PHP抓取淘宝商品的用户晒单评论+图片+搜索商品列表实例

<?php
$url = "https://rate.tmall.com/list_detail_rate.htm?itemId=524394294771&spuId=341564036&sellerId=100414600&order=3&currentPage=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], $matchcomments_only);
echo "<p>".str_replace('","rateDate":"',' ',str_replace('","reply"','',str_replace('"rateContent":"','',$matchcomments_only[0])))."</p>";
$pattern3 = '/img.alicdn(.+?).jpg/is';
preg_match($pattern3, $match[0][$i], $matchpic_only);
echo '<img src="http://'.$matchpic_only[0].'" width=120>';
}
/*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], $matchpic_only);
echo "<p>".$matchpic_only[0]."</p>";
}*/
/*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 "<p>";
foreach($arr as $newstr){
echo '<img src=http://'.$newstr.' width=100 >';
}
echo "</p>";
}*/
?> 

<?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($html);
preg_match_all('/<h3 class="summary">.*</a>/',$html,$result);
//preg_match_all('/<divsid="([a-z0-9_]+)">([^<>]+)</div>/',$html,$result);
var_dump($result);
echo "<br>";
/*
//循环读取数组
foreach($result as $key1){
foreach($key1 as $key => $val){
echo $key.$val;
}
}
*/