etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-01 03:43:02 +00:00
Code Issues Projects Releases Wiki Activity

[motherless] Fix extraction (closes #24699)

Browse source
This commit is contained in:
Sergey M․ 2020-04-09 02:11:19 +07:00
parent c9595ee780
commit dcc8522fdb
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 9 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
youtube_dl/extractor/motherless.py
View file

@ -26,7 +26,7 @@ class MotherlessIE(InfoExtractor):
'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'], 'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'],
'upload_date': '20100913', 'upload_date': '20100913',
'uploader_id': 'famouslyfuckedup', 'uploader_id': 'famouslyfuckedup',
'thumbnail': r're:http://.*\.jpg', 'thumbnail': r're:https?://.*\.jpg',
'age_limit': 18, 'age_limit': 18,
} }
}, { }, {
@ -40,7 +40,7 @@ class MotherlessIE(InfoExtractor):
'game', 'hairy'], 'game', 'hairy'],
'upload_date': '20140622', 'upload_date': '20140622',
'uploader_id': 'Sulivana7x', 'uploader_id': 'Sulivana7x',
'thumbnail': r're:http://.*\.jpg', 'thumbnail': r're:https?://.*\.jpg',
'age_limit': 18, 'age_limit': 18,
}, },
'skip': '404', 'skip': '404',
@ -54,7 +54,7 @@ class MotherlessIE(InfoExtractor):
'categories': ['superheroine heroine superher'], 'categories': ['superheroine heroine superher'],
'upload_date': '20140827', 'upload_date': '20140827',
'uploader_id': 'shade0230', 'uploader_id': 'shade0230',
'thumbnail': r're:http://.*\.jpg', 'thumbnail': r're:https?://.*\.jpg',
'age_limit': 18, 'age_limit': 18,
} }
}, { }, {
@ -76,7 +76,8 @@ def _real_extract(self, url):
raise ExtractorError('Video %s is for friends only' % video_id, expected=True) raise ExtractorError('Video %s is for friends only' % video_id, expected=True)
title = self._html_search_regex( title = self._html_search_regex(
r'id="view-upload-title">\s+([^<]+)<', webpage, 'title') (r'(?s)<div[^>]+\bclass=["\']media-meta-title[^>]+>(.+?)</div>',
r'id="view-upload-title">\s+([^<]+)<'), webpage, 'title')
video_url = (self._html_search_regex( video_url = (self._html_search_regex(
(r'setup\(\{\s*["\']file["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', (r'setup\(\{\s*["\']file["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1',
r'fileurl\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1'), r'fileurl\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1'),
@ -84,14 +85,15 @@ def _real_extract(self, url):
or 'http://cdn4.videos.motherlessmedia.com/videos/%s.mp4?fs=opencloud' % video_id) or 'http://cdn4.videos.motherlessmedia.com/videos/%s.mp4?fs=opencloud' % video_id)
age_limit = self._rta_search(webpage) age_limit = self._rta_search(webpage)
view_count = str_to_int(self._html_search_regex( view_count = str_to_int(self._html_search_regex(
r'<strong>Views</strong>\s+([^<]+)<', (r'>(\d+)\s+Views<', r'<strong>Views</strong>\s+([^<]+)<'),
webpage, 'view count', fatal=False)) webpage, 'view count', fatal=False))
like_count = str_to_int(self._html_search_regex( like_count = str_to_int(self._html_search_regex(
r'<strong>Favorited</strong>\s+([^<]+)<', (r'>(\d+)\s+Favorites<', r'<strong>Favorited</strong>\s+([^<]+)<'),
webpage, 'like count', fatal=False)) webpage, 'like count', fatal=False))
upload_date = self._html_search_regex( upload_date = self._html_search_regex(
r'<strong>Uploaded</strong>\s+([^<]+)<', webpage, 'upload date') (r'class=["\']count[^>]+>(\d+\s+[a-zA-Z]{3}\s+\d{4})<',
r'<strong>Uploaded</strong>\s+([^<]+)<'), webpage, 'upload date')
if 'Ago' in upload_date: if 'Ago' in upload_date:
days = int(re.search(r'([0-9]+)', upload_date).group(1)) days = int(re.search(r'([0-9]+)', upload_date).group(1))
upload_date = (datetime.datetime.now() - datetime.timedelta(days=days)).strftime('%Y%m%d') upload_date = (datetime.datetime.now() - datetime.timedelta(days=days)).strftime('%Y%m%d')