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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_str
   6 from ..utils import int_or_none
   7
   8
   9 class LiveJournalIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:[^.]+\.)?livejournal\.com/video/album/\d+.+?\bid=(?P<id>\d+)'
  11     _TEST = {
  12         'url': 'https://andrei-bt.livejournal.com/video/album/407/?mode=view&id=51272',
  13         'md5': 'adaf018388572ced8a6f301ace49d4b2',
  14         'info_dict': {
  15             'id': '1263729',
  16             'ext': 'mp4',
  17             'title': 'Истребители против БПЛА',
  18             'upload_date': '20190624',
  19             'timestamp': 1561406715,
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         video_id = self._match_id(url)
  25         webpage = self._download_webpage(url, video_id)
  26         record = self._parse_json(self._search_regex(
  27             r'Site\.page\s*=\s*({.+?});', webpage,
  28             'page data'), video_id)['video']['record']
  29         storage_id = compat_str(record['storageid'])
  30         title = record.get('name')
  31         if title:
  32             # remove filename extension(.mp4, .mov, etc...)
  33             title = title.rsplit('.', 1)[0]
  34         return {
  35             '_type': 'url_transparent',
  36             'id': video_id,
  37             'title': title,
  38             'thumbnail': record.get('thumbnail'),
  39             'timestamp': int_or_none(record.get('timecreate')),
  40             'url': 'eagleplatform:vc.videos.livejournal.com:' + storage_id,
  41             'ie_key': 'EaglePlatform',
  42         }