yt_dlp/extractor/fox.py

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