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

   1 import re
   2
   3 from .common import InfoExtractor
   4
   5 class InstagramIE(InfoExtractor):
   6     _VALID_URL = r'(?:http://)?instagram.com/p/(.*?)/'
   7     _TEST = {
   8         u'url': u'http://instagram.com/p/aye83DjauH/?foo=bar#abc',
   9         u'file': u'aye83DjauH.mp4',
  10         u'md5': u'0d2da106a9d2631273e192b372806516',
  11         u'info_dict': {
  12             u"uploader_id": u"naomipq",
  13             u"title": u"Video by naomipq",
  14             u'description': u'md5:1f17f0ab29bd6fe2bfad705f58de3cb8',
  15         }
  16     }
  17
  18     def _real_extract(self, url):
  19         mobj = re.match(self._VALID_URL, url)
  20         video_id = mobj.group(1)
  21         webpage = self._download_webpage(url, video_id)
  22         uploader_id = self._search_regex(r'"owner":{"username":"(.+?)"',
  23             webpage, u'uploader id', fatal=False)
  24         desc = self._search_regex(r'"caption":"(.*?)"', webpage, u'description',
  25             fatal=False)
  26
  27         return [{
  28             'id':        video_id,
  29             'url':       self._og_search_video_url(webpage, secure=False),
  30             'ext':       'mp4',
  31             'title':     u'Video by %s' % uploader_id,
  32             'thumbnail': self._og_search_thumbnail(webpage),
  33             'uploader_id' : uploader_id,
  34             'description': desc,
  35         }]