mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-12-15 15:52:38 +00:00
[moviefap] Allow non-critical fields to change without breaking extraction
This commit is contained in:
parent
a8e6f30d8e
commit
d16ef949ca
1 changed files with 7 additions and 7 deletions
|
@ -89,14 +89,14 @@ class MovieFapIE(InfoExtractor):
|
||||||
'display_id': re.compile(self._VALID_URL).match(url).group('name'),
|
'display_id': re.compile(self._VALID_URL).match(url).group('name'),
|
||||||
'thumbnails': self.__get_thumbnail_data(xml),
|
'thumbnails': self.__get_thumbnail_data(xml),
|
||||||
'thumbnail': xml.find('startThumb').text,
|
'thumbnail': xml.find('startThumb').text,
|
||||||
'description': self._html_search_regex(r'name="description" value="(.*?)"', webpage, 'description'),
|
'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'),
|
'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')),
|
'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')),
|
'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')),
|
'comment_count': str_to_int(self._html_search_regex(r'<span id="comCount">([0-9]+)</span>', webpage, 'comment_count', fatal=False)),
|
||||||
'age_limit': 18,
|
'age_limit': 18,
|
||||||
'webpage_url': self._html_search_regex(r'name="link" value="(.*?)"', webpage, 'webpage_url'),
|
'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').split(', ')
|
'categories': self._html_search_regex(r'</div>\s*(.*?)\s*<br>', webpage, 'categories', fatal=False).split(', ')
|
||||||
}
|
}
|
||||||
|
|
||||||
# find and add the format
|
# find and add the format
|
||||||
|
|
Loading…
Reference in a new issue