C # HTML Tag Filtering

Original article: http://www.ityoudao.com/Web/Csharp_590_1509.html

You can customize it as needed...

Private string filterhtml (string html) {system. text. regularexpressions. regEx regex1 = new system. text. regularexpressions. regEx (@ "<SCRIPT [ss] + </script *>", system. text. regularexpressions. regexoptions. ignorecase); system. text. regularexpressions. regEx regex2 = new system. text. regularexpressions. regEx (@ "href * = * [ss] * script *:", system. text. regularexpressions. regexoptions. ignorecase); system. text. regularexpressions. regEx regex3 = new system. text. regularexpressions. regEx (@ "No [ss] * =", system. text. regularexpressions. regexoptions. ignorecase); system. text. regularexpressions. regEx regex4 = new system. text. regularexpressions. regEx (@ "<IFRAME [ss] + </iframe *>", system. text. regularexpressions. regexoptions. ignorecase); system. text. regularexpressions. regEx regex5 = new system. text. regularexpressions. regEx (@ "<frameset [ss] + </frameset *>", system. text. regularexpressions. regexoptions. ignorecase); system. text. regularexpressions. regEx regex6 = new system. text. regularexpressions. regEx (@ "] +>", system. text. regularexpressions. regexoptions. ignorecase); system. text. regularexpressions. regEx regex7 = new system. text. regularexpressions. regEx (@ "</P>", system. text. regularexpressions. regexoptions. ignorecase); system. text. regularexpressions. regEx regex8 = new system. text. regularexpressions. regEx (@ "<p>", system. text. regularexpressions. regexoptions. ignorecase); system. text. regularexpressions. regEx regex9 = new system. text. regularexpressions. regEx (@ "<[^>] *>", system. text. regularexpressions. regexoptions. ignorecase); html = regex1.replace (HTML, ""); // filter <SCRIPT> </SCRIPT> tags html = regex2.replace (HTML ,""); // filter href = javascript: (<A>) attribute html = regex3.replace (HTML, "_ disibledevent ="); // filter other controls on... event html = regex4.replace (HTML, ""); // filter iframe html = regex5.replace (HTML, ""); // filter frameset html = regex6.replace (HTML ,""); // filter frameset html = regex7.replace (HTML, ""); // filter frameset html = regex8.replace (HTML, ""); // filter frameset html = regex9.replace (HTML, ""); // html = html. replace ("", ""); html = html. replace ("</strong>", ""); html = html. replace ("<strong>", ""); html = RegEx. replace (HTML, "[\ f \ n \ r \ t \ v]", ""); // filter the line feed tab return HTML ;}