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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4
   5
   6 class IconosquareIE(InfoExtractor):
   7     _VALID_URL = r'https?://(www\.)?(?:iconosquare\.com|statigr\.am)/p/(?P<id>[^/]+)'
   8     _TEST = {
   9         'url': 'http://statigr.am/p/522207370455279102_24101272',
  10         'md5': '6eb93b882a3ded7c378ee1d6884b1814',
  11         'info_dict': {
  12             'id': '522207370455279102_24101272',
  13             'ext': 'mp4',
  14             'uploader_id': 'aguynamedpatrick',
  15             'title': 'Instagram photo by @aguynamedpatrick (Patrick Janelle)',
  16             'description': 'md5:644406a9ec27457ed7aa7a9ebcd4ce3d',
  17         },
  18     }
  19
  20     def _real_extract(self, url):
  21         video_id = self._match_id(url)
  22         webpage = self._download_webpage(url, video_id)
  23         title = self._html_search_regex(
  24             r'<title>(.+?)(?: *\(Videos?\))? \| (?:Iconosquare|Statigram)</title>',
  25             webpage, 'title')
  26         uploader_id = self._html_search_regex(
  27             r'@([^ ]+)', title, 'uploader name', fatal=False)
  28
  29         return {
  30             'id': video_id,
  31             'url': self._og_search_video_url(webpage),
  32             'title': title,
  33             'description': self._og_search_description(webpage),
  34             'thumbnail': self._og_search_thumbnail(webpage),
  35             'uploader_id': uploader_id
  36         }