#1745761, #755670, #13357, #12629, #1200313: improve attribute handling in HTMLParser.
diff --git a/Lib/HTMLParser.py b/Lib/HTMLParser.py
index 94ebc7f..cd353f8 100644
--- a/Lib/HTMLParser.py
+++ b/Lib/HTMLParser.py
@@ -24,22 +24,23 @@
piclose = re.compile('>')
commentclose = re.compile(r'--\s*>')
tagfind = re.compile('[a-zA-Z][-.a-zA-Z0-9:_]*')
+
attrfind = re.compile(
- r'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*'
- r'(\'[^\']*\'|"[^"]*"|[^\s"\'=<>`]*))?')
+ r'\s*((?<=[\'"\s])[^\s/>][^\s/=>]*)(\s*=+\s*'
+ r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?')
locatestarttagend = re.compile(r"""
<[a-zA-Z][-.a-zA-Z0-9:_]* # tag name
(?:\s+ # whitespace before attribute name
- (?:[a-zA-Z_][-.:a-zA-Z0-9_]* # attribute name
- (?:\s*=\s* # value indicator
+ (?:(?<=['"\s])[^\s/>][^\s/=>]* # attribute name
+ (?:\s*=+\s* # value indicator
(?:'[^']*' # LITA-enclosed value
- |\"[^\"]*\" # LIT-enclosed value
- |[^'\">\s]+ # bare value
+ |"[^"]*" # LIT-enclosed value
+ |(?!['"])[^>\s]* # bare value
)
- )?
- )
- )*
+ )?\s*
+ )*
+ )?
\s* # trailing whitespace
""", re.VERBOSE)
endendtag = re.compile('>')
@@ -254,6 +255,7 @@
elif attrvalue[:1] == '\'' == attrvalue[-1:] or \
attrvalue[:1] == '"' == attrvalue[-1:]:
attrvalue = attrvalue[1:-1]
+ if attrvalue:
attrvalue = self.unescape(attrvalue)
attrs.append((attrname.lower(), attrvalue))
k = m.end()