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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6
   7
   8 class InstagramIE(InfoExtractor):
   9     _VALID_URL = r'http://instagram\.com/p/(?P<id>.*?)/'
  10     _TEST = {
  11         'url': 'http://instagram.com/p/aye83DjauH/?foo=bar#abc',
  12         'md5': '0d2da106a9d2631273e192b372806516',
  13         'info_dict': {
  14             'id': 'aye83DjauH',
  15             'ext': 'mp4',
  16             'uploader_id': 'naomipq',
  17             'title': 'Video by naomipq',
  18             'description': 'md5:1f17f0ab29bd6fe2bfad705f58de3cb8',
  19         }
  20     }
  21
  22     def _real_extract(self, url):
  23         mobj = re.match(self._VALID_URL, url)
  24         video_id = mobj.group('id')
  25         webpage = self._download_webpage(url, video_id)
  26         uploader_id = self._search_regex(r'"owner":{"username":"(.+?)"',
  27             webpage, 'uploader id', fatal=False)
  28         desc = self._search_regex(r'"caption":"(.*?)"', webpage, 'description',
  29             fatal=False)
  30
  31         return {
  32             'id': video_id,
  33             'url': self._og_search_video_url(webpage, secure=False),
  34             'ext': 'mp4',
  35             'title': 'Video by %s' % uploader_id,
  36             'thumbnail': self._og_search_thumbnail(webpage),
  37             'uploader_id': uploader_id,
  38             'description': desc,
  39         }