yt_dlp/extractor/fox.py

   1 import json
   2 import urllib.parse
   3 import uuid
   4
   5 from .common import InfoExtractor
   6 from ..networking.exceptions import HTTPError
   7 from ..utils import (
   8     ExtractorError,
   9     int_or_none,
  10     parse_age_limit,
  11     parse_duration,
  12     traverse_obj,
  13     try_get,
  14     unified_timestamp,
  15     url_or_none,
  16 )
  17
  18
  19 class FOXIE(InfoExtractor):
  20     _VALID_URL = r'https?://(?:www\.)?fox(?:sports)?\.com/(?:watch|replay)/(?P<id>[\da-fA-F]+)'
  21     _TESTS = [{
  22         # clip
  23         'url': 'https://www.fox.com/watch/4b765a60490325103ea69888fb2bd4e8/',
  24         'md5': 'ebd296fcc41dd4b19f8115d8461a3165',
  25         'info_dict': {
  26             'id': '4b765a60490325103ea69888fb2bd4e8',
  27             'ext': 'mp4',
  28             'title': 'Aftermath: Bruce Wayne Develops Into The Dark Knight',
  29             'description': 'md5:549cd9c70d413adb32ce2a779b53b486',
  30             'duration': 102,
  31             'timestamp': 1504291893,
  32             'upload_date': '20170901',
  33             'creator': 'FOX',
  34             'series': 'Gotham',
  35             'age_limit': 14,
  36             'episode': 'Aftermath: Bruce Wayne Develops Into The Dark Knight',
  37             'thumbnail': r're:^https?://.*\.jpg$',
  38         },
  39         'params': {
  40             'skip_download': True,
  41         },
  42     }, {
  43         # episode, geo-restricted
  44         'url': 'https://www.fox.com/watch/087036ca7f33c8eb79b08152b4dd75c1/',
  45         'only_matching': True,
  46     }, {
  47         # sports event, geo-restricted
  48         'url': 'https://www.fox.com/watch/b057484dade738d1f373b3e46216fa2c/',
  49         'only_matching': True,
  50     }, {
  51         # fox sports replay, geo-restricted
  52         'url': 'https://www.foxsports.com/replay/561f3e071347a24e5e877abc56b22e89',
  53         'only_matching': True,
  54     }]
  55     _GEO_BYPASS = False
  56     _HOME_PAGE_URL = 'https://www.fox.com/'
  57     _API_KEY = '6E9S4bmcoNnZwVLOHywOv8PJEdu76cM9'
  58     _access_token = None
  59     _device_id = str(uuid.uuid4())
  60
  61     def _call_api(self, path, video_id, data=None):
  62         headers = {
  63             'X-Api-Key': self._API_KEY,
  64         }
  65         if self._access_token:
  66             headers['Authorization'] = 'Bearer ' + self._access_token
  67         try:
  68             return self._download_json(
  69                 'https://api3.fox.com/v2.0/' + path,
  70                 video_id, data=data, headers=headers)
  71         except ExtractorError as e:
  72             if isinstance(e.cause, HTTPError) and e.cause.status == 403:
  73                 entitlement_issues = self._parse_json(
  74                     e.cause.response.read().decode(), video_id)['entitlementIssues']
  75                 for e in entitlement_issues:
  76                     if e.get('errorCode') == 1005:
  77                         raise ExtractorError(
  78                             'This video is only available via cable service provider '
  79                             'subscription. You may want to use --cookies.', expected=True)
  80                 messages = ', '.join([e['message'] for e in entitlement_issues])
  81                 raise ExtractorError(messages, expected=True)
  82             raise
  83
  84     def _real_initialize(self):
  85         if not self._access_token:
  86             mvpd_auth = self._get_cookies(self._HOME_PAGE_URL).get('mvpd-auth')
  87             if mvpd_auth:
  88                 self._access_token = (self._parse_json(urllib.parse.unquote(
  89                     mvpd_auth.value), None, fatal=False) or {}).get('accessToken')
  90             if not self._access_token:
  91                 self._access_token = self._call_api(
  92                     'login', None, json.dumps({
  93                         'deviceId': self._device_id,
  94                     }).encode())['accessToken']
  95
  96     def _real_extract(self, url):
  97         video_id = self._match_id(url)
  98
  99         self._access_token = self._call_api(
 100             f'previewpassmvpd?device_id={self._device_id}&mvpd_id=TempPass_fbcfox_60min',
 101             video_id)['accessToken']
 102
 103         video = self._call_api('watch', video_id, data=json.dumps({
 104             'capabilities': ['drm/widevine', 'fsdk/yo'],
 105             'deviceWidth': 1280,
 106             'deviceHeight': 720,
 107             'maxRes': '720p',
 108             'os': 'macos',
 109             'osv': '',
 110             'provider': {
 111                 'freewheel': {'did': self._device_id},
 112                 'vdms': {'rays': ''},
 113                 'dmp': {'kuid': '', 'seg': ''},
 114             },
 115             'playlist': '',
 116             'privacy': {'us': '1---'},
 117             'siteSection': '',
 118             'streamType': 'vod',
 119             'streamId': video_id}).encode())
 120
 121         title = video['name']
 122         release_url = video['url']
 123
 124         try:
 125             m3u8_url = self._download_json(release_url, video_id)['playURL']
 126         except ExtractorError as e:
 127             if isinstance(e.cause, HTTPError) and e.cause.status == 403:
 128                 error = self._parse_json(e.cause.response.read().decode(), video_id)
 129                 if error.get('exception') == 'GeoLocationBlocked':
 130                     self.raise_geo_restricted(countries=['US'])
 131                 raise ExtractorError(error['description'], expected=True)
 132             raise
 133         formats = self._extract_m3u8_formats(
 134             m3u8_url, video_id, 'mp4',
 135             entry_protocol='m3u8_native', m3u8_id='hls')
 136
 137         data = try_get(
 138             video, lambda x: x['trackingData']['properties'], dict) or {}
 139
 140         duration = int_or_none(video.get('durationInSeconds')) or int_or_none(
 141             video.get('duration')) or parse_duration(video.get('duration'))
 142         timestamp = unified_timestamp(video.get('datePublished'))
 143         creator = data.get('brand') or data.get('network') or video.get('network')
 144         series = video.get('seriesName') or data.get(
 145             'seriesName') or data.get('show')
 146
 147         subtitles = {}
 148         for doc_rel in video.get('documentReleases', []):
 149             rel_url = doc_rel.get('url')
 150             if not url or doc_rel.get('format') != 'SCC':
 151                 continue
 152             subtitles['en'] = [{
 153                 'url': rel_url,
 154                 'ext': 'scc',
 155             }]
 156             break
 157
 158         return {
 159             'id': video_id,
 160             'title': title,
 161             'formats': formats,
 162             'description': video.get('description'),
 163             'duration': duration,
 164             'timestamp': timestamp,
 165             'age_limit': parse_age_limit(video.get('contentRating')),
 166             'creator': creator,
 167             'series': series,
 168             'season_number': int_or_none(video.get('seasonNumber')),
 169             'episode': video.get('name'),
 170             'episode_number': int_or_none(video.get('episodeNumber')),
 171             'thumbnail': traverse_obj(video, ('images', 'still', 'raw'), expected_type=url_or_none),
 172             'release_year': int_or_none(video.get('releaseYear')),
 173             'subtitles': subtitles,
 174         }