summaryrefslogtreecommitdiffstats
path: root/yt_dlp/extractor/fancode.py
blob: 1b5db818a19c3e40093ad3cc46e3569c98ff447e (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
178
179
from .common import InfoExtractor

from ..compat import compat_str
from ..utils import (
    parse_iso8601,
    ExtractorError,
    try_get,
    mimetype2ext
)


class FancodeVodIE(InfoExtractor):
    IE_NAME = 'fancode:vod'

    _VALID_URL = r'https?://(?:www\.)?fancode\.com/video/(?P<id>[0-9]+)\b'

    _TESTS = [{
        'url': 'https://fancode.com/video/15043/match-preview-pbks-vs-mi',
        'params': {
            'skip_download': True,
        },
        'info_dict': {
            'id': '6249806281001',
            'ext': 'mp4',
            'title': 'Match Preview: PBKS vs MI',
            'thumbnail': r're:^https?://.*\.jpg$',
            "timestamp": 1619081590,
            'view_count': int,
            'like_count': int,
            'upload_date': '20210422',
            'uploader_id': '6008340455001'
        }
    }, {
        'url': 'https://fancode.com/video/15043',
        'only_matching': True,
    }]

    _ACCESS_TOKEN = None
    _NETRC_MACHINE = 'fancode'

    _LOGIN_HINT = 'Use "--username refresh --password <refresh_token>" to login using a refresh token'

    headers = {
        'content-type': 'application/json',
        'origin': 'https://fancode.com',
        'referer': 'https://fancode.com',
    }

    def _perform_login(self, username, password):
        # Access tokens are shortlived, so get them using the refresh token.
        if username != 'refresh':
            self.report_warning(f'Login using username and password is not currently supported. {self._LOGIN_HINT}')

        self.report_login()
        data = '''{
            "query":"mutation RefreshToken($refreshToken: String\\u0021) { refreshToken(refreshToken: $refreshToken) { accessToken }}",
            "variables":{
                "refreshToken":"%s"
            },
            "operationName":"RefreshToken"
        }''' % password

        token_json = self.download_gql('refresh token', data, "Getting the Access token")
        self._ACCESS_TOKEN = try_get(token_json, lambda x: x['data']['refreshToken']['accessToken'])
        if self._ACCESS_TOKEN is None:
            self.report_warning('Failed to get Access token')
        else:
            self.headers.update({'Authorization': 'Bearer %s' % self._ACCESS_TOKEN})

    def _check_login_required(self, is_available, is_premium):
        msg = None
        if is_premium and self._ACCESS_TOKEN is None:
            msg = f'This video is only available for registered users. {self._LOGIN_HINT}'
        elif not is_available and self._ACCESS_TOKEN is not None:
            msg = 'This video isn\'t available to the current logged in account'
        if msg:
            self.raise_login_required(msg, metadata_available=True, method=None)

    def download_gql(self, variable, data, note, fatal=False, headers=headers):
        return self._download_json(
            'https://www.fancode.com/graphql', variable,
            data=data.encode(), note=note,
            headers=headers, fatal=fatal)

    def _real_extract(self, url):

        BRIGHTCOVE_URL_TEMPLATE = 'https://players.brightcove.net/%s/default_default/index.html?videoId=%s'
        video_id = self._match_id(url)

        brightcove_user_id = '6008340455001'
        data = '''{
            "query":"query Video($id: Int\\u0021, $filter: SegmentFilter) { media(id: $id, filter: $filter) { id contentId title contentId publishedTime totalViews totalUpvotes provider thumbnail { src } mediaSource {brightcove } duration isPremium isUserEntitled tags duration }}",
            "variables":{
                "id":%s,
                "filter":{
                    "contentDataType":"DEFAULT"
                }
            },
            "operationName":"Video"
        }''' % video_id

        metadata_json = self.download_gql(video_id, data, note='Downloading metadata')

        media = try_get(metadata_json, lambda x: x['data']['media'], dict) or {}
        brightcove_video_id = try_get(media, lambda x: x['mediaSource']['brightcove'], compat_str)

        if brightcove_video_id is None:
            raise ExtractorError('Unable to extract brightcove Video ID')

        is_premium = media.get('isPremium')

        self._check_login_required(media.get('isUserEntitled'), is_premium)

        return {
            '_type': 'url_transparent',
            'url': BRIGHTCOVE_URL_TEMPLATE % (brightcove_user_id, brightcove_video_id),
            'ie_key': 'BrightcoveNew',
            'id': video_id,
            'title': media['title'],
            'like_count': media.get('totalUpvotes'),
            'view_count': media.get('totalViews'),
            'tags': media.get('tags'),
            'release_timestamp': parse_iso8601(media.get('publishedTime')),
            'availability': self._availability(needs_premium=is_premium),
        }


class FancodeLiveIE(FancodeVodIE):  # XXX: Do not subclass from concrete IE
    IE_NAME = 'fancode:live'

    _VALID_URL = r'https?://(www\.)?fancode\.com/match/(?P<id>[0-9]+).+'

    _TESTS = [{
        'url': 'https://fancode.com/match/35328/cricket-fancode-ecs-hungary-2021-bub-vs-blb?slug=commentary',
        'info_dict': {
            'id': '35328',
            'ext': 'mp4',
            'title': 'BUB vs BLB',
            "timestamp": 1624863600,
            'is_live': True,
            'upload_date': '20210628',
        },
        'skip': 'Ended'
    }, {
        'url': 'https://fancode.com/match/35328/',
        'only_matching': True,
    }, {
        'url': 'https://fancode.com/match/35567?slug=scorecard',
        'only_matching': True,
    }]

    def _real_extract(self, url):

        id = self._match_id(url)
        data = '''{
            "query":"query MatchResponse($id: Int\\u0021, $isLoggedIn: Boolean\\u0021) { match: matchWithScores(id: $id) { id matchDesc mediaId videoStreamId videoStreamUrl { ...VideoSource } liveStreams { videoStreamId videoStreamUrl { ...VideoSource } contentId } name startTime streamingStatus isPremium isUserEntitled @include(if: $isLoggedIn) status metaTags bgImage { src } sport { name slug } tour { id name } squads { name shortName } liveStreams { contentId } mediaId }}fragment VideoSource on VideoSource { title description posterUrl url deliveryType playerType}",
            "variables":{
                "id":%s,
                "isLoggedIn":true
            },
            "operationName":"MatchResponse"
        }''' % id

        info_json = self.download_gql(id, data, "Info json")

        match_info = try_get(info_json, lambda x: x['data']['match'])

        if match_info.get('streamingStatus') != "STARTED":
            raise ExtractorError('The stream can\'t be accessed', expected=True)
        self._check_login_required(match_info.get('isUserEntitled'), True)  # all live streams are premium only

        return {
            'id': id,
            'title': match_info.get('name'),
            'formats': self._extract_akamai_formats(try_get(match_info, lambda x: x['videoStreamUrl']['url']), id),
            'ext': mimetype2ext(try_get(match_info, lambda x: x['videoStreamUrl']['deliveryType'])),
            'is_live': True,
            'release_timestamp': parse_iso8601(match_info.get('startTime'))
        }