yt_dlp/extractor/hrti.py

   1 import json
   2
   3 from .common import InfoExtractor
   4 from ..networking import Request
   5 from ..networking.exceptions import HTTPError
   6 from ..utils import (
   7     clean_html,
   8     ExtractorError,
   9     int_or_none,
  10     parse_age_limit,
  11     try_get,
  12 )
  13
  14
  15 class HRTiBaseIE(InfoExtractor):
  16     """
  17         Base Information Extractor for Croatian Radiotelevision
  18         video on demand site https://hrti.hrt.hr
  19         Reverse engineered from the JavaScript app in app.min.js
  20     """
  21     _NETRC_MACHINE = 'hrti'
  22
  23     _APP_LANGUAGE = 'hr'
  24     _APP_VERSION = '1.1'
  25     _APP_PUBLICATION_ID = 'all_in_one'
  26     _API_URL = 'http://clientapi.hrt.hr/client_api.php/config/identify/format/json'
  27     _token = None
  28
  29     def _initialize_pre_login(self):
  30         init_data = {
  31             'application_publication_id': self._APP_PUBLICATION_ID
  32         }
  33
  34         uuid = self._download_json(
  35             self._API_URL, None, note='Downloading uuid',
  36             errnote='Unable to download uuid',
  37             data=json.dumps(init_data).encode('utf-8'))['uuid']
  38
  39         app_data = {
  40             'uuid': uuid,
  41             'application_publication_id': self._APP_PUBLICATION_ID,
  42             'application_version': self._APP_VERSION
  43         }
  44
  45         req = Request(self._API_URL, data=json.dumps(app_data).encode('utf-8'))
  46         req.get_method = lambda: 'PUT'
  47
  48         resources = self._download_json(
  49             req, None, note='Downloading session information',
  50             errnote='Unable to download session information')
  51
  52         self._session_id = resources['session_id']
  53
  54         modules = resources['modules']
  55
  56         self._search_url = modules['vod_catalog']['resources']['search']['uri'].format(
  57             language=self._APP_LANGUAGE,
  58             application_id=self._APP_PUBLICATION_ID)
  59
  60         self._login_url = (modules['user']['resources']['login']['uri']
  61                            + '/format/json').format(session_id=self._session_id)
  62
  63         self._logout_url = modules['user']['resources']['logout']['uri']
  64
  65     def _perform_login(self, username, password):
  66         auth_data = {
  67             'username': username,
  68             'password': password,
  69         }
  70
  71         try:
  72             auth_info = self._download_json(
  73                 self._login_url, None, note='Logging in', errnote='Unable to log in',
  74                 data=json.dumps(auth_data).encode('utf-8'))
  75         except ExtractorError as e:
  76             if isinstance(e.cause, HTTPError) and e.cause.status == 406:
  77                 auth_info = self._parse_json(e.cause.response.read().encode('utf-8'), None)
  78             else:
  79                 raise
  80
  81         error_message = auth_info.get('error', {}).get('message')
  82         if error_message:
  83             raise ExtractorError(
  84                 '%s said: %s' % (self.IE_NAME, error_message),
  85                 expected=True)
  86
  87         self._token = auth_info['secure_streaming_token']
  88
  89     def _real_initialize(self):
  90         if not self._token:
  91             # TODO: figure out authentication with cookies
  92             self.raise_login_required(method='password')
  93
  94
  95 class HRTiIE(HRTiBaseIE):
  96     _VALID_URL = r'''(?x)
  97                         (?:
  98                             hrti:(?P<short_id>[0-9]+)|
  99                             https?://
 100                                 hrti\.hrt\.hr/(?:\#/)?video/show/(?P<id>[0-9]+)/(?P<display_id>[^/]+)?
 101                         )
 102                     '''
 103     _TESTS = [{
 104         'url': 'https://hrti.hrt.hr/#/video/show/2181385/republika-dokumentarna-serija-16-hd',
 105         'info_dict': {
 106             'id': '2181385',
 107             'display_id': 'republika-dokumentarna-serija-16-hd',
 108             'ext': 'mp4',
 109             'title': 'REPUBLIKA, dokumentarna serija (1/6) (HD)',
 110             'description': 'md5:48af85f620e8e0e1df4096270568544f',
 111             'duration': 2922,
 112             'view_count': int,
 113             'average_rating': int,
 114             'episode_number': int,
 115             'season_number': int,
 116             'age_limit': 12,
 117         },
 118         'skip': 'Requires account credentials',
 119     }, {
 120         'url': 'https://hrti.hrt.hr/#/video/show/2181385/',
 121         'only_matching': True,
 122     }, {
 123         'url': 'hrti:2181385',
 124         'only_matching': True,
 125     }, {
 126         'url': 'https://hrti.hrt.hr/video/show/3873068/cuvar-dvorca-dramska-serija-14',
 127         'only_matching': True,
 128     }]
 129
 130     def _real_extract(self, url):
 131         mobj = self._match_valid_url(url)
 132         video_id = mobj.group('short_id') or mobj.group('id')
 133         display_id = mobj.group('display_id') or video_id
 134
 135         video = self._download_json(
 136             '%s/video_id/%s/format/json' % (self._search_url, video_id),
 137             display_id, 'Downloading video metadata JSON')['video'][0]
 138
 139         title_info = video['title']
 140         title = title_info['title_long']
 141
 142         movie = video['video_assets']['movie'][0]
 143         m3u8_url = movie['url'].format(TOKEN=self._token)
 144         formats = self._extract_m3u8_formats(
 145             m3u8_url, display_id, 'mp4', entry_protocol='m3u8_native',
 146             m3u8_id='hls')
 147
 148         description = clean_html(title_info.get('summary_long'))
 149         age_limit = parse_age_limit(video.get('parental_control', {}).get('rating'))
 150         view_count = int_or_none(video.get('views'))
 151         average_rating = int_or_none(video.get('user_rating'))
 152         duration = int_or_none(movie.get('duration'))
 153
 154         return {
 155             'id': video_id,
 156             'display_id': display_id,
 157             'title': title,
 158             'description': description,
 159             'duration': duration,
 160             'view_count': view_count,
 161             'average_rating': average_rating,
 162             'age_limit': age_limit,
 163             'formats': formats,
 164         }
 165
 166
 167 class HRTiPlaylistIE(HRTiBaseIE):
 168     _VALID_URL = r'https?://hrti\.hrt\.hr/(?:#/)?video/list/category/(?P<id>[0-9]+)/(?P<display_id>[^/]+)?'
 169     _TESTS = [{
 170         'url': 'https://hrti.hrt.hr/#/video/list/category/212/ekumena',
 171         'info_dict': {
 172             'id': '212',
 173             'title': 'ekumena',
 174         },
 175         'playlist_mincount': 8,
 176         'skip': 'Requires account credentials',
 177     }, {
 178         'url': 'https://hrti.hrt.hr/#/video/list/category/212/',
 179         'only_matching': True,
 180     }, {
 181         'url': 'https://hrti.hrt.hr/video/list/category/212/ekumena',
 182         'only_matching': True,
 183     }]
 184
 185     def _real_extract(self, url):
 186         mobj = self._match_valid_url(url)
 187         category_id = mobj.group('id')
 188         display_id = mobj.group('display_id') or category_id
 189
 190         response = self._download_json(
 191             '%s/category_id/%s/format/json' % (self._search_url, category_id),
 192             display_id, 'Downloading video metadata JSON')
 193
 194         video_ids = try_get(
 195             response, lambda x: x['video_listings'][0]['alternatives'][0]['list'],
 196             list) or [video['id'] for video in response.get('videos', []) if video.get('id')]
 197
 198         entries = [self.url_result('hrti:%s' % video_id) for video_id in video_ids]
 199
 200         return self.playlist_result(entries, category_id, display_id)