package org.jgs1904;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import java.io.IOException;
import java.util.List;
/**
* @Author : 默苍离
* @Create_Date : 2020/08/01/19:08
* @Pack_name : org.jgs1904 : Beijing
* *****************************************************
* 注释: 获取所有省份信息
*/
public class Provincetr {
public static void main(String[] args) throws IOException {
Provincetr provincetr = new Provincetr();
// System.out.println(provincetr.provincetrElements());
System.out.println(provincetr.provincetrUrl());
}
//provincetr 获取 整个 省级 页面 内容
public Elements provincetrElements() throws IOException {
// 获取 整个 省级 页面 内容
Document provincetr = Jsoup.connect("http://www.stats.gov.cn/tjsj/tjbz/tjyqhdmhcxhfdm/2019/index.html").get();
//System.out.println(provincetr);
//通过 选择器组合 获取 所有省份信息
Elements selectProvincetrs = provincetr.select(".provincetr a");
//System.out.println(selectCountytr);
return selectProvincetrs;
}
//provincetr 省级 城市 路径 url 后缀
public List<String> provincetrUrl() throws IOException {
Document provincetr = Jsoup.connect("http://www.stats.gov.cn/tjsj/tjbz/tjyqhdmhcxhfdm/2019/index.html").get();
Elements selectProvincetrs = provincetr.select(".provincetr a");
// System.out.println(selectProvincetrs );
List<String> provincetrListUrl = null;
//循环遍历
for (Element selectProvincetr : selectProvincetrs) {
System.out.println(selectProvincetr);
//获取文本内容
String selectProvincetrString = selectProvincetr.text().toString();
System.out.println("省级:" + selectProvincetrString);
//字符串处理 获取 链接
String provincetrUrl = selectProvincetr.toString();
System.out.println(provincetrUrl);
int provincetri = provincetrUrl.indexOf('"');
System.out.println(provincetri);
int provincetrj = provincetrUrl.indexOf('"', provincetri + 1);
System.out.println(provincetrj);
String provincetrUrlSubstring = provincetrUrl.substring(provincetri + 1, provincetrj);
System.out.println(provincetrUrlSubstring);
provincetrListUrl.add(provincetrUrlSubstring);
}
return provincetrListUrl;
}
}
运行结果:
Exception in thread "main" java.lang.NullPointerException
at org.jgs1904.Provincetr.provincetrUrl(Provincetr.java:68)
at org.jgs1904.Provincetr.main(Provincetr.java:24)
<a href="11.html">北京市<br></a>
省级:北京市
<a href="11.html">北京市<br></a>
8
16
11.html