C#清除HTML标签方法

删除字符串中HTML标签代码

public static string ClearHTMLTags1(string HTML)

        {
            string[] Regexs ={
                        @"<script[^>]*?>.*?</script>",
                        @"<(\/\s*)?!?((\w+:)?\w+)(\w+(\s*=?\s*(([""'])(\\[""'tbnr]|[^\7])*?\7|\w+)|.{0})|\s)*?(\/\s*)?>",
                        @"([\r\n])[\s]+",
                        @"&(quot|#34);",
                        @"&(amp|#38);",
                        @"&(lt|#60);",
                        @"&(gt|#62);",
                        @"&(nbsp|#160);",
                        @"&(iexcl|#161);",
                        @"&(cent|#162);",
                        @"&(pound|#163);",
                        @"&(copy|#169);",
                        @"&#(\d+);",
                        @"-->",
                        @"<!--.*\n",
        };


            string[] Replaces ={
                            "",
                            "",
                            "",
                            "\"",
                            "&",
                            "<",
                            ">",
                            " ",
                            "\xa1", //chr(161),
                            "\xa2", //chr(162),
                            "\xa3", //chr(163),
                            "\xa9", //chr(169),
                            "",
                            "\r\n",
                            "",
                            ""
        };


            string s = HTML;
            for (int i = 0; i < Regexs.Length; i++)
            {
                s = new Regex(Regexs[i], RegexOptions.Multiline | RegexOptions.IgnoreCase).Replace(s, Replaces[i]);
            }
            s.Replace("<", "");
            s.Replace(">", "");
            s.Replace("\r\n", "");
            return s;
        }

 

上一篇:解决php导出csv文件utf8中文乱码问题


下一篇:Python 中英文混输格式对齐问题