yt_dlp/extractor/sen.py

   1 from .common import InfoExtractor
   2 from ..utils import url_or_none
   3 from ..utils.traversal import traverse_obj
   4
   5
   6 class SenIE(InfoExtractor):
   7     _VALID_URL = r'https?://(?:www\.)?sen\.com/video/(?P<id>[0-9a-f-]+)'
   8     _TEST = {
   9         'url': 'https://www.sen.com/video/eef46eb1-4d79-4e28-be9d-bd937767f8c4',
  10         'md5': 'ff615aca9691053c94f8f10d96cd7884',
  11         'info_dict': {
  12             'id': 'eef46eb1-4d79-4e28-be9d-bd937767f8c4',
  13             'ext': 'mp4',
  14             'description': 'Florida, 28 Sep 2022',
  15             'title': 'Hurricane Ian',
  16             'tags': ['North America', 'Storm', 'Weather'],
  17         },
  18     }
  19
  20     def _real_extract(self, url):
  21         video_id = self._match_id(url)
  22
  23         api_data = self._download_json(f'https://api.sen.com/content/public/video/{video_id}', video_id)
  24         m3u8_url = (traverse_obj(api_data, (
  25             'data', 'nodes', lambda _, v: v['id'] == 'player', 'video', 'url', {url_or_none}, any))
  26             or f'https://vod.sen.com/videos/{video_id}/manifest.m3u8')
  27
  28         return {
  29             'id': video_id,
  30             'formats': self._extract_m3u8_formats(m3u8_url, video_id, 'mp4'),
  31             **traverse_obj(api_data, ('data', 'nodes', lambda _, v: v['id'] == 'details', any, 'content', {
  32                 'title': ('title', 'text', {str}),
  33                 'description': ('descriptions', 0, 'text', {str}),
  34                 'tags': ('badges', ..., 'text', {str}),
  35             })),
  36         }