yt_dlp/extractor/zetland.py

@@ -1,10 +1,10 @@
 from .common import InfoExtractor
-from ..utils import merge_dicts, unified_timestamp, url_or_none
+from ..utils import determine_ext, merge_dicts, unified_timestamp
 from ..utils.traversal import traverse_obj
 
 
 class ZetlandDKArticleIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.zetland\.dk/\w+/(?P<id>(?P<story_id>\w{8})-(?P<uploader_id>\w{8})-(?:\w{5}))'
+    _VALID_URL = r'https://www.zetland.dk/\w+/(?P<id>(?P<story_id>\w{8})-(?P<uploader_id>\w{8})-(?:\w{5}))'
     _TESTS = [{
         'url': 'https://www.zetland.dk/historie/sO9aq2MY-a81VP3BY-66e69?utm_source=instagram&utm_medium=linkibio&utm_campaign=artikel',
         'info_dict': {
@@ -19,7 +19,7 @@ class ZetlandDKArticleIE(InfoExtractor):
             'uploader_url': 'https://www.zetland.dk/skribent/a81VP3BY',
             'uploader': 'Helle Fuusager',
             'release_date': '20240116',
-            'thumbnail': r're:https://zetland\.imgix\.net/2aafe500-b14e-11ee-bf83-65d5e1283a57/Zetland_Image_1\.jpg',
+            'thumbnail': 'https://zetland.imgix.net/2aafe500-b14e-11ee-bf83-65d5e1283a57/Zetland_Image_1.jpg?fit=crop&crop=focalpoint&auto=format,compress&cs=srgb&fp-x=0.49421296296296297&fp-y=0.48518518518518516&w=1200&h=630',
             'description': 'md5:9619d426772c133f5abb26db27f26a01',
             'timestamp': 1705377592,
             'series_id': '62d54630-e87b-4ab1-a255-8de58dbe1b14',
@@ -35,10 +35,11 @@ class ZetlandDKArticleIE(InfoExtractor):
         story_data = traverse_obj(next_js_data, ('initialState', 'consume', 'story', 'story'))
 
         formats = []
-        for audio_url in traverse_obj(story_data, ('story_content', 'meta', 'audioFiles', ..., {url_or_none})):
+        for audio_url in traverse_obj(story_data, ('story_content', 'meta', 'audioFiles', ...)):
             formats.append({
                 'url': audio_url,
                 'vcodec': 'none',
+                'ext': determine_ext(audio_url)
             })
 
         return merge_dicts({
@@ -46,26 +47,27 @@ class ZetlandDKArticleIE(InfoExtractor):
             'formats': formats,
             'uploader_id': uploader_id
         }, traverse_obj(story_data, {
-            'title': ((('story_content', 'content', 'title'), 'title'), {str}),
+            'title': ('story_content', 'content', 'title') or 'title',
             'uploader': ('sharer', 'name'),
             'uploader_id': ('sharer', 'sharer_id'),
-            'description': ('story_content', 'content', 'socialDescription'),
+            'description': ('story_content', 'content', 'sosialDescription'),
             'series_id': ('story_content', 'meta', 'seriesId'),
             'release_timestamp': ('published_at', {unified_timestamp}),
             'modified_timestamp': ('revised_at', {unified_timestamp}),
-        }, get_all=False), traverse_obj(next_js_data, ('metaInfo', {
-            'title': ((('meta', 'title'), ('ld', 'headline'), ('og', 'og:title'), ('og', 'twitter:title')), {str}),
-            'description': ((('meta', 'description'), ('ld', 'description'), ('og', 'og:description'), ('og', 'twitter:description')), {str}),
-            'uploader': ((('meta', 'author'), ('ld', 'author', 'name')), {str}),
-            'uploader_url': ('ld', 'author', 'url', {url_or_none}),
-            'thumbnail': ((('ld', 'image'), ('og', 'og:image'), ('og', 'twitter:image')), {url_or_none}),
+        }), traverse_obj(next_js_data, ('metaInfo', {
+            'title': ('meta', 'title') or ('ld', 'headline') or ('og', 'og:title') or ('og', 'twitter:title'),
+            'description': (('meta', 'description') or ('ld', 'description')
+                            or ('og', 'og:description') or ('og', 'twitter:description')),
+            'uploader': ('meta', 'author') or ('ld', 'author', 'name'),
+            'uploader_url': ('ld', 'author', 'url'),
+            'thumbnail': ('ld', 'image') or ('og', 'og:image') or ('og', 'twitter:image'),
             'modified_timestamp': ('ld', 'dateModified', {unified_timestamp}),
             'release_timestamp': ('ld', 'datePublished', {unified_timestamp}),
             'timestamp': ('ld', 'dateCreated', {unified_timestamp}),
-        }), get_all=False), {
+        })), {
             'title': self._html_search_meta(['title', 'og:title', 'twitter:title'], webpage),
             'description': self._html_search_meta(['description', 'og:description', 'twitter:description'], webpage),
             'thumbnail': self._html_search_meta(['og:image', 'twitter:image'], webpage),
             'uploader': self._html_search_meta(['author'], webpage),
             'release_timestamp': unified_timestamp(self._html_search_meta(['article:published_time'], webpage)),
-        }, self._search_json_ld(webpage, display_id, fatal=False))
+        }, self._search_json_ld(webpage, display_id))