yt_dlp/extractor/digitalconcerthall.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     ExtractorError,
   4     parse_resolution,
   5     traverse_obj,
   6     try_get,
   7     urlencode_postdata,
   8 )
   9
  10
  11 class DigitalConcertHallIE(InfoExtractor):
  12     IE_DESC = 'DigitalConcertHall extractor'
  13     _VALID_URL = r'https?://(?:www\.)?digitalconcerthall\.com/(?P<language>[a-z]+)/(?P<type>film|concert)/(?P<id>[0-9]+)'
  14     _OAUTH_URL = 'https://api.digitalconcerthall.com/v2/oauth2/token'
  15     _ACCESS_TOKEN = None
  16     _NETRC_MACHINE = 'digitalconcerthall'
  17     _TESTS = [{
  18         'note': 'Playlist with only one video',
  19         'url': 'https://www.digitalconcerthall.com/en/concert/53201',
  20         'info_dict': {
  21             'id': '53201-1',
  22             'ext': 'mp4',
  23             'composer': 'Kurt Weill',
  24             'title': '[Magic Night]',
  25             'thumbnail': r're:^https?://images.digitalconcerthall.com/cms/thumbnails.*\.jpg$',
  26             'upload_date': '20210624',
  27             'timestamp': 1624548600,
  28             'duration': 2798,
  29             'album_artist': 'Members of the Berliner Philharmoniker / Simon Rössler',
  30         },
  31         'params': {'skip_download': 'm3u8'},
  32     }, {
  33         'note': 'Concert with several works and an interview',
  34         'url': 'https://www.digitalconcerthall.com/en/concert/53785',
  35         'info_dict': {
  36             'id': '53785',
  37             'album_artist': 'Berliner Philharmoniker / Kirill Petrenko',
  38             'title': 'Kirill Petrenko conducts Mendelssohn and Shostakovich',
  39         },
  40         'params': {'skip_download': 'm3u8'},
  41         'playlist_count': 3,
  42     }, {
  43         'url': 'https://www.digitalconcerthall.com/en/film/388',
  44         'info_dict': {
  45             'id': '388',
  46             'ext': 'mp4',
  47             'title': 'The Berliner Philharmoniker and Frank Peter Zimmermann',
  48             'description': 'md5:cfe25a7044fa4be13743e5089b5b5eb2',
  49             'thumbnail': r're:^https?://images.digitalconcerthall.com/cms/thumbnails.*\.jpg$',
  50             'upload_date': '20220714',
  51             'timestamp': 1657785600,
  52             'album_artist': 'Frank Peter Zimmermann / Benedikt von Bernstorff / Jakob von Bernstorff',
  53         },
  54         'params': {'skip_download': 'm3u8'},
  55     }]
  56
  57     def _perform_login(self, username, password):
  58         token_response = self._download_json(
  59             self._OAUTH_URL,
  60             None, 'Obtaining token', errnote='Unable to obtain token', data=urlencode_postdata({
  61                 'affiliate': 'none',
  62                 'grant_type': 'device',
  63                 'device_vendor': 'unknown',
  64                 'app_id': 'dch.webapp',
  65                 'app_version': '1.0.0',
  66                 'client_secret': '2ySLN+2Fwb',
  67             }), headers={
  68                 'Content-Type': 'application/x-www-form-urlencoded',
  69             })
  70         self._ACCESS_TOKEN = token_response['access_token']
  71         try:
  72             self._download_json(
  73                 self._OAUTH_URL,
  74                 None, note='Logging in', errnote='Unable to login', data=urlencode_postdata({
  75                     'grant_type': 'password',
  76                     'username': username,
  77                     'password': password,
  78                 }), headers={
  79                     'Content-Type': 'application/x-www-form-urlencoded',
  80                     'Referer': 'https://www.digitalconcerthall.com',
  81                     'Authorization': f'Bearer {self._ACCESS_TOKEN}'
  82                 })
  83         except ExtractorError:
  84             self.raise_login_required(msg='Login info incorrect')
  85
  86     def _real_initialize(self):
  87         if not self._ACCESS_TOKEN:
  88             self.raise_login_required(method='password')
  89
  90     def _entries(self, items, language, type_, **kwargs):
  91         for item in items:
  92             video_id = item['id']
  93             stream_info = self._download_json(
  94                 self._proto_relative_url(item['_links']['streams']['href']), video_id, headers={
  95                     'Accept': 'application/json',
  96                     'Authorization': f'Bearer {self._ACCESS_TOKEN}',
  97                     'Accept-Language': language
  98                 })
  99
 100             m3u8_url = traverse_obj(
 101                 stream_info, ('channel', lambda k, _: k.startswith('vod_mixed'), 'stream', 0, 'url'), get_all=False)
 102             formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', 'm3u8_native', fatal=False)
 103
 104             yield {
 105                 'id': video_id,
 106                 'title': item.get('title'),
 107                 'composer': item.get('name_composer'),
 108                 'url': m3u8_url,
 109                 'formats': formats,
 110                 'duration': item.get('duration_total'),
 111                 'timestamp': traverse_obj(item, ('date', 'published')),
 112                 'description': item.get('short_description') or stream_info.get('short_description'),
 113                 **kwargs,
 114                 'chapters': [{
 115                     'start_time': chapter.get('time'),
 116                     'end_time': try_get(chapter, lambda x: x['time'] + x['duration']),
 117                     'title': chapter.get('text'),
 118                 } for chapter in item['cuepoints']] if item.get('cuepoints') and type_ == 'concert' else None,
 119             }
 120
 121     def _real_extract(self, url):
 122         language, type_, video_id = self._match_valid_url(url).group('language', 'type', 'id')
 123         if not language:
 124             language = 'en'
 125
 126         thumbnail_url = self._html_search_regex(
 127             r'(https?://images\.digitalconcerthall\.com/cms/thumbnails/.*\.jpg)',
 128             self._download_webpage(url, video_id), 'thumbnail')
 129         thumbnails = [{
 130             'url': thumbnail_url,
 131             **parse_resolution(thumbnail_url)
 132         }]
 133
 134         vid_info = self._download_json(
 135             f'https://api.digitalconcerthall.com/v2/{type_}/{video_id}', video_id, headers={
 136                 'Accept': 'application/json',
 137                 'Accept-Language': language
 138             })
 139         album_artist = ' / '.join(traverse_obj(vid_info, ('_links', 'artist', ..., 'name')) or '')
 140         videos = [vid_info] if type_ == 'film' else traverse_obj(vid_info, ('_embedded', ..., ...))
 141
 142         return {
 143             '_type': 'playlist',
 144             'id': video_id,
 145             'title': vid_info.get('title'),
 146             'entries': self._entries(videos, language, thumbnails=thumbnails, album_artist=album_artist, type_=type_),
 147             'thumbnails': thumbnails,
 148             'album_artist': album_artist,
 149         }