C#清除HTML标签方法汇总

来源：互联网发布：博时大数据100好买编辑：程序博客网时间：2024/06/01 08:43

方法1：

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;

}

方法2：

转载自.http://blog.sina.com.cn/cheneyblog

public stringRemoveHTMLTags(string htmlStream)
       {
           if (htmlStream == null)
           {
               throw new Exception("Your input html stream is null!");
               return null;
           }

           /*
            *最好把所有的特殊HTML标记都找出来，然后把与其相对应的Unicode字符一起影射到Hash表内，最后一起都替换掉
            */

//先单独测试,成功后,再把所有模式合并

           //注:这两个必须单独处理
           //去掉嵌套了HTML标记的JavaScript:(<script)[\\s\\S]*(</script>)
           //去掉css标记:(<style)[\\s\\S]*(</style>)
           //去掉css标记:\\..*\\{[\\s\\S]*\\}
           htmlStream = Regex.Replace(htmlStream,"(<script)[\\s\\S]*?(</script>)|(<style)[\\s\\S]*?(</style>)"," ", RegexOptions.IgnoreCase);
           //htmlStream = RemoveTag(htmlStream, "script");
           //htmlStream = RemoveTag(htmlStream, "style");

           //去掉普通HTML标记:<[^>]+>
           //替换空格: |&|| |
           htmlStream = Regex.Replace(htmlStream,"<[^>]+>| |&|| ||•|<|>"," ", RegexOptions.IgnoreCase);
           //htmlStream = RemoveTag(htmlStream);

//替换左尖括号
//htmlStream = Regex.Replace(htmlStream, "<","<");

//替换右尖括号
//htmlStream = Regex.Replace(htmlStream, ">",">");

           //替换空行
           //htmlStream = Regex.Replace(htmlStream, "[\n|\r|\t]", "");//[\n|\r][\t*| *]*[\n|\r]
           htmlStream = Regex.Replace(htmlStream, "(\r\n[\r|\n|\t|]*\r\n)|(\n[\r|\n|\t| ]*\n)", "\r\n");
           htmlStream = Regex.Replace(htmlStream, "[\t| ]{1,}", "");

return htmlStream.Trim();
}

方法3：

//除去所有在html元素中标记
    publicstatic string striphtml(string strhtml)
    {
       string stroutput = strhtml;
       Regex regex = newRegex(@"<[^>]+>|</[^>]+>");

stroutput = regex.Replace(stroutput, "");
return stroutput;

}

方法4：

转载自.http://blog.csdn.net/hougelou/article/details/7901066

/// <summary>

/// 清除文本中Html的标签

/// </summary>

/// <param name="Content"></param>

/// <returns></returns>

protected string ClearHtml(string Content)

{

Content = Zxj_ReplaceHtml("&#[^>]*;", "", Content);

Content = Zxj_ReplaceHtml("</?marquee[^>]*>", "", Content);

Content = Zxj_ReplaceHtml("</?object[^>]*>", "", Content);

Content = Zxj_ReplaceHtml("</?param[^>]*>", "", Content);

Content = Zxj_ReplaceHtml("</?embed[^>]*>", "", Content);

Content = Zxj_ReplaceHtml("</?table[^>]*>", "", Content);

Content = Zxj_ReplaceHtml(" ", "", Content);

Content = Zxj_ReplaceHtml("</?tr[^>]*>", "", Content);

Content = Zxj_ReplaceHtml("</?th[^>]*>", "", Content);

Content = Zxj_ReplaceHtml("</?p[^>]*>", "", Content);

Content = Zxj_ReplaceHtml("</?a[^>]*>", "", Content);

Content = Zxj_ReplaceHtml("</?img[^>]*>", "", Content);

Content = Zxj_ReplaceHtml("</?tbody[^>]*>", "", Content);

Content = Zxj_ReplaceHtml("</?li[^>]*>", "", Content);

Content = Zxj_ReplaceHtml("</?span[^>]*>", "", Content);

Content = Zxj_ReplaceHtml("</?div[^>]*>", "", Content);

Content = Zxj_ReplaceHtml("</?th[^>]*>", "", Content);

Content = Zxj_ReplaceHtml("</?td[^>]*>", "", Content);

Content = Zxj_ReplaceHtml("</?script[^>]*>", "", Content);

Content = Zxj_ReplaceHtml("(javascript|jscript|vbscript|vbs):", "", Content);

Content = Zxj_ReplaceHtml("on(mouse|exit|error|click|key)", "", Content);

Content = Zxj_ReplaceHtml("<\\?xml[^>]*>", "", Content);

Content = Zxj_ReplaceHtml("<\\/?[a-z]+:[^>]*>", "", Content);

Content = Zxj_ReplaceHtml("</?font[^>]*>", "", Content);

Content = Zxj_ReplaceHtml("</?b[^>]*>", "", Content);

Content = Zxj_ReplaceHtml("</?u[^>]*>", "", Content);

Content = Zxj_ReplaceHtml("</?i[^>]*>", "", Content);

Content = Zxj_ReplaceHtml("</?strong[^>]*>", "", Content);

string clearHtml = Content;

return clearHtml;

}

/// <summary>

/// 清除文本中的Html标签

/// </summary>

/// <param name="patrn">要替换的标签正则表达式</param>

/// <param name="strRep">替换为的内容</param>

/// <param name="content">要替换的内容</param>

/// <returns></returns>

private string Zxj_ReplaceHtml(string patrn, string strRep, string content)

{

if (string.IsNullOrEmpty(content))

{

content = "";

}

Regex rgEx = new Regex(patrn, RegexOptions.IgnoreCase);

string strTxt = rgEx.Replace(content, strRep);

return strTxt;

}

0 0