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

   1 import re
   2
   3 from .common import InfoExtractor
   4
   5 class StatigramIE(InfoExtractor):
   6     _VALID_URL = r'(?:http://)?(?:www\.)?statigr\.am/p/([^/]+)'
   7     _TEST = {
   8         u'url': u'http://statigr.am/p/484091715184808010_284179915',
   9         u'file': u'484091715184808010_284179915.mp4',
  10         u'md5': u'deda4ff333abe2e118740321e992605b',
  11         u'info_dict': {
  12             u"uploader_id": u"videoseconds",
  13             u"title": u"Instagram photo by @videoseconds"
  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:secure_url" 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')
  30         title = re.sub(r'(?: *\(Videos?\))? \| Statigram$', '', html_title)
  31         uploader_id = self._html_search_regex(
  32             r'@([^ ]+)', title, 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         }]