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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import sanitized_Request
   6
   7
   8 class MiaoPaiIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?miaopai\.com/show/(?P<id>[-A-Za-z0-9~_]+).htm'
  10     _TEST = {
  11         'url': 'http://www.miaopai.com/show/n~0hO7sfV1nBEw4Y29-Hqg__.htm',
  12         'md5': '095ed3f1cd96b821add957bdc29f845b',
  13         'info_dict': {
  14             'id': 'n~0hO7sfV1nBEw4Y29-Hqg__',
  15             'ext': 'mp4',
  16             'title': '西游记音乐会的秒拍视频',
  17             'thumbnail': 're:^https?://.*/n~0hO7sfV1nBEw4Y29-Hqg___m.jpg',
  18         }
  19     }
  20
  21     _USER_AGENT_IPAD = 'User-Agent:Mozilla/5.0 ' \
  22                        '(iPad; CPU OS 9_1 like Mac OS X) ' \
  23                        'AppleWebKit/601.1.46 (KHTML, like Gecko) ' \
  24                        'Version/9.0 Mobile/13B143 Safari/601.1'
  25
  26     def _real_extract(self, url):
  27         video_id = self._match_id(url)
  28         request = sanitized_Request(url)
  29         request.add_header('User-Agent', self._USER_AGENT_IPAD)
  30         webpage = self._download_webpage(request, video_id)
  31
  32         title = self._html_search_regex(r'<title>([^<]*)</title>',
  33                                         webpage,
  34                                         'title')
  35         regex = r"""<div *class=['"]video_img[^>]*data-url=['"]([^'"]*\.jpg)['"]"""
  36         thumbnail = self._html_search_regex(regex, webpage, '')
  37         videos = self._parse_html5_media_entries(url, webpage, video_id)
  38         info = videos[0]
  39
  40         info.update({'id': video_id,
  41                      'title': title,
  42                      'thumbnail': thumbnail,
  43                      })
  44         return info