抓取https網頁時,報錯sun.security.validator.ValidatorException: PKIX path building failed 解決辦法 原因是https證書問題,java抓取時忽略掉證書才能通路。jsoup在調用前先執行下以下忽略證書請求就可以了。
抓取https網頁時,報錯sun.security.validator.ValidatorException: PKIX path building failed 解決辦法
try {
//先調用下忽略https證書的再請求才可以
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());
}
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;
}
}
}
大自然,飄然的風,QQ群: python技術交流群:453879716,人工智能深度學習群:251088643
golang技術交流群:316397059,vuejs技術交流群:458915921 滲透技術:534096581,囤币一族:621258209,有興趣的可以加入
微信公衆号:, 心禅道(xinchandao)