You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

40 lines
1.5 KiB

  1. # coding: utf-8
  2. from __future__ import unicode_literals
  3. from .common import InfoExtractor
  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. _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'
  17. def _real_extract(self, url):
  18. video_id = self._match_id(url)
  19. webpage = self._download_webpage(
  20. url, video_id, headers={'User-Agent': self._USER_AGENT_IPAD})
  21. title = self._html_search_regex(
  22. r'<title>([^<]+)</title>', webpage, 'title')
  23. thumbnail = self._html_search_regex(
  24. r'<div[^>]+class=(?P<q1>[\'"]).*\bvideo_img\b.*(?P=q1)[^>]+data-url=(?P<q2>[\'"])(?P<url>[^\'"]+)(?P=q2)',
  25. webpage, 'thumbnail', fatal=False, group='url')
  26. videos = self._parse_html5_media_entries(url, webpage, video_id)
  27. info = videos[0]
  28. info.update({
  29. 'id': video_id,
  30. 'title': title,
  31. 'thumbnail': thumbnail,
  32. })
  33. return info