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     _TEST = {
   9         u'url': u'https://vine.co/v/b9KOOWX7HUx',
  10         u'file': u'b9KOOWX7HUx.mp4',
  11         u'md5': u'2f36fed6235b16da96ce9b4dc890940d',
  12         u'info_dict': {
  13             u"uploader": u"Jack Dorsey",
  14             u"title": u"Chicken."
  15         }
  16     }
  17
  18     def _real_extract(self, url):
  19         mobj = re.match(self._VALID_URL, url)
  20
  21         video_id = mobj.group('id')
  22         webpage_url = 'https://vine.co/v/' + video_id
  23         webpage = self._download_webpage(webpage_url, video_id)
  24
  25         self.report_extraction(video_id)
  26
  27         video_url = self._html_search_regex(r'<meta property="twitter:player:stream" content="(.+?)"',
  28             webpage, u'video URL')
  29
  30         video_title = self._html_search_regex(r'<meta property="og:title" content="(.+?)"',
  31             webpage, u'title')
  32
  33         thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.+?)(\?.*?)?"',
  34             webpage, u'thumbnail', fatal=False)
  35
  36         uploader = self._html_search_regex(r'<div class="user">.*?<h2>(.+?)</h2>',
  37             webpage, u'uploader', fatal=False, flags=re.DOTALL)
  38
  39         return [{
  40             'id':        video_id,
  41             'url':       video_url,
  42             'ext':       'mp4',
  43             'title':     video_title,
  44             'thumbnail': thumbnail,
  45             'uploader':  uploader,
  46         }]