li.的博客
li.的首页 > li.的博客 > 浏览文章

asp.net过滤HTML标签的几个函数

分类:.net应用  人气:902  评论:0  时间:2010-01-06 15:54

using System.Text.RegularExpressions;
using System.Web;

namespace Tools
{
    public class FiterHtml
    {
        ///   <summary>
        ///   去除HTML标记
        ///   </summary>
        public static string NoHTML(string Htmlstring)
        {
            //删除脚本
            Htmlstring = Regex.Replace(Htmlstring, @"<script[^>]*?>.*?</script>", "",
              RegexOptions.IgnoreCase);
            //删除HTML
            Htmlstring = Regex.Replace(Htmlstring, @"<(.[^>]*)>", "",
              RegexOptions.IgnoreCase);
            Htmlstring = Regex.Replace(Htmlstring, @"([\r\n])[\s]+", "",
              RegexOptions.IgnoreCase);
            Htmlstring = Regex.Replace(Htmlstring, @"-->", "", RegexOptions.IgnoreCase);
            Htmlstring = Regex.Replace(Htmlstring, @"<!--.*", "", 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+);", "",
              RegexOptions.IgnoreCase);
            Htmlstring.Replace("<", "");
            Htmlstring.Replace(">", "");
            Htmlstring.Replace("\r\n", "");
            Htmlstring = HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();

            return Htmlstring;
        }
        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",  //chr(161),
              "\xa2",  //chr(162),
              "\xa3",  //chr(163),
              "\xa9",  //chr(169),
              "", "\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;
        }
        ///   <summary>
        ///   移除HTML标签
        ///   </summary>
        ///   <param   name="HTMLStr">HTMLStr</param>
        public static string ParseTags(string HTMLStr)
        {
            return System.Text.RegularExpressions.Regex.Replace(HTMLStr, "<[^>]*>", "");
        }
        ///   取出文本中的图片地址
        /**/
        ///   <summary>
        ///   取出文本中的图片地址
        ///   </summary>
        ///   <param   name="HTMLStr">HTMLStr</param>
        public static string GetImgUrl(string HTMLStr)
        {
            string str = string.Empty;
            string sPattern = @"^<img\s+[^>]*>";
            Regex r = new Regex(@"<img\s+[^>]*\s*src\s*=\s*([']?)(?<url>\S+)'?[^>]*>",
              RegexOptions.Compiled);
            Match m = r.Match(HTMLStr.ToLower());
            if (m.Success)
                str = m.Result("${url}");
            return str;
        }

    }
}

另外两个 

public String ForMatTextReplaceHTMLTags(string HTML)
        {
            if (HTML != "")
            {
                string HTMLTag = @"<\/*[^<>]*>";
                HTML = System.Text.RegularExpressions.Regex.Replace(HTML, HTMLTag, "");
            }
            return HTML;
        }

 

Regex.Replace(str,"<(.|\n)+?>","")
标签(Tag):asp.net
评论(0)
暂无评论
我来评论
(800字以内)