<table width="100%" border="0" cellspacing="0" cellpadding="0">
<thead>
<tr>
<th width="3%">
<input type="checkbox" id="checkbox_all"></input>
</th>
<th>
版权名称
</th>
<th>
歌手名称
</th>
<th>
版权编码
</th>
<th>
CP
</th>
<th>
版权类型
</th>
<th>
有效期
</th>
<th>
创建时间
</th>
<th>
状态
</th>
</tr>
</thead>
<tbody>

<tr >
<td>
<input type="checkbox" id="cb_60056500077 " name="ids"
value='60056500077' exp="待发布"}"></input>
</td>
<td>
    <!-- 
    <a href="/CMS4-COPM/claimCopyright/viewAllClaim.do?id=60056500077">MELODY</a>
    -->
    <a href="/CMS4-COPM/claimCopyright/initRelease.do?id=60056500077">MELODY</a>
</td>
<td>
陶喆
</td>
<td>
60056500077
</td>
<td>
600565
</td>
<td>
0
</td>
<td>
2007-07-11
</td>
<td>
2006-07-13
</td>
<td>
待发布
</td>
</tr>

<tr class="cbg">
<td>
<input type="checkbox" id="cb_60056500103 " name="ids"
value='60056500103' exp="待发布"}"></input>
</td>
<td>
    <!-- 
    <a href="/CMS4-COPM/claimCopyright/viewAllClaim.do?id=60056500103">那年的情书</a>
    -->
    <a href="/CMS4-COPM/claimCopyright/initRelease.do?id=60056500103">那年的情书</a>
</td>
<td>
江美琪
</td>
<td>
60056500103
</td>
<td>
600565
</td>
<td>
0
</td>
<td>
2007-07-11
</td>
<td>
2006-07-13
</td>
<td>
待发布
</td>
</tr>

<tr >
<td>
<input type="checkbox" id="cb_60056500110 " name="ids"
value='60056500110' exp="待发布"}"></input>
</td>
<td>
    <!-- 
    <a href="/CMS4-COPM/claimCopyright/viewAllClaim.do?id=60056500110">化蝶飞</a>
    -->
    <a href="/CMS4-COPM/claimCopyright/initRelease.do?id=60056500110">化蝶飞</a>
</td>
<td>
花儿乐队
</td>
<td>
60056500110
</td>
<td>
600565
</td>
<td>
0
</td>
<td>
2007-07-11
</td>
<td>
2006-08-16
</td>
<td>
待发布
</td>
</tr>

<tr class="cbg">
<td>
<input type="checkbox" id="cb_60056500137 " name="ids"
value='60056500137' exp="待发布"}"></input>
</td>
<td>
    <!-- 
    <a href="/CMS4-COPM/claimCopyright/viewAllClaim.do?id=60056500137">想念圣诞节</a>
    -->
    <a href="/CMS4-COPM/claimCopyright/initRelease.do?id=60056500137">想念圣诞节</a>
</td>
<td>
萧亚轩
</td>
<td>
60056500137
</td>
<td>
600565
</td>
<td>
0
</td>
<td>
2011-10-31
</td>
<td>
2006-12-01
</td>
<td>
待发布
</td>
</tr>

<tr >
<td>
<input type="checkbox" id="cb_60056500138 " name="ids"
value='60056500138' exp="待发布"}"></input>
</td>
<td>
    <!-- 
    <a href="/CMS4-COPM/claimCopyright/viewAllClaim.do?id=60056500138">想念圣诞节</a>
    -->
    <a href="/CMS4-COPM/claimCopyright/initRelease.do?id=60056500138">想念圣诞节</a>
</td>
<td>
萧亚轩
</td>
<td>
60056500138
</td>
<td>
600565
</td>
<td>
0
</td>
<td>
2007-11-30
</td>
<td>
2006-12-01
</td>
<td>
待发布
</td>
</tr>

<tr class="cbg">
<td>
<input type="checkbox" id="cb_60056503164 " name="ids"
value='60056503164' exp="待发布"}"></input>
</td>
<td>
    <!-- 
    <a href="/CMS4-COPM/claimCopyright/viewAllClaim.do?id=60056503164">在水一方</a>
    -->
    <a href="/CMS4-COPM/claimCopyright/initRelease.do?id=60056503164">在水一方</a>
</td>
<td>
江淑娜
</td>
<td>
60056503164
</td>
<td>
600565
</td>
<td>
0
</td>
<td>
2011-10-31
</td>
<td>
2007-01-05
</td>
<td>
待发布
</td>
</tr>

<tr >
<td>
<input type="checkbox" id="cb_60056503168 " name="ids"
value='60056503168' exp="待发布"}"></input>
</td>
<td>
    <!-- 
    <a href="/CMS4-COPM/claimCopyright/viewAllClaim.do?id=60056503168">祈祷</a>
    -->
    <a href="/CMS4-COPM/claimCopyright/initRelease.do?id=60056503168">祈祷</a>
</td>
<td>
李岗霖
</td>
<td>
60056503168
</td>
<td>
600565
</td>
<td>
0
</td>
<td>
2011-10-31
</td>
<td>
2007-01-05
</td>
<td>
待发布
</td>
</tr>

<tr class="cbg">
<td>
<input type="checkbox" id="cb_60056503367 " name="ids"
value='60056503367' exp="待发布"}"></input>
</td>
<td>
    <!-- 
    <a href="/CMS4-COPM/claimCopyright/viewAllClaim.do?id=60056503367">把心放进来</a>
    -->
    <a href="/CMS4-COPM/claimCopyright/initRelease.do?id=60056503367">把心放进来</a>
</td>
<td>
萧亚轩
</td>
<td>
60056503367
</td>
<td>
600565
</td>
<td>
0
</td>
<td>
2011-10-31
</td>
<td>
2007-01-05
</td>
<td>
待发布
</td>
</tr>

<tr >
<td>
<input type="checkbox" id="cb_60056503387 " name="ids"
value='60056503387' exp="待发布"}"></input>
</td>
<td>
    <!-- 
    <a href="/CMS4-COPM/claimCopyright/viewAllClaim.do?id=60056503387">吻</a>
    -->
    <a href="/CMS4-COPM/claimCopyright/initRelease.do?id=60056503387">吻</a>
</td>
<td>
萧亚轩
</td>
<td>
60056503387
</td>
<td>
600565
</td>
<td>
0
</td>
<td>
2011-10-31
</td>
<td>
2007-01-05
</td>
<td>
待发布
</td>
</tr>

<tr class="cbg">
<td>
<input type="checkbox" id="cb_60056503392 " name="ids"
value='60056503392' exp="待发布"}"></input>
</td>
<td>
    <!-- 
    <a href="/CMS4-COPM/claimCopyright/viewAllClaim.do?id=60056503392">想念圣诞节</a>
    -->
    <a href="/CMS4-COPM/claimCopyright/initRelease.do?id=60056503392">想念圣诞节</a>
</td>
<td>
萧亚轩
</td>
<td>
60056503392
</td>
<td>
600565
</td>
<td>
0
</td>
<td>
2011-10-31
</td>
<td>
2007-01-05
</td>
<td>
待发布
</td>
</tr>

<tr >
<td>
<input type="checkbox" id="cb_60056503401 " name="ids"
value='60056503401' exp="待发布"}"></input>
</td>
<td>
    <!-- 
    <a href="/CMS4-COPM/claimCopyright/viewAllClaim.do?id=60056503401">不一样了</a>
    -->
    <a href="/CMS4-COPM/claimCopyright/initRelease.do?id=60056503401">不一样了</a>
</td>
<td>
许茹芸
</td>
<td>
60056503401
</td>
<td>
600565
</td>
<td>
0
</td>
<td>
2011-10-31
</td>
<td>
2007-01-05
</td>
<td>
待发布
</td>
</tr>

<tr class="cbg">
<td>
<input type="checkbox" id="cb_60056503415 " name="ids"
value='60056503415' exp="待发布"}"></input>
</td>
<td>
    <!-- 
    <a href="/CMS4-COPM/claimCopyright/viewAllClaim.do?id=60056503415">长恨哥哥</a>
    -->
    <a href="/CMS4-COPM/claimCopyright/initRelease.do?id=60056503415">长恨哥哥</a>
</td>
<td>
杨千嬅
</td>
<td>
60056503415
</td>
<td>
600565
</td>
<td>
0
</td>
<td>
2011-10-31
</td>
<td>
2007-01-05
</td>
<td>
待发布
</td>
</tr>

<tr >
<td>
<input type="checkbox" id="cb_60056503481 " name="ids"
value='60056503481' exp="待发布"}"></input>
</td>
<td>
    <!-- 
    <a href="/CMS4-COPM/claimCopyright/viewAllClaim.do?id=60056503481">爱一个人好可怕</a>
    -->
    <a href="/CMS4-COPM/claimCopyright/initRelease.do?id=60056503481">爱一个人好可怕</a>
</td>
<td>
张宇
</td>
<td>
60056503481
</td>
<td>
600565
</td>
<td>
0
</td>
<td>
2011-10-31
</td>
<td>
2007-01-05
</td>
<td>
待发布
</td>
</tr>

<tr class="cbg">
<td>
<input type="checkbox" id="cb_60056506024 " name="ids"
value='60056506024' exp="待发布"}"></input>
</td>
<td>
    <!-- 
    <a href="/CMS4-COPM/claimCopyright/viewAllClaim.do?id=60056506024">在水一方</a>
    -->
    <a href="/CMS4-COPM/claimCopyright/initRelease.do?id=60056506024">在水一方</a>
</td>
<td>
江淑娜
</td>
<td>
60056506024
</td>
<td>
600565
</td>
<td>
0
</td>
<td>
2007-11-30
</td>
<td>
2007-01-05
</td>
<td>
待发布
</td>
</tr>

<tr >
<td>
<input type="checkbox" id="cb_60056506028 " name="ids"
value='60056506028' exp="待发布"}"></input>
</td>
<td>
    <!-- 
    <a href="/CMS4-COPM/claimCopyright/viewAllClaim.do?id=60056506028">祈祷</a>
    -->
    <a href="/CMS4-COPM/claimCopyright/initRelease.do?id=60056506028">祈祷</a>
</td>
<td>
李岗霖
</td>
<td>
60056506028
</td>
<td>
600565
</td>
<td>
0
</td>
<td>
2007-11-30
</td>
<td>
2007-01-05
</td>
<td>
待发布
</td>
</tr>

</tbody>
</table>
这个文件,我想要 歌曲的名字、歌手的名字、版权编码 这三项

解决方案 »

  1.   

    import java.util.regex.Matcher;
    import java.util.regex.Pattern;public class TestRegex { public static void main(String[] args) {
        
    String str= "<tr >   <td>    <input type=\"checkbox\" id=\"cb_60056500110 \" name=\"ids\"  value='60056500110' exp=\"待发布\"}\"></input>                </td>   <td>   <!--    <a href=\"/CMS4-COPM/claimCopyright/viewAllClaim.do?id=60056500110\">化蝶飞</a>   -->     <a href=\"/CMS4-COPM/claimCopyright/initRelease.do?id=60056500110\">化蝶飞</a>   </td>  <td>  花儿乐队                </td>     <td> 60056500110  </td>";
    String regex = "<tr.*<td>(.*)</td>.*<td>(.*)</td>.*<td>(.*)</td>";

            Pattern pattern = Pattern.compile(regex, Pattern.CASE_INSENSITIVE);
            Matcher matcher = pattern.matcher(str);
            if (matcher.find()) {
                System.out.println(matcher.group(1));
                System.out.println(matcher.group(2));
                System.out.println(matcher.group(3));
            }else{
                System.out.println("false");
            }
    }
    }这个只是个思路 细节需要修改  主要就是用group就可以了
      

  2.   

    给你推荐个视频网站http://www.langsin.com/index.html?ID=28
      

  3.   

    自己解决了<td>[^<]*<!--[^<]*<a[^>]*>[^<]*</a>\s*-->\s*<a[^>]*>([^<]*)</a>\s*</td>\s*<td>([^<]*)</td>\s*<td>([^<]*)</td>不过我的这个写法很难看,呵呵
      

  4.   

    我实现过些技术,把一个表格中的数据还原成一个domain对象,正则表达式不太可靠,我用的是htmlparser工具包来解析的。