使用jsoup简单实现爬虫

此为jsoup官网地址：https://jsoup.org/

 

从官网下载jar包后 导入eclipse

 

package cn.zsyy.spider;

import java.io.IOException;
import java.util.HashMap;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

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

import cn.zsyy.db.Dao;


public class Article {
	static String yyxwurl = "需要爬取的网站";
	static String host = "网站根目录";
	
	static void innit() throws IOException{
		
		Document document = Jsoup.connect(yyxwurl).get();
	}
	
	static void getlistUrL(String nextUrl) throws IOException{
		String url = nextUrl;
		Document document = Jsoup.connect(url).get(); 
		Element first = document.select(".next").first();
		if (!first.equals("javascript:void(0);")) {
			String