yt_dlp/extractor/zetland.py

   1 from .common import InfoExtractor
   2 from ..utils import merge_dicts, unified_timestamp, url_or_none
   3 from ..utils.traversal import traverse_obj
   4
   5
   6 class ZetlandDKArticleIE(InfoExtractor):
   7     _VALID_URL = r'https?://www\.zetland\.dk/\w+/(?P<id>(?P<story_id>\w{8})-(?P<uploader_id>\w{8})-(?:\w{5}))'
   8     _TESTS = [{
   9         'url': 'https://www.zetland.dk/historie/sO9aq2MY-a81VP3BY-66e69?utm_source=instagram&utm_medium=linkibio&utm_campaign=artikel',
  10         'info_dict': {
  11             'id': 'sO9aq2MY-a81VP3BY-66e69',
  12             'ext': 'mp3',
  13             'modified_date': '20240118',
  14             'title': 'Afsnit 1: “Det føltes som en kidnapning.” ',
  15             'upload_date': '20240116',
  16             'uploader_id': 'a81VP3BY',
  17             'modified_timestamp': 1705568739,
  18             'release_timestamp': 1705377592,
  19             'uploader_url': 'https://www.zetland.dk/skribent/a81VP3BY',
  20             'uploader': 'Helle Fuusager',
  21             'release_date': '20240116',
  22             'thumbnail': r're:https://zetland\.imgix\.net/2aafe500-b14e-11ee-bf83-65d5e1283a57/Zetland_Image_1\.jpg',
  23             'description': 'md5:9619d426772c133f5abb26db27f26a01',
  24             'timestamp': 1705377592,
  25             'series_id': '62d54630-e87b-4ab1-a255-8de58dbe1b14',
  26         },
  27
  28     }]
  29
  30     def _real_extract(self, url):
  31         display_id, uploader_id = self._match_valid_url(url).group('id', 'uploader_id')
  32         webpage = self._download_webpage(url, display_id)
  33
  34         next_js_data = self._search_nextjs_data(webpage, display_id)['props']['pageProps']
  35         story_data = traverse_obj(next_js_data, ('initialState', 'consume', 'story', 'story'))
  36
  37         formats = []
  38         for audio_url in traverse_obj(story_data, ('story_content', 'meta', 'audioFiles', ..., {url_or_none})):
  39             formats.append({
  40                 'url': audio_url,
  41                 'vcodec': 'none',
  42             })
  43
  44         return merge_dicts({
  45             'id': display_id,
  46             'formats': formats,
  47             'uploader_id': uploader_id,
  48         }, traverse_obj(story_data, {
  49             'title': ((('story_content', 'content', 'title'), 'title'), {str}),
  50             'uploader': ('sharer', 'name'),
  51             'uploader_id': ('sharer', 'sharer_id'),
  52             'description': ('story_content', 'content', 'socialDescription'),
  53             'series_id': ('story_content', 'meta', 'seriesId'),
  54             'release_timestamp': ('published_at', {unified_timestamp}),
  55             'modified_timestamp': ('revised_at', {unified_timestamp}),
  56         }, get_all=False), traverse_obj(next_js_data, ('metaInfo', {
  57             'title': ((('meta', 'title'), ('ld', 'headline'), ('og', 'og:title'), ('og', 'twitter:title')), {str}),
  58             'description': ((('meta', 'description'), ('ld', 'description'), ('og', 'og:description'), ('og', 'twitter:description')), {str}),
  59             'uploader': ((('meta', 'author'), ('ld', 'author', 'name')), {str}),
  60             'uploader_url': ('ld', 'author', 'url', {url_or_none}),
  61             'thumbnail': ((('ld', 'image'), ('og', 'og:image'), ('og', 'twitter:image')), {url_or_none}),
  62             'modified_timestamp': ('ld', 'dateModified', {unified_timestamp}),
  63             'release_timestamp': ('ld', 'datePublished', {unified_timestamp}),
  64             'timestamp': ('ld', 'dateCreated', {unified_timestamp}),
  65         }), get_all=False), {
  66             'title': self._html_search_meta(['title', 'og:title', 'twitter:title'], webpage),
  67             'description': self._html_search_meta(['description', 'og:description', 'twitter:description'], webpage),
  68             'thumbnail': self._html_search_meta(['og:image', 'twitter:image'], webpage),
  69             'uploader': self._html_search_meta(['author'], webpage),
  70             'release_timestamp': unified_timestamp(self._html_search_meta(['article:published_time'], webpage)),
  71         }, self._search_json_ld(webpage, display_id, fatal=False))