def sanitize_payload(payload):
"Sanitize HTML"
if not payload:
return '', ''
styles = []
payload = clean_payload(payload)
body_style, body_class = get_body_style(payload)
if body_style:
styles.append(body_style)
safe_attrs = set(defs.safe_attrs)
safe_attrs.add('style')
cleaner = Cleaner(remove_tags=UNCLEANTAGS,
safe_attrs_only=True,
safe_attrs=safe_attrs)
payload = HTMLTITLE_RE.sub('', payload)
try:
html = cleaner.clean_html(payload)
except ValueError:
payload = bytes(bytearray(payload, encoding='utf-8'))
html = cleaner.clean_html(payload)
except XMLSyntaxError:
html = ''
mainstyle = sanitize_css(get_style(html))
if mainstyle:
styles.append(decode(mainstyle))
style = u'\n'.join(styles)
html = clean_styles(CSS_COMMENT_RE.sub('', html))
html = set_body_class(html, body_class)
return html.strip(), style.strip()
def sanitize_payload(payload):
"Sanitize HTML"
if not payload:
return '', ''
styles = []
payload = clean_payload(payload)
body_style, body_class = get_body_style(payload)
if body_style:
styles.append(body_style)
safe_attrs = set(defs.safe_attrs)
safe_attrs.add('style')
cleaner = Cleaner(remove_tags=UNCLEANTAGS,
safe_attrs_only=True,
safe_attrs=safe_attrs)
payload = HTMLTITLE_RE.sub('', payload)
try:
html = cleaner.clean_html(payload)
except ValueError:
payload = bytes(bytearray(payload, encoding='utf-8'))
html = cleaner.clean_html(payload)
except XMLSyntaxError:
html = ''
mainstyle = sanitize_css(get_style(html))
if mainstyle:
styles.append(decode(mainstyle))
style = u'\n'.join(styles)
html = clean_styles(CSS_COMMENT_RE.sub('', html))
html = set_body_class(html, body_class)
return html.strip(), style.strip()
def sanitize_html(self, msg):
"Clean up html"
cleaner = CustomCleaner(style=True,
remove_tags=UNCLEANTAGS,
safe_attrs_only=True)
# workaround to bug in lxml which does not remove title
msg = HTMLTITLE_RE.sub('', msg)
html = cleaner.clean_html(msg)
return html
def sanitize_html(self, msg):
"Clean up html"
cleaner = CustomCleaner(style=True,
remove_tags=UNCLEANTAGS,
safe_attrs_only=True)
# workaround to bug in lxml which does not remove title
msg = HTMLTITLE_RE.sub('', msg)
html = cleaner.clean_html(msg)
return html