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

   1 import re
   2
   3 from .common import InfoExtractor
   4
   5
   6 class VineIE(InfoExtractor):
   7     _VALID_URL = r'(?:https?://)?(?:www\.)?vine\.co/v/(?P<id>\w+)'
   8
   9     def _real_extract(self, url):
  10         mobj = re.match(self._VALID_URL, url)
  11
  12         video_id = mobj.group('id')
  13         webpage_url = 'https://vine.co/v/' + video_id
  14         webpage = self._download_webpage(webpage_url, video_id)
  15
  16         self.report_extraction(video_id)
  17
  18         video_url = self._html_search_regex(r'<meta property="twitter:player:stream" content="(.+?)"',
  19             webpage, u'video URL')
  20
  21         video_title = self._html_search_regex(r'<meta property="og:title" content="(.+?)"',
  22             webpage, u'title')
  23
  24         thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.+?)(\?.*?)?"',
  25             webpage, u'thumbnail', fatal=False)
  26
  27         uploader = self._html_search_regex(r'<div class="user">.*?<h2>(.+?)</h2>',
  28             webpage, u'uploader', fatal=False, flags=re.DOTALL)
  29
  30         return [{
  31             'id':        video_id,
  32             'url':       video_url,
  33             'ext':       'mp4',
  34             'title':     video_title,
  35             'thumbnail': thumbnail,
  36             'uploader':  uploader,
  37         }]