yt_dlp/extractor/servus.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     ExtractorError,
   4     float_or_none,
   5     format_field,
   6     int_or_none,
   7     join_nonempty,
   8     traverse_obj,
   9     unescapeHTML,
  10     unified_timestamp,
  11 )
  12
  13
  14 class ServusIE(InfoExtractor):
  15     _VALID_URL = r'''(?x)
  16                     https?://
  17                         (?:www\.)?
  18                         (?:
  19                             servus\.com/(?:(?:at|de)/p/[^/]+|tv/videos)|
  20                             (?:servustv|pm-wissen)\.com/(?:[^/]+/)?v(?:ideos)?
  21                         )
  22                         /(?P<id>[aA]{2}-?\w+|\d+-\d+)
  23                     '''
  24     _TESTS = [{
  25         # URL schema v3
  26         'url': 'https://www.servustv.com/natur/v/aa-28bycqnh92111/',
  27         'info_dict': {
  28             'id': 'AA-28BYCQNH92111',
  29             'ext': 'mp4',
  30             'title': 'Klettersteige in den Alpen',
  31             'description': 'md5:25e47ddd83a009a0f9789ba18f2850ce',
  32             'thumbnail': r're:^https?://.*\.jpg',
  33             'duration': 2823,
  34             'timestamp': 1655752333,
  35             'upload_date': '20220620',
  36             'series': 'Bergwelten',
  37             'season': 'Season 11',
  38             'season_number': 11,
  39             'episode': 'Episode 8 - Vie Ferrate – Klettersteige in den Alpen',
  40             'episode_number': 8,
  41         },
  42         'params': {'skip_download': 'm3u8'}
  43     }, {
  44         'url': 'https://www.servustv.com/natur/v/aa-1xg5xwmgw2112/',
  45         'only_matching': True,
  46     }, {
  47         'url': 'https://www.servustv.com/natur/v/aansszcx3yi9jmlmhdc1/',
  48         'only_matching': True,
  49     }, {
  50         # URL schema v2
  51         'url': 'https://www.servustv.com/videos/aa-1t6vbu5pw1w12/',
  52         'only_matching': True,
  53     }, {
  54         # URL schema v1
  55         'url': 'https://www.servus.com/de/p/Die-Gr%C3%BCnen-aus-Sicht-des-Volkes/AA-1T6VBU5PW1W12/',
  56         'only_matching': True,
  57     }, {
  58         'url': 'https://www.servus.com/at/p/Wie-das-Leben-beginnt/1309984137314-381415152/',
  59         'only_matching': True,
  60     }, {
  61         'url': 'https://www.servus.com/tv/videos/aa-1t6vbu5pw1w12/',
  62         'only_matching': True,
  63     }, {
  64         'url': 'https://www.servus.com/tv/videos/1380889096408-1235196658/',
  65         'only_matching': True,
  66     }, {
  67         'url': 'https://www.pm-wissen.com/videos/aa-24mus4g2w2112/',
  68         'only_matching': True,
  69     }]
  70
  71     def _real_extract(self, url):
  72         video_id = self._match_id(url).upper()
  73
  74         video = self._download_json(
  75             'https://api-player.redbull.com/stv/servus-tv?timeZone=Europe/Berlin',
  76             video_id, 'Downloading video JSON', query={'videoId': video_id})
  77         if not video.get('videoUrl'):
  78             self._report_errors(video)
  79         formats, subtitles = self._extract_m3u8_formats_and_subtitles(
  80             video['videoUrl'], video_id, 'mp4', m3u8_id='hls')
  81
  82         season = video.get('season')
  83         season_number = int_or_none(self._search_regex(
  84             r'Season (\d+)', season or '', 'season number', default=None))
  85         episode = video.get('chapter')
  86         episode_number = int_or_none(self._search_regex(
  87             r'Episode (\d+)', episode or '', 'episode number', default=None))
  88
  89         return {
  90             'id': video_id,
  91             'title': video.get('title'),
  92             'description': self._get_description(video_id) or video.get('description'),
  93             'thumbnail': video.get('poster'),
  94             'duration': float_or_none(video.get('duration')),
  95             'timestamp': unified_timestamp(video.get('currentSunrise')),
  96             'series': video.get('label'),
  97             'season': season,
  98             'season_number': season_number,
  99             'episode': episode,
 100             'episode_number': episode_number,
 101             'formats': formats,
 102             'subtitles': subtitles,
 103         }
 104
 105     def _get_description(self, video_id):
 106         info = self._download_json(
 107             f'https://backend.servustv.com/wp-json/rbmh/v2/media_asset/aa_id/{video_id}?fieldset=page',
 108             video_id, fatal=False)
 109
 110         return join_nonempty(*traverse_obj(info, (
 111             ('stv_short_description', 'stv_long_description'),
 112             {lambda x: unescapeHTML(x.replace('\n\n', '\n'))})), delim='\n\n')
 113
 114     def _report_errors(self, video):
 115         playability_errors = traverse_obj(video, ('playabilityErrors', ...))
 116         if not playability_errors:
 117             raise ExtractorError('No videoUrl and no information about errors')
 118
 119         elif 'FSK_BLOCKED' in playability_errors:
 120             details = traverse_obj(video, ('playabilityErrorDetails', 'FSK_BLOCKED'), expected_type=dict)
 121             message = format_field(''.join((
 122                 format_field(details, 'minEveningHour', ' from %02d:00'),
 123                 format_field(details, 'maxMorningHour', ' to %02d:00'),
 124                 format_field(details, 'minAge', ' (Minimum age %d)'),
 125             )), None, 'Only available%s') or 'Blocked by FSK with unknown availability'
 126
 127         elif 'NOT_YET_AVAILABLE' in playability_errors:
 128             message = format_field(
 129                 video, (('playabilityErrorDetails', 'NOT_YET_AVAILABLE', 'availableFrom'), 'currentSunrise'),
 130                 'Only available from %s') or 'Video not yet available with unknown availability'
 131
 132         else:
 133             message = f'Video unavailable: {", ".join(playability_errors)}'
 134
 135         raise ExtractorError(message, expected=True)