HTTPCLIENT 基本应用 解决编码乱码问题

先看代码，方便以后复制，就不作为code格式了。

package com.amazon.commons;

import java.io.IOException;
import java.util.HashMap;
import java.util.Map;

import org.apache.commons.httpclient.DefaultHttpMethodRetryHandler;
import org.apache.commons.httpclient.HttpClient;
import org.apache.commons.httpclient.HttpException;
import org.apache.commons.httpclient.HttpStatus;
import org.apache.commons.httpclient.methods.GetMethod;
import org.apache.commons.httpclient.methods.PostMethod;
import org.apache.commons.httpclient.params.HttpMethodParams;

public class HttpClientHelper {
public static String RESPONSE_TEXT="responseText";
public static String CHARSET="charset";

public static void main(String[] args) {
System.out.println(get("http://www.baidu.com/").get(HttpClientHelper.RESPONSE_TEXT));
}

public static Map<String, String> get(String url) {
Map<String, String> result=new HashMap<String, String>();
// Create an instance of HttpClient.

HttpClient client = new HttpClient();



// Create a method instance.

GetMethod method = new GetMethod(url);

// Provide custom retry handler is necessary

method.getParams().setParameter(HttpMethodParams.RETRY_HANDLER,

new DefaultHttpMethodRetryHandler(3, false));


try {

// Execute the method.

int statusCode = client.executeMethod(method);
String charset=method.getResponseCharSet();
System.out.println(charset);
method.getParams().setParameter(HttpMethodParams.HTTP_CONTENT_CHARSET, charset);

if (statusCode != HttpStatus.SC_OK) {

System.err.println("Method failed: " + method.getStatusLine());

}

// Read the response body.

/**
* Note: This will cause the entire response body to be buffered in memory.
* A malicious server may easily exhaust all the VM memory.
* It is strongly recommended, to use getResponseAsStream if the content
* length of the response is unknown or resonably large.
*/
byte[] responseBody = method.getResponseBody();

// Deal with the response.

// Use caution: ensure correct character encoding and is not binary
// data

result.put(HttpClientHelper.RESPONSE_TEXT, new String(responseBody,charset));
result.put(HttpClientHelper.CHARSET, charset);

} catch (HttpException e) {

System.err.println("Fatal protocol violation: " + e.getMessage());

e.printStackTrace();

} catch (IOException e) {

System.err.println("Fatal transport error: " + e.getMessage());

e.printStackTrace();

} finally {

// Release the connection.

method.releaseConnection();
return result;
}

}

}

查看控制台我们可以看到，百度的页面编码设置是gb2312.

核心代码：

int statusCode = client.executeMethod(method);
			String charset=method.getResponseCharSet();
			System.out.println(charset);
			method.getParams().setParameter(HttpMethodParams.HTTP_CONTENT_CHARSET, charset);
result.put(HttpClientHelper.RESPONSE_TEXT, new String(responseBody,charset));
			result.put(HttpClientHelper.CHARSET, charset);

这里我之所以把charset作为一个返回参数是有原因的，因为在action或者servlet调用完这个之后如果只返回一个responseText,那么response在打印输出的时候是不知道这段text的编码的，
action代码：

try {
		  	HttpServletResponse response=	ServletActionContext.getResponse();
		  	response.setCharacterEncoding(result.get(HttpClientHelper.CHARSET));
		  	PrintWriter writer=response.getWriter();
		  	writer.write(result.get(HttpClientHelper.RESPONSE_TEXT));
		  	writer.close();
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}

response.setCharacterEncoding(result.get(HttpClientHelper.CHARSET));这句话不设置就可能导致乱码。