以下代码如何改为用 curl来抓取呢?并且以商品的IID保存
function get_shuxing($type,$iid){if($type=='tmall'){$text=file_get_contents("http://detail.tmall.com/item.htm?id=$iid");preg_match('|<ul id="J_AttrUL">(.*)</ul>|isU',$text, $match);}elseif ($type=='taobao'){$text=file_get_contents("http://item.taobao.com/item.htm?id=$iid");preg_match('|<ul class="attributes-list">(.*)</ul>|isU',$text, $match);}$match=$match[0];$match = iconv('gbk', 'utf-8', $match);echo $match;}
有哪位大神帮忙呢》
你不给测试数据怎么弄,再怎么也得给个$iid吧...
你不给测试数据怎么弄,再怎么也得给个$iid吧...
$html=file_get_contents('http://detail.tmall.com/item.htm?id=13317551791');include 'simple_html_dom.php';//网上下一个 $dom=new simple_html_dom();// $html utf8才可以$dom->load($html);$names=$dom->find('select[id=js]');$res=array();$lis=$dom->find('ul[id=J_AttrUL] li');foreach($lis as $k=>$li){ $temp=$li->text(); list($key,$value)=explode(':',$temp); $data[$key]=$value;}echo "<pre class="brush:php;toolbar:false;">";print_r($data);echo "
$html=file_get_contents('http://detail.tmall.com/item.htm?id=13317551791');include 'simple_html_dom.php';//网上下一个 $dom=new simple_html_dom();// $html utf8才可以$dom->load($html);$names=$dom->find('select[id=js]');$res=array();$lis=$dom->find('ul[id=J_AttrUL] li');foreach($lis as $k=>$li){ $temp=$li->text(); list($key,$value)=explode(':',$temp); $data[$key]=$value;}echo "<pre class="brush:php;toolbar:false;">";print_r($data);echo "这些不是产品参数?数据都取出来了,至于怎么用,就看你自己处理,我又不是知道你要什么样的数据格式,一维,二维?键值对?
不要用正则,我记得抓这些属性有http请求方法的,你抓个包就知道了
这样吗?
function get_shuxing($type,$iid){ if($type=='tmall'){ //$text=file_get_contents("http://detail.tmall.com/item.htm?id=$iid"); $text=use_curl("http://detail.tmall.com/item.htm?id=$iid"); preg_match('|<ul id="J_AttrUL">(.*)</ul>|isU',$text, $match); }elseif ($type=='taobao'){ //$text=file_get_contents("http://item.taobao.com/item.htm?id=$iid"); $text=use_curl("http://item.taobao.com/item.htm?id=$iid"); preg_match('|<ul class="attributes-list">(.*)</ul>|isU',$text, $match); } $match=$match[0]; $match = iconv('gbk', 'utf-8', $match); echo $match;}function use_curl($url){ $ch = curl_init($url); curl_setopt($ch, CURLOPT_HEADER, 0); curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); $output = curl_exec($ch); curl_close($ch); return $output;}get_shuxing('taobao',45098460735);
这样吗?
function get_shuxing($type,$iid){ if($type=='tmall'){ //$text=file_get_contents("http://detail.tmall.com/item.htm?id=$iid"); $text=use_curl("http://detail.tmall.com/item.htm?id=$iid"); preg_match('|<ul id="J_AttrUL">(.*)</ul>|isU',$text, $match); }elseif ($type=='taobao'){ //$text=file_get_contents("http://item.taobao.com/item.htm?id=$iid"); $text=use_curl("http://item.taobao.com/item.htm?id=$iid"); preg_match('|<ul class="attributes-list">(.*)</ul>|isU',$text, $match); } $match=$match[0]; $match = iconv('gbk', 'utf-8', $match); echo $match;}function use_curl($url){ $ch = curl_init($url); curl_setopt($ch, CURLOPT_HEADER, 0); curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); $output = curl_exec($ch); curl_close($ch); return $output;}get_shuxing('taobao',45098460735);
这样吗?
function get_shuxing($type,$iid){ if($type=='tmall'){ //$text=file_get_contents("http://detail.tmall.com/item.htm?id=$iid"); $text=use_curl("http://detail.tmall.com/item.htm?id=$iid"); preg_match('|<ul id="J_AttrUL">(.*)</ul>|isU',$text, $match); }elseif ($type=='taobao'){ //$text=file_get_contents("http://item.taobao.com/item.htm?id=$iid"); $text=use_curl("http://item.taobao.com/item.htm?id=$iid"); preg_match('|<ul class="attributes-list">(.*)</ul>|isU',$text, $match); } $match=$match[0]; $match = iconv('gbk', 'utf-8', $match); echo $match;}function use_curl($url){ $ch = curl_init($url); curl_setopt($ch, CURLOPT_HEADER, 0); curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); $output = curl_exec($ch); curl_close($ch); return $output;}get_shuxing('taobao',45098460735);<!DOCTYPE HTML PUBLIC "-//IETF//DTD HTML 2.0//EN"><html><head><title>302 Found</title></head><body bgcolor="white"><h1>302 Found</h1><p>The requested resource resides temporarily under a different URI.</p>
<div class="aritcle_card">
<a class="aritcle_card_img" href="/ai/1577">
<img src="https://img.php.cn/upload/ai_manual/000/969/633/68b6dc5584c99537.png" alt="AI帮个忙">
</a>
<div class="aritcle_card_info">
<a href="/ai/1577">AI帮个忙</a>
<p>多功能AI小工具,帮你快速生成周报、日报、邮、简历等</p>
<div class="">
<img src="/static/images/card_xiazai.png" alt="AI帮个忙">
<span>55</span>
</div>
</div>
<a href="/ai/1577" class="aritcle_card_btn">
<span>查看详情</span>
<img src="/static/images/cardxiayige-3.png" alt="AI帮个忙">
</a>
</div>
<hr/>Powered by Tengine</body></html>
Copyright 2014-2025 https://www.php.cn/ All Rights Reserved | php.cn | 湘ICP备2023035733号