You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
yt-dlp/youtube_dl/extractor/xnxx.py

46 lines
1.5 KiB
Python

11 years ago
# encoding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_urllib_parse_unquote
class XNXXIE(InfoExtractor):
_VALID_URL = r'^https?://(?:video|www)\.xnxx\.com/video-?(?P<id>[0-9a-z]+)/(.*)'
_TESTS = [{
'url': 'http://www.xnxx.com/video-6gqggeb/hd_star-581_sam',
'md5': '6a2a6aff3f10467d94e572edb7b7deb6',
11 years ago
'info_dict': {
'id': '6gqggeb',
11 years ago
'ext': 'flv',
'title': 'HD STAR-581 sam',
11 years ago
'age_limit': 18,
},
}, {
'url': 'http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
11 years ago
video_url = self._search_regex(r'flv_url=(.*?)&amp;',
webpage, 'video URL')
video_url = compat_urllib_parse_unquote(video_url)
11 years ago
video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XNXX.COM',
webpage, 'title')
11 years ago
video_thumbnail = self._search_regex(r'url_bigthumb=(.*?)&amp;',
webpage, 'thumbnail', fatal=False)
11 years ago
return {
'id': video_id,
'url': video_url,
'title': video_title,
'ext': 'flv',
'thumbnail': video_thumbnail,
'age_limit': 18,
11 years ago
}