Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/porn91.py

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