jsoup网络爬虫抓数据

API文档地址: https://jsoup.org/apidocs/
官网 : https://jsoup.org/

小例子:

package com.tanle;

import java.io.IOException;

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

public class Test {

public static void main(String[] args) throws IOException {
// 获取该网址的所有a标签href
Document doc = Jsoup.connect("http://www.123hao.cn").get();
Elements elements = doc.select("a");
for(Element element : elements){
System.out.println(element.attr("href"));
}
}

}