yt_dlp/extractor/foxsports.py

   1 from .common import InfoExtractor
   2 from .uplynk import UplynkPreplayIE
   3 from ..networking import HEADRequest
   4 from ..utils import float_or_none, make_archive_id, smuggle_url
   5
   6
   7 class FoxSportsIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?foxsports\.com/watch/(?P<id>[\w-]+)'
   9     _TESTS = [{
  10         'url': 'https://www.foxsports.com/watch/play-612168c6700004b',
  11         'info_dict': {
  12             'id': 'b72f5bd8658140baa5791bb676433733',
  13             'ext': 'mp4',
  14             'display_id': 'play-612168c6700004b',
  15             'title': 'md5:e0c4ecac3a1f25295b4fae22fb5c126a',
  16             'description': 'md5:371bc43609708ae2b9e1a939229762af',
  17             'uploader_id': '06b4a36349624051a9ba52ac3a91d268',
  18             'upload_date': '20221205',
  19             'timestamp': 1670262586,
  20             'duration': 31.7317,
  21             'thumbnail': r're:^https?://.*\.jpg$',
  22             'extra_param_to_segment_url': str,
  23         },
  24         'params': {
  25             'skip_download': 'm3u8',
  26         },
  27     }]
  28
  29     def _real_extract(self, url):
  30         video_id = self._match_id(url)
  31         webpage = self._download_webpage(url, video_id)
  32         json_ld = self._search_json_ld(webpage, video_id, expected_type='VideoObject', default={})
  33         data = self._download_json(
  34             f'https://api3.fox.com/v2.0/vodplayer/sportsclip/{video_id}',
  35             video_id, note='Downloading API JSON', headers={
  36                 'x-api-key': 'cf289e299efdfa39fb6316f259d1de93',
  37             })
  38         preplay_url = self._request_webpage(
  39             HEADRequest(data['url']), video_id, 'Fetching preplay URL').url
  40
  41         return {
  42             '_type': 'url_transparent',
  43             'ie_key': UplynkPreplayIE.ie_key(),
  44             'url': smuggle_url(preplay_url, {'Origin': 'https://www.foxsports.com'}),
  45             'display_id': video_id,
  46             'title': data.get('name') or json_ld.get('title'),
  47             'description': data.get('description') or json_ld.get('description'),
  48             'duration': float_or_none(data.get('durationInSeconds')),
  49             'timestamp': json_ld.get('timestamp'),
  50             'thumbnails': json_ld.get('thumbnails'),
  51             '_old_archive_ids': [make_archive_id(self, video_id)],
  52         }