[ie/crunchyroll] Fix stream extraction (#10005)

[yt-dlp.git] / yt_dlp / extractor / vrt.py

diff --git a/yt_dlp/extractor/vrt.py b/yt_dlp/extractor/vrt.py
index bacd3df29ada51728838c4f83e1569c423619532..3d26549a4036ce78a06f089367971266a54a0d6d 100644 (file)
--- a/yt_dlp/extractor/vrt.py
+++ b/yt_dlp/extractor/vrt.py
@@ -1,10 +1,10 @@
 import functools
 import json
 import time
-import urllib.error
 import urllib.parse
 
 from .gigya import GigyaBaseIE
+from ..networking.exceptions import HTTPError
 from ..utils import (
     ExtractorError,
     clean_html,
@@ -16,6 +16,7 @@
     join_nonempty,
     jwt_encode_hs256,
     make_archive_id,
+    merge_dicts,
     parse_age_limit,
     parse_iso8601,
     str_or_none,
@@ -44,9 +45,11 @@ class VRTBaseIE(GigyaBaseIE):
             'version': '2.7.4-prod-2023-04-19T06:05:45'
         }
     }
-    # From https://player.vrt.be/vrtnws/js/main.js & https://player.vrt.be/ketnet/js/main.fd1de01a40a1e3d842ea.js
+    # From https://player.vrt.be/vrtnws/js/main.js & https://player.vrt.be/ketnet/js/main.8cdb11341bcb79e4cd44.js
     _JWT_KEY_ID = '0-0Fp51UZykfaiCJrfTE3+oMI8zvDteYfPtR+2n1R+z8w='
-    _JWT_SIGNING_KEY = '2a9251d782700769fb856da5725daf38661874ca6f80ae7dc2b05ec1a81a24ae'
+    _JWT_SIGNING_KEY = 'b5f500d55cb44715107249ccd8a5c0136cfb2788dbb71b90a4f142423bacaf38'  # -dev
+    # player-stag.vrt.be key:    d23987504521ae6fbf2716caca6700a24bb1579477b43c84e146b279de5ca595
+    # player.vrt.be key:         2a9251d782700769fb856da5725daf38661874ca6f80ae7dc2b05ec1a81a24ae
 
     def _extract_formats_and_subtitles(self, data, video_id):
         if traverse_obj(data, 'drm'):
@@ -261,7 +264,7 @@ def _perform_login(self, username, password):
                         '_csrf': self._get_cookies('https://login.vrt.be').get('OIDCXSRF').value,
                     }))
             except ExtractorError as e:
-                if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 401:
+                if isinstance(e.cause, HTTPError) and e.cause.status == 401:
                     retry.error = e
                     continue
                 raise
@@ -423,3 +426,64 @@ def _real_extract(self, url):
                 ['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),
+            }))