[extractor/common] Allow HTML5 unquoted attribute values

Fixes #7108

HTML5 allows unquoted attribute values. See the "Unquoted attribute value
syntax" section [1] for more information

[1] http://www.w3.org/TR/html5/syntax.html
This commit is contained in:
Yen Chi Hsuan 2015-10-09 14:11:00 +08:00
parent 54a5428518
commit 57935b2564

View file

@ -646,7 +646,7 @@ def _get_tfa_info(self, note='two-factor verification code'):
@staticmethod
def _og_regexes(prop):
content_re = r'content=(?:"([^>]+?)"|\'([^>]+?)\')'
property_re = r'(?:name|property)=[\'"]og:%s[\'"]' % re.escape(prop)
property_re = r'(?:name|property)=[\'"]?og:%s[\'"]?' % re.escape(prop)
template = r'<meta[^>]+?%s[^>]+?%s'
return [
template % (property_re, content_re),