From 36baaa10e06715ccba06b78885b2042c4844c826 Mon Sep 17 00:00:00 2001
From: HobbyistDev <105957301+HobbyistDev@users.noreply.github.com>
Date: Thu, 4 Apr 2024 02:51:14 +0800
Subject: [PATCH] [ie/Radio1Be] Add extractor (#9122)

Closes #8707
Authored by: HobbyistDev
---
 yt_dlp/extractor/_extractors.py |  1 +
 yt_dlp/extractor/vrt.py         | 62 +++++++++++++++++++++++++++++++++
 2 files changed, 63 insertions(+)

diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py
index f8d6a6542..2ad5801c4 100644
--- a/yt_dlp/extractor/_extractors.py
+++ b/yt_dlp/extractor/_extractors.py
@@ -2290,6 +2290,7 @@ from .vrt import (
     VrtNUIE,
     KetnetIE,
     DagelijkseKostIE,
+    Radio1BeIE,
 )
 from .vtm import VTMIE
 from .medialaan import MedialaanIE
diff --git a/yt_dlp/extractor/vrt.py b/yt_dlp/extractor/vrt.py
index 497233d95..3d26549a4 100644
--- a/yt_dlp/extractor/vrt.py
+++ b/yt_dlp/extractor/vrt.py
@@ -16,6 +16,7 @@ from ..utils import (
     join_nonempty,
     jwt_encode_hs256,
     make_archive_id,
+    merge_dicts,
     parse_age_limit,
     parse_iso8601,
     str_or_none,
@@ -425,3 +426,64 @@ class DagelijkseKostIE(VRTBaseIE):
                 ['description', 'twitter:description', 'og:description'], webpage),
             '_old_archive_ids': [make_archive_id('Canvas', video_id)],
         }
+
+
+class Radio1BeIE(VRTBaseIE):
+    _VALID_URL = r'https?://radio1\.be/(?:lees|luister/select)/(?P<id>[\w/-]+)'
+    _TESTS = [{
+        'url': 'https://radio1.be/luister/select/de-ochtend/komt-n-va-volgend-jaar-op-in-wallonie',
+        'info_dict': {
+            'id': 'eb6c22e9-544f-44f4-af39-cf8cccd29e22',
+            'title': 'Komt N-VA volgend jaar op in Wallonië?',
+            'display_id': 'de-ochtend/komt-n-va-volgend-jaar-op-in-wallonie',
+            'description': 'md5:b374ea1c9302f38362df9dea1931468e',
+            'thumbnail': r're:https?://cds\.vrt\.radio/[^/#\?&]+'
+        },
+        'playlist_mincount': 1
+    }, {
+        'url': 'https://radio1.be/lees/europese-unie-wil-onmiddellijke-humanitaire-pauze-en-duurzaam-staakt-het-vuren-in-gaza?view=web',
+        'info_dict': {
+            'id': '5d47f102-dbdb-4fa0-832b-26c1870311f2',
+            'title': 'Europese Unie wil "onmiddellijke humanitaire pauze" en "duurzaam staakt-het-vuren" in Gaza',
+            'description': 'md5:1aad1fae7d39edeffde5d3e67d276b64',
+            'thumbnail': r're:https?://cds\.vrt\.radio/[^/#\?&]+',
+            'display_id': 'europese-unie-wil-onmiddellijke-humanitaire-pauze-en-duurzaam-staakt-het-vuren-in-gaza'
+        },
+        'playlist_mincount': 1
+    }]
+
+    def _extract_video_entries(self, next_js_data, display_id):
+        video_data = traverse_obj(
+            next_js_data, ((None, ('paragraphs', ...)), {lambda x: x if x['mediaReference'] else None}))
+        for data in video_data:
+            media_reference = data['mediaReference']
+            formats, subtitles = self._extract_formats_and_subtitles(
+                self._call_api(media_reference), display_id)
+
+            yield {
+                'id': media_reference,
+                'formats': formats,
+                'subtitles': subtitles,
+                **traverse_obj(data, {
+                    'title': ('title', {str}),
+                    'description': ('body', {clean_html})
+                }),
+            }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        next_js_data = self._search_nextjs_data(webpage, display_id)['props']['pageProps']['item']
+
+        return self.playlist_result(
+            self._extract_video_entries(next_js_data, display_id), **merge_dicts(traverse_obj(
+                next_js_data, ({
+                    'id': ('id', {str}),
+                    'title': ('title', {str}),
+                    'description': (('description', 'content'), {clean_html}),
+                }), get_all=False), {
+                    'display_id': display_id,
+                    'title': self._html_search_meta(['name', '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),
+            }))