71 lines
2.7 KiB
Python
71 lines
2.7 KiB
Python
"""
|
|
Created on 19.10.2011
|
|
|
|
@author: christian
|
|
"""
|
|
from BeautifulSoup import BeautifulSoup
|
|
|
|
|
|
class HtmlCleaner(object):
|
|
ACCEPTABLE_ELEMENTS = ['a', 'abbr', 'acronym', 'address', 'area', 'b',
|
|
'big', 'blockquote', 'br', 'button', 'caption',
|
|
'center', 'cite',
|
|
'code', 'col', 'colgroup', 'dd', 'del', 'dfn', 'dir',
|
|
'div', 'dl',
|
|
'dt', 'em', 'font', 'h1', 'h2', 'h3', 'h4', 'h5',
|
|
'h6', 'hr', 'i',
|
|
'img', 'ins', 'kbd', 'label', 'legend', 'li', 'map',
|
|
'menu', 'ol',
|
|
'p', 'pre', 'q', 's', 'samp', 'small', 'span',
|
|
'strike',
|
|
'strong', 'sub', 'sup', 'table', 'tbody', 'td',
|
|
'tfoot', 'th',
|
|
'thead', 'tr', 'tt', 'u', 'ul', 'var']
|
|
|
|
ACCEPTABELE_ATTRIBUTES = [
|
|
'abbr', 'accept', 'accept-charset', 'accesskey',
|
|
'action', 'align', 'class', 'alt', 'axis',
|
|
'char', 'charoff', 'charset', 'checked', 'cite', 'clear', 'cols',
|
|
'colspan', 'color', 'compact', 'coords', 'datetime', 'dir',
|
|
'enctype', 'for', 'headers', 'height', 'href', 'hreflang', 'hspace',
|
|
'id', 'ismap', 'label', 'lang', 'longdesc', 'maxlength', 'method',
|
|
'multiple', 'name', 'nohref', 'noshade', 'nowrap', 'prompt',
|
|
'rel', 'rev', 'rows', 'rowspan', 'rules', 'scope', 'shape', 'size',
|
|
'span', 'src', 'start', 'summary', 'tabindex', 'target', 'title',
|
|
'type', 'usemap', 'valign', 'value', 'vspace', 'width']
|
|
|
|
counter = 1
|
|
tag_removed = False
|
|
|
|
def clean_attributes(self, tag):
|
|
for attr in tag._getAttrMap().keys():
|
|
if attr not in self.ACCEPTABELE_ATTRIBUTES:
|
|
del tag[attr]
|
|
elif tag[attr].count('script:'):
|
|
del tag[attr]
|
|
|
|
def clean_tag(self, tag):
|
|
if tag.name not in self.ACCEPTABLE_ELEMENTS:
|
|
tag.extract() # remove the bad ones
|
|
self.tag_removed = True
|
|
else:
|
|
self.clean_attributes(tag)
|
|
|
|
def clean_html(self, fragment=''):
|
|
"""
|
|
Reparses and cleans the html from XSS Attacks until it stops changing.
|
|
@param fragment:
|
|
"""
|
|
while True:
|
|
soup = BeautifulSoup(fragment)
|
|
self.tag_removed = False
|
|
self.counter += 1
|
|
for tag in soup.findAll(True):
|
|
self.clean_tag(tag)
|
|
fragment = unicode(soup)
|
|
if self.tag_removed:
|
|
continue
|
|
else:
|
|
break
|
|
return fragment
|