yt_dlp/extractor/saitosan.py

   1 from .common import InfoExtractor
   2 from ..utils import ExtractorError, try_get
   3
   4
   5 class SaitosanIE(InfoExtractor):
   6     _WORKING = False
   7     IE_NAME = 'Saitosan'
   8     _VALID_URL = r'https?://(?:www\.)?saitosan\.net/bview.html\?id=(?P<id>[0-9]+)'
   9     _TESTS = [{
  10         'url': 'http://www.saitosan.net/bview.html?id=10031846',
  11         'info_dict': {
  12             'id': '10031846',
  13             'ext': 'mp4',
  14             'title': '井下原 和弥',
  15             'uploader': '井下原 和弥',
  16             'thumbnail': 'http://111.171.196.85:8088/921f916f-7f55-4c97-b92e-5d9d0fef8f5f/thumb',
  17             'is_live': True,
  18         },
  19         'params': {
  20             # m3u8 download
  21             'skip_download': True,
  22         },
  23         'skip': 'Broadcasts are ephemeral',
  24     },
  25         {
  26         'url': 'http://www.saitosan.net/bview.html?id=10031795',
  27         'info_dict': {
  28             'id': '10031795',
  29             'ext': 'mp4',
  30             'title': '橋本',
  31             'uploader': '橋本',
  32             'thumbnail': 'http://111.171.196.85:8088/1a3933e1-a01a-483b-8931-af15f37f8082/thumb',
  33             'is_live': True,
  34         },
  35         'params': {
  36             # m3u8 download
  37             'skip_download': True,
  38         },
  39         'skip': 'Broadcasts are ephemeral',
  40     }]
  41
  42     def _real_extract(self, url):
  43         b_id = self._match_id(url)
  44
  45         base = 'http://hankachi.saitosan-api.net:8002/socket.io/?transport=polling&EIO=3'
  46         sid = self._download_socket_json(base, b_id, note='Opening socket').get('sid')
  47         base += '&sid=' + sid
  48
  49         self._download_webpage(base, b_id, note='Polling socket')
  50         payload = f'420["room_start_join",{{"room_id":"{b_id}"}}]'
  51         payload = f'{len(payload)}:{payload}'
  52
  53         self._download_webpage(base, b_id, data=payload, note='Polling socket with payload')
  54         response = self._download_socket_json(base, b_id, note='Polling socket')
  55         if not response.get('ok'):
  56             err = response.get('error') or {}
  57             raise ExtractorError(
  58                 '{} said: {} - {}'.format(self.IE_NAME, err.get('code', '?'), err.get('msg', 'Unknown')) if err
  59                 else 'The socket reported that the broadcast could not be joined. Maybe it\'s offline or the URL is incorrect',
  60                 expected=True, video_id=b_id)
  61
  62         self._download_webpage(base, b_id, data='26:421["room_finish_join",{}]', note='Polling socket')
  63         b_data = self._download_socket_json(base, b_id, note='Getting broadcast metadata from socket')
  64         m3u8_url = b_data.get('url')
  65
  66         self._download_webpage(base, b_id, data='1:1', note='Closing socket', fatal=False)
  67
  68         return {
  69             'id': b_id,
  70             'title': b_data.get('name'),
  71             'formats': self._extract_m3u8_formats(m3u8_url, b_id, 'mp4', live=True),
  72             'thumbnail': m3u8_url.replace('av.m3u8', 'thumb'),
  73             'uploader': try_get(b_data, lambda x: x['broadcast_user']['name']),  # same as title
  74             'is_live': True,
  75         }