1,导入jar包
<dependency>
<groupId>org.jsoup</groupId>
<artifactId>jsoup</artifactId>
<version>1.11.3</version>
</dependency>
2,爬取数据
public static void main(String[] args) {
Document doc1 = null;
try {
//获取所有页面html元素
doc1 = Jsoup.connect("https://www.zq12369.com/environment.php?order=DESC&tab=rank").timeout(4000).get();
}catch (Exception e){
e.printStackTrace();
}
Element select = doc1.select(".tab-content").first();//获取class为tab-content的div元素
Element table = select.select(".tab-pane").first().select(".table").first();//获取table
Elements tr = table.select("tr");//获取所有的tr
List<ZqwPm> zqwPms = new ArrayList<>();//定义实体类接收
for(int i=2;i<10;i++){
//遍历tr列表跳过前两条tr 前两条为表名和列名
//解析前八条
Elements td = tr.get(i).select("td");
ZqwPm zqwPm = new ZqwPm();
zqwPm.setPm(td.get(0).text());
zqwPm.setCity(td.get(1).text());
zqwPm.setArea(td.get(2).text());
zqwPm.setAqi(td.get(3).text());
zqwPm.setQuality(td.get(4).text());
zqwPms.add(zqwPm);
System.out.println("排名:"+i+"---"+zqwPm);
}
}
结果展示: