From b901e4fb8a612783cfa72bf54788eec0208bc46a Mon Sep 17 00:00:00 2001
From: Lucas Rademaker <44430780+lr4d@users.noreply.github.com>
Date: Tue, 8 Oct 2024 17:39:47 +0545
Subject: [PATCH] [Zoom] add intepreter audio formats

Use the options `-f "best+mergeall[vcodec=none]" --audio-multistreams` to merge all intepreter tracks alongside the main video
---
 yt_dlp/extractor/zoom.py | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)

diff --git a/yt_dlp/extractor/zoom.py b/yt_dlp/extractor/zoom.py
index fe2db846ad..a7cc8dfefc 100644
--- a/yt_dlp/extractor/zoom.py
+++ b/yt_dlp/extractor/zoom.py
@@ -86,7 +86,6 @@ def _get_real_webpage(self, url, base_url, video_id, url_type):
 
     def _real_extract(self, url):
         base_url, url_type, video_id = self._match_valid_url(url).group('base_url', 'type', 'id')
-        query = {}
 
         if url_type == 'share':
             webpage = self._get_real_webpage(url, base_url, video_id, 'share')
@@ -95,7 +94,6 @@ def _real_extract(self, url):
                 f'{base_url}nws/recording/1.0/play/share-info/{meeting_id}',
                 video_id, note='Downloading share info JSON')['result']['redirectUrl']
             url = urljoin(base_url, redirect_path)
-            query['continueMode'] = 'true'
 
         webpage = self._get_real_webpage(url, base_url, video_id, 'play')
         file_id = self._get_page_data(webpage, video_id)['fileId']
@@ -104,10 +102,13 @@ def _real_extract(self, url):
             raise ExtractorError('Unable to extract file ID')
 
         data = self._download_json(
-            f'{base_url}nws/recording/1.0/play/info/{file_id}', video_id, query=query,
+            f'{base_url}nws/recording/1.0/play/info/{file_id}', video_id, query={
+                'continueMode': 'true',  # Makes this return value include interpreter audio information
+            },
             note='Downloading play info JSON')['result']
 
         subtitles = {}
+        # XXX: Would be more appropriate to parse chapters separate from subtitles
         for _type in ('transcript', 'cc', 'chapter'):
             if data.get(f'{_type}Url'):
                 subtitles[_type] = [{
@@ -117,6 +118,19 @@ def _real_extract(self, url):
 
         formats = []
 
+        if data.get('interpreterAudioList'):
+            for audio in data.get('interpreterAudioList'):
+                formats.append({
+                    'format_note': f'Intepreter: {audio["languageText"]}',
+                    'url': audio['audioUrl'],
+                    'format_id': f'interpreter-{ audio["icon"].lower()}',
+                    'ext': 'm4a',
+                    # There doesn't seem to be an explicit field for a standardized language code,
+                    # sometimes the `language` field may be more accurate than `icon`
+                    'language': audio['icon'].lower(),
+                    'vcodec': 'none',
+                })
+
         if data.get('viewMp4Url'):
             formats.append({
                 'format_note': 'Camera stream',