_ Git - youtube-dl/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         }
  15     }
  16
  17     def _real_extract(self, url):
  18         mobj = re.match(self._VALID_URL, url)
  19         video_id = mobj.group(1)
  20         webpage = self._download_webpage(url, video_id)
  21         html_title = self._html_search_regex(
  22             r'<title>(.+?)</title>',
  23             webpage, u'title', flags=re.DOTALL)
  24         title = re.sub(u'(?: *\(Videos?\))? \u2022 Instagram$', '', html_title).strip()
  25         uploader_id = self._html_search_regex(r'<div class="media-user" id="media_user"><h2><a href="[^"]*">([^<]*)</a></h2>',
  26             webpage, u'uploader name', fatal=False)
  27         ext = 'mp4'
  28
  29         return [{
  30             'id':        video_id,
  31             'url':       self._og_search_video_url(webpage),
  32             'ext':       ext,
  33             'title':     title,
  34             'thumbnail': self._og_search_thumbnail(webpage),
  35             'uploader_id' : uploader_id
  36         }]