html编辑及JS脚本过滤

关注

原创最新推荐文章于 2026-04-22 09:18:34 发布 2.7k 阅读 AI 写同款· GEO 优化 ›

javascript过滤危险脚本方法下面是他们的字符串规则： 1、<(script|link|style|iframe)(.|\n)*<\/\1>\s* 2、\s*on[a-z]+\s*=\s*(“[^”]+”|'[^’]+’|[^\s]+)\s*(?=>) 3、\s*(href|src)\s*=\s*(“\s*(javascript|vbscript):[^”]+”|’\s*(javascript|vbscript):[^’]+’|(javascript|vbscript):[^\s]+)\s*(?=>) 4、epression\((.|\n)*\);? 了解他们的规则后，抓虫行动就水到渠成。抓虫1 a { heigh 立即下载

public static string NoHTML(string Htmlstring) //去除HTML标记 { //删除脚本 Htmlstring = Regex.Replace(Htmlstring, @"(?is)<(script)/b[^>]*>(?(?!/1/b).)*<//1>", string.Empty, RegexOptions.IgnoreCase); //删除HTML Htmlstring = Regex.Replace(Htmlstring,@"<(?>[^>]*)>",string.Empty, RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"([/r/n])[/s]+", string.Empty, RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"-->", string.Empty, RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"<!--.*", string.Empty, RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(quot|#34);", "/"", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(amp|#38);", "&", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(lt|#60);", "<", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(gt|#62);", ">", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(nbsp|#160);", " ", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(iexcl|#161);", "/xa1", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(cent|#162);", "/xa2", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(pound|#163);", "/xa3", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(copy|#169);", "/xa9", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&#(/d+);", string.Empty, RegexOptions.IgnoreCase); //Htmlstring = Htmlstring.Replace("<", string.Empty);//根据实际情况去掉注释 //Htmlstring = Htmlstring.Replace(">", string.Empty); //根据实际情况去掉注释 Htmlstring=Htmlstring.Replace("/r/n",string.Empty); //Htmlstring = HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim(); return Htmlstring; }

收录于