正则表达式替换table表格中的样式与空标记(保留rowspan与colspan)

所属分类：网络编程 / 正则表达式阅读数： 1373

收藏 0赞 0分享

完整测试代码

<script>
var str='<p>';
str='<table id="tblSort" cellspacing="0" helvetica="" sans=""><tr id="sdf"><td style="color:red" class="ok" colspan="8" height="500" rowspan="5">';
str+='<td style = "color:blue" style="color:blue" colspan="8" style="color:red" rowspan="5">';
str+='<td id="asdfj" class="dbclick"><span id="s159015" class="p_check"><a style="text-decoration: none; color: rgb(0,136,255)" href="http://www.17ce.com/site/dns/20200408_3875c5d0799211eab8bc2bbb7b33a12c:1.html#s159015" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" >GET</a> <a style="text-decoration: none; color: rgb(0,136,255)" href="http://www.17ce.com/site/dns/20200408_3875c5d0799211eab8bc2bbb7b33a12c:1.html#s159015" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" >PING</a> <a style="text-decoration: none; color: rgb(0,136,255)" href="http://www.17ce.com/site/dns/20200408_3875c5d0799211eab8bc2bbb7b33a12c:1.html#s159015" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" >Trace</a> <a style="text-decoration: none; color: rgb(0,136,255)" href="http://www.17ce.com/site/dns/20200408_3875c5d0799211eab8bc2bbb7b33a12c:1.html#s159015" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" >Dig</a></span></td>';
str+='<td class="sdf" colspan="8" style="color:red" rowspan="5"><p style="color:red">jb51.net</p></td>';
str+='<td class="sdf" colspan="8" style="color:red" rowspan="5" width="100"></td></tr></table>';

str+='<table><tr style = "color:bluefffffffffffffffffffffffffffffffffffffffffff"><td style="color:green" class="ok" colspan="8" height="500" rowspan="5">';
str+='<tr id="trinfo146798" class="alt">   <td id="tdinfo146798" colspan="16"></td>  </tr>';
str+='<td id="asdfj" class="dbclick"><span id="s159015" class="p_check"><a style="text-decoration: none; color: rgb(0,136,255)" href="http://www.17ce.com/site/dns/20200408_3875c5d0799211eab8bc2bbb7b33a12c:1.html#s159015" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" >GET</a> <a style="text-decoration: none; color: rgb(0,136,255)" href="http://www.17ce.com/site/dns/20200408_3875c5d0799211eab8bc2bbb7b33a12c:1.html#s159015" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" >PING</a> <a style="text-decoration: none; color: rgb(0,136,255)" href="http://www.17ce.com/site/dns/20200408_3875c5d0799211eab8bc2bbb7b33a12c:1.html#s159015" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" >Trace</a> <a style="text-decoration: none; color: rgb(0,136,255)" href="http://www.17ce.com/site/dns/20200408_3875c5d0799211eab8bc2bbb7b33a12c:1.html#s159015" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" >Dig</a></span></td>';
str+='<td class="sdf" colspan="8" style="color:red" rowspan="5"><p style="color:red">jb51.net</p></td>';
str+='<td class="sdf" colspan="8" style="color:red" rowspan="5" width="100"> <font color="#0f0000">122.227.189.106 [中国浙江宁波电信]</font><br /></td></tr></table>';

str+='<p><img alt="" src="https://cdn.zhanzhang360.cn/imgupload/000423/2020041112113912.png" /></p>';
str+='<p>选择安装然后选择全新的sql server独立安装</p>';
str+='<p><img alt="" src="https://cdn.zhanzhang360.cn/imgupload/000423/2020041112113913.png" /></p>';

console.log(str);

//去除table的宽度
str=str.replace(/<table[^>]*>/ig, "<table>");
str=str.replace(/<table[^>]*>[\s\S]*?<\/table>/gi,function(match,capture){
match=match.replace(/(style|class|id)[\s]*=[\s]*("|')[^<>"']*?\2/gi,'');
match=match.replace(/<\/?span[^<>]*>/gi,'');
match=match.replace(/<p [^<>]*>|<\/p>/gi,'');
match=match.replace(/<font[^<>]*>|<\/font>/gi,'');
return match;
});

//alert(str);
console.log(str);
</script>

原来的代码是这样的

//普通替换
function doRepNormal(s){
var str=s.replace(/<p><br type="_moz">\s*?<\/p>/ig,"");
str=str.replace(/<p>\s*?<br type="_moz">\s*?<\/p>/ig, "");
str=str.replace(/<p>(\s|\&nbsp\;| |　|\xc2\xa0)*?<\/p>/ig, "");
str=str.replace(/<p>\s*?<\/p>/ig,"");
str=str.replace(/<p>&nbsp;<\/p>/ig,"");
str=str.replace(/<br type="_moz">\n&nbsp;<\/p>/ig, "</p>");
str=str.replace(/<br type="_moz">\s*?<\/p>/ig, "</p>");
str=str.replace(/<br\s*?\/?>\s*?<\/p>/ig, "</p>");
str=str.replace(/<br \/>\n&nbsp;<\/p>/ig, "</p>");
str=str.replace(/<br>\n&nbsp;<\/p>/ig, "</p>");
//表格替换 
str=str.replace(/<table[^>]*>/ig, "<table>");
str=str.replace(/<table[^>]*>[\s\S]*?<\/table>/gi,function(match,capture){
match=match.replace(/style[\s]*=[\s]*("|')[^<>"']*?\1/gi,'');
match=match.replace(/cl\ass[\s]*=[\s]*("|')[^<>"']*?\1/gi,'');
match=match.replace(/id[\s]*=[\s]*("|')[^<>"']*?\1/gi,'');
match=match.replace(/<font[^<>]*>|<\/font>/gi,'');
return match;
});
str=str.replace(/<td[^>]*>/gi,function(match,capture){
match=match.replace(/style[\s]*=[\s]*("|')[^<>"']*?\1/gi,'');
match=match.replace(/cl\ass[\s]*=[\s]*("|')[^<>"']*?\1/gi,'');
match=match.replace(/id[\s]*=[\s]*("|')[^<>"']*?\1/gi,'');
return match;
});
return str;
}

后台修改成这样的

str=str.replace(/<table[^>]*>/ig, "<table>");
str=str.replace(/<table[^>]*>[\s\S]*?<\/table>/gi,function(match,capture){
match=match.replace(/(style|class|id)[\s]*=[\s]*("|')[^<>"']*?\2/gi,'');
match=match.replace(/<\/?span[^<>]*>/gi,'');
match=match.replace(/<p [^<>]*>|<\/p>/gi,'');
match=match.replace(/<font[^<>]*>|<\/font>/gi,'');
return match;
});

经过测试发现chrome中正常，但在ie8与ie7中有bug无法实现class与id的替换，文档声明<!DOCTYPE html>都会影响一些结果，真是涨了见识

正好看到别的人分享的先留存一份，后续更新

用正则表达式取出table中的所有行（支持嵌套table）

此是通过csdn询问得高人之手写的。
谢谢gzdiablo

表达式:

<tr[^>]*>(?:(?:\s|\S)*?(?=<table|</tr>)(?(<table)<table[^>]*>(?:\s|\S)*?(?:</table>|(?:(?:<table[^>]*>(?:\s|\S)*?</table>(?:\s|\S)*?)*?</table>))(?:\s|\S)*?|))*</tr>

一条表达式就可以获取你想要的
写得好辛苦
测试:

<table width="300" border="1" cellspacing="0" cellpadding="0">
 <tr>
 <td>&nbsp;</td>
 <td><table width="100%" border="1" cellspacing="0" cellpadding="0">
  <tr>
  <td>&nbsp;</td>
  </tr>

 </table>
  <table width="100%" border="1" cellspacing="0" cellpadding="0">
  <tr>
   <td>&nbsp;</td>
  </tr>
  </table></td>
 <td>&nbsp;</td>
 </tr>
 <tr>
 <td>&nbsp;</td>
 <td>&nbsp;</td>
 <td><table width="100%" border="1" cellspacing="0" cellpadding="0">

  <tr>
  <td>&nbsp;</td>
  </tr>
 </table></td>
 </tr>
 <tr>
 <td><table width="100%" border="1" cellspacing="0" cellpadding="0">
  <tr>
  <td>&nbsp;</td>
  </tr>

 </table></td>
 <td>&nbsp;</td>
 <td>&nbsp;</td>
 </tr>
</table>

-------------------获取3个match

============================================match1
<tr>
    <td> </td>
    <td><table width="100%" border="1" cellspacing="0" cellpadding="0">
      <tr>
        <td> </td>
        </tr>

    </table>
      <table width="100%" border="1" cellspacing="0" cellpadding="0">
        <tr>
          <td> </td>
        </tr>
      </table></td>
    <td> </td>
</tr>
==============================================match2
<tr>
    <td> </td>
    <td> </td>
    <td><table width="100%" border="1" cellspacing="0" cellpadding="0">

      <tr>
        <td> </td>
        </tr>
    </table></td>
</tr>
==============================================match3
<tr>
    <td><table width="100%" border="1" cellspacing="0" cellpadding="0">
      <tr>
        <td> </td>
        </tr>

    </table></td>
    <td> </td>
    <td> </td>
</tr>

正则表达式匹配html标签table

首先，要匹配任意内容“.”是不行的，因为不匹配“\n”，取不到想要的内容，所以有了如下表达式：
[\s\S]*

当然，你也可以用 “[\d\D]*”、“[\w\W]*” 来表示。

现在我们来匹配一个html标签，匹配table如下：

<table.*?>[\s\S]*<\/table>
或
<table.*?>[\s\S]*?<\/table>

以上两个表达式，一个加了"?"和一个却不加“?”，那么这有什么区别呢？
我们知道“?”在正则表达式里是一个通配符：匹配前面的子表达式零次或一次，或指明一个非贪婪限定符。

在这里，通过测试，我们得出这样的结论：在不加“?”的情况下，在匹配下面一段内容的时候：

<table>这是第一个table</table>
我不是table里的内容
<table>这是第二个table</table>
我也不是table里的内容
<table>这是第三个table</table>

会把以<table>开始，</table>结束的内容都匹配出来

加了“?”之后，只匹配第n个匹配的内容

完整测试代码脚本之家小编提供

<script>
var str='<table>这是第一个table</table>';
str+='我不是table里的内容';
str+='<table>这是第二个table</table>';
str+='我也不是table里的内容';
str+='<table>这是第三个table</table>';

var reg1 = /<table.*?>[\s\S]*<\/table>/gi;
var res1 = str.match(reg1);
console.log(res1) 
var reg2 = /<table.*?>[\s\S]*?<\/table>/gi;
var res2 = str.match(reg2);
console.log(res2) 
</script>

效果图