From: Tithen-Firion <tithen.firion.0@gmail.com>
Date: Fri, 28 Apr 2017 15:34:27 +0000 (+0200)
Subject: [utils] Fix inconsistent output of clean_html
X-Git-Url: https://git.cielonegro.org/gitweb.cgi?a=commitdiff_plain;h=edd9221cd22614b9d06f52b16bad278201fabd01;p=youtube-dl.git

[utils] Fix inconsistent output of clean_html

`\s` in Python 2.x doesn't match unicode whitespace characters by
default
---

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