页面源代码如下:
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3c.org/TR/1999/REC-html401-19991224/loose.dtd"><HTML><HEAD><TITLE></TITLE><META content="text/html; charset=GBK" http-equiv=Content-Type><META name=GENERATOR content="MSHTML 8.00.7601.18106"></HEAD><BODY><FORM method=post name=pusManageForm action=pus.do><INPUT type=hidden name=method> <INPUT value=15647695 type=hidden name=sid> <INPUT value=2 type=hidden name=partCount> <TABLE width="100%" align=center> <TBODY> <TR> <TD> <TABLE border=0 width="100%"> <TBODY> <TR> <TD width=10> </TD> <TD> <TABLE border=0 cellSpacing=1 cellPadding=0 width="95%" align=center> <TBODY> <TR> <TD height=40 align=left><B><FONT color=rgb(0,0,20) size=2>aaaaaa</FONT></B> <BR><B><FONT color=rgb(0,0,20) size=2>aaaaaa</FONT></B> </TD></TR> <TR> <TD height=40 align=left><FONT color=rgb(0,0,20) size=1>aaaaaa</FONT> <FONT color=rgb(0,0,20) size=1>xxxx(aaaaaa)</FONT> </TD></TR> <TR> <TD align=left><FONT color=rgb(0,0,20) size=1>aaaaaa</FONT> <FONT color=rgb(0,0,20) size=1>xxxx</FONT> </TD></TR> <TR> <TD align=left><FONT color=rgb(0,0,20) size=1>adress aaaaaa</FONT> <FONT color=rgb(0,0,20) size=1>adress</FONT> </TD></TR></TBODY></TABLE></TD> <TD align=middle><IMG src="http://aaa/DY/images/pus/DYNP_new.jpg"> </TD> <TD align=right> <TABLE border=0 cellSpacing=1 cellPadding=1 width="95%" align=center> <TBODY> <TR> <TD align=right><B><FONT color=rgb(0,0,20) size=4>交货计划单</FONT></B> </TD></TR> <TR> <TD align=right><FONT color=rgb(0,0,20) size=1>计划到达时间 2013-09-16 </FONT></TD></TR> <TR> <TD align=right><FONT color=rgb(0,0,20) size=2>PUS编号 770266110 版本00 </FONT></TD></TR> <TR> <TD align=right><FONT color=rgb(0,0,20) size=3>Customer 客户 </FONT></TD></TR> <TR> <TD noWrap align=right><FONT size=+3 face=C39P36DmTt color="blue">*DYNP-770266110-00*</FONT> </TD></TR></TBODY></TABLE></TD> <TD width=10> </TD> <TR></TR></TBODY></TABLE><BR> <TABLE border=1 width="95%" align=center> <TBODY> <TR class=table_head> <TD colSpan=4 align=left><B><FONT>Delivery Information 交货信息</FONT></B> </TD></TR> <TR> <TD size="20%"><B><FONT color=rgb(0,0,255)>工厂<BR>Plant</FONT></B> </TD> <TD colSpan=3>xxxxxx </TD></TR> <TR class=table_c2> <TD size="20%"><B><FONT color=rgb(0,0,255)>取货时间<BR>Pick Up Time</FONT></B> </TD> <TD size="30%"><font color = "blue">2013-09-09 16:30 </font></TD> <TD size="20%"><B><FONT color=rgb(0,0,255)>需要供应商反馈<BR>Need Duns Response</FONT></B> </TD> <TD size="30%">N </TD></TR> <TR> <TD size="20%"><B><FONT color=rgb(0,0,255)>交货日期<BR>Delivery Date</FONT></B> </TD> <TD size="30%">2013-09-16 </TD> <TD size="20%"><B><FONT color=rgb(0,0,255)>窗口时间<BR>Window Time</FONT></B> </TD> <TD size="30%">16:30 </TD></TR> <TR class=table_c2> <TD><B><FONT color=rgb(0,0,255)>卸货口<BR>Dock</FONT></B> </TD> <TD>CC-70D </TD> <TD><B><FONT color=rgb(0,0,255)>卸货口负责人<BR>Dock Incharger</FONT></B> </TD> <TD>kkk</TD></TR> <TR> <TD><B><FONT color=rgb(0,0,255)>卸货口电话<BR>Dock Tel</FONT></B> </TD> <TD>011-1111 </TD> <TD><B><FONT color=rgb(0,0,255)>卸货口地址<BR>Dock Address</FONT></B> </TD> <TD>adress </TD></TR> <TR class=table_c2> <TD size="20%"><B><FONT color=rgb(0,0,255)>交货地点<BR>Delivery Place</FONT></B> </TD> <TD colSpan=3></TD></TR> <TR> <TD><B><FONT color=rgb(0,0,255)>计划跟踪员<BR>Follow Up</FONT></B> </TD> <TD>kkkk </TD> <TD><B><FONT color=rgb(0,0,255)>计划跟踪员电话/传真<BR>FollowUp Tel/Fax</FONT></B> </TD> <TD>011-1111</TD></TR> <TR class=table_c2> <TD><B><FONT color=rgb(0,0,255)>交货说明<BR>Delivery Note</FONT></B> </TD> <TD colSpan=3></TD></TR></TBODY></TABLE><BR> <TABLE border=1 width="95%" align=center> <TBODY> <TR class=table_head> <TD colSpan=14 align=left><B><FONT>Part Information 零件清单</FONT></B> </TD></TR> <TR> <TD align=middle><FONT color=rgb(0,0,0)>序号</FONT></TD> <TD align=middle><FONT color=rgb(0,0,0)>零件号</FONT></TD> <TD align=middle><FONT color=rgb(0,0,0)>零件说明</FONT></TD> <TD align=middle><FONT color=rgb(0,0,0)>需求数量</FONT></TD> <TD align=middle><FONT color=rgb(0,0,0)>承诺数量</FONT></TD> <TD align=middle><FONT color=rgb(0,0,0)>实收数量</FONT></TD> <TD align=middle><FONT color=rgb(0,0,0)>包装数</FONT></TD> <TD align=middle><FONT color=rgb(0,0,0)>料箱数</FONT></TD> <TD align=middle><FONT color=rgb(0,0,0)>料箱号</FONT></TD> <TD align=middle><FONT color=rgb(0,0,0)>实发料箱号</FONT></TD> <TD align=middle><FONT color=rgb(0,0,0)>实发料箱数</FONT></TD> <TD align=middle><FONT color=rgb(0,0,0)>实收料箱号</FONT></TD> <TD align=middle><FONT color=rgb(0,0,0)>实收料箱数</FONT></TD> <TD align=middle><FONT color=rgb(0,0,0)>备注</FONT></TD></TR> <TR> <TD align=middle>1</TD> <TD align=middle><font color = "blue">12647212</font></TD> <TD align=middle></TD> <TD align=middle><font color = "blue">60</font></TD> <TD align=middle>60 </TD> <TD align=middle></TD> <TD align=middle><font color = "blue">15</font></TD> <TD align=middle><font color = "blue">4</font></TD> <TD align=middle><font color = "blue">P000000D</font></TD> <TD align=middle></TD> <TD align=middle></TD> <TD align=middle></TD> <TD align=middle></TD> <TD align=middle></TD></TR> <TR class=table_c2> <TD align=middle>2</TD> <TD align=middle><font color = "blue">12654172</font></TD> <TD align=middle></TD> <TD align=middle><font color = "blue">615</font></TD> <TD align=middle>615 </TD> <TD align=middle></TD> <TD align=middle><font color = "blue">15</font></TD> <TD align=middle><font color = "blue">41</font></TD> <TD align=middle><font color = "blue">P000000D</font></TD> <TD align=middle></TD> <TD align=middle></TD> <TD align=middle></TD> <TD align=middle></TD> <TD align=middle></TD></TR></TBODY></TABLE><BR> </FORM></BODY></HTML>
循环table的tr,直接抓取td的值
这个页面本身返回数据的时候就有蓝色在上面吗?若是,则
<?php$string = '<TABLE width="100%" align=center> <TBODY> <TR> <TD> <TABLE border=0 width="100%"> <TBODY> <TR> <TD width=10> </TD> <TD> <TABLE border=0 cellSpacing=1 cellPadding=0 width="95%" align=center> <TBODY> <TR> <TD height=40 align=left><B><FONT color=rgb(0,0,20) size=2>aaaaaa</FONT></B> <BR><B><FONT color=rgb(0,0,20) size=2>aaaaaa</FONT></B> </TD></TR> <TR> <TD height=40 align=left><FONT color=rgb(0,0,20) size=1>aaaaaa</FONT> <FONT color=rgb(0,0,20) size=1>xxxx(aaaaaa)</FONT> </TD></TR> <TR> <TD align=left><FONT color=rgb(0,0,20) size=1>aaaaaa</FONT> <FONT color=rgb(0,0,20) size=1>xxxx</FONT> </TD></TR> <TR> <TD align=left><FONT color=rgb(0,0,20) size=1>adress aaaaaa</FONT> <FONT color=rgb(0,0,20) size=1>adress</FONT> </TD></TR></TBODY></TABLE></TD> <TD align=middle><IMG src="http://aaa/DY/images/pus/DYNP_new.jpg"> </TD> <TD align=right> <TABLE border=0 cellSpacing=1 cellPadding=1 width="95%" align=center> <TBODY> <TR> <TD align=right><B><FONT color=rgb(0,0,20) size=4>交货计划单</FONT></B> </TD></TR> <TR> <TD align=right><FONT color=rgb(0,0,20) size=1>计划到达时间 2013-09-16 </FONT></TD></TR> <TR> <TD align=right><FONT color=rgb(0,0,20) size=2>PUS编号 770266110 版本00 </FONT></TD></TR> <TR> <TD align=right><FONT color=rgb(0,0,20) size=3>Customer 客户 </FONT></TD></TR> <TR> <TD noWrap align=right><FONT size=+3 face=C39P36DmTt color="blue">*DYNP-770266110-00*</FONT> </TD></TR></TBODY></TABLE></TD> <TD width=10> </TD> <TR></TR></TBODY></TABLE><BR> <TABLE border=1 width="95%" align=center> <TBODY> <TR class=table_head> <TD colSpan=4 align=left><B><FONT>Delivery Information 交货信息</FONT></B> </TD></TR> <TR> <TD size="20%"><B><FONT color=rgb(0,0,255)>工厂<BR>Plant</FONT></B> </TD> <TD colSpan=3>xxxxxx </TD></TR> <TR class=table_c2> <TD size="20%"><B><FONT color=rgb(0,0,255)>取货时间<BR>Pick Up Time</FONT></B> </TD> <TD size="30%"><font color = "blue">2013-09-09 16:30 </font></TD> <TD size="20%"><B><FONT color=rgb(0,0,255)>需要供应商反馈<BR>Need Duns Response</FONT></B> </TD> <TD size="30%">N </TD></TR> <TR> <TD size="20%"><B><FONT color=rgb(0,0,255)>交货日期<BR>Delivery Date</FONT></B> </TD> <TD size="30%">2013-09-16 </TD> <TD size="20%"><B><FONT color=rgb(0,0,255)>窗口时间<BR>Window Time</FONT></B> </TD> <TD size="30%">16:30 </TD></TR> <TR class=table_c2> <TD><B><FONT color=rgb(0,0,255)>卸货口<BR>Dock</FONT></B> </TD> <TD>CC-70D </TD> <TD><B><FONT color=rgb(0,0,255)>卸货口负责人<BR>Dock Incharger</FONT></B> </TD> <TD>kkk</TD></TR> <TR> <TD><B><FONT color=rgb(0,0,255)>卸货口电话<BR>Dock Tel</FONT></B> </TD> <TD>011-1111 </TD> <TD><B><FONT color=rgb(0,0,255)>卸货口地址<BR>Dock Address</FONT></B> </TD> <TD>adress </TD></TR> <TR class=table_c2> <TD size="20%"><B><FONT color=rgb(0,0,255)>交货地点<BR>Delivery Place</FONT></B> </TD> <TD colSpan=3></TD></TR> <TR> <TD><B><FONT color=rgb(0,0,255)>计划跟踪员<BR>Follow Up</FONT></B> </TD> <TD>kkkk </TD> <TD><B><FONT color=rgb(0,0,255)>计划跟踪员电话/传真<BR>FollowUp Tel/Fax</FONT></B> </TD> <TD>011-1111</TD></TR> <TR class=table_c2> <TD><B><FONT color=rgb(0,0,255)>交货说明<BR>Delivery Note</FONT></B> </TD> <TD colSpan=3></TD></TR></TBODY></TABLE><BR> <TABLE border=1 width="95%" align=center> <TBODY> <TR class=table_head> <TD colSpan=14 align=left><B><FONT>Part Information 零件清单</FONT></B> </TD></TR> <TR> <TD align=middle><FONT color=rgb(0,0,0)>序号</FONT></TD> <TD align=middle><FONT color=rgb(0,0,0)>零件号</FONT></TD> <TD align=middle><FONT color=rgb(0,0,0)>零件说明</FONT></TD> <TD align=middle><FONT color=rgb(0,0,0)>需求数量</FONT></TD> <TD align=middle><FONT color=rgb(0,0,0)>承诺数量</FONT></TD> <TD align=middle><FONT color=rgb(0,0,0)>实收数量</FONT></TD> <TD align=middle><FONT color=rgb(0,0,0)>包装数</FONT></TD> <TD align=middle><FONT color=rgb(0,0,0)>料箱数</FONT></TD> <TD align=middle><FONT color=rgb(0,0,0)>料箱号</FONT></TD> <TD align=middle><FONT color=rgb(0,0,0)>实发料箱号</FONT></TD> <TD align=middle><FONT color=rgb(0,0,0)>实发料箱数</FONT></TD> <TD align=middle><FONT color=rgb(0,0,0)>实收料箱号</FONT></TD> <TD align=middle><FONT color=rgb(0,0,0)>实收料箱数</FONT></TD> <TD align=middle><FONT color=rgb(0,0,0)>备注</FONT></TD></TR> <TR> <TD align=middle>1</TD> <TD align=middle><font color = "blue">12647212</font></TD> <TD align=middle></TD> <TD align=middle><font color = "blue">60</font></TD> <TD align=middle>60 </TD> <TD align=middle></TD> <TD align=middle><font color = "blue">15</font></TD> <TD align=middle><font color = "blue">4</font></TD> <TD align=middle><font color = "blue">P000000D</font></TD> <TD align=middle></TD> <TD align=middle></TD> <TD align=middle></TD> <TD align=middle></TD> <TD align=middle></TD></TR> <TR class=table_c2> <TD align=middle>2</TD> <TD align=middle><font color = "blue">12654172</font></TD> <TD align=middle></TD> <TD align=middle><font color = "blue">615</font></TD> <TD align=middle>615 </TD> <TD align=middle></TD> <TD align=middle><font color = "blue">15</font></TD> <TD align=middle><font color = "blue">41</font></TD> <TD align=middle><font color = "blue">P000000D</font></TD> <TD align=middle></TD> <TD align=middle></TD> <TD align=middle></TD> <TD align=middle></TD> <TD align=middle></TD></TR></TBODY></TABLE><BR>';$result = array();preg_match_all('#<font\s*color\s*=\s*"blue">(.*)</font>#iUus',$string,$result);print_r($result[1]);
本身要是没蓝色的(id,class之类的也没有的)话那就只能全部单元格正则匹配出来按页面结构需要来取了
本身无颜色区分,只是我标识出来的罢了。
$s 为你提供的页面内容
preg_match_all('#<td.+/td>#isU', $s, $r);$r = array_map('trim', array_map('strip_tags', $r[0]));print_r($r);
Array( [0] => [1] => aaaaaa aaaaaa [2] => aaaaaa xxxx(aaaaaa) [3] => aaaaaa xxxx [4] => adress aaaaaa adress [5] => [6] => 交货计划单 [7] => 计划到达时间 2013-09-16 [8] => PUS编号 770266110 版本00 [9] => Customer 客户 [10] => *DYNP-770266110-00* [11] => [12] => Delivery Information 交货信息 [13] => 工厂Plant [14] => xxxxxx [15] => 取货时间Pick Up Time [16] => 2013-09-09 16:30 [17] => 需要供应商反馈Need Duns Response [18] => N [19] => 交货日期Delivery Date [20] => 2013-09-16 [21] => 窗口时间Window Time [22] => 16:30 [23] => 卸货口Dock [24] => CC-70D [25] => 卸货口负责人Dock Incharger [26] => kkk [27] => 卸货口电话Dock Tel [28] => 011-1111 [29] => 卸货口地址Dock Address [30] => adress [31] => 交货地点Delivery Place [32] => [33] => 计划跟踪员Follow Up [34] => kkkk [35] => 计划跟踪员电话/传真FollowUp Tel/Fax [36] => 011-1111 [37] => 交货说明Delivery Note [38] => [39] => Part Information 零件清单 [40] => 序号 [41] => 零件号 [42] => 零件说明 [43] => 需求数量 [44] => 承诺数量 [45] => 实收数量 [46] => 包装数 [47] => 料箱数 [48] => 料箱号 [49] => 实发料箱号 [50] => 实发料箱数 [51] => 实收料箱号 [52] => 实收料箱数 [53] => 备注 [54] => 1 [55] => 12647212 [56] => [57] => 60 [58] => 60 [59] => [60] => 15 [61] => 4 [62] => P000000D [63] => [64] => [65] => [66] => [67] => [68] => 2 [69] => 12654172 [70] => [71] => 615 [72] => 615 [73] => [74] => 15 [75] => 41 [76] => P000000D [77] => [78] => [79] => [80] => [81] => )
//第二个表从下标 40 开始,14 列$t = array_chunk(array_slice($r, 40), 14);for($i=1; $i<count($t); $i++) $res[] = array_combine($t[0], $t[$i]);print_r($res);
Array( [0] => Array ( [序号] => 1 [零件号] => 12647212 [零件说明] => [需求数量] => 60 [承诺数量] => 60 [实收数量] => [包装数] => 15 [料箱数] => 4 [料箱号] => P000000D [实发料箱号] => [实发料箱数] => [实收料箱号] => [实收料箱数] => [备注] => ) [1] => Array ( [序号] => 2 [零件号] => 12654172 [零件说明] => [需求数量] => 615 [承诺数量] => 615 [实收数量] => [包装数] => 15 [料箱数] => 41 [料箱号] => P000000D [实发料箱号] => [实发料箱数] => [实收料箱号] => [实收料箱数] => [备注] => ))
preg_match_all('#
preg_match_all('#
那就是你的问题了
一般说明文字与数据总是配对的,并且说明文字在前,数据在后
那就是你的问题了
一般说明文字与数据总是配对的,并且说明文字在前,数据在后
如果在1楼之前还有一个table,那么array_combine会有一个warning提示。
<TABLE width="95%" align=center border=0> <TBODY> <TR> <TD align=left width="44%"><B><FONT size=1>Supplier Signature Carrier Signature<BR>供应商签字</FONT></B><FONT size=2> <B><FONT size=+0>_____________</FONT></B> <B> 承运商</B></FONT><FONT size=2><B>签字</B> </FONT><B><FONT size=1>_____________</FONT></B></TD> <TD align=right width="45%"><B><FONT size=1>Supplier Confirm Time <BR>供应商确认时间 13-09-10 09:01 </FONT></B></TD></TR> <TR> <TD align=left width="55%"><B><FONT size=1>Receiver Signature <BR>收货人签字</FONT></B><FONT size=2> <B><FONT size=+0>_______________</FONT></B> </FONT></TD> <TD align=right width="45%"><B><FONT size=1><BR>Date 日期</FONT></B><FONT size=2> <B><FONT size=+0>______________</FONT></B> </FONT></TD></TR> <TR> <TD align=middle colSpan=2><B>*** END OF PAGE ***</B> </TD></TR></TBODY></TABLE></TD></TR></TBODY></TABLE>