yt_dlp/extractor/sverigesradio.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     determine_ext,
   4     extract_attributes,
   5     get_element_by_id,
   6     get_element_html_by_class,
   7     int_or_none,
   8     str_or_none,
   9     traverse_obj,
  10     url_or_none,
  11 )
  12
  13
  14 class SverigesRadioBaseIE(InfoExtractor):
  15     _BASE_URL = 'https://sverigesradio.se/sida/playerajax/'
  16     _QUALITIES = ['low', 'medium', 'high']
  17     _EXT_TO_CODEC_MAP = {
  18         'mp3': 'mp3',
  19         'm4a': 'aac',
  20     }
  21     _CODING_FORMAT_TO_ABR_MAP = {
  22         5: 128,
  23         11: 192,
  24         12: 32,
  25         13: 96,
  26     }
  27
  28     def _real_extract(self, url):
  29         audio_id, display_id = self._match_valid_url(url).group('id', 'slug')
  30         if not audio_id:
  31             webpage = self._download_webpage(url, display_id)
  32             audio_id = (
  33                 traverse_obj(
  34                     get_element_html_by_class('audio-button', webpage),
  35                     ({extract_attributes}, ('data-audio-id', 'data-publication-id')), get_all=False)
  36                 or self._parse_json(get_element_by_id('gtm-metadata', webpage), display_id)['pageId'])
  37
  38         query = {
  39             'id': audio_id,
  40             'type': self._AUDIO_TYPE,
  41         }
  42
  43         item = self._download_json(
  44             self._BASE_URL + 'audiometadata', audio_id,
  45             'Downloading audio JSON metadata', query=query)['items'][0]
  46
  47         query['format'] = 'iis'
  48         urls = []
  49         formats = []
  50         for quality in self._QUALITIES:
  51             query['quality'] = quality
  52             audio_url_data = self._download_json(
  53                 self._BASE_URL + 'getaudiourl', audio_id,
  54                 f'Downloading {quality} format JSON metadata',
  55                 fatal=False, query=query) or {}
  56             audio_url = audio_url_data.get('audioUrl')
  57             if not audio_url or audio_url in urls:
  58                 continue
  59             urls.append(audio_url)
  60             ext = determine_ext(audio_url)
  61             coding_format = audio_url_data.get('codingFormat')
  62             abr = int_or_none(self._search_regex(
  63                 r'_a(\d+)\.m4a', audio_url, 'audio bitrate',
  64                 default=None)) or self._CODING_FORMAT_TO_ABR_MAP.get(coding_format)
  65             formats.append({
  66                 'abr': abr,
  67                 'acodec': self._EXT_TO_CODEC_MAP.get(ext),
  68                 'ext': ext,
  69                 'format_id': str_or_none(coding_format),
  70                 'vcodec': 'none',
  71                 'url': audio_url,
  72             })
  73
  74         return {
  75             'id': audio_id,
  76             'formats': formats,
  77             **traverse_obj(item, {
  78                 'title': 'subtitle',
  79                 'series': 'title',
  80                 'duration': ('duration', {int_or_none}),
  81                 'thumbnail': ('displayimageurl', {url_or_none}),
  82                 'description': 'description',
  83             }),
  84         }
  85
  86
  87 class SverigesRadioPublicationIE(SverigesRadioBaseIE):
  88     IE_NAME = 'sverigesradio:publication'
  89     _VALID_URL = r'https?://(?:www\.)?sverigesradio\.se/(?:sida/)?(?:artikel|gruppsida)(?:\.aspx\?.*?\bartikel=(?P<id>[0-9]+)|/(?P<slug>[\w-]+))'
  90     _TESTS = [{
  91         'url': 'https://sverigesradio.se/sida/artikel.aspx?programid=83&artikel=7038546',
  92         'md5': '6a4917e1923fccb080e5a206a5afa542',
  93         'info_dict': {
  94             'id': '7038546',
  95             'ext': 'm4a',
  96             'duration': 132,
  97             'series': 'Nyheter (Ekot)',
  98             'title': 'Esa Teittinen: Sanningen har inte kommit fram',
  99             'description': 'md5:daf7ce66a8f0a53d5465a5984d3839df',
 100             'thumbnail': r're:^https?://.*\.jpg',
 101         },
 102     }, {
 103         'url': 'https://sverigesradio.se/artikel/tysk-fotbollsfeber-bayern-munchens-10-ariga-segersvit-kan-brytas',
 104         'md5': 'f8a914ad50f491bb74eed403ab4bfef6',
 105         'info_dict': {
 106             'id': '8360345',
 107             'ext': 'm4a',
 108             'title': 'Tysk fotbollsfeber när Bayern Münchens 10-åriga segersvit kan brytas',
 109             'series': 'Radiosporten',
 110             'description': 'md5:5254610e20ce527ecb3a6102a06dcc5f',
 111             'duration': 72,
 112             'thumbnail': r're:^https?://.*\.jpg',
 113         },
 114     }, {
 115         'url': 'https://sverigesradio.se/sida/gruppsida.aspx?programid=3304&grupp=6247&artikel=7146887',
 116         'only_matching': True,
 117     }]
 118     _AUDIO_TYPE = 'publication'
 119
 120
 121 class SverigesRadioEpisodeIE(SverigesRadioBaseIE):
 122     IE_NAME = 'sverigesradio:episode'
 123     _VALID_URL = r'https?://(?:www\.)?sverigesradio\.se/(?:sida/)?avsnitt/(?:(?P<id>\d+)|(?P<slug>[\w-]+))(?:$|[#?])'
 124     _TESTS = [{
 125         'url': 'https://sverigesradio.se/avsnitt/1140922?programid=1300',
 126         'md5': '20dc4d8db24228f846be390b0c59a07c',
 127         'info_dict': {
 128             'id': '1140922',
 129             'ext': 'mp3',
 130             'duration': 3307,
 131             'series': 'Konflikt',
 132             'title': 'Metoo och valen',
 133             'description': 'md5:fcb5c1f667f00badcc702b196f10a27e',
 134             'thumbnail': r're:^https?://.*\.jpg',
 135         },
 136     }, {
 137         'url': 'https://sverigesradio.se/avsnitt/p4-live-med-first-aid-kit-scandinavium-mars-2023',
 138         'md5': 'ce17fb82520a8033dbb846993d5589fe',
 139         'info_dict': {
 140             'id': '2160416',
 141             'ext': 'm4a',
 142             'title': 'P4 Live med First Aid Kit',
 143             'description': 'md5:6d5b78eed3d2b65f6de04daa45e9285d',
 144             'thumbnail': r're:^https?://.*\.jpg',
 145             'series': 'P4 Live',
 146             'duration': 5640,
 147         },
 148     }]
 149     _AUDIO_TYPE = 'episode'