yt_dlp/extractor/olympics.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import unified_strdate
   6
   7
   8 class OlympicsReplayIE(InfoExtractor):
   9     _VALID_URL = r'(?:https?://)(?:www\.)?olympics\.com/tokyo-2020/(?:[a-z]{2}/)?replay/(?P<id>[^/#&?]+)'
  10     _TESTS = [{
  11         'url': 'https://olympics.com/tokyo-2020/en/replay/300622eb-abc0-43ea-b03b-c5f2d429ec7b/jumping-team-qualifier',
  12         'info_dict': {
  13             'id': '300622eb-abc0-43ea-b03b-c5f2d429ec7b',
  14             'ext': 'mp4',
  15             'title': 'Jumping Team Qualifier',
  16             'release_date': '20210806',
  17             'upload_date': '20210713',
  18         },
  19         'params': {
  20             'format': 'bv',
  21         },
  22     }, {
  23         'url': 'https://olympics.com/tokyo-2020/en/replay/bd242924-4b22-49a5-a846-f1d4c809250d/mens-bronze-medal-match-hun-esp',
  24         'only_matching': True,
  25     }]
  26
  27     def _real_extract(self, url):
  28         id = self._match_id(url)
  29         # The parameters are hardcoded in the webpage, it's not necessary to download the webpage just for these parameters.
  30         # If in downloading webpage serves other functions aswell, then extract these parameters from it.
  31         token_url = 'https://appovptok.ovpobs.tv/api/identity/app/token?api_key=OTk5NDcxOjpvY3N3LWFwaXVzZXI%3D&api_secret=ODY4ODM2MjE3ODMwYmVjNTAxMWZlMDJiMTYxZmY0MjFiMjMwMjllMjJmNDA1YWRiYzA5ODcxYTZjZTljZDkxOTo6NTM2NWIzNjRlMTM1ZmI2YWNjNmYzMGMzOGM3NzZhZTY%3D'
  32         token = self._download_webpage(token_url, id)
  33         headers = {'x-obs-app-token': token}
  34         data_json = self._download_json(f'https://appocswtok.ovpobs.tv/api/schedule-sessions/{id}?include=stream',
  35                                         id, headers=headers)
  36         meta_data = data_json['data']['attributes']
  37         for t_dict in data_json['included']:
  38             if t_dict.get('type') == 'Stream':
  39                 stream_data = t_dict['attributes']
  40         m3u8_url = self._download_json(
  41             'https://meteringtok.ovpobs.tv/api/playback-sessions', id, headers=headers, query={
  42                 'alias': stream_data['alias'],
  43                 'stream': stream_data['stream'],
  44                 'type': 'vod'
  45             })['data']['attributes']['url']
  46         formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, id)
  47         self._sort_formats(formats)
  48
  49         return {
  50             'id': id,
  51             'title': meta_data['title'],
  52             'release_date': unified_strdate(meta_data.get('start') or meta_data.get('broadcastPublished')),
  53             'upload_date': unified_strdate(meta_data.get('publishedAt')),
  54             'formats': formats,
  55             'subtitles': subtitles,
  56         }