yt_dlp/extractor/miaopai.py

   1 from .common import InfoExtractor
   2
   3
   4 class MiaoPaiIE(InfoExtractor):
   5     _VALID_URL = r'https?://(?:www\.)?miaopai\.com/show/(?P<id>[-A-Za-z0-9~_]+)'
   6     _TEST = {
   7         'url': 'http://www.miaopai.com/show/n~0hO7sfV1nBEw4Y29-Hqg__.htm',
   8         'md5': '095ed3f1cd96b821add957bdc29f845b',
   9         'info_dict': {
  10             'id': 'n~0hO7sfV1nBEw4Y29-Hqg__',
  11             'ext': 'mp4',
  12             'title': '西游记音乐会的秒拍视频',
  13             'thumbnail': 're:^https?://.*/n~0hO7sfV1nBEw4Y29-Hqg___m.jpg',
  14         }
  15     }
  16
  17     _USER_AGENT_IPAD = 'Mozilla/5.0 (iPad; CPU OS 9_1 like Mac OS X) AppleWebKit/601.1.46 (KHTML, like Gecko) Version/9.0 Mobile/13B143 Safari/601.1'
  18
  19     def _real_extract(self, url):
  20         video_id = self._match_id(url)
  21         webpage = self._download_webpage(
  22             url, video_id, headers={'User-Agent': self._USER_AGENT_IPAD})
  23
  24         title = self._html_extract_title(webpage)
  25         thumbnail = self._html_search_regex(
  26             r'<div[^>]+class=(?P<q1>[\'"]).*\bvideo_img\b.*(?P=q1)[^>]+data-url=(?P<q2>[\'"])(?P<url>[^\'"]+)(?P=q2)',
  27             webpage, 'thumbnail', fatal=False, group='url')
  28         videos = self._parse_html5_media_entries(url, webpage, video_id)
  29         info = videos[0]
  30
  31         info.update({
  32             'id': video_id,
  33             'title': title,
  34             'thumbnail': thumbnail,
  35         })
  36         return info