统计用区划和城乡划分代码,在线爬取代码

统计用区划和城乡划分代码,在线爬取代码【根据实际情况自行更改】

相关依赖【最好使用Java8进行调试】
官方链接
Maven Gradle 离线JAR包下载

转发请标明文章出处 https://blog.csdn.net/AntsCode/article/details/109817067

GetRegionalism.java

/*
 * ProjectName: ########
 * PackageName: top.smartprinting
 * CompanyName: ########
 * Datetime: 2020/11/16 下午12:19
 * E-mail: MyEvery7655@gmail.com
 */
package top.smartprinting;

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

import java.io.File;
import java.io.IOException;
import java.nio.charset.StandardCharsets;
import java.util.Collection;
import java.util.List;
import java.util.stream.Collectors;
import java.util.stream.Stream;

/**
 * Description:<br>
 *
 * @author AntsCode
 */
public class GetRegionalism {
   

    private static final String ROOT_PATH = "http://www.stats.gov.cn/tjsj/tjbz/tjyqhdmhcxhfdm/2020/";

    private GetRegionalism() {
   
    }

    public static void main(String[] args) {
   
        System.out.println(getCCTV(Area.TOWNTR, getCCTV(Area.COUNTYTR, getCCTV(Area.CITYTR, getP(), false), false), false)
                .size());
    }

    public static List<RegionalismCode> getPCCTV(Area area, String href) {
   
        if (area.equals(Area.TOWNTR)) {
   
            href = href.substring(3, 5) + File.separator + href;
        } else if (area.equals(Area.VILLAGETR)) {
   
            href = href.substring(3, 5) + File.separator + href.substring(5, 7) + File.separator + href;
        }
        return getRegionalismCodeStream(area, href)