java爬虫 之 搜狐新闻爬虫（三）

package com.sohu;
import java.io.IOException;
import java.util.*;

import org.jsoup.*;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
public class ClawerMain {

public static void main(String[] args) {
// TODO Auto-generated method stub
try {
Document doc = Jsoup.connect("http://news.sohu.com/").get();
Elements links = doc.select("a[href]");
for(Element link : links){
String StrUrl = link.attr("abs:href");
if(StrUrl.startsWith("http://news.sohu.com/2016"))//抓2016年的新闻
{
System.out.println(StrUrl);
try {
Document TempDoc;

TempDoc = Jsoup.connect(StrUrl).get();

Elements h = TempDoc.select("h1[itemprop]");//标题

System.out.println(h.text());

Elements time = TempDoc.select("div.time");//时间

System.out.println(time.text());

Elements source = TempDoc.select("div[class=source]");//来源

System.out.println(source.text());

Elements body = TempDoc.select("div[itemprop=articleBody]");//内容

System.out.println(body.text());

} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}

}
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}

}

}