yt-dlp/youtube_dl/extractor/xnxx.py

50 lines
1.5 KiB
Python
Raw Normal View History

2014-03-09 16:22:53 +00:00
# encoding: utf-8
from __future__ import unicode_literals
2013-06-23 20:01:57 +00:00
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
)
class XNXXIE(InfoExtractor):
2014-03-09 16:22:53 +00:00
_VALID_URL = r'^https?://(?:video|www)\.xnxx\.com/video(?P<id>[0-9]+)/(.*)'
2013-06-27 18:46:46 +00:00
_TEST = {
2014-03-09 16:22:53 +00:00
'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,
2013-06-27 18:46:46 +00:00
}
}
2013-06-23 20:01:57 +00:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
2014-03-09 16:22:53 +00:00
video_id = mobj.group('id')
2013-06-23 20:01:57 +00:00
# Get webpage content
webpage = self._download_webpage(url, video_id)
2014-03-09 16:22:53 +00:00
video_url = self._search_regex(r'flv_url=(.*?)&amp;',
2014-11-23 20:39:15 +00:00
webpage, 'video URL')
2013-06-23 20:01:57 +00:00
video_url = compat_urllib_parse.unquote(video_url)
2014-03-09 16:22:53 +00:00
video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XNXX.COM',
2014-11-23 20:39:15 +00:00
webpage, 'title')
2013-06-23 20:01:57 +00:00
2014-03-09 16:22:53 +00:00
video_thumbnail = self._search_regex(r'url_bigthumb=(.*?)&amp;',
2014-11-23 20:39:15 +00:00
webpage, 'thumbnail', fatal=False)
2013-06-23 20:01:57 +00:00
2014-03-09 16:22:53 +00:00
return {
2013-06-23 20:01:57 +00:00
'id': video_id,
'url': video_url,
'title': video_title,
'ext': 'flv',
'thumbnail': video_thumbnail,
2013-10-18 21:35:17 +00:00
'age_limit': 18,
2014-03-09 16:22:53 +00:00
}