from __future__ import unicode_literals
+import re
+
from .common import InfoExtractor
class SlutloadIE(InfoExtractor):
_VALID_URL = r'^https?://(?:\w+\.)?slutload\.com/video/[^/]+/(?P<id>[^/]+)/?$'
- _TEST = {
+ _TESTS = [{
'url': 'http://www.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/',
'md5': '868309628ba00fd488cf516a113fd717',
'info_dict': {
'ext': 'mp4',
'title': 'virginie baisee en cam',
'age_limit': 18,
- 'thumbnail': 're:https?://.*?\.jpg'
+ 'thumbnail': r're:https?://.*?\.jpg'
}
- }
+ }, {
+ # mobile site
+ 'url': 'http://mobile.slutload.com/video/masturbation-solo/fviFLmc6kzJ/',
+ 'only_matching': True,
+ }]
def _real_extract(self, url):
video_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
+
+ desktop_url = re.sub(r'^(https?://)mobile\.', r'\1', url)
+ webpage = self._download_webpage(desktop_url, video_id)
video_title = self._html_search_regex(r'<h1><strong>([^<]+)</strong>',
webpage, 'title').strip()