Java解析网页内容简单实例

package com.webkfa.test;

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

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

/**
 * web开发技术提供
 * 网址:
 * http://www.webkfa.com
 */
   
public class Test {
	/**
	 * Java解析网页内容简单实例
	 * @param args
	 * @throws IOException
	 */
    public static void main(String[] args) throws IOException {
    	String url="http://www.webkfa.com";
    	String html=getHtmlContext(url).toString();
    	System.out.println(html);
    	Document doc =Jsoup.parse(html);
    	Elements links =doc.getElementsByTag("a");
    	for (Element link : links) { 
    	     String linkHref = link.attr("href"); 
    	     String linkText = link.text();
    	     System.out.println(linkHref);
    	     System.out.println(linkText);
    	}
    }
    /**
	 * 得到http内容
	 * @param hpath
	 * @return
	 * @throws IOException
	 */
	public static StringBuffer getHtmlContext(String hpath) throws IOException{
		StringBuffer bf=new StringBuffer();
		HttpURLConnection httpUrl = null;
		URL uobj = new URL(hpath);
		httpUrl = (HttpURLConnection) uobj.openConnection();
		httpUrl.connect();
		InputStream is = httpUrl.getInputStream();
		InputStreamReader isr = new InputStreamReader(is,"utf-8");
		BufferedReader br = new BufferedReader(isr);
		String line = null;
		while( (line = br.readLine()) != null ){
			bf.append(line+"\r\n");
		}
		br.close();
		isr.close();
		is.close();
		
		return bf;
	}
}