使用jsoup去解析历史在今天的html内容

package com.test;

import java.net.URL;

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

/**
*@Author:liangjilong
*@Date:2014-2-27
*@Version:1.0
*@Description:
*/
public class Test1 {

	public static void main(String[] args) throws Exception{
		
		String url="http://www.todayonhistory.com/";
		
		URL _url=new URL(url);
		Document doc=Jsoup.parse(_url, 3000);
		//从class=gong样式下面抓取
		Elements lists = doc.getElementsByAttributeValue("class", "gong");
		 
		for(Element e:lists){
			System.out.println(e.select("em").html()+e.select("i").html());
		}
	}
}

 

package com.test;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
/**
*@Author:liangjilong
*@Date:2014-2-27
*@Version:1.0
*@Description:
*/
public class Test {

	/**
	 * @param args
	 */
	public static void main(String[] args) throws Exception {

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

		Document doc = Jsoup.connect(url).get();
		if (doc != null) {
			// 取出div的class="listren"的所有内容
			Elements listrens = doc.getElementsByAttributeValue("class", "listren");
			for (Element listren : listrens) {
				String text = listren.select("li").select("a").html();
				System.out.println(text);
			}
		} else {
			System.err.println("网络出异常！");
		}
	}
}