[javase]Java里面的java.net.url类介绍

最新推荐文章于 2023-10-11 09:09:30 发布

转载最新推荐文章于 2023-10-11 09:09:30 发布 · 724 阅读

javase 专栏收录该内容

16 篇文章

订阅专栏

本文介绍如何使用Java语言解析URL并获取网页内容，包括URL的打开、数据读取及关闭等操作。

原文地址

http://webservices.ctocio.com.cn/java/128/9331628.shtml

import java.io.BufferedInputStream;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.Reader;
import java.net.URL;
import java.net.URLConnection;

public class NetUtils {
	/**
	 * @param urls
	 * @exception IOException
	 * @see: 读一个URL的数据直到下一个字节为空。其中InputStream 类里面的read() 表示读取下一个字节的
	 */
	public void urlparse(String urls) throws IOException {
		URL url = new URL(urls);
		URLConnection uc = url.openConnection();
		InputStream in = uc.getInputStream();
		int c;
		while ((c = in.read()) != -1) {
			System.out.println(c);
		}
		in.close();
	}

	/**
	 * @param URL
	 * @see 读取URL所指定的网页内容
	 */
	public void urlparses(String urls) throws IOException {
		URL url = new URL(urls);
		Reader reader = new InputStreamReader(new BufferedInputStream(url
				.openStream()));
		int c;
		while ((c = reader.read()) != -1) {
			System.out.println((char) c);
		}
		reader.close();
	}

	/**
	 * 抓取指定URL地址的网页内容值并返回内容
	 */

	public String parseContent(String urls) throws IOException {
		URL url = new URL(urls);
		BufferedReader br = new BufferedReader(new InputStreamReader(url
				.openStream()));
		String s = "";
		StringBuffer sb = new StringBuffer("");
		while ((s = br.readLine()) != null) {
			sb.append(s + "rn");
		}
		br.close();
		return sb.toString();
	}

	public static void main(String[] args) {
		try {
			System.out.println(new NetUtils()
					.parseContent("http://www.sina.cn"));
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
	}
}