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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6
   7 class MiaoPaiIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?miaopai\.com/show/(?P<id>[-A-Za-z0-9~_]+)'
   9     _TEST = {
  10         'url': 'http://www.miaopai.com/show/n~0hO7sfV1nBEw4Y29-Hqg__.htm',
  11         'md5': '095ed3f1cd96b821add957bdc29f845b',
  12         'info_dict': {
  13             'id': 'n~0hO7sfV1nBEw4Y29-Hqg__',
  14             'ext': 'mp4',
  15             'title': '西游记音乐会的秒拍视频',
  16             'thumbnail': 're:^https?://.*/n~0hO7sfV1nBEw4Y29-Hqg___m.jpg',
  17         }
  18     }
  19
  20     _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'
  21
  22     def _real_extract(self, url):
  23         video_id = self._match_id(url)
  24         webpage = self._download_webpage(
  25             url, video_id, headers={'User-Agent': self._USER_AGENT_IPAD})
  26
  27         title = self._html_search_regex(
  28             r'<title>([^<]+)</title>', webpage, 'title')
  29         thumbnail = self._html_search_regex(
  30             r'<div[^>]+class=(?P<q1>[\'"]).*\bvideo_img\b.*(?P=q1)[^>]+data-url=(?P<q2>[\'"])(?P<url>[^\'"]+)(?P=q2)',
  31             webpage, 'thumbnail', fatal=False, group='url')
  32         videos = self._parse_html5_media_entries(url, webpage, video_id)
  33         info = videos[0]
  34
  35         info.update({
  36             'id': video_id,
  37             'title': title,
  38             'thumbnail': thumbnail,
  39         })
  40         return info