java爬虫

package com.train.monitoring.Reptile_mobile_monitoring.util;

import java.io.IOException;

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

public class Spider {
	/**
	 * 
	 * @param url
	 *            访问路径
	 * @return
	 */
	public Document getDocument(String url) {
		try {
			// 5000是设置连接超时时间，单位ms
			return Jsoup.connect(url).timeout(5000).get();
		} catch (IOException e) {
			e.printStackTrace();
		}
		return null;
	}

	public static void main(String[] args) {

		Spider t = new Spider();
		String url="http://www.weather.com.cn/weather/101230101.shtml";
		Document doc = t.getDocument(url);
		// 获取目标HTML代码
		Elements elements1 = doc.select("[class=t clearfix]");
		// 今天
        Elements elements2 = elements1.select("[class=sky skyid lv2 on]");
        String today = elements2.get(0).text();
        System.out.println("今日天气： "+today);

	}

}