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': 'Vie Ferrate - 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             'categories': ['Bergwelten'],
  42         },
  43         'params': {'skip_download': 'm3u8'},
  44     }, {
  45         'url': 'https://www.servustv.com/natur/v/aa-1xg5xwmgw2112/',
  46         'only_matching': True,
  47     }, {
  48         'url': 'https://www.servustv.com/natur/v/aansszcx3yi9jmlmhdc1/',
  49         'only_matching': True,
  50     }, {
  51         # URL schema v2
  52         'url': 'https://www.servustv.com/videos/aa-1t6vbu5pw1w12/',
  53         'only_matching': True,
  54     }, {
  55         # URL schema v1
  56         'url': 'https://www.servus.com/de/p/Die-Gr%C3%BCnen-aus-Sicht-des-Volkes/AA-1T6VBU5PW1W12/',
  57         'only_matching': True,
  58     }, {
  59         'url': 'https://www.servus.com/at/p/Wie-das-Leben-beginnt/1309984137314-381415152/',
  60         'only_matching': True,
  61     }, {
  62         'url': 'https://www.servus.com/tv/videos/aa-1t6vbu5pw1w12/',
  63         'only_matching': True,
  64     }, {
  65         'url': 'https://www.servus.com/tv/videos/1380889096408-1235196658/',
  66         'only_matching': True,
  67     }, {
  68         'url': 'https://www.pm-wissen.com/videos/aa-24mus4g2w2112/',
  69         'only_matching': True,
  70     }]
  71
  72     def _real_extract(self, url):
  73         video_id = self._match_id(url).upper()
  74
  75         webpage = self._download_webpage(url, video_id)
  76         next_data = self._search_nextjs_data(webpage, video_id, fatal=False)
  77
  78         video = self._download_json(
  79             'https://api-player.redbull.com/stv/servus-tv-playnet',
  80             video_id, 'Downloading video JSON', query={'videoId': video_id})
  81         if not video.get('videoUrl'):
  82             self._report_errors(video)
  83         formats, subtitles = self._extract_m3u8_formats_and_subtitles(
  84             video['videoUrl'], video_id, 'mp4', m3u8_id='hls')
  85
  86         season = video.get('season')
  87         season_number = int_or_none(self._search_regex(
  88             r'Season (\d+)', season or '', 'season number', default=None))
  89         episode = video.get('chapter')
  90         episode_number = int_or_none(self._search_regex(
  91             r'Episode (\d+)', episode or '', 'episode number', default=None))
  92
  93         return {
  94             'id': video_id,
  95             'title': video.get('title'),
  96             'description': self._get_description(next_data) or video.get('description'),
  97             'thumbnail': video.get('poster'),
  98             'duration': float_or_none(video.get('duration')),
  99             'timestamp': unified_timestamp(video.get('currentSunrise')),
 100             'series': video.get('label'),
 101             'season': season,
 102             'season_number': season_number,
 103             'episode': episode,
 104             'episode_number': episode_number,
 105             'formats': formats,
 106             'subtitles': subtitles,
 107             **traverse_obj(next_data, ('props', 'pageProps', 'data', {
 108                 'title': ('title', 'rendered', {str}),
 109                 'timestamp': ('stv_date', 'raw', {int}),
 110                 'duration': ('stv_duration', {float_or_none}),
 111                 'categories': ('category_names', ..., {str}),
 112             })),
 113         }
 114
 115     def _get_description(self, next_data):
 116         return join_nonempty(*traverse_obj(next_data, (
 117             'props', 'pageProps', 'data',
 118             ('stv_short_description', 'stv_long_description'), {str},
 119             {lambda x: x.replace('\n\n', '\n')}, {unescapeHTML})), delim='\n\n')
 120
 121     def _report_errors(self, video):
 122         playability_errors = traverse_obj(video, ('playabilityErrors', ...))
 123         if not playability_errors:
 124             raise ExtractorError('No videoUrl and no information about errors')
 125
 126         elif 'FSK_BLOCKED' in playability_errors:
 127             details = traverse_obj(video, ('playabilityErrorDetails', 'FSK_BLOCKED'), expected_type=dict)
 128             message = format_field(''.join((
 129                 format_field(details, 'minEveningHour', ' from %02d:00'),
 130                 format_field(details, 'maxMorningHour', ' to %02d:00'),
 131                 format_field(details, 'minAge', ' (Minimum age %d)'),
 132             )), None, 'Only available%s') or 'Blocked by FSK with unknown availability'
 133
 134         elif 'NOT_YET_AVAILABLE' in playability_errors:
 135             message = format_field(
 136                 video, (('playabilityErrorDetails', 'NOT_YET_AVAILABLE', 'availableFrom'), 'currentSunrise'),
 137                 'Only available from %s') or 'Video not yet available with unknown availability'
 138
 139         else:
 140             message = f'Video unavailable: {", ".join(playability_errors)}'
 141
 142         raise ExtractorError(message, expected=True)