全国服务热线:400-6566-535 广州热线:020-82105691 客服QQ:858560031
后台演示 猪八戒 阿里巴巴商铺 手机版
网络营销电子商务建站知识编程知识行业资讯SEO知识常见问题网络安全
您当前位置: 首页 >资讯活动 > 建站知识 > php采集模拟点击伪造IP,伪造浏览器useragent伪造来源防反爬虫例子

php采集模拟点击伪造IP,伪造浏览器useragent伪造来源防反爬虫例子

时间:2017-09-26 作者:七想网络

 

先上两个文件 index.php  一个curl.php

index.php是我们要采集的。以下是源码


$client_ip = getip();
$referer = getreferer();

$allow_ip = '192.168.1.100';
$allow_referer = 'http://www.amztool.cn';
$useragent=$_SERVER['HTTP_USER_AGENT'];
plog( 'client_ip='.$client_ip." || useragent=".$useragent.' ');
echo '<br>client_ip=';
echo $client_ip;
echo " || useragent=";
echo $useragent;

echo '<hr><br>';
// 获取访问者ip
function getip(){
    if(!empty($_SERVER['HTTP_CLIENT_IP'])){
        $cip = $_SERVER['HTTP_CLIENT_IP'];
    }elseif(!empty($_SERVER['HTTP_X_FORWARDED_FOR'])){
        $cip = $_SERVER['HTTP_X_FORWARDED_FOR'];
    }elseif(!empty($_SERVER['REMOTE_ADDR'])){
        $cip = $_SERVER['REMOTE_ADDR'];
    }else{
        $cip = '';
    }
    return $cip;
}

// 获取访问者来源
function getreferer(){
    if(isset($_SERVER['HTTP_REFERER'])){
        return $_SERVER['HTTP_REFERER'];
    }
    return '';
}

function plog($message){
    $file=__DIR__."/text.txt";

     if($f  = file_put_contents($file, $message." ",FILE_APPEND)){// 这个函数支持版本(PHP 5) 打印到文件

        }
}



再上curl.php 这个文件是用来采集的执行文件


$ch = curl_init();
$curlurl = "http://www.amztool.cn/index.php";
$referurl = "http://www.amztool.cn";
$ip=mt_rand(11, 191).".".mt_rand(0, 240).".".mt_rand(1, 240).".".mt_rand(1, 240);   //随机ip
$agentarry=[
    //PC端的UserAgent
    "safari 5.1 – MAC"=>"Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11",
    "safari 5.1 – Windows"=>"Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
    "Firefox 38esr"=>"Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0",
    "IE 11"=>"Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko",
    "IE 9.0"=>"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0",
    "IE 8.0"=>"Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)",
    "IE 7.0"=>"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",
    "IE 6.0"=>"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",
    "Firefox 4.0.1 – MAC"=>"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
    "Firefox 4.0.1 – Windows"=>"Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
    "Opera 11.11 – MAC"=>"Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
    "Opera 11.11 – Windows"=>"Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
    "Chrome 17.0 – MAC"=>"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
    "傲游(Maxthon)"=>"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)",
    "腾讯TT"=>"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)",
    "世界之窗(The World) 2.x"=>"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
    "世界之窗(The World) 3.x"=>"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)",
    "360浏览器"=>"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)",
    "搜狗浏览器 1.x"=>"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)",
    "Avant"=>"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)",
    "Green Browser"=>"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
    //移动端口
    "safari iOS 4.33 – iPhone"=>"Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
    "safari iOS 4.33 – iPod Touch"=>"Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
    "safari iOS 4.33 – iPad"=>"Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
    "Android N1"=>"Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
    "Android QQ浏览器 For android"=>"MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
    "Android Opera Mobile"=>"Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10",
    "Android Pad Moto Xoom"=>"Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13",
    "BlackBerry"=>"Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile Safari/534.1+",
    "WebOS HP Touchpad"=>"Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.0; U; en-US) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/233.70 Safari/534.6 TouchPad/1.0",
    "UC标准"=>"NOKIA5700/ UCWEB7.0.2.37/28/999",
    "UCOpenwave"=>"Openwave/ UCWEB7.0.2.37/28/999",
    "UC Opera"=>"Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999",
    "微信内置浏览器"=>"Mozilla/5.0 (Linux; Android 6.0; 1503-M02 Build/MRA58K) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/37.0.0.0 Mobile MQQBrowser/6.2 TBS/036558 Safari/537.36 MicroMessenger/6.3.25.861 NetType/WIFI Language/zh_CN",
   // ""=>"",

];
//$useragent="Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11";  //要得到类似这样useranget 可以自定义
$useragent=$agentarry[array_rand($agentarry,1)];  //随机浏览器useragent
$header = array(
    'CLIENT-IP:'.$ip,
    'X-FORWARDED-FOR:'.$ip,
);    //构造ip
curl_setopt($ch, CURLOPT_URL, $curlurl); //要抓取的网址
curl_setopt($ch, CURLOPT_HTTPHEADER, $header);
curl_setopt($ch, CURLOPT_RETURNTRANSFER,true);
curl_setopt($ch, CURLOPT_REFERER, $referurl);  //模拟来源网址
curl_setopt($ch, CURLOPT_USERAGENT, $useragent); //模拟常用浏览器的useragent

$page_content = curl_exec($ch);
curl_close($ch);
echo $page_content;


这两个文件放在同一目录,目录下新建一个text.txt文件用来记录采集的仿问的ip和useragent头。

 

准备开展业务? 立即创建网站 成为代理商
网络营销
  1. 企业网站如何做好网站优化与推广工作?
  2. 中小企业怎样做网络营销 广州七想网络...
  3. 网络营销并不神秘,七想网络带您揭开秘...
  4. 透过优衣库事件 看网络营销?
  5. QQ营销推广技巧?
  6. 中小企业网站如何推广才有效果呢?