snoopy 模拟表单提交

栏目分类：PHP教程    发布日期：2017-08-25    浏览次数：4635次     收藏

setcookies() 该方法没有参数，保存响应cookie信息 用于下一次请求

//登录blogbus，获取cookie  
$loginUrl = 'http://passport.blogbus.com/login';  
$loginFormData['username'] = 'neverfailor';  
$loginFormData['password'] = '66263679';  
$snoopy->submit($loginUrl, $loginFormData);  
$snoopy->setcookies();  
$cookies = $snoopy->cookies;  
  
//表单页面  
$blogFormUrl = 'http://blog.home.blogbus.com/5865443/posts/form';  
//post数据  
$blogPostUrl = 'http://blog.home.blogbus.com/5865443/posts/';  
$form_data = array(  
'title' => '321333',  
'content' => '132131',  
'post_time' => date('Y-m-d H:i'),  
);  
getPostPage($blogPostUrl, $form_data , $blogFormUrl);  
function getPostPage($postUrl, $form_data , $formUrl){  
    include_once 'Snoopy.class.php';  
    $snoopy = new Snoopy;  
  
    $snoopy->fetch($formUrl); //获取所有内容  
    $snoopy->setcookies();  
    $cookies = $snoopy->cookies;  
  
    $snoopy->referer = $formUrl;  
    $snoopy->cookies = $cookies;  
    $snoopy->submit($postUrl, $form_data , $formUrl);  
    return $snoopy->results;  
}  
function findGetPage($route, $param = array())  
{  
    $query_string = http_build_query($param);  
    $query_string = $query_string ? "?" . $query_string : '';  
    $url = $route . $query_string;  
    $snoopy = new Snoopy;  
    $snoopy->fetch($url); //获取所有内容  
    return $snoopy->results; //显示结果  
}  

<?php  
$url = "http://www.youtube.com";  
include("snoopy.php");  
$snoopy = new Snoopy;  
$snoopy->fetch($url); //获取所有内容  
echo $snoopy->results; //显示结果  
//可选以下  
$snoopy->fetchtext; //获取文本内容（去掉html代码）  
$snoopy->fetchlinks; //获取链接  
$snoopy->fetchform; //获取表单  
?>   

2、表单提交 

首先说明一下，$snoopy->status是远程返回的状态码，成功返回的应该是200，其他情况下返回的都应该是错误的， 并且有效的请求状态应该是大于0的，$snoopy->timed_out在未超时的情况下值为false，如果读取请求超时的话，返回值应该为true。

$snoopy->read_timeout=4;  //读取超时时间  
$snoopy->fetch($url); //获取所有内容  
if ($snoopy->status=='200'&&!$snoopy->timed_out) {  
    $snoopy->setcookies();  
    $cookies = $snoopy->cookies;  
    $snoopy->cookies = $cookies;  
    $snoopy->referer = $url;  
    $status = $snoopy->submit($post_url, $pdata);//$pdata为提交的数组,$post_url采集提交url  
    if($status == true){  
        return $snoopy->results;  
    }  
}  

3、伪装

<?php  
$formvars["username"] = "admin";  
$formvars["pwd"] = "admin";  
$action = "http://www.taoav.com";  
include "snoopy.php";  
$snoopy = new Snoopy;  
$snoopy->cookies["PHPSESSID"] = 'fc106b1918bd522cc863f36890e6fff7'; //伪装sessionid  
$snoopy->agent = "(compatible; MSIE 4.01; MSN 2.5; AOL 4.0; Windows 98)"; //伪装浏览器  
$snoopy->referer = "http://www.only4.cn"; //伪装来源页地址 http_referer  
$snoopy->rawheaders["Pragma"] = "no-cache"; //cache 的http头信息  
$snoopy->rawheaders["X_FORWARDED_FOR"] = "127.0.0.101"; //伪装ip  
$snoopy->submit($action,$formvars);  
echo $snoopy->results;  
?>  

<?php  
$snoopy->proxy_host = "www.only4.cn";  
$snoopy->proxy_port = "8080"; //使用代理  
$snoopy->maxredirs = 2; //重定向次数  
$snoopy->expandlinks = true; //是否补全链接 在采集的时候经常用到  
// 例如链接为 /images/taoav.gif 可改为它的全链接 [img]http://www.taoav.com/images/taoav.gif[/img]  
  
$snoopy->maxframes = 5; //允许的最大框架数  
//注意抓取框架的时候 $snoopy->results 返回的是一个数组  
  
$snoopy->error; //返回报错信息  
?>