yt_dlp/extractor/fancode.py

   1 from .common import InfoExtractor
   2
   3 from ..compat import compat_str
   4 from ..utils import (
   5     parse_iso8601,
   6     ExtractorError,
   7     try_get,
   8     mimetype2ext
   9 )
  10
  11
  12 class FancodeVodIE(InfoExtractor):
  13     _WORKING = False
  14     IE_NAME = 'fancode:vod'
  15
  16     _VALID_URL = r'https?://(?:www\.)?fancode\.com/video/(?P<id>[0-9]+)\b'
  17
  18     _TESTS = [{
  19         'url': 'https://fancode.com/video/15043/match-preview-pbks-vs-mi',
  20         'params': {
  21             'skip_download': True,
  22         },
  23         'info_dict': {
  24             'id': '6249806281001',
  25             'ext': 'mp4',
  26             'title': 'Match Preview: PBKS vs MI',
  27             'thumbnail': r're:^https?://.*\.jpg$',
  28             "timestamp": 1619081590,
  29             'view_count': int,
  30             'like_count': int,
  31             'upload_date': '20210422',
  32             'uploader_id': '6008340455001'
  33         }
  34     }, {
  35         'url': 'https://fancode.com/video/15043',
  36         'only_matching': True,
  37     }]
  38
  39     _ACCESS_TOKEN = None
  40     _NETRC_MACHINE = 'fancode'
  41
  42     _LOGIN_HINT = 'Use "--username refresh --password <refresh_token>" to login using a refresh token'
  43
  44     headers = {
  45         'content-type': 'application/json',
  46         'origin': 'https://fancode.com',
  47         'referer': 'https://fancode.com',
  48     }
  49
  50     def _perform_login(self, username, password):
  51         # Access tokens are shortlived, so get them using the refresh token.
  52         if username != 'refresh':
  53             self.report_warning(f'Login using username and password is not currently supported. {self._LOGIN_HINT}')
  54
  55         self.report_login()
  56         data = '''{
  57             "query":"mutation RefreshToken($refreshToken: String\\u0021) { refreshToken(refreshToken: $refreshToken) { accessToken }}",
  58             "variables":{
  59                 "refreshToken":"%s"
  60             },
  61             "operationName":"RefreshToken"
  62         }''' % password
  63
  64         token_json = self.download_gql('refresh token', data, "Getting the Access token")
  65         self._ACCESS_TOKEN = try_get(token_json, lambda x: x['data']['refreshToken']['accessToken'])
  66         if self._ACCESS_TOKEN is None:
  67             self.report_warning('Failed to get Access token')
  68         else:
  69             self.headers.update({'Authorization': 'Bearer %s' % self._ACCESS_TOKEN})
  70
  71     def _check_login_required(self, is_available, is_premium):
  72         msg = None
  73         if is_premium and self._ACCESS_TOKEN is None:
  74             msg = f'This video is only available for registered users. {self._LOGIN_HINT}'
  75         elif not is_available and self._ACCESS_TOKEN is not None:
  76             msg = 'This video isn\'t available to the current logged in account'
  77         if msg:
  78             self.raise_login_required(msg, metadata_available=True, method=None)
  79
  80     def download_gql(self, variable, data, note, fatal=False, headers=headers):
  81         return self._download_json(
  82             'https://www.fancode.com/graphql', variable,
  83             data=data.encode(), note=note,
  84             headers=headers, fatal=fatal)
  85
  86     def _real_extract(self, url):
  87
  88         BRIGHTCOVE_URL_TEMPLATE = 'https://players.brightcove.net/%s/default_default/index.html?videoId=%s'
  89         video_id = self._match_id(url)
  90
  91         brightcove_user_id = '6008340455001'
  92         data = '''{
  93             "query":"query Video($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 }}",
  94             "variables":{
  95                 "id":%s,
  96                 "filter":{
  97                     "contentDataType":"DEFAULT"
  98                 }
  99             },
 100             "operationName":"Video"
 101         }''' % video_id
 102
 103         metadata_json = self.download_gql(video_id, data, note='Downloading metadata')
 104
 105         media = try_get(metadata_json, lambda x: x['data']['media'], dict) or {}
 106         brightcove_video_id = try_get(media, lambda x: x['mediaSource']['brightcove'], compat_str)
 107
 108         if brightcove_video_id is None:
 109             raise ExtractorError('Unable to extract brightcove Video ID')
 110
 111         is_premium = media.get('isPremium')
 112
 113         self._check_login_required(media.get('isUserEntitled'), is_premium)
 114
 115         return {
 116             '_type': 'url_transparent',
 117             'url': BRIGHTCOVE_URL_TEMPLATE % (brightcove_user_id, brightcove_video_id),
 118             'ie_key': 'BrightcoveNew',
 119             'id': video_id,
 120             'title': media['title'],
 121             'like_count': media.get('totalUpvotes'),
 122             'view_count': media.get('totalViews'),
 123             'tags': media.get('tags'),
 124             'release_timestamp': parse_iso8601(media.get('publishedTime')),
 125             'availability': self._availability(needs_premium=is_premium),
 126         }
 127
 128
 129 class FancodeLiveIE(FancodeVodIE):  # XXX: Do not subclass from concrete IE
 130     _WORKING = False
 131     IE_NAME = 'fancode:live'
 132
 133     _VALID_URL = r'https?://(www\.)?fancode\.com/match/(?P<id>[0-9]+).+'
 134
 135     _TESTS = [{
 136         'url': 'https://fancode.com/match/35328/cricket-fancode-ecs-hungary-2021-bub-vs-blb?slug=commentary',
 137         'info_dict': {
 138             'id': '35328',
 139             'ext': 'mp4',
 140             'title': 'BUB vs BLB',
 141             "timestamp": 1624863600,
 142             'is_live': True,
 143             'upload_date': '20210628',
 144         },
 145         'skip': 'Ended'
 146     }, {
 147         'url': 'https://fancode.com/match/35328/',
 148         'only_matching': True,
 149     }, {
 150         'url': 'https://fancode.com/match/35567?slug=scorecard',
 151         'only_matching': True,
 152     }]
 153
 154     def _real_extract(self, url):
 155
 156         id = self._match_id(url)
 157         data = '''{
 158             "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}",
 159             "variables":{
 160                 "id":%s,
 161                 "isLoggedIn":true
 162             },
 163             "operationName":"MatchResponse"
 164         }''' % id
 165
 166         info_json = self.download_gql(id, data, "Info json")
 167
 168         match_info = try_get(info_json, lambda x: x['data']['match'])
 169
 170         if match_info.get('streamingStatus') != "STARTED":
 171             raise ExtractorError('The stream can\'t be accessed', expected=True)
 172         self._check_login_required(match_info.get('isUserEntitled'), True)  # all live streams are premium only
 173
 174         return {
 175             'id': id,
 176             'title': match_info.get('name'),
 177             'formats': self._extract_akamai_formats(try_get(match_info, lambda x: x['videoStreamUrl']['url']), id),
 178             'ext': mimetype2ext(try_get(match_info, lambda x: x['videoStreamUrl']['deliveryType'])),
 179             'is_live': True,
 180             'release_timestamp': parse_iso8601(match_info.get('startTime'))
 181         }