# cython: language_level=3str
"""A cleanup tool for HTML.
Removes unwanted tags and content. See the `Cleaner` class for
details.
"""
import copy
import re
from collections import deque
from urllib.parse import urlsplit, unquote_plus
import warnings
from lxml import etree
from lxml.html import defs
from lxml.html import fromstring as lxml_fromstring, XHTML_NAMESPACE
from lxml.html import xhtml_to_html, _transform_result
__all__ = ['clean_html', 'clean', 'Cleaner', 'autolink', 'autolink_html',
'word_break', 'word_break_html', 'LXMLHTMLCleanWarning', 'AmbiguousURLWarning']
# 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' 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})
# Regex to remove all ASCII control characters (00-1F,7F) except:
# - 09 - Horizontal tab
# - 0A - Line Feed
# - 0B - Vertical tab
# - 0D - Carriage Return
_ascii_control_characters_str = re.compile("[\x00-\x08\x0C\x0E-\x1F\x7F]")
_ascii_control_characters_bytes = re.compile(b"[\x00-\x08\x0C\x0E-\x1F\x7F]")
def fromstring(data):
"""
Enhanced fromstring function that removes ASCII control chars
before passing the input to the original lxml.html.fromstring.
"""
if isinstance(data, bytes):
return lxml_fromstring(_ascii_control_characters_bytes.sub(b"", data))
else:
return lxml_fromstring(_ascii_control_characters_str.sub("", data))
# This regular expression is inspired by the one in urllib3.
_URI_RE = re.compile(
r"^(?:(?P[a-zA-Z][a-zA-Z0-9+.-]*[a-zA-Z0-9]):)?"
r"(?://(?P[^\\/?#]*))?"
r"(?P[^?#]*)"
r"(?:\?(?P[^#]*))?"
r"(?:#(?P.*))?$",
re.UNICODE,
)
def _get_authority_from_url(url):
match = _URI_RE.match(url)
if match:
return match.group("authority")
else:
return None
class LXMLHTMLCleanWarning(Warning):
pass
class AmbiguousURLWarning(LXMLHTMLCleanWarning):
pass
class Cleaner:
"""
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 ``