From f50ffa94abe67c6ef5e615198af15f72e7cd2a9b Mon Sep 17 00:00:00 2001 From: Ezio Melotti Date: Fri, 28 Oct 2011 13:21:09 +0300 Subject: #13273: fix a bug that prevented HTMLParser to properly detect some tags when strict=False. --- Lib/html/parser.py | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'Lib/html') diff --git a/Lib/html/parser.py b/Lib/html/parser.py index a6d5be94fa..affaf7344f 100644 --- a/Lib/html/parser.py +++ b/Lib/html/parser.py @@ -30,7 +30,7 @@ attrfind = re.compile( r'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*' r'(\'[^\']*\'|"[^"]*"|[^\s"\'=<>`]*))?') attrfind_tolerant = re.compile( - r'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*' + r',?\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*' r'(\'[^\']*\'|"[^"]*"|[^>\s]*))?') locatestarttagend = re.compile(r""" <[a-zA-Z][-.a-zA-Z0-9:_]* # tag name @@ -277,12 +277,11 @@ class HTMLParser(_markupbase.ParserBase): assert match, 'unexpected call to parse_starttag()' k = match.end() self.lasttag = tag = rawdata[i+1:k].lower() - while k < endpos: if self.strict: m = attrfind.match(rawdata, k) else: - m = attrfind_tolerant.search(rawdata, k) + m = attrfind_tolerant.match(rawdata, k) if not m: break attrname, rest, attrvalue = m.group(1, 2, 3) -- cgit v1.2.1