From edd9221cd22614b9d06f52b16bad278201fabd01 Mon Sep 17 00:00:00 2001
From: Tithen-Firion <tithen.firion.0@gmail.com>
Date: Fri, 28 Apr 2017 17:34:27 +0200
Subject: [PATCH 1/2] [utils] Fix inconsistent output of clean_html

`\s` in Python 2.x doesn't match unicode whitespace characters by
default
---
 youtube_dl/utils.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index 91e235ff2..41bc20544 100644
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -421,8 +421,8 @@ def clean_html(html):
 
     # Newline vs <br />
     html = html.replace('\n', ' ')
-    html = re.sub(r'\s*<\s*br\s*/?\s*>\s*', '\n', html)
-    html = re.sub(r'<\s*/\s*p\s*>\s*<\s*p[^>]*>', '\n', 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

From 9222d945107411ba657dab965fab63de8e8781b9 Mon Sep 17 00:00:00 2001
From: Tithen-Firion <tithen.firion.0@gmail.com>
Date: Fri, 28 Apr 2017 18:05:14 +0200
Subject: [PATCH 2/2] [test_utils] Add one more clean_html test

---
 test/test_utils.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/test/test_utils.py b/test/test_utils.py
index 4cd818850..9e1808e6b 100644
--- a/test/test_utils.py
+++ b/test/test_utils.py
@@ -899,6 +899,7 @@ class TestUtil(unittest.TestCase):
     def test_clean_html(self):
         self.assertEqual(clean_html('a:\nb'), 'a: b')
         self.assertEqual(clean_html('a:\n   "b"'), 'a:    "b"')
+        self.assertEqual(clean_html('a<br>\xa0b'), 'a\nb')
 
     def test_intlist_to_bytes(self):
         self.assertEqual(