From 4918522735149b880586fc6b8cea31fa6a28e136 Mon Sep 17 00:00:00 2001
From: pukkandan <pukkandan.ytdlp@gmail.com>
Date: Thu, 3 Feb 2022 19:45:57 +0530
Subject: [PATCH] [utils] Strip double spaces in `clean_html`

Closes #2497
Authored by: dirkf
---
 yt_dlp/utils.py | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/yt_dlp/utils.py b/yt_dlp/utils.py
index 13ad5fd489..fd3912d188 100644
--- a/yt_dlp/utils.py
+++ b/yt_dlp/utils.py
@@ -639,10 +639,9 @@ def clean_html(html):
     if html is None:  # Convenience for sanitizing descriptions etc.
         return html
 
-    # Newline vs <br />
-    html = html.replace('\n', ' ')
-    html = re.sub(r'(?u)\s*<\s*br\s*/?\s*>\s*', '\n', html)
-    html = re.sub(r'(?u)<\s*/\s*p\s*>\s*<\s*p[^>]*>', '\n', html)
+    html = re.sub(r'\s+', ' ', html)
+    html = re.sub(r'(?u)\s?<\s?br\s?/?\s?>\s?', '\n', html)
+    html = re.sub(r'(?u)<\s?/\s?p\s?>\s?<\s?p[^>]*>', '\n', html)
     # Strip html tags
     html = re.sub('<.*?>', '', html)
     # Replace html entities