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