from __future__ import unicode_literals
+import re
+
from ..utils import (
int_or_none,
str_to_int,
'title': 'Kasia music video',
'age_limit': 18,
'duration': 230,
- }
+ 'categories': ['Teen'],
+ 'tags': ['dancing'],
+ },
}, {
'url': 'http://www.tube8.com/shemale/teen/blonde-cd-gets-kidnapped-by-two-blacks-and-punished-for-being-a-slutty-girl/19569151/',
'only_matching': True,
}]
+ @staticmethod
+ def _extract_urls(webpage):
+ return re.findall(
+ r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?tube8\.com/embed/(?:[^/]+/)+\d+)',
+ webpage)
+
def _real_extract(self, url):
webpage, info = self._extract_info(url)
r'<span id="allCommentsCount">(\d+)</span>',
webpage, 'comment count', fatal=False))
+ category = self._search_regex(
+ r'Category:\s*</strong>\s*<a[^>]+href=[^>]+>([^<]+)',
+ webpage, 'category', fatal=False)
+ categories = [category] if category else None
+
+ tags_str = self._search_regex(
+ r'(?s)Tags:\s*</strong>(.+?)</(?!a)',
+ webpage, 'tags', fatal=False)
+ tags = [t for t in re.findall(
+ r'<a[^>]+href=[^>]+>([^<]+)', tags_str)] if tags_str else None
+
info.update({
'description': description,
'uploader': uploader,
'like_count': like_count,
'dislike_count': dislike_count,
'comment_count': comment_count,
+ 'categories': categories,
+ 'tags': tags,
})
return info