = thumbnail.replace('\\/', '/')
-
- video_url = self._html_search_regex(r'"video_url":"([^"]+)', webpage, u'video_url')
- if webpage.find('"encrypted":true')!=-1:
- password = self._html_search_regex(r'"video_title":"([^"]+)', webpage, u'password')
- video_url = aes_decrypt_text(video_url, password, 32).decode('utf-8')
- path = compat_urllib_parse_urlparse( video_url ).path
- extension = os.path.splitext( path )[1][1:]
- format = path.split('/')[4].split('_')[:2]
- format = "-".join( format )
-
- return {
- 'id': video_id,
- 'uploader': video_uploader,
- 'title': video_title,
- 'thumbnail': thumbnail,
- 'description': video_description,
- 'url': video_url,
- 'ext': extension,
- 'format': format,
- 'format_id': format,
- }
+ webpage, info = self._extract_info(url)
+
+ if not info['title']:
+ info['title'] = self._html_search_regex(
+ r'videoTitle\s*=\s*"([^"]+)', webpage, 'title')
+
+ description = self._html_search_regex(
+ r'(?s)Description:</dt>\s*<dd>(.+?)</dd>', webpage, 'description', fatal=False)
+ uploader = self._html_search_regex(
+ r'<span class="username">\s*(.+?)\s*<',
+ webpage, 'uploader', fatal=False)
+
+ like_count = int_or_none(self._search_regex(
+ r'rupVar\s*=\s*"(\d+)"', webpage, 'like count', fatal=False))
+ dislike_count = int_or_none(self._search_regex(
+ r'rdownVar\s*=\s*"(\d+)"', webpage, 'dislike count', fatal=False))
+ view_count = str_to_int(self._search_regex(
+ r'Views:\s*</dt>\s*<dd>([\d,\.]+)',
+ webpage, 'view count', fatal=False))
+ comment_count = str_to_int(self._search_regex(
+ r'<span id="allCommentsCount">(\d+)</span>',
+ webpage, 'comment count', fatal=False))
+
+ category = self._search_regex(
+ r'Category:\s*</dt>\s*<dd>\s*<a[^>]+href=[^>]+>([^<]+)',
+ webpage, 'category', fatal=False)
+ categories = [category] if category else None
+
+ tags_str = self._search_regex(
+ r'(?s)Tags:\s*</dt>\s*<dd>(.+?)</(?!a)',
+ webpage, 'tags', fatal=False)
+ tags = [t for t in re.findall(
+ r'<a[^>]+href=[^>]+>([^<]+)', tags_str)] if tags_str else None
+
+ info.update({
+ 'description': description,
+ 'uploader': uploader,
+ 'view_count': view_count,
+ 'like_count': like_count,
+ 'dislike_count': dislike_count,
+ 'comment_count': comment_count,
+ 'categories': categories,
+ 'tags': tags,
+ })
+
+ return info