使用CharBuffer和 InputStreamReader读取各种编码的网页

只要指明编码格式，就能正确的读取。

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.URL;
import java.nio.CharBuffer;

public class PageParser {

	public static void main(String args[]) {
		BufferedReader in = null;
		try {
			in = new BufferedReader(new InputStreamReader(new URL(
					"http://news.cnool.net/0-1-19/35941/3.html").openStream(),
					"utf-8"));
		} catch (Exception e2) {
			e2.printStackTrace();
		}
		CharBuffer bos = CharBuffer.allocate(20480);
		int read = 0;
		StringBuilder sb = new StringBuilder();
		try {
			while (in.read(bos) != -1) {
				bos.flip();
				sb.append(bos.toString());
			}
		} catch (IOException e1) {
			e1.printStackTrace();
		}
		System.out.println(sb.toString());
	}
}