From 6a765f135ccb654861336ea27a2c1c24ea8e286f Mon Sep 17 00:00:00 2001
From: vidiot720 <128325907+vidiot720@users.noreply.github.com>
Date: Wed, 19 Apr 2023 09:46:57 +1000
Subject: [extractor/sbs] Overhaul extractor for new API (#6839)

Closes #6543
Authored by: vidiot720, dirkf, bashonly
---
 yt_dlp/utils.py | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'yt_dlp/utils.py')

diff --git a/yt_dlp/utils.py b/yt_dlp/utils.py
index 40533c2cb..746a2885d 100644
--- a/yt_dlp/utils.py
+++ b/yt_dlp/utils.py
@@ -4093,6 +4093,10 @@ def dfxp2srt(dfxp_data):
         def close(self):
             return self._out.strip()
 
+    # Fix UTF-8 encoded file wrongly marked as UTF-16. See https://github.com/yt-dlp/yt-dlp/issues/6543#issuecomment-1477169870
+    # This will not trigger false positives since only UTF-8 text is being replaced
+    dfxp_data = dfxp_data.replace(b'encoding=\'UTF-16\'', b'encoding=\'UTF-8\'')
+
     def parse_node(node):
         target = TTMLPElementParser()
         parser = xml.etree.ElementTree.XMLParser(target=target)
-- 
cgit v1.2.3