java 获取网页源码

为什么80%的码农都做不了架构师？>>>   

package gogo.cool;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;

public class test1 {

	public static void main(String[] a) throws IOException {

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

		System.out.println(getHTML(url, "gbk")); // 使用原网页里声明的gb2312反而会出现乱码

	}

	public static String getHTML(String pageURL, String encoding) {

		StringBuilder pageHTML = new StringBuilder();

		try {

			URL url = new URL(pageURL);

			HttpURLConnection connection = (HttpURLConnection) url
					.openConnection();

			connection.setRequestProperty("User-Agent", "MSIE 7.0");

			BufferedReader br = new BufferedReader(new InputStreamReader(
					connection.getInputStream(), encoding));

			String line = null;

			while ((line = br.readLine()) != null) {

				pageHTML.append(line);

				pageHTML.append("\r\n");

			}

			connection.disconnect();

		} catch (Exception e) {

			e.printStackTrace();

		}

		return pageHTML.toString();

	}
}

转载于:https://my.oschina.net/neo600/blog/62705