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(
# 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