java http url 编码_java自动检测获取http请求URL地址的网页内容编码工具类

package com.zuidaima.encoding.util;

import java.io.BufferedInputStream;

import java.io.InputStream;

import java.net.HttpURLConnection;

import java.net.URL;

import org.apache.http.util.ByteArrayBuffer;

import org.apache.http.util.EncodingUtils;

import org.junit.Test;

public class Main {

@Test

public void testZuidaima() throws Exception {

String url = "http://www.zuidaima.com/";

String html = parseHttpEncoding(url);

System.out.println(html);

}

@Test

public void testBaidu() throws Exception {

String url = "http://www.baidu.com/";

String html = parseHttpEncoding(url);

System.out.println(html);

}

@Test

public void testSinaGBK() throws Exception {

String url = "http://www.sina.com.cn/";

String html = parseHttpEncoding(url);

System.out.println(html);

}

@Test

public void testSinaJp() throws Exception {

String url = "http://sina.jp/";

String html = parseHttpEncoding(url);

System.out.println(html);

}

@Test

public void testGov() throws Exception {

String url = "http://www.gov.cn/";

String html = parseHttpEncoding(url);

System.out.println(html);

}

@Test

public void testBeijingGov() throws Exception {

String url = "http://www.beijing.gov.cn/";

String html = parseHttpEncoding(url);

System.out.println(html);

}

public String parseHttpEncoding(String url) throws Exception {

BytesEncodingDetect bytesEncodingDetect = new BytesEncodingDetect();

HttpURLConnection conn = null;

URL serverUrl = new URL(url);

conn = (HttpURLConnection) serverUrl.openConnection();

conn.setInstanceFollowRedirects(false);

conn.setRequestMethod("GET");

conn.setConnectTimeout(10000);

conn.setReadTimeout(10000);

conn.connect();

InputStream ins = conn.getInputStream();

String charset = "utf-8";

BufferedInputStream bis = new BufferedInputStream(ins);

ByteArrayBuffer baf = new ByteArrayBuffer(bis.available());

int data = 0;

while ((data = bis.read()) != -1) {

baf.append((byte) data);

}

int encodingGuess = bytesEncodingDetect.detectEncoding(baf

.toByteArray());

charset = BytesEncodingDetect.htmlname[encodingGuess];

String html = EncodingUtils.getString(baf.toByteArray(), charset); // 转换为字符串

conn.disconnect();

System.out.println(url + ":" + charset);

return html;

}

}

评论
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