1
mirror of https://github.com/yt-dlp/yt-dlp synced 2024-12-17 01:55:56 +01:00
yt-dlp/youtube_dl/extractor/porn91.py

61 lines
2.0 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# encoding: utf-8
from __future__ import unicode_literals
import re
from ..compat import compat_urllib_parse
from .common import InfoExtractor
from ..utils import ExtractorError
class Porn91IE(InfoExtractor):
IE_NAME = '91porn'
_VALID_URL = r'(?:https?://)(?:www\.|)91porn\.com/.+?\?viewkey=(?P<id>[\w\d]+)'
_TEST = {
'url': 'http://91porn.com/view_video.php?viewkey=7e42283b4f5ab36da134',
'md5': '6df8f6d028bc8b14f5dbd73af742fb20',
'info_dict': {
'id': '7e42283b4f5ab36da134',
'title': '18岁大一漂亮学妹水嫩性感再爽一次',
'ext': 'mp4'
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
url = 'http://91porn.com/view_video.php?viewkey=%s' % video_id
self._set_cookie('91porn.com', 'language', 'cn_CN')
webpage = self._download_webpage(url, video_id, "get HTML content")
title = self._search_regex(
r'<div id="viewvideo-title">(?P<title>.+?)</div>',
webpage, 'title', flags=re.DOTALL)
title = title.replace('\n', '')
# get real url
n1 = self._search_regex(
r'so.addVariable\(\'file\',\'(?P<n1>\d+)\'', webpage, 'n1')
n2 = self._search_regex(
r'so.addVariable\(\'seccode\',\'(?P<n2>.+?)\'', webpage, 'n2')
n3 = self._search_regex(
r'so.addVariable\(\'max_vid\',\'(?P<n3>\d+)\'', webpage, 'n3')
url_params = compat_urllib_parse.urlencode({
'VID': n1,
'mp4': '1',
'seccode': n2,
'max_vid': n3,
})
t_url = 'http://91porn.com/getfile.php?' + url_params
info_cn = self._download_webpage(t_url, video_id, "get real video_url")
video_url = self._search_regex(r'file=(?P<url>http.+?)&', info_cn, 'url')
# construct info
info = {
'id': video_id,
'title': title,
'url': video_url,
}
return info