from .common import InfoExtractor
from ..utils import (
+ ExtractorError,
str_to_int,
unified_strdate,
)
'thumbnail': 're:http://.*\.jpg',
'age_limit': 18,
}
+ },
+ {
+ # no keywords
+ 'url': 'http://motherless.com/8B4BBC1',
+ 'only_matching': True,
}
]
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
+ if any(p in webpage for p in (
+ '<title>404 - MOTHERLESS.COM<',
+ ">The page you're looking for cannot be found.<")):
+ raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+
title = self._html_search_regex(
r'id="view-upload-title">\s+([^<]+)<', webpage, 'title')
video_url = self._html_search_regex(
r'"thumb-member-username">\s+<a href="/m/([^"]+)"',
webpage, 'uploader_id')
- categories = self._html_search_meta('keywords', webpage)
+ categories = self._html_search_meta('keywords', webpage, default=None)
if categories:
categories = [cat.strip() for cat in categories.split(',')]