ASP.net（C#）中如何截取字符串时去除HTml标记

[koudefa]

ASP.net（C#）中如何截取字符串时去除HTml标记


<a hrfe = "" >gafgafgdfgadfgadf </a>gfdagadfgadfgdafgdafgadfgdafgdafgdafgadfgdaf

截取前20个字符如果没有去掉html的标记截取的字符串就会出错

[q107770540]

public string NoHTML(string Htmlstring) //去除HTML标记 
    { 
        //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; 
    }

[sugercgq]

先过滤html再截取

/// <summary>
        /// Html过滤
        /// </summary>
        /// <param name="pHtml"></param>
        /// <returns></returns>
        public static string ReplaceHTML(string pHtml)
        {
            return TestReplace.ReplaceHtmlTag(pHtml).Replace(" ", string.Empty).Replace("　", string.Empty);
        }

        public class TestReplace
        {
            private TestReplace() { }

            private static string sNR = "\r\n";
            private static string sXiaoYu = "<";
            private static string sDaYu = ">";
            private static IList<Regex> iList = new List<Regex>();

            private static string[] aReplace = new string[]
            {
                "","","","","","","","\"","&","<",">","","\xa1","\xa2","\xa3","\xa9",""
            };

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

                for (int i = 0; i < aPattern.Length; i++)
                {
                    iList.Add(new Regex(aPattern[i]));
                }
            }

            /// <summary>
            /// 去除HTML标记
            /// </summary>
            /// <param name="Htmlstring">包括HTML的源码 </param>
            /// <returns>已经去除后的文字</returns>
            public static string ReplaceHtmlTag(string Htmlstring)
            {
                Htmlstring = Htmlstring.Replace(sNR, string.Empty);

                Regex r;
                for (int i = 0; i < iList.Count; i++)
                {
                    r = iList[i];
                    if (r != null)
                        Htmlstring = r.Replace(Htmlstring, aReplace[i], -1, 0);
                }

                Htmlstring = Htmlstring.Replace(sXiaoYu, string.Empty);
                Htmlstring = Htmlstring.Replace(sDaYu, string.Empty);
                Htmlstring = Htmlstring.Replace(sNR, string.Empty);
                return Htmlstring;
            }
        }

调用 ReplaceHTML('html代码').Substring(0,20);

[Peter200694013]

http://www.cnblogs.com/yintian2/archive/2007/11/22/968127.html

[Peter200694013]

[Quote=引用楼主 koudefa 的回复:]
<a hrfe = "" >gafgafgdfgadfgadf </a>gfdagadfgadfgdafgdafgadfgdafgdafgdafgadfgdaf

截取前20个字符如果没有去掉html的标记截取的字符串就会出错
[/Quote]
你说的出错是指什么？
结果不对？

            String str = @"<a hrfe = "" >gafgafgdfgadfgadf </a>gfdagadfgadfgdafgdafgadfgdafgdafgdafgadfgdaf";
            str = str.Replace("\"","\"\"");

            Console.WriteLine(str.Substring(0,20));

[wilensky]

 #region 移除字符串中的html标记
        /// <summary>
        /// 移除字符串中的html标记
        /// </summary>
        /// <param name="html">要过滤的字符串</param>
        /// <returns>返回的结果</returns>
        public static string RemoveHtml(string html)
        {
            string result = html;
            
            MatchCollection matches = objReg.Matches(html);
            foreach (Match match in matches)
            {
                result = result.Replace(match.Value, string.Empty);
            }
            return HttpUtility.HtmlEncode(result.Replace("\"", ""));
        }

        private static readonly Regex objReg = new Regex("<.+?>", RegexOptions.IgnoreCase | RegexOptions.Compiled | RegexOptions.CultureInvariant);

[winner2050]

#2 的代码是错误的。那个作者的博客那里号称比 1# 贴出的代码性能高，其实是没有区分大小写带来性能提高。

但是带来健壮性问题。

[wuyq11]

过滤html Regex.Replace(str,@"<[^> ]+>","");

[村长_乐]

/// <summary>
/// 过滤HTML字符 和 UBB代码
/// </summary>
public static string NoCode(string str)
{
if (str == null || str.Length == 0) return "";
str = Regex.Replace(str, @"\<(?<x>[^\>]*)\>", @"", RegexOptions.IgnoreCase);
str = Regex.Replace(str, @"\[(?<x>[^\]]*)\]", @"", RegexOptions.IgnoreCase);
str = str.Replace(" ", " ");
str = str.Replace(">", ">");
str = str.Replace("<", "<");
str = str.Replace("\n", " ");
str = str.Replace("\r", "");
str = str.Replace("'", "");
return str;
}

[zhenshangzhengren]

呵呵，牛叉。这样的方法可以呢

[Dylan-Wang]

楼主说的出错应该是页面样式的跑偏，因为截取字符串中可能只有一半的html代码，如只有一个<div>而没有</div>,而关于html过滤这个方面，1楼的方法已经很全了，楼主完全可以引用的。