diff --git a/ox/html.py b/ox/html.py
index 28dcec1..f7ca816 100644
--- a/ox/html.py
+++ b/ox/html.py
@@ -16,7 +16,7 @@ TRAILING_PUNCTUATION = ['.', ',', ')', '>', '\n', '>', "'", '"']
DOTS = ['·', '*', '\xe2\x80\xa2', '', '•', '•']
unencoded_ampersands_re = re.compile(r'&(?!(\w+|#\d+);)')
-word_split_re = re.compile(r'(\s+)')
+word_split_re = re.compile(r'(\s+|
)')
punctuation_re = re.compile('^(?P(?:%s)*)(?P.*?)(?P(?:%s)*)$' % (
'|'.join([re.escape(x) for x in LEADING_PUNCTUATION]),
'|'.join([re.escape(x) for x in TRAILING_PUNCTUATION])))
@@ -393,7 +393,7 @@ def sanitize_html(html, tags=None, global_attributes=[]):
parts[i] = escape_html(decode_html(part))
html = ''.join(parts)
html = add_links(html)
- html = html.replace('\n\n', '
')
+ html = html.replace('\n\n', '
')
return sanitize_fragment(html)
def split_tags(string):