正则表达式提取html代码中的数据

<table>
  <tr> 
            <td valign=center align=middle width=87 bgcolor=#CBF1FC height=20> 
              <div align="center"><span 
      style="FONT-SIZE: 9pt; FONT-FAMILY: 宋体, Verdana"><script language="JavaScript">tranCode("840")</script></span></div>
            </td>
            <td valign=center align=right width=79 height=20> 
              <div align="center"><span 
      style="FONT-SIZE: 9pt; FONT-FAMILY: 宋体, Verdana">6.7674</span></div>
            </td>
            <td valign=center align=right width=79 height=20> 
              <div align="center"><span 
      style="FONT-SIZE: 9pt; FONT-FAMILY: 宋体, Verdana">6.7946</span></div>
            </td>
            <td valign=center align=right width=79 height=20> 
              <div align="center"><span 
      style="FONT-SIZE: 9pt; FONT-FAMILY: 宋体, Verdana">6.7132</span></div>
            </td>
            <td valign=center align=right width=79 height=20> 
              <div align="center"><span 
      style="FONT-SIZE: 9pt; FONT-FAMILY: 宋体, Verdana">6.7946</span></div>
            </td>          </tr></table>
   我从一个网站上获取的信息，下面是获取信息的一行，我要提取每一行中每一列的数据
6.7674  6.7946 6.7946 6.7132
用正则表达式怎么提取，请指点一下，谢谢！

解决方案 »

  1.   

    >(-?\d+)(\.\d+)<$
    may it be
      

  2.   

    public string wipescript(string html)
        {
            System.Text.RegularExpressions.Regex regex1 = new System.Text.RegularExpressions.
            Regex(@"<script[\s\s]+</script *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
            System.Text.RegularExpressions.Regex regex2 = new System.Text.RegularExpressions.Regex
            (@" href *= *[\s\s]*script *:", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
            System.Text.RegularExpressions.Regex regex3 = new System.Text.RegularExpressions.Regex
            (@" on[\s\s]*=", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
            System.Text.RegularExpressions.Regex regex4 = new System.Text.RegularExpressions.Regex
            (@"<iframe[\s\s]+</iframe *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
            System.Text.RegularExpressions.Regex regex5 = new System.Text.RegularExpressions.Regex
            (@"<frameset[\s\s]+</frameset *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
            System.Text.RegularExpressions.Regex regex6 = new System.Text.RegularExpressions.Regex
            (@"<\/*[^<>]*>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
            // html = regex1.Replace(html, ""); //过滤<script></script>标记   
            // html = regex2.Replace(html, ""); //过滤href=javascript: (<a>) 属性   
            // html = regex3.Replace(html, " _disibledevent="); //过滤其它控件的on...事件   
            // html = regex4.Replace(html, ""); //过滤iframe   
            // html = regex5.Replace(html, ""); //过滤frameset   
            html = regex6.Replace(html, ""); //过滤html  
            //html通用标签："/<(?:(?:\/?[A-Za-z]\w+\b(?:[=\s](['"]?)[\s\S]*?\1)*)|(?:!--[\s\S]*?--))>/g"
            return html;
        }
      

  3.   

    干嘛一定要用正则
    <head runat="server">
        <title>无标题页</title>    <script src="App_common/scripts/jquery-1.4.2.min.js" type="text/javascript"></script>    <script type="text/javascript">
            $(function(){
            
               var Htmls=$("table").find("span");
               var temp="";
               $(Htmls).each(function(entrtyIndex,entrty){
                if(Htmls.eq(parseInt(entrtyIndex)).html()!="")
                 temp+=Htmls.eq(parseInt(entrtyIndex)).html()+",";
               })
               alert(temp);
            });
        </script>
    </head>
    <body>
        <form id="form1" runat="server">
        <table>
            <tr>
                <td valign="center" align="middle" width="87" bgcolor="#CBF1FC" height="20">
                    <div align="center">
                        <span style="font-size: 9pt; font-family: 宋体, Verdana">
                        
                        </span>
                    </div>
                </td>
                <td valign="center" align="right" width="79" height="20">
                    <div align="center">
                        <span style="font-size: 9pt; font-family: 宋体, Verdana">6.7674</span></div>
                </td>
                <td valign="center" align="right" width="79" height="20">
                    <div align="center">
                        <span style="font-size: 9pt; font-family: 宋体, Verdana">6.7946</span></div>
                </td>
                <td valign="center" align="right" width="79" height="20">
                    <div align="center">
                        <span style="font-size: 9pt; font-family: 宋体, Verdana">6.7132</span></div>
                </td>
                <td valign="center" align="right" width="79" height="20">
                    <div align="center">
                        <span style="font-size: 9pt; font-family: 宋体, Verdana">6.7946</span></div>
                </td>
            </tr>
        </table>
        </form>
    </body>
    </html>
      

  4.   


    加个
    <input type="hidden" raunt="server" id="hdTemp">js$("hdTemp").val(temp);cs后台：this.hdTemp.vaule;//再做字符串操作，不就一样么 
      

  5.   

                string content = "html 文本";
                string regStr = "<span\\s+style=\"FONT-SIZE: 9pt; FONT-FAMILY: 宋体, Verdana\">\\s*([\\d\\.]*)\\s*</span>";
                MatchCollection matches = Regex.Matches(content, regStr, RegexOptions.Multiline);
                foreach (Match mc in matches)
                {
                    //按你的原文，这里应依次得到4个mc
                    int yourData=int.Parse(mc.Groups[1].Value);
                }
      

  6.   

    //应该是double型
    double yourData=double.Parse(mc.Groups[1].Value);
      

  7.   


    MatchCollection mc = Regex.Matches(html,@"(?is)"><span\s+style="FONT-SIZE: 9pt; FONT-FAMILY: 宋体, Verdana">(?<value>\d+(.\d+)?)</span>");
    foreach(Match m in mc)
    {
        //m.Groups["value"].Value;
    }