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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6
   7 class PearIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?pearvideo\.com/video_(?P<id>[0-9]+)'
   9     _TEST = {
  10         'url': 'http://www.pearvideo.com/video_1076290',
  11         'info_dict': {
  12             'id': '1076290',
  13             'ext': 'mp4',
  14             'title': '小浣熊在主人家玻璃上滚石头：没砸',
  15             'description': '小浣熊找到一个小石头，仿佛发现了一个宝贝。它不停地用石头按在玻璃上，滚来滚去，吸引主人注意。',
  16             'url': 'http://video.pearvideo.com/mp4/short/20170508/cont-1076290-10438018-hd.mp4'
  17         }
  18     }
  19
  20     def _real_extract(self, url):
  21         video_id = self._match_id(url)
  22         webpage = self._download_webpage(url, video_id)
  23
  24         title = self._html_search_regex(r'<h1[^>]+class="video-tt">(.+)</h1>', webpage, 'title', fatal=False)
  25         description = self._html_search_regex(r'<div[^>]+class="summary"[^>]*>([^<]+)<', webpage, 'description', fatal=False)
  26         url = self._html_search_regex(r'hdUrl="(.*?)"', webpage, 'url', fatal=False)
  27
  28         return {
  29             'id': video_id,
  30             'ext': 'mp4',
  31             'title': title,
  32             'description': description,
  33             'url': url
  34         }