需求是這樣的,需要登錄帶驗證碼的網站,獲取數據,但是不可能人為一直去記錄數據,想通過自動采集的方式進行,如下是試驗出來的結果代碼!有需要的可以參考下!
<?php namespace Home\Controller; use Think\Controller; class LoginController extends Controller { protected $cookieName = array('cookie_verify', 'cookie_verify'); protected $cookiePath = '/cookie/'; protected $cookiePathFile = array(); public function index() { $this->display(); } public function _initialize(){ foreach($this->cookieName as $key => $name) { $this->cookiePathFile[] = ROOT_PATH . $this->cookiePath . $this->cookieName[$key] . '_xxx.txt'; } } /** * 登錄xxx */ public function xxxLogin() { $username = I('username'); $password = I('password'); $verifyCode = I('verify'); $loginData = array( '__VIEWSTATE' => '/wEPDwUKMTU0MzAzOTU4NmQYAQUeX19Db250cm9sc1JlcXVpcmVQb3N0QmFja0tleV9fFgEFDExvZ2luX1N1Ym1pdL/yae69NsY163G3yuP0lxjz8oXu', //不把參數補全可能會不被響應哦 '__VIEWSTATEGENERATOR' => 'DC42DE27', 'txt_UserName' => $username, 'txt_PWD' => $password, 'txt_VerifyCode' => $verifyCode, 'SMONEY' => 'ABC', 'Login_Submit.x' => '52', 'Login_Submit.y' => '19', ); $getBack = $this->_cookieRequest('http://xxx.com/noLogin.aspx', $loginData); if(preg_match('/<div[^\<div]*?id\s*=\s*[\'\"]{1}div_msg[\'\"]{1}.*?>(.*?)<\/div>/s', $getBack, $match)){ echo 'matched\r\n'; print_r($match); }else{ echo $getBack, '<br />'; $paramsFull = parse_url($getBack); parse_str($paramsFull['query'], $paramsFull['parsedQuery']); if(!empty($paramsFull['parsedQuery']['Warn'])) { $msg = "您好,歡迎來P,請先登錄。"; switch ($paramsFull['parsedQuery']['Warn']) { case '2': $msg = '您輸入的驗證碼錯誤,請重試'; break; case '3': $msg = '該帳號不存在,還沒帳號?'; break; case '5': $msg = '賬戶已注銷'; break; case '6': $msg = '密碼錯誤,如果連續錯誤3次半小時內不能登錄!'; break; case '20': $msg = '今日密碼錯誤3次及以上,請於半小時後再來登錄!'; break; case '21': $msg = '今日您所在IP的所有帳號密碼錯誤9次以上,請於半小時後再來登錄!'; break; case '22': $msg = '登錄失敗,您所在IP今日登錄的帳號過多!'; break; case '23': $msg = '登錄失敗,驗證碼失效!'; break; case '32': $msg = '該帳號已經綁定其他xx帳號!'; break; case '33': $msg = '一台電腦一天只能注冊一個帳號!'; break; } $this->error($msg, '', 5); }else{ $_SESSION['user_id'] = '123456'; //登錄設置session $this->success('登錄P網站成功', U('Index/index'), 5); } } } /** * 獲取驗證碼 */ public function getVerifyCode() { $img = $this->_cookieRequest('http://xxx.com/VerifyCode_Login.aspx?id=' . rand(10000,999999), null, true, 1); echo $img; } /** * 刪除cookie */ public function clearCookie() { for($i = 0; $i <count($this->cookieName); $i++) { setcookie($this->cookieName[$i], '', time() - 3600); } // unlink($this->cookiePathFile); $this->success('清除cookie成功!'); } /** * 帶COOKIE的訪問curl * @param $url 訪問地址 * @param bool|array $data 傳遞的數據 * @param bool $redirect 是否獲取重定向的地址 * @return mixed 地址或者返回內容 */ public function _cookieRequest($url, $data = null, $redirect = false, $cookieNum = 0) { $ch = curl_init(); $params[CURLOPT_URL] = $url; //請求url地址 $params[CURLOPT_HEADER] = false; //是否返回響應頭信息 $params[CURLOPT_RETURNTRANSFER] = true; //是否將結果返回 $params[CURLOPT_FOLLOWLOCATION] = true; //是否重定向 $params[CURLOPT_USERAGENT] = 'Mozilla/5.0 (Windows NT 5.1; rv:9.0.1) Gecko/20100101 Firefox/9.0.1'; if($data) { $params[CURLOPT_POST] = true; $params[CURLOPT_POSTFIELDS] = http_build_query($data); } //判斷是否有cookie,有的話直接使用 if (!empty($_COOKIE[$this->cookieName[$cookieNum]]) && is_file($this->cookiePathFile[$cookieNum])) { $params[CURLOPT_COOKIEFILE] = $this->cookiePathFile[$cookieNum]; //這裡判斷cookie } else { // $cookie_jar = tempnam($cookie_path, 'cookie'); //產生一個cookie文件 $params[CURLOPT_COOKIEJAR] = $this->cookiePathFile[$cookieNum]; //寫入cookie信息 setcookie($this->cookieName[$cookieNum], $this->cookiePathFile[$cookieNum], time() + 120); //保存cookie路徑 } curl_setopt_array($ch, $params); //傳入curl參數 $content = curl_exec($ch); $headers = curl_getinfo($ch); // echo $content; curl_close($ch); if ($url != $headers["url"] && $redirect == false) { return $headers["url"]; } return $content; } }
登錄以後,就可以使用帶cookie的訪問其他頁面了!