java爬虫--免登录,通过httpclient模拟登录并获取登录后的信息

以新安人才网为例
1、使用依赖
httpclient 进行http请求
jsoup 对html进行解析

 <dependency>
            <groupId>org.jsoup</groupId>
            <artifactId>jsoup</artifactId>
            <version>1.8.1</version>
        </dependency>
        <dependency>
            <groupId>commons-httpclient</groupId>
            <artifactId>commons-httpclient</artifactId>
            <version>3.0.1</version>
        </dependency>

2、具体实现如下

package com.ssjk.website.service.JsoupHtml;

import org.apache.commons.httpclient.Cookie;
import org.apache.commons.httpclient.HttpClient;
import org.apache.commons.httpclient.NameValuePair;
import org.apache.commons.httpclient.cookie.CookiePolicy;
import org.apache.commons.httpclient.cookie.CookieSpec;
import org.apache.commons.httpclient.methods.PostMethod;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;

import java.io.IOException;

/**
 * 爬取新安人才网信息
 */
public class XinAnRenCaiWang {
    private static final String SITE = "login.goodjobs.cn";
    private static final int PORT = 80;

    private static final String loginAction = "/index.php/action/UserLogin";
    private static final String forwardURL =
            "http://user.goodjobs.cn/dispatcher.php/module/Personal/";
    private static final String toUrl = "d:\\jsoup_test\\";
    private static final String hostCss = "d:\\jsoup_test\\style.txt";
    private static final String Img = "http://user.goodjobs.cn/images";
    private static final String _JS = "http://user.goodjobs.cn/scripts/fValidate/fValidate.one.js";
    /**
     * 模拟等录
     *
     * @param LOGON_SITE
     * @param LOGON_PORT
     * @param login_Action
     * @param params
     * @throws Exception
     */
    private static String[] loginHtml(String LOGON_SITE, int LOGON_PORT, String
            login_Action, String... params) throws Exception {
        String[] result=null;
        HttpClient client = new HttpClient();
        client.getHostConfiguration().setHost(LOGON_SITE, LOGON_PORT);
// 模拟登录页面
        PostMethod post = new PostMethod(login_Action);
        NameValuePair userName = new NameValuePair("memberName", params[0]);
        NameValuePair password = new NameValuePair("password", params[1]);
        post.setRequestBody(new NameValuePair[]{userName, password});
        client.executeMethod(post);
        System.out.println("执行状态:"+client.getState());
        post.releaseConnection();
// 查看 cookie 信息
        CookieSpec cookiespec = CookiePolicy.getDefaultSpec();
        Cookie[] cookies = cookiespec.match(LOGON_SITE, LOGON_PORT, "/", false,
                client.getState().getCookies());
        if (cookies != null)
            if (cookies.length == 0) {
                System.out.println("Cookies is not Exists ");
            } else {
                for (int i = 0; i < cookies.length; i++) {
                    System.out.println("----------------------------------------------------");
                    System.out.println(cookies[i].toString());
                    result = cookies[i].toString().split("=");
                    System.out.println("----------------------------------------------------");
                }
            }

            return result;
    }

    /**
     *
     * @param cookies
     * @return
     */
    public static Document getHtmlDocument(String[] cookies){
        try {
            Document doc = Jsoup.connect(forwardURL).cookie(cookies[0],cookies[1]).get();
            return doc;
        } catch (IOException e) {
            System.out.println("页面获取异常!");
            e.printStackTrace();
        }
        return null;
    }

    public static void main(String[] args) {
        String[] params = {"job17093123661", "2534133662qq"};
        String[] strings = null;
        try {
            strings = loginHtml(SITE, PORT, loginAction, params);
            if(strings.length>0){
                Document htmlDocument = getHtmlDocument(strings);
                System.out.println(htmlDocument);
            }

        } catch (Exception e) {
            e.printStackTrace();
        }

    }
}
  • 0
    点赞
  • 15
    收藏
    觉得还不错? 一键收藏
  • 3
    评论
评论 3
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值