【网络爬虫】Httpclient4.X中使用HTTPS的方法采集12306网站-优快云博客

本文提供了一个使用Java的HttpClient库发起HTTPS请求的具体示例。该示例通过自定义信任管理器来绕过证书验证，创建了SSL上下文，并注册到HttpClient中。文中详细展示了如何配置SSL连接工厂及设置HTTPS方案的过程。

HttpClient请求https的实例：

package train;

import java.io.IOException;
import java.security.NoSuchAlgorithmException;
import java.security.cert.CertificateException;
import java.security.cert.X509Certificate;

import javax.net.ssl.SSLContext;
import javax.net.ssl.TrustManager;
import javax.net.ssl.X509TrustManager;

import org.apache.http.client.ClientProtocolException;
import org.apache.http.client.HttpClient;
import org.apache.http.client.ResponseHandler;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.conn.ClientConnectionManager;
import org.apache.http.conn.scheme.Scheme;
import org.apache.http.conn.scheme.SchemeRegistry;
import org.apache.http.conn.ssl.SSLSocketFactory;
import org.apache.http.impl.client.BasicResponseHandler;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.params.HttpParams;

public class train {

    public static void main(String args[]) {

        try {

            HttpClient httpclient = new DefaultHttpClient();
            // Secure Protocol implementation.
            SSLContext ctx = SSLContext.getInstance("SSL");
            // Implementation of a trust manager for X509 certificates
            X509TrustManager tm = new X509TrustManager() {

                public void checkClientTrusted(X509Certificate[] xcs, String string) throws CertificateException {

                }

                public void checkServerTrusted(X509Certificate[] xcs, String string) throws CertificateException {
                }

                public X509Certificate[] getAcceptedIssuers() {
                    return null;
                }
            };
            ctx.init(null, new TrustManager[] { tm }, null);
            SSLSocketFactory ssf = new SSLSocketFactory(ctx);

            ClientConnectionManager ccm = httpclient.getConnectionManager();
            // register https protocol in httpclient's scheme registry
            SchemeRegistry sr = ccm.getSchemeRegistry();
            sr.register(new Scheme("https", 443, ssf));

            HttpGet httpget = new HttpGet(
                    "https://kyfw.12306.cn/otn/lcxxcx/query?purpose_codes=ADULT&queryDate=2016-08-23&from_station=BJP&to_station=TJP");
            HttpParams params = httpclient.getParams();

            System.out.println("Request URL:" + httpget.getURI());
            ResponseHandler responseHandler = new BasicResponseHandler();

            String responseBody = (String) httpclient.execute(httpget, responseHandler);
            

            System.out.println(responseBody);

            // Create a response handler

        } catch (NoSuchAlgorithmException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } catch (ClientProtocolException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } catch (Exception ex) {
            ex.printStackTrace();

        }
    }
}

转载于:https://www.cnblogs.com/zeze/p/5800087.html