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

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

Browse source
This commit is contained in:
Ezio Melotti 2011-11-14 18:53:33 +02:00
parent b245ed1cdf
commit c2fe57762b
3 changed files with 106 additions and 23 deletions
Download patch file Download diff file Expand all files Collapse all files

19
Lib/html/parser.py
View file

@ -30,8 +30,8 @@ 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]*))?')
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
@ -49,16 +49,16 @@ locatestarttagend = re.compile(r"""
locatestarttagend_tolerant = re.compile(r"""
<[a-zA-Z][-.a-zA-Z0-9:_]* # tag name
(?:\s* # optional 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*,)* # possibly followed by a comma
)?
)
)*
)?\s*
)*
)?
\s* # trailing whitespace
""", re.VERBOSE)
endendtag = re.compile('>')
@ -295,6 +295,7 @@ 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()