對於限制了ip和來源的網站,使用正常的採集方式是不行的。本文將介紹一種方法,使用php的curl類實現類比ip和來源,實現採集限制ip和來源的網站。
1.設定頁面限制ip和來源訪問
server.php
<?php $client_ip = getip();$referer = getreferer(); $allow_ip = '192.168.1.100';$allow_referer = 'http://www.uxuew.cn'; if($client_ip==$allow_ip && strpos($referer, $allow_referer)===0){ echo 'allow access';}else{ echo 'deny access';} // 擷取訪問者ipfunction getip(){ if(!empty($_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 $cip;} // 擷取訪問者來源function getreferer(){ if(isset($_SERVER['HTTP_REFERER'])){return $_SERVER['HTTP_REFERER']; } return '';} ?>
2.使用curl正常訪問
<?phpfunction doCurl($url, $data=array(), $header=array(), $timeout=30){ $ch = curl_init(); curl_setopt($ch, CURLOPT_URL, $url); curl_setopt($ch, CURLOPT_HTTPHEADER, $header); curl_setopt($ch, CURLOPT_POST, true); curl_setopt($ch, CURLOPT_POSTFIELDS, http_build_query($data)); curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); curl_setopt($ch, CURLOPT_TIMEOUT, $timeout); $response = curl_exec($ch); if($error=curl_error($ch)){die($error); } curl_close($ch); return $response; } // 調用$url = 'http://www.uxuew.cn/server.php';$response = doCurl($url); echo $response;?>
3.使用curl類比ip和來源進行訪問
類比來源
curl_setopt($ch, CURLOPT_REFERER, '來源');
類比ip
curl_setopt($ch, CURLOPT_HTTPHEADER, array('CLIENT-IP: 類比ip','X-FORWARDED-FOR: 類比ip'));
完整代碼如下:
<?phpfunction doCurl($url, $data=array(), $header=array(), $referer='', $timeout=30){ $ch = curl_init(); curl_setopt($ch, CURLOPT_URL, $url); curl_setopt($ch, CURLOPT_HTTPHEADER, $header); curl_setopt($ch, CURLOPT_POST, true); curl_setopt($ch, CURLOPT_POSTFIELDS, http_build_query($data)); curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); curl_setopt($ch, CURLOPT_TIMEOUT, $timeout); // 類比來源 curl_setopt($ch, CURLOPT_REFERER, $referer); $response = curl_exec($ch); if($error=curl_error($ch)){die($error); } curl_close($ch); return $response; } // 調用$url = 'http://www.example.com/server.php';$data = array(); // 設定IP$header = array( 'CLIENT-IP: 192.168.1.100', 'X-FORWARDED-FOR: 192.168.1.100'); // 設定來源$referer = 'http://www.uxuew.cn/'; $response = doCurl($url, $data, $header, $referer, 5); echo $response;?>