尝试过转成dom文件去操作,但是源htm不标准,不能转成dom文件。然后文本方式+正则处理,处理完发现数据和表项混在一起了,没办法分开了,于是各种杯具就产生了。希望有高手指点一下部分源htm代码
 <TABLE width="100%">
              <TBODY>
              <TR vAlign=top>
                <TD width="50%">
                  <TABLE class=shade cellSpacing=0 width="90%" border=1>
                    <TBODY>
                    <TR>
                      <TD class=unl><STRONG>发往:</STRONG></TD></TR>
                    <TR>
                      <TD class=unl>Various</TD></TR>
                    <TR></TR>
                    <TR>
                      <TD class=unl><INPUT type=hidden value=~~~ name=addr3> 
                      </TD></TR>
                    <TR>
                      <TD class=unl></TD><INPUT type=hidden name=addr2> </TR>
                    <TR>
                      <TD class=unl></TD></TR></TBODY></TABLE><BR>
                  <TABLE class=shade cellSpacing=0 width="90%" border=1>
                    <TBODY>
                    <TR>
                      <TD class=unl><STRONG>帐单送往:</STRONG></TD></TR>
                    <TR>
                      <TD class=unl>邮政编码:518040 </TD></TR>
                    <TR>
                      <TD class=unl>深圳市福田区农林路69号深国投广场 </TD></TR>
                    <TR>
                      <TD class=unl>二号楼2-5层及三号楼1-12层 </TD></TR>
                    <TR>
                      <TD class=unl>沃尔玛(中国)投资有限公司 </TD></TR>
                    <TR>
                      <TD class=unl>财 </TD></TR>
                    <TR>
                      <TD 
                    class=unl><STRONG>税号:</STRONG> 440301710936858</TD></TR></TBODY></TABLE><BR><BR><BR><BR>
                  <TABLE class=shade cellSpacing=0 width="100%" border=1>
                    <TBODY>
                    <TR>
                      <TD class=unl><STRONG>供应商名 :</STRONG></TD>
                      <TD class=unl>东莞市远梦家用纺织品有限公司<INPUT type=hidden 
                        value=东莞市远梦家用纺织品有限公司 name=supname> </TD></TR>
                    <TR>
                      <TD class=unl>供应商号: </TD>
                      <TD class=unl><INPUT type=hidden value=717782226 
                        name=supnbr>717782226</TD></TR></TBODY></TABLE></TD>
                <TD>
                  <TABLE width="100%" valign="top">
                    <TBODY>
                    <TR vAlign=top>
                      <TD>
                        <TABLE class=shade cellSpacing=0 width="90%" align=right 
                        border=1 valign="top">
                          <TBODY>
                          <TR vAlign=top>
                            <TD class=unl><STRONG>订单号:</STRONG></TD>
                            <TD class=unl> 2300040593</TD></TR><INPUT type=hidden 
                          value=2300040593 name=ponbr><INPUT type=hidden 
                          value=SA name=potype><INPUT type=hidden name=relnbr>
                          <TR>
                            <TD class=unl>订单日期: </TD>
                            <TD class=unl> 11/2/2010<INPUT type=hidden 
                              value=20101102 name=podate> </TD></TR>
                          <TR>
                            <TD class=unl>发货日期 :</TD>
                            <TD class=unl> 11/3/2010</TD></TR>
                          <TR>
                            <TD class=unl>取消日期:</TD>
                            <TD 
class=unl> 11/10/2010</TD></TR></TBODY></TABLE></TD></TR>
                    <TR>
                      <TD colSpan=2></TD></TR>
                    <TR>
                      <TD colSpan=2>
                        <TABLE class=shade cellSpacing=0 width="80%" align=left 
                        border=1 valign="bottom">
                          <TBODY>
                          <TR>
                            <TD class=unll width="30%">订货类型: </TD>
                            <TD class=unll> 0057<INPUT type=hidden value=0057 
                              name=ordtyp> </TD></TR>
                          <TR>
                            <TD class=unll>部门: </TD>
                            <TD class=unl> 00022<INPUT type=hidden value=00022 
                              name=deptnbr> </TD></TR>
                          <TR>
                            <TD class=unll>主题#: </TD>
                            <TD class=unll> TAB</TD></TR>
                          <TR>
                            <TD class=unll>付款条件: </TD>
                            <TD class=unll>NET 60<INPUT type=hidden value=05 
                              name=ITD01><INPUT type=hidden value=15 
                              name=ITD02><INPUT type=hidden name=ITD03><INPUT 
                              type=hidden name=ITD05><INPUT type=hidden value=60 
                              name=terms> </TD></TR>
                          <TR>
                            <TD class=unll>交货点 </TD>
                            <TD class=unll> 制表人(售方)<INPUT type=hidden value=PP 
                              name=fob> </TD></TR>
                          <TR>
                            <TD class=unll>承运者 </TD>
                            <TD class=unll> VENDOR ROUTE<INPUT type=hidden 
                              value="VENDOR ROUTE" name=carrier> </TD></TR>
                          <TR>
                            <TD class=unll>启运地 </TD>
                            <TD class=unll> SHENZHEN 
                    CN</TD></TR></TBODY></TABLE></TD></TR></TBODY></TABLE></TD></TR></TBODY>
                    </TABLE>