CURL模拟登录、抓取页面数据

最新推荐文章于 2023-11-21 16:11:46 发布

原创最新推荐文章于 2023-11-21 16:11:46 发布 · 955 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#PHP #curl #模拟登录

PHP 同时被 2 个专栏收录

7 篇文章

订阅专栏

ThinkPHP3.2

1 篇文章

订阅专栏

本文介绍使用PHP进行模拟登录及抓取登录后页面内容的方法。通过curl和phpQuery库，实现设置登录表单参数、获取并设置验证码hash、保存和读取cookie，完成对特定网站的模拟登录流程，并获取登录后的页面信息。

<?php

require('phpQuery-master/phpQuery/phpQuery.php');

try {

    //模拟登录表单Fields
    $post = [
        'username' => '100000',
        'password' => '123456',
        'submit' => '登录'
    ];

    $login_url = "http://www.test.com/User/Auth/login";

    \phpQuery::newDocumentFile($login_url);

    //引入hash
    $post['__hash__'] = pq('input[name="__hash__"]')->val();

    $cookie = dirname(__FILE__) . '/cookie.conf';

    $url = "http://www.test.com/User/Profile/index";

    //调用模拟登录
    login_post($login_url, $cookie, $post);

    //登录后，调用get_content()函数获取登录后指定的页面信息
    $content = get_content($url, $cookie);

    var_dump($content);
} catch (\Exception $exception) {
    var_dump($exception);
}

//file_put_contents('save.txt', $content); //保存抓取的页面内容

//模拟登录
function login_post($url, $cookie, $post)
{
    $ch = curl_init();
    curl_setopt($ch, CURLOPT_URL, $url);
    curl_setopt($ch, CURLOPT_HEADER, 0);
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, 0);
    curl_setopt($ch, CURLOPT_COOKIEJAR, $cookie);
    curl_setopt($ch, CURLOPT_COOKIEFILE, $cookie);
    curl_setopt($ch, CURLOPT_POST, 1);
    curl_setopt($ch, CURLOPT_POSTFIELDS, http_build_query($post));
    //301等重定向
    //curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
    curl_setopt($ch, CURLOPT_USERAGENT, $_SERVER['HTTP_USER_AGENT']);
    curl_exec($ch);
    curl_close($ch);
}

//用cookie获取登陆后链接界面
function get_content($url, $cookie)
{
    $ch = curl_init();
    curl_setopt($ch, CURLOPT_URL, $url);
    curl_setopt($ch, CURLOPT_HEADER, 0);
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
    curl_setopt($ch, CURLOPT_COOKIEJAR, $cookie);
    curl_setopt($ch, CURLOPT_COOKIEFILE, $cookie);
    //301等重定向
    //curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
    curl_setopt($ch, CURLOPT_USERAGENT, $_SERVER['HTTP_USER_AGENT']);
    $rs = curl_exec($ch);
    curl_close($ch);
    return $rs;
}