From 00869c4d5757a56dc0a89fae6272e608cfc12aa1 Mon Sep 17 00:00:00 2001
From: "J.Luis" <root@heavydeck.net>
Date: Thu, 27 Mar 2025 23:12:34 +0100
Subject: [PATCH] [ivoox] Add extractor

---
 supportedsites.md               |  1 +
 yt_dlp/extractor/_extractors.py |  1 +
 yt_dlp/extractor/ivoox.py       | 81 +++++++++++++++++++++++++++++++++
 3 files changed, 83 insertions(+)
 create mode 100644 yt_dlp/extractor/ivoox.py

diff --git a/supportedsites.md b/supportedsites.md
index 4a0e7519a6..c35b681cb4 100644
--- a/supportedsites.md
+++ b/supportedsites.md
@@ -633,6 +633,7 @@ The only reliable way to check if a site is supported is to try it.
  - **ivi**: ivi.ru
  - **ivi:compilation**: ivi.ru compilations
  - **ivideon**: Ivideon TV
+ - **iVoox**
  - **IVXPlayer**
  - **iwara**: [*iwara*](## "netrc machine")
  - **iwara:playlist**: [*iwara*](## "netrc machine")
diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py
index a44601b14d..16af868571 100644
--- a/yt_dlp/extractor/_extractors.py
+++ b/yt_dlp/extractor/_extractors.py
@@ -902,6 +902,7 @@ from .ivi import (
     IviIE,
 )
 from .ivideon import IvideonIE
+from .ivoox import IvooxIE
 from .iwara import (
     IwaraIE,
     IwaraPlaylistIE,
diff --git a/yt_dlp/extractor/ivoox.py b/yt_dlp/extractor/ivoox.py
new file mode 100644
index 0000000000..c001b4018e
--- /dev/null
+++ b/yt_dlp/extractor/ivoox.py
@@ -0,0 +1,81 @@
+from .common import InfoExtractor
+from datetime import datetime
+import json
+
+class IvooxIE(InfoExtractor):
+    _VALID_URL = (
+        r'https?://(?:www\.)?ivoox\.com/.*_rf_(?P<id>[0-9]+)_1\.html',
+        r'https?://go\.ivoox\.com/rf/(?P<id>[0-9]+)'
+    )
+    _TESTS = [
+    {
+        'url': 'https://www.ivoox.com/dex-08x30-rostros-del-mal-los-asesinos-en-audios-mp3_rf_143594959_1.html',
+        'md5': 'f3cc6b8db8995e0c95604deb6a8f0f2f',
+        'info_dict': {
+            # For videos, only the 'id' and 'ext' fields are required to RUN the test:
+            'id': '143594959',
+            'ext': 'mp3',
+            'timestamp': 1742727600,
+            'author': 'Santiago Camacho',
+            'channel': 'DIAS EXTRAÑOS con Santiago Camacho',
+            'title': 'DEx 08x30 Rostros del mal: Los asesinos en serie que aterrorizaron España',
+        }
+    },
+    {
+        'url': 'https://go.ivoox.com/rf/143594959',
+        'md5': 'f3cc6b8db8995e0c95604deb6a8f0f2f',
+        'info_dict': {
+            # For videos, only the 'id' and 'ext' fields are required to RUN the test:
+            'id': '143594959',
+            'ext': 'mp3',
+            'timestamp': 1742727600,
+            'author': 'Santiago Camacho',
+            'channel': 'DIAS EXTRAÑOS con Santiago Camacho',
+            'title': 'DEx 08x30 Rostros del mal: Los asesinos en serie que aterrorizaron España',
+        }
+    },
+    ]
+
+    def _real_extract(self, url):
+        media_id = self._match_id(url)
+        webpage = self._download_webpage(url, media_id)
+
+        # Extract the podcast info
+        date = datetime.fromisoformat(self._html_search_regex(r'data-prm-pubdate="(.+?)"', webpage, 'title'))
+        timestamp = int(datetime.timestamp(date))
+        author = self._html_search_regex(r'data-prm-author="(.+?)"', webpage, 'title')
+        podcast = self._html_search_regex(r'data-prm-podname="(.+?)"', webpage, 'title')
+        title = self._html_search_regex(r'data-prm-title="(.+?)"', webpage, 'title')
+
+        # Extract the download URL
+        headers={
+            'Accept': 'application/json, text/plain, */*',
+            'Accept-Encoding': 'identity',
+            'Origin': 'https://www.ivoox.com',
+            'Referer': 'https://www.ivoox.com/',
+            'Priority': 'u=1, i'
+        }
+        metadata_url = f'https://vcore-web.ivoox.com/v1/public/audios/{media_id}/download-url'
+        download_json = self._download_json(metadata_url, media_id, headers=headers)
+        download_url = download_json['data']['downloadUrl']
+        url = f'https://ivoox.com{download_url}'
+
+        # Formats
+        formats = [
+            {
+                'url': url,
+                'ext': 'mp3',
+                'format_id': 'mp3_default',
+                'http_headers': headers
+            }
+        ]
+
+        return {
+            'id': media_id,
+            'title': title,
+            'uploader': author,
+            'channel': podcast,
+            'timestamp': timestamp,
+            'description': self._og_search_description(webpage),
+            'formats': formats,
+        }
\ No newline at end of file