youtube_dl/extractor/iconosquare.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6
   7
   8 class IconosquareIE(InfoExtractor):
   9     _VALID_URL = r'https?://(www\.)?(?:iconosquare\.com|statigr\.am)/p/(?P<id>[^/]+)'
  10     _TEST = {
  11         'url': 'http://statigr.am/p/522207370455279102_24101272',
  12         'md5': '6eb93b882a3ded7c378ee1d6884b1814',
  13         'info_dict': {
  14             'id': '522207370455279102_24101272',
  15             'ext': 'mp4',
  16             'uploader_id': 'aguynamedpatrick',
  17             'title': 'Instagram photo by @aguynamedpatrick (Patrick Janelle)',
  18             'description': 'md5:644406a9ec27457ed7aa7a9ebcd4ce3d',
  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         html_title = self._html_search_regex(
  27             r'<title>(.+?)</title>',
  28             webpage, 'title')
  29         title = re.sub(r'(?: *\(Videos?\))? \| (?:Iconosquare|Statigram)$', '', html_title)
  30         uploader_id = self._html_search_regex(
  31             r'@([^ ]+)', title, 'uploader name', fatal=False)
  32
  33         return {
  34             'id': video_id,
  35             'url': self._og_search_video_url(webpage),
  36             'title': title,
  37             'description': self._og_search_description(webpage),
  38             'thumbnail': self._og_search_thumbnail(webpage),
  39             'uploader_id': uploader_id
  40         }