去除HTML标记

37

作者:管理员 发布时间:2021年10月13日 15时34分05秒

    /// <summary>
    /// 去除HTML标记
    /// </summary>
    /// <param name="strHtml">包括HTML的源码 </param>
    /// <returns>已经去除后的文字</returns>
    public static string StripHTML(string strHtml)
    {
        string[] aryReg = { @"<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[] aryRep = { "", "", "", "\"", "&", "<", ">", " ", "\xa1", "\xa2", "\xa3", "\xa9", "", "\r\n", "" };
        string newReg = aryReg[0];
        string strOutput = strHtml;
        for (int i = 0; i < aryReg.Length; i++)
        {
            Regex regex = new Regex(aryReg[i], RegexOptions.IgnoreCase);
            strOutput = regex.Replace(strOutput, aryRep[i]);
        }
        strOutput.Replace("<", ""); strOutput.Replace(">", "");
        strOutput.Replace("\r\n", ""); return strOutput;
    }

去除HTML标记

Copyright © 2021 奥纳拉. onala       湘ICP备2021002517号-1        湘公网安备43010402000262号