From: George Brighton Date: Sat, 27 Jun 2015 19:36:46 +0000 (+0100) Subject: [moviefap] Allow non-critical fields to change without breaking extraction X-Git-Url: http://git.oshgnacknak.de/?a=commitdiff_plain;h=d16ef949ca94ffb998c4db5a8367f0b367d659e3;p=youtube-dl [moviefap] Allow non-critical fields to change without breaking extraction --- diff --git a/youtube_dl/extractor/moviefap.py b/youtube_dl/extractor/moviefap.py index 1985c53c0..23575d30a 100644 --- a/youtube_dl/extractor/moviefap.py +++ b/youtube_dl/extractor/moviefap.py @@ -89,14 +89,14 @@ class MovieFapIE(InfoExtractor): 'display_id': re.compile(self._VALID_URL).match(url).group('name'), 'thumbnails': self.__get_thumbnail_data(xml), 'thumbnail': xml.find('startThumb').text, - 'description': self._html_search_regex(r'name="description" value="(.*?)"', webpage, 'description'), - 'uploader_id': self._html_search_regex(r'name="username" value="(.*?)"', webpage, 'uploader_id'), - 'view_count': str_to_int(self._html_search_regex(r'
Views ([0-9]+)', webpage, 'view_count')), - 'average_rating': float(self._html_search_regex(r'Current Rating
(.*?)', webpage, 'average_rating')), - 'comment_count': str_to_int(self._html_search_regex(r'([0-9]+)', webpage, 'comment_count')), + 'description': self._html_search_regex(r'name="description" value="(.*?)"', webpage, 'description', fatal=False), + 'uploader_id': self._html_search_regex(r'name="username" value="(.*?)"', webpage, 'uploader_id', fatal=False), + 'view_count': str_to_int(self._html_search_regex(r'
Views ([0-9]+)', webpage, 'view_count, fatal=False')), + 'average_rating': float(self._html_search_regex(r'Current Rating
(.*?)', webpage, 'average_rating', fatal=False)), + 'comment_count': str_to_int(self._html_search_regex(r'([0-9]+)', webpage, 'comment_count', fatal=False)), 'age_limit': 18, - 'webpage_url': self._html_search_regex(r'name="link" value="(.*?)"', webpage, 'webpage_url'), - 'categories': self._html_search_regex(r'\s*(.*?)\s*
', webpage, 'categories').split(', ') + 'webpage_url': self._html_search_regex(r'name="link" value="(.*?)"', webpage, 'webpage_url', fatal=False), + 'categories': self._html_search_regex(r'\s*(.*?)\s*
', webpage, 'categories', fatal=False).split(', ') } # find and add the format