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

   1 import re
   2
   3 from .common import InfoExtractor
   4
   5 class StatigramIE(InfoExtractor):
   6     _VALID_URL = r'(?:http://)?(?:www\.)?statigr\.am/p/([^/]+)'
   7
   8     def _real_extract(self, url):
   9         mobj = re.match(self._VALID_URL, url)
  10         video_id = mobj.group(1)
  11         webpage = self._download_webpage(url, video_id)
  12         video_url = self._html_search_regex(
  13             r'<meta property="og:video:secure_url" content="(.+?)">',
  14             webpage, u'video URL')
  15         thumbnail_url = self._html_search_regex(
  16             r'<meta property="og:image" content="(.+?)" />',
  17             webpage, u'thumbnail URL', fatal=False)
  18         html_title = self._html_search_regex(
  19             r'<title>(.+?)</title>',
  20             webpage, u'title')
  21         title = html_title.rpartition(u' | Statigram')[0]
  22         uploader_id = self._html_search_regex(
  23             r'@([^ ]+)', title, u'uploader name', fatal=False)
  24         ext = 'mp4'
  25
  26         return [{
  27             'id':        video_id,
  28             'url':       video_url,
  29             'ext':       ext,
  30             'title':     title,
  31             'thumbnail': thumbnail_url,
  32             'uploader_id' : uploader_id
  33         }]