_ Git - youtube-dl/blob - youtube_dl/extractor/statigram.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6
   7
   8 class StatigramIE(InfoExtractor):
   9     _VALID_URL = r'https?://(www\.)?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         },
  19     }
  20
  21     def _real_extract(self, url):
  22         mobj = re.match(self._VALID_URL, url)
  23         video_id = mobj.group('id')
  24         webpage = self._download_webpage(url, video_id)
  25         html_title = self._html_search_regex(
  26             r'<title>(.+?)</title>',
  27             webpage, 'title')
  28         title = re.sub(r'(?: *\(Videos?\))? \| Statigram$', '', html_title)
  29         uploader_id = self._html_search_regex(
  30             r'@([^ ]+)', title, 'uploader name', fatal=False)
  31
  32         return {
  33             'id': video_id,
  34             'url': self._og_search_video_url(webpage),
  35             'title': title,
  36             'thumbnail': self._og_search_thumbnail(webpage),
  37             'uploader_id': uploader_id
  38         }