yt_dlp/extractor/gofile.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     ExtractorError,
   4     try_get
   5 )
   6
   7
   8 class GofileIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?gofile\.io/d/(?P<id>[^/]+)'
  10     _TESTS = [{
  11         'url': 'https://gofile.io/d/AMZyDw',
  12         'info_dict': {
  13             'id': 'AMZyDw',
  14         },
  15         'playlist_mincount': 2,
  16         'playlist': [{
  17             'info_dict': {
  18                 'id': 'de571ac1-5edc-42e2-8ec2-bdac83ad4a31',
  19                 'filesize': 928116,
  20                 'ext': 'mp4',
  21                 'title': 'nuuh',
  22                 'release_timestamp': 1638338704,
  23                 'release_date': '20211201',
  24             }
  25         }]
  26     }, {
  27         'url': 'https://gofile.io/d/is8lKr',
  28         'info_dict': {
  29             'id': 'TMjXd9',
  30             'ext': 'mp4',
  31         },
  32         'playlist_count': 0,
  33         'skip': 'No video/audio found at provided URL.',
  34     }, {
  35         'url': 'https://gofile.io/d/TMjXd9',
  36         'info_dict': {
  37             'id': 'TMjXd9',
  38         },
  39         'playlist_count': 1,
  40     }]
  41     _TOKEN = None
  42
  43     def _real_initialize(self):
  44         token = self._get_cookies('https://gofile.io/').get('accountToken')
  45         if token:
  46             self._TOKEN = token.value
  47             return
  48
  49         account_data = self._download_json(
  50             'https://api.gofile.io/createAccount', None, note='Getting a new guest account')
  51         self._TOKEN = account_data['data']['token']
  52         self._set_cookie('gofile.io', 'accountToken', self._TOKEN)
  53
  54     def _entries(self, file_id):
  55         files = self._download_json('https://api.gofile.io/getContent', 'Gofile', note='Getting filelist', query={
  56             'contentId': file_id,
  57             'token': self._TOKEN,
  58             'websiteToken': 12345,
  59         })
  60
  61         status = files['status']
  62         if status != 'ok':
  63             raise ExtractorError(f'{self.IE_NAME} said: status {status}', expected=True)
  64
  65         found_files = False
  66         for file in (try_get(files, lambda x: x['data']['contents'], dict) or {}).values():
  67             file_type, file_format = file.get('mimetype').split('/', 1)
  68             if file_type not in ('video', 'audio') and file_format != 'vnd.mts':
  69                 continue
  70
  71             found_files = True
  72             file_url = file.get('link')
  73             if file_url:
  74                 yield {
  75                     'id': file['id'],
  76                     'title': file['name'].rsplit('.', 1)[0],
  77                     'url': file_url,
  78                     'filesize': file.get('size'),
  79                     'release_timestamp': file.get('createTime')
  80                 }
  81
  82         if not found_files:
  83             raise ExtractorError('No video/audio found at provided URL.', expected=True)
  84
  85     def _real_extract(self, url):
  86         file_id = self._match_id(url)
  87         return self.playlist_result(self._entries(file_id), playlist_id=file_id)