yt_dlp/extractor/fancode.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6 from ..compat import compat_str
   7 from ..utils import (
   8     parse_iso8601,
   9     ExtractorError,
  10     try_get,
  11     mimetype2ext
  12 )
  13
  14
  15 class FancodeVodIE(InfoExtractor):
  16     IE_NAME = 'fancode:vod'
  17
  18     _VALID_URL = r'https?://(?:www\.)?fancode\.com/video/(?P<id>[0-9]+)\b'
  19
  20     _TESTS = [{
  21         'url': 'https://fancode.com/video/15043/match-preview-pbks-vs-mi',
  22         'params': {
  23             'skip_download': True,
  24             'format': 'bestvideo'
  25         },
  26         'info_dict': {
  27             'id': '6249806281001',
  28             'ext': 'mp4',
  29             'title': 'Match Preview: PBKS vs MI',
  30             'thumbnail': r're:^https?://.*\.jpg$',
  31             "timestamp": 1619081590,
  32             'view_count': int,
  33             'like_count': int,
  34             'upload_date': '20210422',
  35             'uploader_id': '6008340455001'
  36         }
  37     }, {
  38         'url': 'https://fancode.com/video/15043',
  39         'only_matching': True,
  40     }]
  41
  42     _ACCESS_TOKEN = None
  43     _NETRC_MACHINE = 'fancode'
  44
  45     _LOGIN_HINT = 'Use "--user refresh --password <refresh_token>" to login using a refresh token'
  46
  47     headers = {
  48         'content-type': 'application/json',
  49         'origin': 'https://fancode.com',
  50         'referer': 'https://fancode.com',
  51     }
  52
  53     def _login(self):
  54         # Access tokens are shortlived, so get them using the refresh token.
  55         username, password = self._get_login_info()
  56         if username == 'refresh' and password is not None:
  57             self.report_login()
  58             data = '''{
  59                 "query":"mutation RefreshToken($refreshToken: String\\u0021) { refreshToken(refreshToken: $refreshToken) { accessToken }}",
  60                 "variables":{
  61                     "refreshToken":"%s"
  62                 },
  63                 "operationName":"RefreshToken"
  64             }''' % password
  65
  66             token_json = self.download_gql('refresh token', data, "Getting the Access token")
  67             self._ACCESS_TOKEN = try_get(token_json, lambda x: x['data']['refreshToken']['accessToken'])
  68             if self._ACCESS_TOKEN is None:
  69                 self.report_warning('Failed to get Access token')
  70             else:
  71                 self.headers.update({'Authorization': 'Bearer %s' % self._ACCESS_TOKEN})
  72         elif username is not None:
  73             self.report_warning(f'Login using username and password is not currently supported. {self._LOGIN_HINT}')
  74
  75     def _real_initialize(self):
  76         self._login()
  77
  78     def _check_login_required(self, is_available, is_premium):
  79         msg = None
  80         if is_premium and self._ACCESS_TOKEN is None:
  81             msg = f'This video is only available for registered users. {self._LOGIN_HINT}'
  82         elif not is_available and self._ACCESS_TOKEN is not None:
  83             msg = 'This video isn\'t available to the current logged in account'
  84         if msg:
  85             self.raise_login_required(msg, metadata_available=True, method=None)
  86
  87     def download_gql(self, variable, data, note, fatal=False, headers=headers):
  88         return self._download_json(
  89             'https://www.fancode.com/graphql', variable,
  90             data=data.encode(), note=note,
  91             headers=headers, fatal=fatal)
  92
  93     def _real_extract(self, url):
  94
  95         BRIGHTCOVE_URL_TEMPLATE = 'https://players.brightcove.net/%s/default_default/index.html?videoId=%s'
  96         video_id = self._match_id(url)
  97
  98         brightcove_user_id = '6008340455001'
  99         data = '''{
 100             "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 }}",
 101             "variables":{
 102                 "id":%s,
 103                 "filter":{
 104                     "contentDataType":"DEFAULT"
 105                 }
 106             },
 107             "operationName":"Video"
 108         }''' % video_id
 109
 110         metadata_json = self.download_gql(video_id, data, note='Downloading metadata')
 111
 112         media = try_get(metadata_json, lambda x: x['data']['media'], dict) or {}
 113         brightcove_video_id = try_get(media, lambda x: x['mediaSource']['brightcove'], compat_str)
 114
 115         if brightcove_video_id is None:
 116             raise ExtractorError('Unable to extract brightcove Video ID')
 117
 118         is_premium = media.get('isPremium')
 119
 120         self._check_login_required(media.get('isUserEntitled'), is_premium)
 121
 122         return {
 123             '_type': 'url_transparent',
 124             'url': BRIGHTCOVE_URL_TEMPLATE % (brightcove_user_id, brightcove_video_id),
 125             'ie_key': 'BrightcoveNew',
 126             'id': video_id,
 127             'title': media['title'],
 128             'like_count': media.get('totalUpvotes'),
 129             'view_count': media.get('totalViews'),
 130             'tags': media.get('tags'),
 131             'release_timestamp': parse_iso8601(media.get('publishedTime')),
 132             'availability': self._availability(needs_premium=is_premium),
 133         }
 134
 135
 136 class FancodeLiveIE(FancodeVodIE):
 137     IE_NAME = 'fancode:live'
 138
 139     _VALID_URL = r'https?://(www\.)?fancode\.com/match/(?P<id>[0-9]+).+'
 140
 141     _TESTS = [{
 142         'url': 'https://fancode.com/match/35328/cricket-fancode-ecs-hungary-2021-bub-vs-blb?slug=commentary',
 143         'info_dict': {
 144             'id': '35328',
 145             'ext': 'mp4',
 146             'title': 'BUB vs BLB',
 147             "timestamp": 1624863600,
 148             'is_live': True,
 149             'upload_date': '20210628',
 150         },
 151         'skip': 'Ended'
 152     }, {
 153         'url': 'https://fancode.com/match/35328/',
 154         'only_matching': True,
 155     }, {
 156         'url': 'https://fancode.com/match/35567?slug=scorecard',
 157         'only_matching': True,
 158     }]
 159
 160     def _real_extract(self, url):
 161
 162         id = self._match_id(url)
 163         data = '''{
 164             "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}",
 165             "variables":{
 166                 "id":%s,
 167                 "isLoggedIn":true
 168             },
 169             "operationName":"MatchResponse"
 170         }''' % id
 171
 172         info_json = self.download_gql(id, data, "Info json")
 173
 174         match_info = try_get(info_json, lambda x: x['data']['match'])
 175
 176         if match_info.get('streamingStatus') != "STARTED":
 177             raise ExtractorError('The stream can\'t be accessed', expected=True)
 178         self._check_login_required(match_info.get('isUserEntitled'), True)  # all live streams are premium only
 179
 180         return {
 181             'id': id,
 182             'title': match_info.get('name'),
 183             'formats': self._extract_akamai_formats(try_get(match_info, lambda x: x['videoStreamUrl']['url']), id),
 184             'ext': mimetype2ext(try_get(match_info, lambda x: x['videoStreamUrl']['deliveryType'])),
 185             'is_live': True,
 186             'release_timestamp': parse_iso8601(match_info.get('startTime'))
 187         }