# cython: language_level=3str
"""A cleanup tool for HTML.
Removes unwanted tags and content. See the `Cleaner` class for
details.
"""
from __future__ import absolute_import
import copy
import re
import sys
try:
from urlparse import urlsplit
from urllib import unquote_plus
except ImportError:
# Python 3
from urllib.parse import urlsplit, unquote_plus
from lxml import etree
from lxml.html import defs
from lxml.html import fromstring, XHTML_NAMESPACE
from lxml.html import xhtml_to_html, _transform_result
try:
unichr
except NameError:
# Python 3
unichr = chr
try:
unicode
except NameError:
# Python 3
unicode = str
try:
basestring
except NameError:
basestring = (str, bytes)
__all__ = ['clean_html', 'clean', 'Cleaner', 'autolink', 'autolink_html',
'word_break', 'word_break_html']
# Look at http://code.sixapart.com/trac/livejournal/browser/trunk/cgi-bin/cleanhtml.pl
# Particularly the CSS cleaning; most of the tag cleaning is integrated now
# I have multiple kinds of schemes searched; but should schemes be
# whitelisted instead?
# max height?
# remove images? Also in CSS? background attribute?
# Some way to whitelist object, iframe, etc (e.g., if you want to
# allow *just* embedded YouTube movies)
# Log what was deleted and why?
# style="behavior: ..." might be bad in IE?
# Should we have something for just ? That's the worst of the
# metas.
# UTF-7 detections? Example:
# +ADw-SCRIPT+AD4-alert('XSS');+ADw-/SCRIPT+AD4-
# you don't always have to have the charset set, if the page has no charset
# and there's UTF7-like code in it.
# Look at these tests: http://htmlpurifier.org/live/smoketests/xssAttacks.php
# This is an IE-specific construct you can have in a stylesheet to
# run some Javascript:
_replace_css_javascript = re.compile(
r'expression\s*\(.*?\)', re.S|re.I).sub
# Do I have to worry about @\nimport?
_replace_css_import = re.compile(
r'@\s*import', re.I).sub
_looks_like_tag_content = re.compile(
r'= 3 else ())).search
# All kinds of schemes besides just javascript: that can cause
# execution:
_find_image_dataurls = re.compile(
r'data:image/(.+);base64,', re.I).findall
_possibly_malicious_schemes = re.compile(
r'(javascript|jscript|livescript|vbscript|data|about|mocha):',
re.I).findall
# SVG images can contain script content
_is_unsafe_image_type = re.compile(r"(xml|svg)", re.I).search
def _has_javascript_scheme(s):
safe_image_urls = 0
for image_type in _find_image_dataurls(s):
if _is_unsafe_image_type(image_type):
return True
safe_image_urls += 1
return len(_possibly_malicious_schemes(s)) > safe_image_urls
_substitute_whitespace = re.compile(r'[\s\x00-\x08\x0B\x0C\x0E-\x19]+').sub
# FIXME: check against: http://msdn2.microsoft.com/en-us/library/ms537512.aspx
_conditional_comment_re = re.compile(
r'\[if[\s\n\r]+.*?][\s\n\r]*>', re.I|re.S)
_find_styled_elements = etree.XPath(
"descendant-or-self::*[@style]")
_find_external_links = etree.XPath(
("descendant-or-self::a [normalize-space(@href) and substring(normalize-space(@href),1,1) != '#'] |"
"descendant-or-self::x:a[normalize-space(@href) and substring(normalize-space(@href),1,1) != '#']"),
namespaces={'x':XHTML_NAMESPACE})
class Cleaner(object):
"""
Instances cleans the document of each of the possible offending
elements. The cleaning is controlled by attributes; you can
override attributes in a subclass, or set them in the constructor.
``scripts``:
Removes any ``