HttpClient解析页面总结

最新推荐文章于 2024-10-10 09:56:47 发布

weixin_34124651

最新推荐文章于 2024-10-10 09:56:47 发布

阅读量187

点赞数

文章标签： javascript java ViewUI

原文链接：http://blog.51cto.com/3157689/1126415

版权

1、遇到安全控件证书（单向和双向认证）

//安全证书的处理
Protocol myhttps = new Protocol("https",
new MySecureProtocolSocketFactory(), 443);
Protocol.registerProtocol("https", myhttps);

package com.bwzy.jiaotongyunguan.util;
import java.io.IOException;
import java.net.InetAddress;
import java.net.InetSocketAddress;
import java.net.Socket;
import java.net.SocketAddress;
import java.net.UnknownHostException;
import java.security.KeyManagementException;
import java.security.NoSuchAlgorithmException;
import java.security.cert.CertificateException;
import java.security.cert.X509Certificate;
import javax.net.SocketFactory;
import javax.net.ssl.SSLContext;
import javax.net.ssl.TrustManager;
import javax.net.ssl.X509TrustManager;
import org.apache.commons.httpclient.ConnectTimeoutException;
import org.apache.commons.httpclient.params.HttpConnectionParams;
import org.apache.commons.httpclient.protocol.SecureProtocolSocketFactory;
public class MySecureProtocolSocketFactory implements SecureProtocolSocketFactory {
static{
System.out.println(">>>>in MySecureProtocolSocketFactory>>");
}
private SSLContext sslcontext = null;
private SSLContext createSSLContext() {
SSLContext sslcontext=null;
try {
sslcontext = SSLContext.getInstance("SSL");
sslcontext.init(null, new TrustManager[]{new TrustAnyTrustManager()}, new java.security.SecureRandom());
} catch (NoSuchAlgorithmException e) {
e.printStackTrace();
} catch (KeyManagementException e) {
e.printStackTrace();
}
return sslcontext;
}
private SSLContext getSSLContext() {
if (this.sslcontext == null) {
this.sslcontext = createSSLContext();
}
return this.sslcontext;
}
public Socket createSocket(Socket socket, String host, int port, boolean autoClose)
throws IOException, UnknownHostException {
return getSSLContext().getSocketFactory().createSocket(
socket,
host,
port,
autoClose
);
}
public Socket createSocket(String host, int port) throws IOException,
UnknownHostException {
return getSSLContext().getSocketFactory().createSocket(
host,
port
);
}
public Socket createSocket(String host, int port, InetAddress clientHost, int clientPort)
throws IOException, UnknownHostException {
return getSSLContext().getSocketFactory().createSocket(host, port, clientHost, clientPort);
}
public Socket createSocket(String host, int port, InetAddress localAddress,
int localPort, HttpConnectionParams params) throws IOException,
UnknownHostException, ConnectTimeoutException {
if (params == null) {
throw new IllegalArgumentException("Parameters may not be null");
}
int timeout = params.getConnectionTimeout();
SocketFactory socketfactory = getSSLContext().getSocketFactory();
if (timeout == 0) {
return socketfactory.createSocket(host, port, localAddress, localPort);
} else {
Socket socket = socketfactory.createSocket();
SocketAddress localaddr = new InetSocketAddress(localAddress, localPort);
SocketAddress remoteaddr = new InetSocketAddress(host, port);
socket.bind(localaddr);
socket.connect(remoteaddr, timeout);
return socket;
}
}
//自定义私有类
private static class TrustAnyTrustManager implements X509TrustManager {
public void checkClientTrusted(X509Certificate[] chain, String authType) throws CertificateException {
}
public void checkServerTrusted(X509Certificate[] chain, String authType) throws CertificateException {
}
public X509Certificate[] getAcceptedIssuers() {
return new X509Certificate[]{};
}
}
}

所需要的jar包有commons-httpclient-3.1.jar、 commons-codec-1.7.jar 、httpcore.jar、commons-logging.jar

HttpClient相当于一个浏览器（但不支持javascript脚本）

//创建一个HttpClient

HttpClient client = new HttpClient();

//已某种方式发出请求（7中请求方式包括：Get、post、head……），接下来以Get和post来说明问题。

//创建一个请求方式

GetMethod get = new GetMethod(url);

//其中Url是访问的网址（解析的目标）,如果你解析百度首页String url="http://www.baidu.com"

//通过client的该方法来发出请求，参数是请求的方式。

client.executeMethode(get);

//执行之后调用method的方法来获取client的响应。

get.getResponseBodyAsString();

//这样就可以得到百度页面的HTML代码，你可以从代码中获取你所需要的数据。

//如果你的请求指向的是一个文件，如word文档。你可以以流的方式获取。

get.getResponseBodyAsStream();

//请求方式有一些方法，能获取和修改请求头和相应头的信息，还可以设置一些编码方式。接下来是一段获取流的代码。

get.setURI(new URI(url, false, "gb2312"));
httpClient.executeMethod(get);
InputStream in = get.getResponseBodyAsStream();
ByteArrayOutputStream outStream = new ByteArrayOutputStream();
int b = 0;
while ((b = in.read()) != -1) {
outStream.write(b);
}
byte[] bytes = outStream.toByteArray();
long tempLong = System.currentTimeMillis();
String[] paths = PdfConverterServlet.class.getClassLoader().getResource("/").getPath().split("/");
String path ="";
for (int i = 1; i < paths.length-2; i++) {
path+=paths[i]+"/";
}
System.out.println(path);
OutputStream out = new FileOutputStream(new File(path+"fileTemp/",
tempLong + ".doc"));
out.write(bytes);
out.close();