<li onmouseover=this.className='kuang_c_2' onmouseout=this.className='kuang_c' class='kuang_c'><h2><a href='procat/pro_629.html'>光度计</a></h2><p><a href='prolist/prolist_859_1.html'>成像光度计</a></p></li><li onmouseover=this.className='kuang_c_2' onmouseout=this.className='kuang_c' class='kuang_c'><h2><a href='procat/pro_572.html'>分光光度计</a></h2><p><a href='prolist/prolist_408_1.html'>红外分光光度计</a> | <a href='prolist/prolist_409_1.html'>紫外分光光度计</a> | <a href='prolist/prolist_410_1.html'>原子吸收分光光度计</a> | <a href='prolist/prolist_411_1.html'>可见分光光度计</a></p></li><li onmouseover=this.className='kuang_c_2' onmouseout=this.className='kuang_c' class='kuang_c'><h2><a href='procat/pro_565.html'>天平</a></h2><p><a href='prolist/prolist_382_1.html'>精密天平</a> | <a href='prolist/prolist_383_1.html'>分析天平</a> | <a href='prolist/prolist_384_1.html'>架盘天平</a></p></li><li onmouseover=this.className='kuang_c_2' onmouseout=this.className='kuang_c' class='kuang_c'><h2><a href='procat/pro_568.html'>离心机</a></h2><p><a href='prolist/prolist_393_1.html'>迷你型离心机</a> | <a href='prolist/prolist_394_1.html'>台式离心机</a> | <a href='prolist/prolist_395_1.html'>落地式离心机</a></p></li><li onmouseover=this.className='kuang_c_2' onmouseout=this.className='kuang_c' class='kuang_c'><h2><a href='procat/pro_573.html'>旋转蒸发仪</a></h2><p><a href='prolist/prolist_412_1.html'>小型旋转蒸发仪</a> | <a href='prolist/prolist_413_1.html'>台式旋转蒸发仪</a> | <a href='prolist/prolist_414_1.html'>大型旋转蒸发仪</a> | <a href='prolist/prolist_727_1.html'>过滤器</a> | <a href='prolist/prolist_728_1.html'>萃取仪</a></p></li>大小类采集 对应存入数据库 谁能给写一下
$str= <<< HTML
<li onmouseover=this.className='kuang_c_2' onmouseout=this.className='kuang_c' class='kuang_c'><h2><a href='procat/pro_629.html'>光度计</a></h2><p><a href='prolist/prolist_859_1.html'>成像光度计</a></p></li>
<li onmouseover=this.className='kuang_c_2' onmouseout=this.className='kuang_c' class='kuang_c'><h2><a href='procat/pro_572.html'>分光光度计</a></h2><p><a href='prolist/prolist_408_1.html'>红外分光光度计</a> | <a href='prolist/prolist_409_1.html'>紫外分光光度计</a> | <a href='prolist/prolist_410_1.html'>原子吸收分光光度计</a> | <a href='prolist/prolist_411_1.html'>可见分光光度计</a></p></li>
<li onmouseover=this.className='kuang_c_2' onmouseout=this.className='kuang_c' class='kuang_c'><h2><a href='procat/pro_565.html'>天平</a></h2><p><a href='prolist/prolist_382_1.html'>精密天平</a> | <a href='prolist/prolist_383_1.html'>分析天平</a> | <a href='prolist/prolist_384_1.html'>架盘天平</a></p></li>
<li onmouseover=this.className='kuang_c_2' onmouseout=this.className='kuang_c' class='kuang_c'><h2><a href='procat/pro_568.html'>离心机</a></h2><p><a href='prolist/prolist_393_1.html'>迷你型离心机</a> | <a href='prolist/prolist_394_1.html'>台式离心机</a> | <a href='prolist/prolist_395_1.html'>落地式离心机</a></p></li>
<li onmouseover=this.className='kuang_c_2' onmouseout=this.className='kuang_c' class='kuang_c'><h2><a href='procat/pro_573.html'>旋转蒸发仪</a></h2><p><a href='prolist/prolist_412_1.html'>小型旋转蒸发仪</a> | <a href='prolist/prolist_413_1.html'>台式旋转蒸发仪</a> | <a href='prolist/prolist_414_1.html'>大型旋转蒸发仪</a> | <a href='prolist/prolist_727_1.html'>过滤器</a> | <a href='prolist/prolist_728_1.html'>萃取仪</a></p></li>
HTML;
preg_match_all("/<a\s*href='([^']*)'>(.*)<\/a>/isU",$str,$arr);
print_r($arr);$arr[1]即为连接,$arr[2]即为文字
采集导航
preg_match_all('/<li[^>]*>(.*)<\/li>/isU',$str,$arr);
print_r($arr);
foreach($arr[1] as $v){
preg_match_all("/<a\s*href='(.*)'>(.*)<\/a>/isU",$v,$matches[]);
}
print_r($matches);
自己去看下结果就知道了。
preg_match_all("/<a\s*href='(.*)'>(.*)<\/a>/isU",$v,$matches[]);
foreach ($matches[$k] as $key=>$values){
$title =$matches[$key][2];
}
}
Array
(
[0] => Array
(
[0] => <a href='procat/pro_629.html'>光度计</a>
[1] => <a href='prolist/prolist_859_1.html'>成像光度计</a>
) [1] => Array
(
[0] => procat/pro_629.html
[1] => prolist/prolist_859_1.html
) [2] => Array
(
[0] => 光度计
[1] => 成像光度计
))
Array
(
[0] => Array
(
[0] => <a href='procat/pro_572.html'>分光光度计</a>
[1] => <a href='prolist/prolist_408_1.html'>红外分光光度计</a>
[2] => <a href='prolist/prolist_409_1.html'>紫外分光光度计</a>
[3] => <a href='prolist/prolist_410_1.html'>原子吸收分光光度计</a>
[4] => <a href='prolist/prolist_411_1.html'>可见分光光度计</a>
) [1] => Array
(
[0] => procat/pro_572.html
[1] => prolist/prolist_408_1.html
[2] => prolist/prolist_409_1.html
[3] => prolist/prolist_410_1.html
[4] => prolist/prolist_411_1.html
) [2] => Array
(
[0] => 分光光度计
[1] => 红外分光光度计
[2] => 紫外分光光度计
[3] => 原子吸收分光光度计
[4] => 可见分光光度计
))
为什么我这么取值不可以呀