2014年12月9日 星期二

curl半人工方式解決驗證碼問題

如果有比較複雜的驗證碼沒辦法用curl擷取資料時,發現有個網站提供另一個思路解決問題,雖然有點麻煩,但也是方法之一....

/**
 * 模拟登录
 * Design by maben 
 */

//初始化变量
$cookie_file = "tmp.cookie";
$login_url = "http://xxx.com/logon.php";
$verify_code_url = "http://xxx.com/verifyCode.php";

echo "正在获取COOKIE...\n";
$curlj = curl_init();
$timeout = 5;
curl_setopt($curl, CURLOPT_URL, $login_url);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($curl, CURLOPT_CONNECTTIMEOUT, $timeout);
curl_setopt($curl,CURLOPT_COOKIEJAR,$cookie_file); //获取COOKIE并存储
$contents = curl_exec($curl);
curl_close($curl);

echo "COOKIE获取完成,正在取验证码...\n";
//取出验证码
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $verify_code_url);
curl_setopt($curl, CURLOPT_COOKIEFILE, $cookie_file);
curl_setopt($curl, CURLOPT_HEADER, 0);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
$img = curl_exec($curl);
curl_close($curl);

$fp = fopen("verifyCode.jpg","w");
fwrite($fp,$img);
fclose($fp);
echo "验证码取出完成,正在休眠,20秒内请把验证码填入code.txt并保存\n";
//停止运行20秒
sleep(20);

echo "休眠完成,开始取验证码...\n";
$code = file_get_contents("code.txt");
echo "验证码成功取出:$code\n";
echo "正在准备模拟登录...\n";

$post = "username=xxx&pwd=xxx&verifycode=$code";
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_HEADER, false);
curl_setopt($curl, CURLOPT_RETURNTRANSFER,1);
curl_setopt($curl, CURLOPT_POSTFIELDS, $post);
curl_setopt($curl, CURLOPT_COOKIEFILE, $cookie_file);
$result=curl_exec($curl);
curl_close($curl);

if(substr_count($result,"登录成功")){
 echo "登录成功\n";
}else{
 echo "登录失败\n";
 exit;
}

沒有留言:

張貼留言