_ Git - youtube-dl/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 )
  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             'duration': 431,
  24         }
  25     }
  26
  27     def _real_extract(self, url):
  28         video_id = self._match_id(url)
  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 = self._search_regex(
  33             r'<div id="viewvideo-title">([^<]+)</div>', webpage, 'title')
  34         title = title.replace('\n', '')
  35
  36         # get real url
  37         file_id = self._search_regex(
  38             r'so.addVariable\(\'file\',\'(\d+)\'', webpage, 'file id')
  39         sec_code = self._search_regex(
  40             r'so.addVariable\(\'seccode\',\'([^\']+)\'', webpage, 'sec code')
  41         max_vid = self._search_regex(
  42             r'so.addVariable\(\'max_vid\',\'(\d+)\'', webpage, 'max vid')
  43         url_params = compat_urllib_parse.urlencode({
  44             'VID': file_id,
  45             'mp4': '1',
  46             'seccode': sec_code,
  47             'max_vid': max_vid,
  48         })
  49         info_cn = self._download_webpage(
  50             'http://91porn.com/getfile.php?' + url_params, video_id,
  51             "get real video url")
  52         video_url = self._search_regex(r'file=([^&]+)&', info_cn, 'url')
  53
  54         duration = parse_duration(self._search_regex(
  55             r'时长:\s*</span>\s*(\d+:\d+)', webpage, 'duration', fatal=False))
  56
  57         comment_count = int_or_none(self._search_regex(
  58             r'留言:\s*</span>\s*(\d+)', webpage, 'comment count', fatal=False))
  59
  60         return {
  61             'id': video_id,
  62             'title': title,
  63             'url': video_url,
  64             'duration': duration,
  65             'comment_count': comment_count,
  66         }