java 网络爬虫使用httpclient4 https连接认证问题，求各位大神帮帮忙，急！！！

发布于 2021-11-18 22:31:44 字数 5981 浏览 721 评论 2

详细代码：

---1、入口login1 传入一个url，获取验证身份，第一个url为http://****.com

public static void login1(String url,int ***){
HttpClient httpClient = new DefaultHttpClient(new ThreadSafeClientConnManager());
HttpClientParams.setCookiePolicy(httpClient.getParams(),
CookiePolicy.BROWSER_COMPATIBILITY);
HttpHost httpHost = new HttpHost("***.com");
HttpGet httpGet = new HttpGet(url);
HttpResponse response = null;
try {
response = httpClient.execute(httpHost, httpGet);
} catch (ClientProtocolException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
if (HttpStatus.SC_OK == response.getStatusLine().getStatusCode()) {
// 请求成功
// 取得请求内容
HttpEntity entity = response.getEntity();
// 显示内容
if (entity != null) {
// 显示结果
try {
// EntityUtils.toString(entity, "utf-8");
// System.out.println("login1::::::"+html);
// httpConsume(response,httpGet,httpClient);
} catch (ParseException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
getTxlinfo(httpClient);
}
}
2、加载完第一个url，将当前httpclient传给下个处理单元

private static void getTxlinfo(HttpClient httpClient){

// HttpClient httpClient = new DefaultHttpClient();

httpClient = wrapClient(httpClient);//此处将当前httpClient传给warpClient处理，转换请求模式https，自动加载证书

HttpClientParams.setCookiePolicy(httpClient.getParams(),
CookiePolicy.BROWSER_COMPATIBILITY);
HttpHost httpHost = new HttpHost("***.com");
HttpGet httpGet = new HttpGet("https://***.com/**/contact.jsp");
HttpResponse response = null;

try {
response = httpClient.execute(httpHost, httpGet);
} catch (ClientProtocolException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
if (HttpStatus.SC_OK == response.getStatusLine().getStatusCode()) {
// 请求成功
// 取得请求内容
HttpEntity entity = response.getEntity();
// 显示内容
if (entity != null) {
// 显示结果
try {
String html;
try {
html = EntityUtils.toString(entity, "utf-8");
System.out.println("login1::::::"+html);
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
httpConsume(response,httpGet,httpClient);
} catch (ParseException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}

}

private static void httpConsume(HttpResponse response,HttpGet httpGet,HttpClient httpClient)
{
try {
EntityUtils.consume(response.getEntity());
} catch (IOException e) {
e.printStackTrace();
}
httpGet.abort();
httpGet = null;
httpClient = null;
}

/**
* 传入一个当前的httpclient，返回一个https的httpclient
*/
public static HttpClient wrapClient(HttpClient base) {
try {
SSLContext ctx = SSLContext.getInstance("TLS");
X509TrustManager tm = new X509TrustManager() {
public X509Certificate[] getAcceptedIssuers() {
return null;
}
@Override
public void checkClientTrusted(X509Certificate[] arg0, String arg1) throws CertificateException {}
@Override
public void checkServerTrusted(X509Certificate[] arg0, String arg1) throws CertificateException {}

};
ctx.init(null, new TrustManager[] { tm }, null);
SSLSocketFactory ssf = new SSLSocketFactory(ctx, SSLSocketFactory.ALLOW_ALL_HOSTNAME_VERIFIER);
SchemeRegistry registry = new SchemeRegistry();
registry.register(new Scheme("https", 443, ssf));
ThreadSafeClientConnManager mgr = new ThreadSafeClientConnManager(registry);
return new DefaultHttpClient(mgr, base.getParams());
} catch (Exception ex) {
ex.printStackTrace();
return null;
}
}

程序执行抛出异常信息：

org.apache.http.client.ClientProtocolException
at org.apache.http.impl.client.AbstractHttpClient.execute(AbstractHttpClient.java:822)
at org.apache.http.impl.client.AbstractHttpClient.execute(AbstractHttpClient.java:776)
at https.getTxl.getTxlinfo(getTxl.java:156)
at https.getTxl.login1(getTxl.java:140)
at https.getTxl.getDBdata(getTxl.java:77)
at https.getTxl.main(getTxl.java:39)
Caused by: org.apache.http.HttpException: Scheme 'http' not registered.
at org.apache.http.impl.conn.DefaultHttpRoutePlanner.determineRoute(DefaultHttpRoutePlanner.java:115)
at org.apache.http.impl.client.DefaultRequestDirector.determineRoute(DefaultRequestDirector.java:721)
at org.apache.http.impl.client.DefaultRequestDirector.execute(DefaultRequestDirector.java:358)
at org.apache.http.impl.client.AbstractHttpClient.execute(AbstractHttpClient.java:820)
... 5 more
Exception in thread "main" java.lang.NullPointerException
at https.getTxl.getTxlinfo(getTxl.java:162)
at https.getTxl.login1(getTxl.java:140)
at https.getTxl.getDBdata(getTxl.java:77)
at https.getTxl.main(getTxl.java:39)