1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-11-30 12:22:57 +08:00
youtube-dl/youtube_dl/extractor/xnxx.py

43 lines
1.4 KiB
Python
Raw Normal View History

2014-03-10 00:22:53 +08:00
# encoding: utf-8
from __future__ import unicode_literals
2013-06-24 04:01:57 +08:00
from .common import InfoExtractor
2015-07-18 01:49:38 +08:00
from ..compat import compat_urllib_parse_unquote
2013-06-24 04:01:57 +08:00
class XNXXIE(InfoExtractor):
2014-03-10 00:22:53 +08:00
_VALID_URL = r'^https?://(?:video|www)\.xnxx\.com/video(?P<id>[0-9]+)/(.*)'
2013-06-28 02:46:46 +08:00
_TEST = {
2014-03-10 00:22:53 +08:00
'url': 'http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_',
'md5': '0831677e2b4761795f68d417e0b7b445',
'info_dict': {
'id': '1135332',
'ext': 'flv',
'title': 'lida » Naked Funny Actress (5)',
'age_limit': 18,
2013-06-28 02:46:46 +08:00
}
}
2013-06-24 04:01:57 +08:00
def _real_extract(self, url):
video_id = self._match_id(url)
2013-06-24 04:01:57 +08:00
webpage = self._download_webpage(url, video_id)
2014-03-10 00:22:53 +08:00
video_url = self._search_regex(r'flv_url=(.*?)&amp;',
2014-11-24 04:39:15 +08:00
webpage, 'video URL')
2015-07-18 01:49:38 +08:00
video_url = compat_urllib_parse_unquote(video_url)
2013-06-24 04:01:57 +08:00
2014-03-10 00:22:53 +08:00
video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XNXX.COM',
2014-11-24 04:39:15 +08:00
webpage, 'title')
2013-06-24 04:01:57 +08:00
2014-03-10 00:22:53 +08:00
video_thumbnail = self._search_regex(r'url_bigthumb=(.*?)&amp;',
2014-11-24 04:39:15 +08:00
webpage, 'thumbnail', fatal=False)
2013-06-24 04:01:57 +08:00
2014-03-10 00:22:53 +08:00
return {
2013-06-24 04:01:57 +08:00
'id': video_id,
'url': video_url,
'title': video_title,
'ext': 'flv',
'thumbnail': video_thumbnail,
2013-10-19 05:35:17 +08:00
'age_limit': 18,
2014-03-10 00:22:53 +08:00
}