搜狐新闻爬虫

小试身手，爬取搜狐新闻主页面上新闻的内容

package com.test1;
import java.io.IOException;

import org.jsoup.*;
import org.jsoup.helper.*;
import org.jsoup.nodes.*;
import org.jsoup.parser.*;
import org.jsoup.select.*;
public class HtmlParser {
	static void print(Document doc){

		//<h1 itemprop="headline">日本物流公司瞄准中国海淘族 跨境快递4天到货</h1>

				Elements h = doc.select("h1[itemprop]");//标题
				
				System.out.println(h.text());
				
				Elements time = doc.select("div.time");//时间
				
				System.out.println(time.text());
				/*
				Element source = doc.select("span[itemprop=name]").first();//来源
				
				System.out.println(source.text());
				*/
				//maybe 更好
				Elements source = doc.select("div[class=source]");
				
				System.out.println(source.text());
				
				Elements body = doc.select("div[itemprop=articleBody]");
				
				System.out.println(body.text());
	
	}
	public static void main(String[] args) {
		// TODO Auto-generated method stub
		
		try {
			String url = "http://news.sohu.com/";
			Document doc,TempDoc;
			doc = Jsoup.connect(url).get();
			//System.out.println(doc);
			//findalllinks
			Elements links = doc.select("a[href]");
			for (Element link : links){
				String StrUrl = link.attr("abs:href");
				if (StrUrl.startsWith("http://news.sohu.com/2016"))
				{
					System.out.println(StrUrl);
					TempDoc = Jsoup.connect(StrUrl).get();
					print(TempDoc);
				}
				
				
				
			}
			
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
		
	}

}