etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-23 02:25:11 +00:00
Code Issues Projects Releases Wiki Activity

[moviefap] Allow non-critical fields to change without breaking extraction

Browse source
This commit is contained in:
George Brighton 2015-06-27 20:36:46 +01:00
parent a8e6f30d8e
commit d16ef949ca
1 changed files with 7 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
youtube_dl/extractor/moviefap.py
View file

@ -89,14 +89,14 @@ def _real_extract(self, url):
'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