yt_dlp/extractor/cbssports.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 # from .cbs import CBSBaseIE
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     int_or_none,
   9     try_get,
  10 )
  11
  12
  13 # class CBSSportsEmbedIE(CBSBaseIE):
  14 class CBSSportsEmbedIE(InfoExtractor):
  15     IE_NAME = 'cbssports:embed'
  16     _VALID_URL = r'''(?ix)https?://(?:(?:www\.)?cbs|embed\.247)sports\.com/player/embed.+?
  17         (?:
  18             ids%3D(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})|
  19             pcid%3D(?P<pcid>\d+)
  20         )'''
  21     _TESTS = [{
  22         'url': 'https://www.cbssports.com/player/embed/?args=player_id%3Db56c03a6-231a-4bbe-9c55-af3c8a8e9636%26ids%3Db56c03a6-231a-4bbe-9c55-af3c8a8e9636%26resizable%3D1%26autoplay%3Dtrue%26domain%3Dcbssports.com%26comp_ads_enabled%3Dfalse%26watchAndRead%3D0%26startTime%3D0%26env%3Dprod',
  23         'only_matching': True,
  24     }, {
  25         'url': 'https://embed.247sports.com/player/embed/?args=%3fplayer_id%3d1827823171591%26channel%3dcollege-football-recruiting%26pcid%3d1827823171591%26width%3d640%26height%3d360%26autoplay%3dTrue%26comp_ads_enabled%3dFalse%26uvpc%3dhttps%253a%252f%252fwww.cbssports.com%252fapi%252fcontent%252fvideo%252fconfig%252f%253fcfg%253duvp_247sports_v4%2526partner%253d247%26uvpc_m%3dhttps%253a%252f%252fwww.cbssports.com%252fapi%252fcontent%252fvideo%252fconfig%252f%253fcfg%253duvp_247sports_m_v4%2526partner_m%253d247_mobile%26utag%3d247sportssite%26resizable%3dTrue',
  26         'only_matching': True,
  27     }]
  28
  29     # def _extract_video_info(self, filter_query, video_id):
  30     #     return self._extract_feed_info('dJ5BDC', 'VxxJg8Ymh8sE', filter_query, video_id)
  31
  32     def _real_extract(self, url):
  33         uuid, pcid = re.match(self._VALID_URL, url).groups()
  34         query = {'id': uuid} if uuid else {'pcid': pcid}
  35         video = self._download_json(
  36             'https://www.cbssports.com/api/content/video/',
  37             uuid or pcid, query=query)[0]
  38         video_id = video['id']
  39         title = video['title']
  40         metadata = video.get('metaData') or {}
  41         # return self._extract_video_info('byId=%d' % metadata['mpxOutletId'], video_id)
  42         # return self._extract_video_info('byGuid=' + metadata['mpxRefId'], video_id)
  43
  44         formats = self._extract_m3u8_formats(
  45             metadata['files'][0]['url'], video_id, 'mp4',
  46             'm3u8_native', m3u8_id='hls', fatal=False)
  47         self._sort_formats(formats)
  48
  49         image = video.get('image')
  50         thumbnails = None
  51         if image:
  52             image_path = image.get('path')
  53             if image_path:
  54                 thumbnails = [{
  55                     'url': image_path,
  56                     'width': int_or_none(image.get('width')),
  57                     'height': int_or_none(image.get('height')),
  58                     'filesize': int_or_none(image.get('size')),
  59                 }]
  60
  61         return {
  62             'id': video_id,
  63             'title': title,
  64             'formats': formats,
  65             'thumbnails': thumbnails,
  66             'description': video.get('description'),
  67             'timestamp': int_or_none(try_get(video, lambda x: x['dateCreated']['epoch'])),
  68             'duration': int_or_none(metadata.get('duration')),
  69         }
  70
  71
  72 class CBSSportsBaseIE(InfoExtractor):
  73     def _real_extract(self, url):
  74         display_id = self._match_id(url)
  75         webpage = self._download_webpage(url, display_id)
  76         iframe_url = self._search_regex(
  77             r'<iframe[^>]+(?:data-)?src="(https?://[^/]+/player/embed[^"]+)"',
  78             webpage, 'embed url')
  79         return self.url_result(iframe_url, CBSSportsEmbedIE.ie_key())
  80
  81
  82 class CBSSportsIE(CBSSportsBaseIE):
  83     IE_NAME = 'cbssports'
  84     _VALID_URL = r'https?://(?:www\.)?cbssports\.com/[^/]+/video/(?P<id>[^/?#&]+)'
  85     _TESTS = [{
  86         'url': 'https://www.cbssports.com/college-football/video/cover-3-stanford-spring-gleaning/',
  87         'info_dict': {
  88             'id': 'b56c03a6-231a-4bbe-9c55-af3c8a8e9636',
  89             'ext': 'mp4',
  90             'title': 'Cover 3: Stanford Spring Gleaning',
  91             'description': 'The Cover 3 crew break down everything you need to know about the Stanford Cardinal this spring.',
  92             'timestamp': 1617218398,
  93             'upload_date': '20210331',
  94             'duration': 502,
  95         },
  96     }]
  97
  98
  99 class TwentyFourSevenSportsIE(CBSSportsBaseIE):
 100     IE_NAME = '247sports'
 101     _VALID_URL = r'https?://(?:www\.)?247sports\.com/Video/(?:[^/?#&]+-)?(?P<id>\d+)'
 102     _TESTS = [{
 103         'url': 'https://247sports.com/Video/2021-QB-Jake-Garcia-senior-highlights-through-five-games-10084854/',
 104         'info_dict': {
 105             'id': '4f1265cb-c3b5-44a8-bb1d-1914119a0ccc',
 106             'ext': 'mp4',
 107             'title': '2021 QB Jake Garcia senior highlights through five games',
 108             'description': 'md5:8cb67ebed48e2e6adac1701e0ff6e45b',
 109             'timestamp': 1607114223,
 110             'upload_date': '20201204',
 111             'duration': 208,
 112         },
 113     }]