Merge pull request #12906 from Tithen-Firion/clean-html-fix

[utils] Fix inconsistent output of clean_html
This commit is contained in:
Yen Chi Hsuan 2017-04-29 15:58:45 +08:00 committed by GitHub
commit d19093bd50
2 changed files with 3 additions and 2 deletions

View file

@ -899,6 +899,7 @@ def test_extract_attributes(self):
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(

View file

@ -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