yt_dlp/extractor/err.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     clean_html,
   4     int_or_none,
   5     str_or_none,
   6     url_or_none,
   7 )
   8 from ..utils.traversal import traverse_obj
   9
  10
  11 class ERRJupiterIE(InfoExtractor):
  12     _VALID_URL = r'https?://jupiter(?:pluss)?\.err\.ee/(?P<id>\d+)'
  13     _TESTS = [{
  14         'note': 'Jupiter: Movie: siin-me-oleme',
  15         'url': 'https://jupiter.err.ee/1211107/siin-me-oleme',
  16         'md5': '9b45d1682a98853acaa1e1b0c791f425',
  17         'info_dict': {
  18             'id': '1211107',
  19             'ext': 'mp4',
  20             'title': 'Siin me oleme!',
  21             'alt_title': '',
  22             'description': 'md5:1825b795f5f7584241aeb59e5bbb4f70',
  23             'release_date': '20231226',
  24             'upload_date': '20201217',
  25             'modified_date': '20201217',
  26             'release_timestamp': 1703577600,
  27             'timestamp': 1608210000,
  28             'modified_timestamp': 1608220800,
  29             'release_year': 1978,
  30         },
  31     }, {
  32         'note': 'Jupiter: Series: Impulss',
  33         'url': 'https://jupiter.err.ee/1609145945/impulss',
  34         'md5': 'a378486df07ed1ba74e46cc861886243',
  35         'info_dict': {
  36             'id': '1609145945',
  37             'ext': 'mp4',
  38             'title': 'Impulss',
  39             'alt_title': 'Loteriipilet hooldekodusse',
  40             'description': 'md5:fa8a2ed0cdccb130211513443ee4d571',
  41             'release_date': '20231107',
  42             'upload_date': '20231026',
  43             'modified_date': '20231118',
  44             'release_timestamp': 1699380000,
  45             'timestamp': 1698327601,
  46             'modified_timestamp': 1700311802,
  47             'series': 'Impulss',
  48             'season': 'Season 1',
  49             'season_number': 1,
  50             'episode': 'Loteriipilet hooldekodusse',
  51             'episode_number': 6,
  52             'series_id': '1609108187',
  53             'release_year': 2023,
  54             'episode_id': '1609145945',
  55         },
  56     }, {
  57         'note': 'Jupiter: Radio Show: mnemoturniir episode',
  58         'url': 'https://jupiter.err.ee/1037919/mnemoturniir',
  59         'md5': 'f1eb95fe66f9620ff84e81bbac37076a',
  60         'info_dict': {
  61             'id': '1037919',
  62             'ext': 'm4a',
  63             'title': 'Mnemoturniir',
  64             'alt_title': '',
  65             'description': 'md5:626db52394e7583c26ab74d6a34d9982',
  66             'release_date': '20240121',
  67             'upload_date': '20240108',
  68             'modified_date': '20240121',
  69             'release_timestamp': 1705827900,
  70             'timestamp': 1704675602,
  71             'modified_timestamp': 1705827601,
  72             'series': 'Mnemoturniir',
  73             'season': 'Season 0',
  74             'season_number': 0,
  75             'episode': 'Episode 0',
  76             'episode_number': 0,
  77             'series_id': '1037919',
  78             'release_year': 2024,
  79             'episode_id': '1609215101',
  80         },
  81     }, {
  82         'note': 'Jupiter+: Clip: bolee-zelenyj-tallinn',
  83         'url': 'https://jupiterpluss.err.ee/1609180445/bolee-zelenyj-tallinn',
  84         'md5': '1b812270c4daf6ce51c06bfeaf33ed95',
  85         'info_dict': {
  86             'id': '1609180445',
  87             'ext': 'mp4',
  88             'title': 'Более зеленый Таллинн',
  89             'alt_title': '',
  90             'description': 'md5:fd34d9bf939c28c4a725b19a7f0d6320',
  91             'release_date': '20231224',
  92             'upload_date': '20231130',
  93             'modified_date': '20231207',
  94             'release_timestamp': 1703423400,
  95             'timestamp': 1701338400,
  96             'modified_timestamp': 1701967200,
  97             'release_year': 2023,
  98         },
  99     }, {
 100         'note': 'Jupiter+: Series: The Sniffer',
 101         'url': 'https://jupiterpluss.err.ee/1608311387/njuhach',
 102         'md5': '2abdeb7131ce551bce49e8d0cea08536',
 103         'info_dict': {
 104             'id': '1608311387',
 105             'ext': 'mp4',
 106             'title': 'Нюхач',
 107             'alt_title': '',
 108             'description': 'md5:8c5c7d8f32ec6e54cd498c9e59ca83bc',
 109             'release_date': '20230601',
 110             'upload_date': '20210818',
 111             'modified_date': '20210903',
 112             'release_timestamp': 1685633400,
 113             'timestamp': 1629318000,
 114             'modified_timestamp': 1630686000,
 115             'release_year': 2013,
 116             'episode': 'Episode 1',
 117             'episode_id': '1608311390',
 118             'episode_number': 1,
 119             'season': 'Season 1',
 120             'season_number': 1,
 121             'series': 'Нюхач',
 122             'series_id': '1608311387',
 123         },
 124     }, {
 125         'note': 'Jupiter+: Podcast: lesnye-istorii-aisty',
 126         'url': 'https://jupiterpluss.err.ee/1608990335/lesnye-istorii-aisty',
 127         'md5': '8b46d7e4510b254a14b7a52211b5bf96',
 128         'info_dict': {
 129             'id': '1608990335',
 130             'ext': 'm4a',
 131             'title': 'Лесные истории | Аисты',
 132             'alt_title': '',
 133             'description': 'md5:065e721623e271e7a63e6540d409ca6b',
 134             'release_date': '20230609',
 135             'upload_date': '20230527',
 136             'modified_date': '20230608',
 137             'release_timestamp': 1686308700,
 138             'timestamp': 1685145600,
 139             'modified_timestamp': 1686252600,
 140             'release_year': 2023,
 141             'episode': 'Episode 0',
 142             'episode_id': '1608990335',
 143             'episode_number': 0,
 144             'season': 'Season 0',
 145             'season_number': 0,
 146             'series': 'Лесные истории | Аисты',
 147             'series_id': '1037497',
 148         },
 149     }]
 150
 151     def _real_extract(self, url):
 152         video_id = self._match_id(url)
 153         data = self._download_json(
 154             'https://services.err.ee/api/v2/vodContent/getContentPageData', video_id,
 155             query={'contentId': video_id})['data']['mainContent']
 156
 157         media_data = traverse_obj(data, ('medias', ..., {dict}), get_all=False)
 158         if traverse_obj(media_data, ('restrictions', 'drm', {bool})):
 159             self.report_drm(video_id)
 160
 161         formats, subtitles = [], {}
 162         for format_url in set(traverse_obj(media_data, ('src', ('hls', 'hls2', 'hlsNew'), {url_or_none}))):
 163             fmts, subs = self._extract_m3u8_formats_and_subtitles(
 164                 format_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
 165             formats.extend(fmts)
 166             self._merge_subtitles(subs, target=subtitles)
 167         for format_url in set(traverse_obj(media_data, ('src', ('dash', 'dashNew'), {url_or_none}))):
 168             fmts, subs = self._extract_mpd_formats_and_subtitles(
 169                 format_url, video_id, mpd_id='dash', fatal=False)
 170             formats.extend(fmts)
 171             self._merge_subtitles(subs, target=subtitles)
 172         if format_url := traverse_obj(media_data, ('src', 'file', {url_or_none})):
 173             formats.append({
 174                 'url': format_url,
 175                 'format_id': 'http',
 176             })
 177
 178         return {
 179             'id': video_id,
 180             'formats': formats,
 181             'subtitles': subtitles,
 182             **traverse_obj(data, {
 183                 'title': ('heading', {str}),
 184                 'alt_title': ('subHeading', {str}),
 185                 'description': (('lead', 'body'), {clean_html}, {lambda x: x or None}),
 186                 'timestamp': ('created', {int_or_none}),
 187                 'modified_timestamp': ('updated', {int_or_none}),
 188                 'release_timestamp': (('scheduleStart', 'publicStart'), {int_or_none}),
 189                 'release_year': ('year', {int_or_none}),
 190             }, get_all=False),
 191             **(traverse_obj(data, {
 192                 'series': ('heading', {str}),
 193                 'series_id': ('rootContentId', {str_or_none}),
 194                 'episode': ('subHeading', {str}),
 195                 'season_number': ('season', {int_or_none}),
 196                 'episode_number': ('episode', {int_or_none}),
 197                 'episode_id': ('id', {str_or_none}),
 198             }) if data.get('type') == 'episode' else {}),
 199         }