]> gitweb @ CieloNegro.org - youtube-dl.git/commitdiff
[moviefap] Allow non-critical fields to change without breaking extraction
authorGeorge Brighton <george@gebn.co.uk>
Sat, 27 Jun 2015 19:36:46 +0000 (20:36 +0100)
committerGeorge Brighton <george@gebn.co.uk>
Sat, 27 Jun 2015 19:36:46 +0000 (20:36 +0100)
youtube_dl/extractor/moviefap.py

index 1985c53c00682524b07e9bdcb0fec515e9be81dc..23575d30a80344ce8e2477312602ae47f54c50ef 100644 (file)
@@ -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'<br>Views <strong>([0-9]+)</strong>', webpage, 'view_count')),
-            'average_rating': float(self._html_search_regex(r'Current Rating<br> <strong>(.*?)</strong>', webpage, 'average_rating')),
-            'comment_count': str_to_int(self._html_search_regex(r'<span id="comCount">([0-9]+)</span>', 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'<br>Views <strong>([0-9]+)</strong>', webpage, 'view_count, fatal=False')),
+            'average_rating': float(self._html_search_regex(r'Current Rating<br> <strong>(.*?)</strong>', webpage, 'average_rating', fatal=False)),
+            'comment_count': str_to_int(self._html_search_regex(r'<span id="comCount">([0-9]+)</span>', 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'</div>\s*(.*?)\s*<br>', webpage, 'categories').split(', ')
+            'webpage_url': self._html_search_regex(r'name="link" value="(.*?)"', webpage, 'webpage_url', fatal=False),
+            'categories': self._html_search_regex(r'</div>\s*(.*?)\s*<br>', webpage, 'categories', fatal=False).split(', ')
         }
 
         # find and add the format