1
0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-05 12:38:05 +01:00
youtube-dl/youtube_dl/extractor/slutload.py

45 lines
1.4 KiB
Python
Raw Normal View History

2014-05-13 10:04:29 +02:00
from __future__ import unicode_literals
2014-05-12 10:28:56 +02:00
import re
from .common import InfoExtractor
2014-05-13 10:04:29 +02:00
2014-05-12 10:28:56 +02:00
class SlutloadIE(InfoExtractor):
2014-05-13 10:04:29 +02:00
_VALID_URL = r'^https?://(?:\w+\.)?slutload\.com/video/[^/]+/(?P<id>[^/]+)/?$'
2014-05-12 10:28:56 +02:00
_TEST = {
2014-05-13 10:04:29 +02:00
'url': 'http://www.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/',
'md5': '0cf531ae8006b530bd9df947a6a0df77',
'info_dict': {
'id': 'TD73btpBqSxc',
'ext': 'mp4',
"title": "virginie baisee en cam",
"age_limit": 18,
'thumbnail': 're:https?://.*?\.jpg'
2014-05-12 10:28:56 +02:00
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
2014-05-13 10:04:29 +02:00
video_id = mobj.group('id')
2014-05-12 10:28:56 +02:00
webpage = self._download_webpage(url, video_id)
video_title = self._html_search_regex(r'<h1><strong>([^<]+)</strong>',
2014-11-23 21:39:15 +01:00
webpage, 'title').strip()
2014-05-13 10:04:29 +02:00
video_url = self._html_search_regex(
r'(?s)<div id="vidPlayer"\s+data-url="([^"]+)"',
webpage, 'video URL')
thumbnail = self._html_search_regex(
r'(?s)<div id="vidPlayer"\s+.*?previewer-file="([^"]+)"',
webpage, 'thumbnail', fatal=False)
return {
'id': video_id,
'url': video_url,
'title': video_title,
'thumbnail': thumbnail,
'age_limit': 18
}