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/#',
   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         video_url = self._html_search_regex(
  22             r'<meta property="og:video" content="(.+?)"',
  23             webpage, u'video URL')
  24         thumbnail_url = self._html_search_regex(
  25             r'<meta property="og:image" content="(.+?)" />',
  26             webpage, u'thumbnail URL', fatal=False)
  27         html_title = self._html_search_regex(
  28             r'<title>(.+?)</title>',
  29             webpage, u'title', flags=re.DOTALL)
  30         title = re.sub(u'(?: *\(Videos?\))? \u2022 Instagram$', '', html_title).strip()
  31         uploader_id = self._html_search_regex(r'content="(.*?)\'s video on Instagram',
  32             webpage, u'uploader name', fatal=False)
  33         ext = 'mp4'
  34
  35         return [{
  36             'id':        video_id,
  37             'url':       video_url,
  38             'ext':       ext,
  39             'title':     title,
  40             'thumbnail': thumbnail_url,
  41             'uploader_id' : uploader_id
  42         }]