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