def _clean_for_render(text): whitelist = [ 'backColor', 'backcolor', 'bgcolor', 'color', 'fg', 'fontName', 'fontSize', 'fontname', 'fontsize', 'href', 'name', 'textColor', 'textcolor' ] html = BeautifulSoup(text) html.attrs = None for e in html.findAll(True): for attribute in e.attrs: if attribute[0] not in whitelist: del e[attribute[0]] return unicode(html)