mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-22 09:45:06 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 13

#13273: fix a bug that prevented HTMLParser to properly detect some tags when strict=False.

Browse source
This commit is contained in:
Ezio Melotti 2011-10-28 13:21:09 +03:00
parent 0b85cd0680
commit f50ffa94ab
3 changed files with 38 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

5
Lib/html/parser.py
View file

@ -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)