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/522207370455279102_24101272',
   9         u'file': u'522207370455279102_24101272.mp4',
  10         u'md5': u'6eb93b882a3ded7c378ee1d6884b1814',
  11         u'info_dict': {
  12             u'uploader_id': u'aguynamedpatrick',
  13             u'title': u'Instagram photo by @aguynamedpatrick (Patrick Janelle)',
  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         html_title = self._html_search_regex(
  22             r'<title>(.+?)</title>',
  23             webpage, u'title')
  24         title = re.sub(r'(?: *\(Videos?\))? \| Statigram$', '', html_title)
  25         uploader_id = self._html_search_regex(
  26             r'@([^ ]+)', title, u'uploader name', fatal=False)
  27         ext = 'mp4'
  28
  29         return [{
  30             'id':        video_id,
  31             'url':       self._og_search_video_url(webpage),
  32             'ext':       ext,
  33             'title':     title,
  34             'thumbnail': self._og_search_thumbnail(webpage),
  35             'uploader_id' : uploader_id
  36         }]