#14538: HTMLParser can now parse correctly start tags that contain a bare /.
diff --git a/Lib/html/parser.py b/Lib/html/parser.py
index 2bfd187..de504ab 100644
--- a/Lib/html/parser.py
+++ b/Lib/html/parser.py
@@ -22,7 +22,7 @@
starttagopen = re.compile('<[a-zA-Z]')
piclose = re.compile('>')
commentclose = re.compile(r'--\s*>')
-tagfind = re.compile('[a-zA-Z][-.a-zA-Z0-9:_]*')
+tagfind = re.compile('([a-zA-Z][-.a-zA-Z0-9:_]*)(?:\s|/(?!>))*')
# see http://www.w3.org/TR/html5/tokenization.html#tag-open-state
# and http://www.w3.org/TR/html5/tokenization.html#tag-name-state
tagfind_tolerant = re.compile('[a-zA-Z][^\t\n\r\f />\x00]*')
@@ -36,7 +36,7 @@
r'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*'
r'(\'[^\']*\'|"[^"]*"|[^\s"\'=<>`]*))?')
attrfind_tolerant = re.compile(
- r'[\s/]*((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*'
+ r'((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*'
r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*')
locatestarttagend = re.compile(r"""
<[a-zA-Z][-.a-zA-Z0-9:_]* # tag name
@@ -327,7 +327,7 @@
match = tagfind.match(rawdata, i+1)
assert match, 'unexpected call to parse_starttag()'
k = match.end()
- self.lasttag = tag = rawdata[i+1:k].lower()
+ self.lasttag = tag = match.group(1).lower()
while k < endpos:
if self.strict:
m = attrfind.match(rawdata, k)