php 模拟登陆（不带验证码）采集数据

Posted 2020-10-18 学无边涯

这里模拟表单登陆窗口

提交代码部分

1，生成session_id保存到 cookie

$login_url = \'http://www.96net.com.cn/Login.php\';
$cookie_file = dirname(__FILE__)."/pic.cookie";

$ch = curl_init();

curl_setopt($ch, CURLOPT_URL, $login_url);

curl_setopt($ch, CURLOPT_HEADER, 0);

curl_setopt($ch, CURLOPT_RETURNTRANSFER,1);

curl_setopt($ch, CURLOPT_COOKIEJAR, $cookie_file);

curl_exec($ch);

curl_close($ch);

2,处理提交的登陆的数据

if($_POST[\'acti\']==\'tj\'){

    $userid=$_POST[\'userid\'];
    $password=$_POST[\'password\'];

    $_post_url = \'http://www.96net.com.cn/login.php?action=Login\';     //登录表单提交地址

    $post = "userid=$userid&password=$password";

    $ch12 = curl_init();

    curl_setopt($ch12, CURLOPT_URL, $_post_url);

    curl_setopt($ch12, CURLOPT_HEADER, false);

    curl_setopt($ch12, CURLOPT_RETURNTRANSFER,1);

    curl_setopt($ch12, CURLOPT_POSTFIELDS, $post);         //提交方式为post

    curl_setopt($ch12, CURLOPT_COOKIEFILE, $cookie_file);

    curl_exec($ch12);

    curl_close($ch12);

   //以上表示登陆成功
   //以下开始采集数据
 

$data_url19 = "http://www.96net.com.cn/xxxxxxx.php?id=10";     //数据所在地址

$ch19 = curl_init();

curl_setopt($ch19, CURLOPT_URL, $data_url19);

curl_setopt($ch19, CURLOPT_HEADER, false);

curl_setopt($ch19, CURLOPT_HEADER, 0);

curl_setopt($ch19, CURLOPT_RETURNTRANSFER, true);

curl_setopt($ch19, CURLOPT_COOKIEFILE, $cookie_file);

$content12 = curl_exec($ch19);

file_put_contents("./content0/31-35/net" . $k . ".txt", $content12); //文件存放的位置

}