_ Git - youtube-dl/blob - youtube_dl/extractor/porn91.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from ..compat import compat_urllib_parse
   7 from .common import InfoExtractor
   8
   9
  10 class Porn91IE(InfoExtractor):
  11     IE_NAME = '91porn'
  12     _VALID_URL = r'(?:https?://)(?:www\.|)91porn\.com/.+?\?viewkey=(?P<id>[\w\d]+)'
  13
  14     _TEST = {
  15         'url': 'http://91porn.com/view_video.php?viewkey=7e42283b4f5ab36da134',
  16         'md5': '6df8f6d028bc8b14f5dbd73af742fb20',
  17         'info_dict': {
  18             'id': '7e42283b4f5ab36da134',
  19             'title': '18岁大一漂亮学妹，水嫩性感，再爽一次！',
  20             'ext': 'mp4'
  21         }
  22     }
  23
  24     def _real_extract(self, url):
  25         mobj = re.match(self._VALID_URL, url)
  26         video_id = mobj.group('id')
  27         url = 'http://91porn.com/view_video.php?viewkey=%s' % video_id
  28         self._set_cookie('91porn.com', 'language', 'cn_CN')
  29         webpage = self._download_webpage(url, video_id, "get HTML content")
  30         title = self._search_regex(
  31             r'<div id="viewvideo-title">(?P<title>.+?)</div>',
  32             webpage, 'title', flags=re.DOTALL)
  33         title = title.replace('\n', '')
  34
  35         # get real url
  36         n1 = self._search_regex(
  37             r'so.addVariable\(\'file\',\'(?P<n1>\d+)\'', webpage, 'n1')
  38         n2 = self._search_regex(
  39             r'so.addVariable\(\'seccode\',\'(?P<n2>.+?)\'', webpage, 'n2')
  40         n3 = self._search_regex(
  41             r'so.addVariable\(\'max_vid\',\'(?P<n3>\d+)\'', webpage, 'n3')
  42         url_params = compat_urllib_parse.urlencode({
  43             'VID': n1,
  44             'mp4': '1',
  45             'seccode': n2,
  46             'max_vid': n3,
  47         })
  48         t_url = 'http://91porn.com/getfile.php?' + url_params
  49         info_cn = self._download_webpage(t_url, video_id, "get real video_url")
  50         video_url = self._search_regex(r'file=(?P<url>http.+?)&', info_cn, 'url')
  51
  52         # construct info
  53         info = {
  54             'id': video_id,
  55             'title': title,
  56             'url': video_url,
  57         }
  58
  59         return info