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

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from ..compat import (
   5     compat_urllib_parse,
   6     compat_urllib_parse_unquote,
   7 )
   8 from .common import InfoExtractor
   9 from ..utils import (
  10     parse_duration,
  11     int_or_none,
  12     ExtractorError,
  13 )
  14
  15
  16 class Porn91IE(InfoExtractor):
  17     IE_NAME = '91porn'
  18     _VALID_URL = r'(?:https?://)(?:www\.|)91porn\.com/.+?\?viewkey=(?P<id>[\w\d]+)'
  19
  20     _TEST = {
  21         'url': 'http://91porn.com/view_video.php?viewkey=7e42283b4f5ab36da134',
  22         'md5': '6df8f6d028bc8b14f5dbd73af742fb20',
  23         'info_dict': {
  24             'id': '7e42283b4f5ab36da134',
  25             'title': '18岁大一漂亮学妹，水嫩性感，再爽一次！',
  26             'ext': 'mp4',
  27             'duration': 431,
  28             'age_limit': 18,
  29         }
  30     }
  31
  32     def _real_extract(self, url):
  33         video_id = self._match_id(url)
  34         url = 'http://91porn.com/view_video.php?viewkey=%s' % video_id
  35         self._set_cookie('91porn.com', 'language', 'cn_CN')
  36         webpage = self._download_webpage(url, video_id, 'get HTML content')
  37
  38         if '作为游客，你每天只可观看10个视频' in webpage:
  39             raise ExtractorError('91 Porn says: Daily limit 10 videos exceeded', expected=True)
  40
  41         title = self._search_regex(
  42             r'<div id="viewvideo-title">([^<]+)</div>', webpage, 'title')
  43         title = title.replace('\n', '')
  44
  45         # get real url
  46         file_id = self._search_regex(
  47             r'so.addVariable\(\'file\',\'(\d+)\'', webpage, 'file id')
  48         sec_code = self._search_regex(
  49             r'so.addVariable\(\'seccode\',\'([^\']+)\'', webpage, 'sec code')
  50         max_vid = self._search_regex(
  51             r'so.addVariable\(\'max_vid\',\'(\d+)\'', webpage, 'max vid')
  52         url_params = compat_urllib_parse.urlencode({
  53             'VID': file_id,
  54             'mp4': '1',
  55             'seccode': sec_code,
  56             'max_vid': max_vid,
  57         })
  58         info_cn = self._download_webpage(
  59             'http://91porn.com/getfile.php?' + url_params, video_id,
  60             'get real video url')
  61         video_url = compat_urllib_parse_unquote(self._search_regex(
  62             r'file=([^&]+)&', info_cn, 'url'))
  63
  64         duration = parse_duration(self._search_regex(
  65             r'时长:\s*</span>\s*(\d+:\d+)', webpage, 'duration', fatal=False))
  66
  67         comment_count = int_or_none(self._search_regex(
  68             r'留言:\s*</span>\s*(\d+)', webpage, 'comment count', fatal=False))
  69
  70         return {
  71             'id': video_id,
  72             'title': title,
  73             'url': video_url,
  74             'duration': duration,
  75             'comment_count': comment_count,
  76             'age_limit': self._rta_search(webpage),
  77         }