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

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import json
   6
   7 from ..compat import compat_urllib_parse
   8 from .common import InfoExtractor
   9 from ..utils import ExtractorError
  10
  11
  12 class Porn91IE(InfoExtractor):
  13     IE_NAME = '91porn'
  14     _VALID_URL = r'(?:https?://)(?:www\.|)91porn\.com/.+?\?viewkey=(?P<id>[\w\d]+)'
  15
  16     _TEST = {
  17             'url': 'http://91porn.com/view_video.php?viewkey=7e42283b4f5ab36da134',
  18             'md5': '6df8f6d028bc8b14f5dbd73af742fb20',
  19             'info_dict': {
  20                 'id': '7e42283b4f5ab36da134',
  21                 'title': '18岁大一漂亮学妹，水嫩性感，再爽一次！',
  22                 'ext': 'mp4'
  23             }
  24     }
  25
  26     def _real_extract(self, url):
  27         mobj = re.match(self._VALID_URL, url)
  28         video_id = mobj.group('id')
  29         url = 'http://91porn.com/view_video.php?viewkey=%s' % video_id
  30         self._set_cookie('91porn.com', 'language', 'cn_CN')
  31         webpage = self._download_webpage(url, video_id, "get HTML content")
  32         title = re.search(
  33             r'<div id="viewvideo-title">(.+?)</div>',
  34             webpage,
  35             re.DOTALL)
  36         assert title
  37         title = title.group(1).replace('\n', '')
  38
  39         # get real url
  40         n1 = re.search(r'so.addVariable\(\'file\',\'(\d+)\'', webpage)
  41         n2 = re.search(r'so.addVariable\(\'seccode\',\'(.+?)\'', webpage)
  42         n3 = re.search(r'so.addVariable\(\'max_vid\',\'(\d+)\'', webpage)
  43         if not (n1 and n2 and n3):
  44             raise ExtractorError("You are Blocked by Server.")
  45
  46         url_params = compat_urllib_parse.urlencode({
  47             'VID': n1.group(1),
  48             'mp4': '1',
  49             'seccode': n2.group(1),
  50             'max_vid': n3.group(1),
  51         })
  52         t_url = 'http://91porn.com/getfile.php?' + url_params
  53         info_cn = self._download_webpage(t_url, video_id, "get real video_url")
  54         video_url = re.search(r'file=(http.+?)&', info_cn).group(1)
  55
  56         info = {
  57             'id': video_id,
  58             'title': title,
  59             'url': video_url,
  60         }
  61
  62         return info