summaryrefslogtreecommitdiffstats
path: root/yt_dlp/extractor/fox.py
blob: e00e977bdd2cab734e6f83c480847f6ba6668114 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
import json
import uuid

from .common import InfoExtractor
from ..compat import (
    compat_str,
    compat_urllib_parse_unquote,
)
from ..networking.exceptions import HTTPError
from ..utils import (
    ExtractorError,
    int_or_none,
    parse_age_limit,
    parse_duration,
    traverse_obj,
    try_get,
    unified_timestamp,
    url_or_none,
)


class FOXIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?fox(?:sports)?\.com/(?:watch|replay)/(?P<id>[\da-fA-F]+)'
    _TESTS = [{
        # clip
        'url': 'https://www.fox.com/watch/4b765a60490325103ea69888fb2bd4e8/',
        'md5': 'ebd296fcc41dd4b19f8115d8461a3165',
        'info_dict': {
            'id': '4b765a60490325103ea69888fb2bd4e8',
            'ext': 'mp4',
            'title': 'Aftermath: Bruce Wayne Develops Into The Dark Knight',
            'description': 'md5:549cd9c70d413adb32ce2a779b53b486',
            'duration': 102,
            'timestamp': 1504291893,
            'upload_date': '20170901',
            'creator': 'FOX',
            'series': 'Gotham',
            'age_limit': 14,
            'episode': 'Aftermath: Bruce Wayne Develops Into The Dark Knight',
            'thumbnail': r're:^https?://.*\.jpg$',
        },
        'params': {
            'skip_download': True,
        },
    }, {
        # episode, geo-restricted
        'url': 'https://www.fox.com/watch/087036ca7f33c8eb79b08152b4dd75c1/',
        'only_matching': True,
    }, {
        # sports event, geo-restricted
        'url': 'https://www.fox.com/watch/b057484dade738d1f373b3e46216fa2c/',
        'only_matching': True,
    }, {
        # fox sports replay, geo-restricted
        'url': 'https://www.foxsports.com/replay/561f3e071347a24e5e877abc56b22e89',
        'only_matching': True,
    }]
    _GEO_BYPASS = False
    _HOME_PAGE_URL = 'https://www.fox.com/'
    _API_KEY = '6E9S4bmcoNnZwVLOHywOv8PJEdu76cM9'
    _access_token = None
    _device_id = compat_str(uuid.uuid4())

    def _call_api(self, path, video_id, data=None):
        headers = {
            'X-Api-Key': self._API_KEY,
        }
        if self._access_token:
            headers['Authorization'] = 'Bearer ' + self._access_token
        try:
            return self._download_json(
                'https://api3.fox.com/v2.0/' + path,
                video_id, data=data, headers=headers)
        except ExtractorError as e:
            if isinstance(e.cause, HTTPError) and e.cause.status == 403:
                entitlement_issues = self._parse_json(
                    e.cause.response.read().decode(), video_id)['entitlementIssues']
                for e in entitlement_issues:
                    if e.get('errorCode') == 1005:
                        raise ExtractorError(
                            'This video is only available via cable service provider '
                            'subscription. You may want to use --cookies.', expected=True)
                messages = ', '.join([e['message'] for e in entitlement_issues])
                raise ExtractorError(messages, expected=True)
            raise

    def _real_initialize(self):
        if not self._access_token:
            mvpd_auth = self._get_cookies(self._HOME_PAGE_URL).get('mvpd-auth')
            if mvpd_auth:
                self._access_token = (self._parse_json(compat_urllib_parse_unquote(
                    mvpd_auth.value), None, fatal=False) or {}).get('accessToken')
            if not self._access_token:
                self._access_token = self._call_api(
                    'login', None, json.dumps({
                        'deviceId': self._device_id,
                    }).encode())['accessToken']

    def _real_extract(self, url):
        video_id = self._match_id(url)

        self._access_token = self._call_api(
            'previewpassmvpd?device_id=%s&mvpd_id=TempPass_fbcfox_60min' % self._device_id,
            video_id)['accessToken']

        video = self._call_api('watch', video_id, data=json.dumps({
            'capabilities': ['drm/widevine', 'fsdk/yo'],
            'deviceWidth': 1280,
            'deviceHeight': 720,
            'maxRes': '720p',
            'os': 'macos',
            'osv': '',
            'provider': {
                'freewheel': {'did': self._device_id},
                'vdms': {'rays': ''},
                'dmp': {'kuid': '', 'seg': ''}
            },
            'playlist': '',
            'privacy': {'us': '1---'},
            'siteSection': '',
            'streamType': 'vod',
            'streamId': video_id}).encode('utf-8'))

        title = video['name']
        release_url = video['url']

        try:
            m3u8_url = self._download_json(release_url, video_id)['playURL']
        except ExtractorError as e:
            if isinstance(e.cause, HTTPError) and e.cause.status == 403:
                error = self._parse_json(e.cause.response.read().decode(), video_id)
                if error.get('exception') == 'GeoLocationBlocked':
                    self.raise_geo_restricted(countries=['US'])
                raise ExtractorError(error['description'], expected=True)
            raise
        formats = self._extract_m3u8_formats(
            m3u8_url, video_id, 'mp4',
            entry_protocol='m3u8_native', m3u8_id='hls')

        data = try_get(
            video, lambda x: x['trackingData']['properties'], dict) or {}

        duration = int_or_none(video.get('durationInSeconds')) or int_or_none(
            video.get('duration')) or parse_duration(video.get('duration'))
        timestamp = unified_timestamp(video.get('datePublished'))
        creator = data.get('brand') or data.get('network') or video.get('network')
        series = video.get('seriesName') or data.get(
            'seriesName') or data.get('show')

        subtitles = {}
        for doc_rel in video.get('documentReleases', []):
            rel_url = doc_rel.get('url')
            if not url or doc_rel.get('format') != 'SCC':
                continue
            subtitles['en'] = [{
                'url': rel_url,
                'ext': 'scc',
            }]
            break

        return {
            'id': video_id,
            'title': title,
            'formats': formats,
            'description': video.get('description'),
            'duration': duration,
            'timestamp': timestamp,
            'age_limit': parse_age_limit(video.get('contentRating')),
            'creator': creator,
            'series': series,
            'season_number': int_or_none(video.get('seasonNumber')),
            'episode': video.get('name'),
            'episode_number': int_or_none(video.get('episodeNumber')),
            'thumbnail': traverse_obj(video, ('images', 'still', 'raw'), expected_type=url_or_none),
            'release_year': int_or_none(video.get('releaseYear')),
            'subtitles': subtitles,
        }