[parsing] search for case-insensitive tag names

This commit is contained in:
Marcel 2022-11-29 15:01:18 +01:00
parent 6169b3eca8
commit 65f91148fc
No known key found for this signature in database
GPG key ID: 7813C97693AD6AAE
2 changed files with 6 additions and 2 deletions

View file

@ -222,6 +222,10 @@ def test_get_element_text_and_html_by_tag_malformed(self):
get_element_text_and_html_by_tag('orphan', f'<orphan>{html}'), ('', '<orphan>'))
self.assertIsNone(get_element_text_and_html_by_tag('orphan', f'{html}</orphan>'))
# ignore case on tags
ci_html = f'<SpAn>{html}</sPaN>'
self.assertEqual(get_element_text_and_html_by_tag('span', ci_html), (html, ci_html))
def test_strict_html_parsing(self):
class StrictTagParser(HTMLTagParser):
STRICT = True

View file

@ -245,7 +245,7 @@ def matching_tag_regex(tag, attribute, value_regex, escape=True):
value_regex = re.escape(value_regex)
return rf'''(?x)
<(?:{tag})
<(?i:{tag})
(?:\s(?:[^>"'\\]|"[^"\\]*"|'[^'\\]*')*)?
\s{re.escape(attribute)}\s*=\s*(?P<_q>['"])(?-x:{value_regex})(?P=_q)
'''
@ -263,7 +263,7 @@ def tags_by_name(cls, tag, html):
def matchfunc(tag_str, _attrs):
return tag_str == tag
tag_regex = rf'''<\s*{re.escape(tag)}(?:\s(?:[^>"'\\]|"[^"\\]*"|'[^'\\]*')*)?>'''
tag_regex = rf'''<\s*(?i:{re.escape(tag)})(?:\s(?:[^>"'\\]|"[^"\\]*"|'[^'\\]*')*)?>'''
yield from cls.iter_tags(tag_regex, html, matchfunc=matchfunc)
@classmethod