mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-07-30 06:34:15 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

#1745761, #755670, #13357, #12629, #1200313: improve attribute handling in HTMLParser.

Browse source
This commit is contained in:
Ezio Melotti 2011-11-14 18:04:05 +02:00
parent 74592919d6
commit 0f1571ce7f
3 changed files with 87 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

20
Lib/HTMLParser.py
View file

@ -24,22 +24,23 @@ starttagopen = re.compile('<[a-zA-Z]')
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 @@ class HTMLParser(markupbase.ParserBase):
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()