要解析一个纯HTML文件 有什么好的办法 ,像下面这样的<html>
<head>
<body>
<div align="center">   
  <table style="width:98%" border="0" cellspacing="0" cellpadding="0">
    <tr  bgcolor="#FFFFFF"> 
      <td ><b><font size="+1">报告编号:A-200501000001</font></b> <br>
        <br>
      </td>   </tr>    <tr> 
      <td valign="top" > 
        <div>        <table width="100%" border="0" align="center" cellpadding="0" cellspacing="0" >
            <td align="center" bgcolor="#FFFFFF" > 
              <table width="100%"  border="0" cellpadding="0" cellspacing="0">
                <tr>         <td> 
                    <div align="center" class="style2"><font size="+2">基本信用信息报告</font></div>
                    <br>
                  </td>  </tr>
 </table>
            </td>
            </tr>
            <tr> 
              <td bgcolor="#FFFFFF"> 
                <TABLE width="100%" border="0" align="center" cellpadding="0" cellspacing="0" id="list">
                  <TBODY> 
                  <TR bgcolor="#FFFFFF"> 
                    <TD colspan="1" align="right" > 
                      <div align="center"><strong> <font size="+1">基本状况</font></strong></div>                    </TD>
                  </TR>
                  <TR bgcolor="#FFFFFF"> 
                    <TD colspan="1"><b><font size="3">概况信息</font></b></TD>
                  </TR>
                  <TR bgcolor="#FFFFFF"> 
                    <TD> 
                      <table width=100% border="1" cellpadding="0" cellspacing="0" bordercolor=black id="list">
                        <tr  bgcolor="#FFFFFF"> 
                          <TD align="left" width="197"> 借款人中文名称:</TD>
                          <TD colspan=3>&nbsp;  </TD>
                        </tr>
                        <TR bgcolor="#FFFFFF"> 
                          <TD align="left" width="197" >借款人外文名称:</TD>
                          <TD align="left" colspan="3" >&nbsp;</TD>
                        </TR>
                        <tr  bgcolor="#FFFFFF"> 
                          <TD width=197 align="left"> 
                            <div align="left">登记注册号:</div>                          </TD>
                          <TD width=343 align="left">&nbsp;</TD>
                          <TD align="left" width="152">组织机构代码:</TD>
                          <TD align="left" width="280">&nbsp;</TD>
                        </tr>
                        <TR bgcolor="#FFFFFF"> 
                          <TD align="left" width="197" > 
                            <div align="left">国税登记证号码:</div>                          </TD>
                          <TD align="left" width="343" >&nbsp;</TD>
                          <TD align="left" width="152">地税登记证号码:</TD>
                          <TD align="left" width="280">&nbsp;</TD>
                        </TR>              
                  <TR bgcolor="#FFFFFF"> 
                          <TD align="left" width="197">财务部联系方式: </TD>
                          <TD align="left" colspan="3">&nbsp;</TD>
                        </TR>
                      </table>                    </TD>
                  </TR>
                  <TR bgcolor="#FFFFFF"> 
                    <TD  colspan="1"><br><b>
                      <font size="3">资本构成信息</font></b><b><font size="3"> 
                      单位:万元</font></b></TD>
                  </TR>
                  <TR bgcolor="#FFFFFF"> 
                    <TD colspan="1"> 
                      <table width="75%" border="1">
                        <tr> 
                          <td width="12%" rowspan="2" valign=top nowrap><b><font size="3">注册资金</font>:</b></td>
                          <td width="88%">0.00 RMB</td>
                        </tr>
                        <tr> 
                          <td width="88%">&nbsp;0.00 USD </td>
                        </tr>
                      </table>                    </TD>
                  </TR>
                  <TR bgcolor="#FFFFFF"> 
                    <TD > 
                      <table width=100% border="1" cellpadding="0" cellspacing="0" bordercolor=black id="list">
                        <tr  bgcolor="#FFFFFF"> 
                          <td width="19%" align=center><b>出资方名称</b></td>
                          <td width="16%" align=center><b>贷款卡编码</b></td>
                          <td width="8%" align=center><b>证件类型</b></td>
                          <td width="11%" align=center><b>证件号码</b></td>
                          <td width="21%" align=center><b>登记注册号</b></td>
                          <td width="7%" align=center><b>币种</b></td>
                          <td width="18%" align=center><b>出资金额</b></td>
                        </tr>
                        <tr>
                               <td align="center"><b>1</b></td>
                               <td align="center"><b>1</b></td>
                               <td align="center"><b>1</b></td>
                               <td align="center"><b>1</b></td>
                               <td align="center"><b>1</b></td>
                               <td align="center"><b>1</b></td>
                               <td align="center"><b>1</b></td>
                            </tr>
                        </table>    </TD>          </TR>     </table>  </TD>          </TR>
                  <TR bgcolor="#FFFFFF"> 
                    <TD colspan="1" align="center"><br><b><font size="3">借款人财务信息</font></b></TD>
                  </TR>
                  <TR bgcolor="#FFFFFF"> 
                    <TD colspan="1"> 
                      <table width="100%" border="0">
                        <tr> 
                          <td width="88%"><br><b><font size="3">借款人资产状况</font></b></td>
                          <td width="12%"><b>单位:元</b></td>
                        </tr>
                      </table>                    </TD>
                  </TR>
                  <TR bgcolor="#FFFFFF"> 
                    <TD colspan="1"> 
                      <table width=100% border="1" cellpadding="0" cellspacing="0" bordercolor=black id="list">
                        <tr  bgcolor="#FFFFFF"> 
                          <td width="14%" align=center><b>资产</b></td>
                          <td width="14%" align=center><b>2003年</b></td>
                          <td width="14%" align=center><b>2004年</b></td>
                          <td width="21%" align=center><b>2005年</b></td>
                        </tr>
                        <tr  bgcolor="#FFFFFF"> 
                          <td width="14%">货币资金 </td>
                          <td width="14%" align=right>&nbsp;</td>
                          <td width="14%" align=right>&nbsp;</td>
                          <td align=right>&nbsp;</td>
                        </tr>
                        <tr  bgcolor="#FFFFFF"> 
                          <td width="14%">短期投资</td>
                          <td width="14%" align=right> 
                            <div align="right"></div>                          </td>
                          <td width="14%" align=right>&nbsp;</td>
                          <td width="21%" align=right>&nbsp;</td>
                        </tr>
                        <tr  bgcolor="#FFFFFF"> 
                          <td width="14%" >应收票据</td>
                          <td width="14%" align=right>&nbsp;</td>
                          <td width="14%" align=right>&nbsp;</td>
                          <td width="21%" align=right>&nbsp;</td>
                        </tr>           
                      </table>                    </TD>
                  </TR>
                  <TR bgcolor="#FFFFFF"> 
                    <TD colspan="1"> 
                      <table width="100%" border="0">
                        <tr> 
                          <td width="88%"><b><font size="3">借款人负债状况</font></b></td>
                          <td width="12%"><b>单位:元</b></td>
                        </tr>
                      </table>                    </TD>
                  </TR>