简单HTTP抓取网页内容

最新推荐文章于 2021-09-09 17:31:53 发布

iteye_19207

最新推荐文章于 2021-09-09 17:31:53 发布

阅读量147

点赞数

分类专栏： JTOEE 文章标签： Java .net

本文链接：https://blog.csdn.net/iteye_19207/article/details/82064480

版权

JTOEE 专栏收录该内容

3 篇文章 0 订阅

订阅专栏


package com.test;

import java.io.BufferedReader;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
public class TestHttp {

	public static void main(String[] args) throws Exception {

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

		HttpURLConnection urlConnection = null;
		URL url = new URL(urlString);
		urlConnection = (HttpURLConnection) url.openConnection();
		urlConnection.setRequestMethod("GET");
		urlConnection.setDoOutput(true);
		urlConnection.setDoInput(true);
		urlConnection.setUseCaches(false);
		InputStream in = urlConnection.getInputStream();
		BufferedReader bufferedReader = new BufferedReader(
				new InputStreamReader(in));
		StringBuffer temp = new StringBuffer();
		String line = bufferedReader.readLine();
		while (line != null) {
			temp.append(line);
			line = bufferedReader.readLine();
		}
		bufferedReader.close();
		String ecod = urlConnection.getContentEncoding();
		if (ecod == null)
			ecod = "UTF-8";
		String result = new String(temp.toString().getBytes(), ecod);
		System.out.println(result);
	}
}