yt_dlp/extractor/livejournal.py

   1 from .common import InfoExtractor
   2 from ..utils import int_or_none
   3
   4
   5 class LiveJournalIE(InfoExtractor):
   6     _VALID_URL = r'https?://(?:[^.]+\.)?livejournal\.com/video/album/\d+.+?\bid=(?P<id>\d+)'
   7     _TEST = {
   8         'url': 'https://andrei-bt.livejournal.com/video/album/407/?mode=view&id=51272',
   9         'md5': 'adaf018388572ced8a6f301ace49d4b2',
  10         'info_dict': {
  11             'id': '1263729',
  12             'ext': 'mp4',
  13             'title': 'Истребители против БПЛА',
  14             'upload_date': '20190624',
  15             'timestamp': 1561406715,
  16         },
  17     }
  18
  19     def _real_extract(self, url):
  20         video_id = self._match_id(url)
  21         webpage = self._download_webpage(url, video_id)
  22         record = self._parse_json(self._search_regex(
  23             r'Site\.page\s*=\s*({.+?});', webpage,
  24             'page data'), video_id)['video']['record']
  25         storage_id = str(record['storageid'])
  26         title = record.get('name')
  27         if title:
  28             # remove filename extension(.mp4, .mov, etc...)
  29             title = title.rsplit('.', 1)[0]
  30         return {
  31             '_type': 'url_transparent',
  32             'id': video_id,
  33             'title': title,
  34             'thumbnail': record.get('thumbnail'),
  35             'timestamp': int_or_none(record.get('timecreate')),
  36             'url': 'eagleplatform:vc.videos.livejournal.com:' + storage_id,
  37             'ie_key': 'EaglePlatform',
  38         }