抓取https网页时,报错sun.security.validator.ValidatorException: PKIX path building failed 解决办法...

抓取https网页时,报错sun.security.validator.ValidatorException: PKIX path building failed 解决办法

原因是https证书问题,java抓取时忽略掉证书才能访问。jsoup在调用前先执行下以下忽略证书请求就可以了。

try {
            //先调用下忽略https证书的再请求才可以
            HttpsUrlValidator.retrieveResponseFromServer(url); 
            doc = Jsoup
                    .connect(url)
                    .header("User-Agent",rand_agents)
                    .timeout(10000).get();
            body = doc.getElementsByTag("body").html();
        } catch (Exception e) {
            log.info(e.getMessage());
        }

HttpsUrlValidator 类:

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;

import javax.net.ssl.HostnameVerifier;
import javax.net.ssl.HttpsURLConnection;
import javax.net.ssl.SSLSession;


public class HttpsUrlValidator {

    static HostnameVerifier hv = new HostnameVerifier() {
        public boolean verify(String urlHostName, SSLSession session) {
            System.out.println("Warning: URL Host: " + urlHostName + " vs. "
                               + session.getPeerHost());
            return true;
        }
    };

    public final static String retrieveResponseFromServer(final String url) {
        HttpURLConnection connection = null;
        
        try {
            URL validationUrl = new URL(url);
            trustAllHttpsCertificates();
            HttpsURLConnection.setDefaultHostnameVerifier(hv);

            connection = (HttpURLConnection) validationUrl.openConnection();
            final BufferedReader in = new BufferedReader(new InputStreamReader(
                    connection.getInputStream()));

            String line;
            final StringBuffer stringBuffer = new StringBuffer(255);

            synchronized (stringBuffer) {
                while ((line = in.readLine()) != null) {
                    stringBuffer.append(line);
                    stringBuffer.append("\n");
                }
                return stringBuffer.toString();
            }

        } catch (final IOException e) {
            System.out.println(e.getMessage());
            return null;
        } catch (final Exception e1){
            System.out.println(e1.getMessage());
            return null;
        }finally {
            if (connection != null) {
                connection.disconnect();
            }
        }
    }
    
    public static void trustAllHttpsCertificates() throws Exception {
        javax.net.ssl.TrustManager[] trustAllCerts = new javax.net.ssl.TrustManager[1];
        javax.net.ssl.TrustManager tm = new miTM();
        trustAllCerts[0] = tm;
        javax.net.ssl.SSLContext sc = javax.net.ssl.SSLContext
                .getInstance("SSL");
        sc.init(null, trustAllCerts, null);
        javax.net.ssl.HttpsURLConnection.setDefaultSSLSocketFactory(sc
                .getSocketFactory());
    }

    static class miTM implements javax.net.ssl.TrustManager,
            javax.net.ssl.X509TrustManager {
        public java.security.cert.X509Certificate[] getAcceptedIssuers() {
            return null;
        }

        public boolean isServerTrusted(
                java.security.cert.X509Certificate[] certs) {
            return true;
        }

        public boolean isClientTrusted(
                java.security.cert.X509Certificate[] certs) {
            return true;
        }

        public void checkServerTrusted(
                java.security.cert.X509Certificate[] certs, String authType)
                throws java.security.cert.CertificateException {
            return;
        }

        public void checkClientTrusted(
                java.security.cert.X509Certificate[] certs, String authType)
                throws java.security.cert.CertificateException {
            return;
        }
    }

}

 

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 1
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 1
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