说起来做这个功能还真是一时好奇。前段时间在做一个淘客网站的时候，想到是否能抓取到淘宝商品的买家秀呢？经过一番折腾发现，淘宝商品用户评价信息是通过Ajax来调取的，通过嗅探网址发现，评论数据的请求接口是：
https://rate.tmall.com/list_detail_rate.htm?itemId=524394294771&spuId=341564036&sellerId=100414600&order=3¤tPage=1&append=0&content=1&tagId=&posi=&picture=1&callback=jsonp2339
其实上面很多参数也很容易理解，itemId是商品的ID，currentPage是当前页，picture为1时显示有图的评价，既然是抓取买家秀，那么picture参数一定要为1了。
如果你直接去访问上面的接口时，会得到如下图所示的请求结果：
看到请求结果是jsonp格式我就蛋碎了，我不知道如何去解析，但是换种思路，直接用PHP的正则去解析也未尝不可嘛，通过尝试，已经正确的能够解析到评论内容和买家秀的图片内容，如图：
效果不错，代码实现了评论内容的抓娶买家秀图片的抓取，代码奉上：
<?php
$url = "https://rate.tmall.com/list_detail_rate.htm?itemId=524394294771&spuId=341564036&sellerId=100414600&order=3¤tPage=1&append=0&content=1&tagId=&posi=&picture=1&callback=jsonp2339";
$ch2 = curl_init();
curl_setopt($ch2, CURLOPT_URL, $url);
curl_setopt($ch2, CURLOPT_FOLLOWLOCATION, TRUE);
curl_setopt($ch2, CURLOPT_SSL_VERIFYHOST, FALSE);
curl_setopt($ch2, CURLOPT_SSL_VERIFYPEER, false);
curl_setopt($ch2, CURLOPT_RETURNTRANSFER, TRUE);
$texts = curl_exec($ch2);
curl_close($ch2);
//echo $texts;
$pattern = '/"pics"(.+?)","reply"/is';
preg_match_all($pattern, $texts, $match);
for($i=0;$i<count($match[0]);$i++){
$pattern2 = '/"rateContent":"(.+?)."reply"/is';
preg_match($pattern2, $match[0][$i], $matchcomments_only);
echo "".str_replace('","rateDate":"',' ',str_replace('","reply"','',str_replace('"rateContent":"','',$matchcomments_only[0])))."
";
$pattern3 = '/img.alicdn(.+?).jpg/is';
preg_match($pattern3, $match[0][$i], $matchpic_only);
echo '
';
}
/*匹配一张图片
$pattern = '/"pics"(.+?)","position"/is';
preg_match_all($pattern, $texts, $matchpic);
for($i=0;$i<count($matchpic[0]);$i++){
$pattern3 = '/img.alicdn(.+?).jpg/is';
preg_match($pattern3, $matchpic[0][$i], $matchpic_only);
echo "".$matchpic_only[0]."
";
}*/
/*匹配所有图片
$pattern = '/"pics"(.+?)","position"/is';
preg_match_all($pattern, $texts, $matchpic);
for($i=0;$i<count($matchpic[0]);$i++){
$pics_str=str_replace('"pics":["//','',str_replace('"],"picsSmall":"","position"','',$matchpic[0][$i]));
$arr = explode('","//',$pics_str);
echo "";
foreach($arr as $newstr){
echo '
';
}
echo "
";
}*/
?>
下面给大家介绍PHP抓取淘宝搜索商品列表实例
<?php
header("Content-Type:text/html;charset=gbk");
include "Snoopy.class.php";
$snoopy = new Snoopy;
$snoopy->fetch("http://s.taobao.com/search?spm=a230r.1.8.7.2NN4M7&q=%C7%EF%B6%AC%B4%F3%D2%C2&source=tbsy&refpid=420461_1006&discount_index=1&newpre=null&p4p_str=fp_midtop%3D0%26firstpage_pushleft%3D0&style=list&s=0#J_Filter");
$html=$snoopy->results;
//说明：抓取网页使用的是 Snoopyphp 框架 也可以直接使用file_get_contents函数获取即可，
//var_dump($html);
preg_match_all('/.*/',$html,$result);
//preg_match_all('/([^<>]+)
