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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     parse_duration,
   7     int_or_none,
   8     ExtractorError,
   9 )
  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': '7fcdb5349354f40d41689bd0fa8db05a',
  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             'duration': 431,
  24             'age_limit': 18,
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30         self._set_cookie('91porn.com', 'language', 'cn_CN')
  31
  32         webpage = self._download_webpage(
  33             'http://91porn.com/view_video.php?viewkey=%s' % video_id, video_id)
  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         video_link_url = self._search_regex(
  43             r'<textarea[^>]+id=["\']fm-video_link[^>]+>([^<]+)</textarea>',
  44             webpage, 'video link')
  45         videopage = self._download_webpage(video_link_url, video_id)
  46
  47         info_dict = self._parse_html5_media_entries(url, videopage, video_id)[0]
  48
  49         duration = parse_duration(self._search_regex(
  50             r'时长:\s*</span>\s*(\d+:\d+)', webpage, 'duration', fatal=False))
  51
  52         comment_count = int_or_none(self._search_regex(
  53             r'留言:\s*</span>\s*(\d+)', webpage, 'comment count', fatal=False))
  54
  55         info_dict.update({
  56             'id': video_id,
  57             'title': title,
  58             'duration': duration,
  59             'comment_count': comment_count,
  60             'age_limit': self._rta_search(webpage),
  61         })
  62
  63         return info_dict