Java爬虫——模拟登录知乎

 

登录界面，首先随意输入一个账号，登录查看发送表单的请求

 

 可以发现请求是Post : https://www.zhihu.com/login/phone_num

发送的表单是

_xsrf: 
password: 密码  无需加密
captcha: 验证码  无需验证码时为不用此项 ，需要验证码时为验证码图片倒立字体坐标
captcha_type:cn
phone_num: 账号

package 知乎模拟登录;

import org.apache.http.HttpEntity;
import org.apache.http.NameValuePair;
import org.apache.http.client.entity.UrlEncodedFormEntity;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpPost;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.message.BasicNameValuePair;
import org.apache.http.protocol.HTTP;
import org.apache.http.util.EntityUtils;

import java.util.ArrayList;
import java.util.List;

public class GetProblem {
    public static void main(String[] args) throws Exception {
        CloseableHttpClient closeableHttpClient = HttpClients.createDefault() ;
        HttpPost httpPost = new HttpPost("https://www.zhihu.com/login/phone_num") ;
        List<NameValuePair> nvps = new ArrayList<NameValuePair>();
        nvps.add(new BasicNameValuePair("_xsrf", "66653239623962342d396237632d346233332d396331362d333434386438326438616139"));
        nvps.add(new BasicNameValuePair("password", "33665511886622"));
        nvps.add(new BasicNameValuePair("captcha_type", "cn"));
        nvps.add(new BasicNameValuePair("phone_num", "15890956765"));

        httpPost.setEntity(new UrlEncodedFormEntity(nvps));
        CloseableHttpResponse closeableHttpResponse = closeableHttpClient.execute(httpPost) ;
        HttpEntity entity = closeableHttpResponse.getEntity() ;
        String s = EntityUtils.toString(entity);
        System.out.println(s);
    }
} 

   可能出现的情况

   请求返回体为：

　　　　{

　　"r": 1,
　　"errcode": 1991829,
　　"data": {"captcha":"\u9a8c\u8bc1\u7801\u9519\u8bef"},
　　"msg": "\u9a8c\u8bc1\u7801\u9519\u8bef"
　}

"errcode": 1991829