采集淘宝或天猫商品的店铺名称/商家旺旺/商品首图/商品标题

一用的QueryList库

二安装方法

确认已经安装了composer，因为速度会很慢，可以切换到中国镜像：

composer config -g repo.packagist composer https://packagist.phpcomposer.com

安装QueryList：

composer require jaeger/querylist

QueryList文档地址，可以了解下：

http://www.querylist.cc/#one

三需求如下

通过淘宝或天猫的商品链接，采集该商品链接对应的商品标题、商品首图、店铺名称、商家旺旺名称

四目前的采集数据Demo可以适用于所有天猫商品+店铺名称在右边或上边的

五代码如下

<?php  include "vendor/autoload.php";  use QL\QueryList;  function uni_decode($s) {  //针对部分淘宝宝贝链接的店铺名被加密进行解密处理   preg_match_all('/\&\#([0-9]{2,5})\;/', $s, $html_uni);     preg_match_all('/[\\\%]u([0-9a-f]{4})/ie', $s, $js_uni);     $source = array_merge($html_uni[0], $js_uni[0]);     $js = array();     for($i=0;$i<count($js_uni[1]);$i++) {       $js[] = hexdec($js_uni[1][$i]);     }     $utf8 = array_merge($html_uni[1], $js);     $code = $s;     for($j=0;$j<count($utf8);$j++) {       $code = str_replace($source[$j], unicode2utf8($utf8[$j]), $code);     }     return $code; }       function unicode2utf8($c) {     $str="";     if ($c < 0x80) {        $str.=chr($c);     } else if ($c < 0x800) {        $str.=chr(0xc0 | $c>>6);        $str.=chr(0x80 | $c & 0x3f);     } else if ($c < 0x10000) {        $str.=chr(0xe0 | $c>>12);        $str.=chr(0x80 | $c>>6 & 0x3f);        $str.=chr(0x80 | $c & 0x3f);     } else if ($c < 0x200000) {        $str.=chr(0xf0 | $c>>18);        $str.=chr(0x80 | $c>>12 & 0x3f);        $str.=chr(0x80 | $c>>6 & 0x3f);        $str.=chr(0x80 | $c & 0x3f);     }     return $str;   }   function get_between($input, $start, $end) {//截取指定两个字符之间的内容  	return substr($input, strlen($start)+strpos($input, $start),(strlen($input) - strpos($input, $end))*(-1)); }  function trimall($str)//删除空格 {     $qian=array(" ","　","\t","\n","\r");     $hou=array("","","","","");     return str_replace($qian,$hou,$str);  }  $url = 'https://item.taobao.com/item.htm?spm=a230r.1.14.34.47cd6ace3iAnm0&id=564043247193&ns=1&abbucket=19#detail';  $ql = QueryList::get($url)->encoding('UTF-8','GB2312');//防止数据乱码  //针对1天猫宝贝链接 2淘宝店铺名在右边 3淘宝店铺名在上面 采取不同的采集方式 if (substr($url, 0, 24) == 'https://detail.tmall.com') {  	$rt = [ 		'img' 		=> $ql->find('#J_ImgBooth')->attr('src'), 		'title' 	=> $ql->find(':input[name="title"]')->attr('value'), 		'shop_name' => $ql->find('.slogo-shopname')->text() 	];  	$rt['seller_name'] = $rt['shop_name'];  } else {  	$rt = [ 		'img' 		  => $ql->find('#J_ImgBooth')->attr('src'), 		'title' 	  => $ql->find('.tb-main-title')->text(), 		'shop_name'   => $ql->find('.tb-shop-name>dl>dd>strong>a')->text(), 		'seller_name' => $ql->find('.tb-seller-name')->text() 	];  	if (!$rt['shop_name']) {  		$config = substr(trimall($ql->find('script')->eq(0)->text()), 100, 150);  		$shop_name = get_between($config, "shopName:'", "',sellerId");  		$rt['shop_name'] = uni_decode($shop_name);  		$rt['seller_name'] = get_between($config, "sellerNick:'", "',sibUrl"); 	} } 	 var_dump($rt['shop_name']);  echo '<hr />'; ?>   <!DOCTYPE html> <html lang="en"> <head> 	<meta charset="UTF-8"> 	<title>爬取淘宝商品数据Demo</title> </head> <body> 	<h4>标题：<?php echo $rt['title']; ?></h4> 	<h4>店铺：<?php echo $rt['shop_name']; ?></h4> 	<h4>旺旺：<?php echo $rt['seller_name']; ?></h4> 	<h4>图片：</h4> 	<img src="<?php echo $rt['img'] ?>" alt=""> </body> </html>