最新全国区划编码

一、数据来源

国家统计局2023年数据:
在这里插入图片描述

二、区划编码现成文件

1、获取方式：

csdn：资源绑定
v：JFAN0329

三、python部分代码分析

import time

import requests
from bs4 import BeautifulSoup
import re
import xlsxwriter


def mainClass():
    urlindex = 'https://www.stats.gov.cn/sj/tjbz/tjyqhdmhcxhfdm/2023/'
    url = urlindex+'index.html'
    dic = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36 Edg/119.0.0.0"
       }
    resp = requests.get(url, headers=dic)
    resp.encoding = 'zh-CN'
    page = BeautifulSoup(resp.text, "html.parser")
    httpCode = resp.status_code
    workbook = xlsxwriter.Workbook('F:\Study_file\python\getqgqhbm\ssxqybm.xlsx')
    worksheet = workbook.add_worksheet()

    # 如果请求失败，则休息2秒再次请求
    if(httpCode != 200):
        while httpCode != 200:
            time.sleep(2)
            resp = requests.get(url, headers=dic)
            resp.encoding = 'zh-CN'
            page = BeautifulSoup(resp.text, "html.parser")
            httpCode = resp.status_code
    tr = page.find_all("tr",attrs={"class": "provincetr"})  # 将属性写成一个字典，等同于”page.find("div", class_="img-list-tt hh")”
    i = 0;
    dataid = 1;
    oneid = 1;
    twoid = 1;
    treeid = 1;
    for td in tr:
        td_content = td.find_all("td")
        for a in td_content:
            a_tag = a.find_all("a")
            urlsxq = a_tag[0].get("href")  # 直接获取 href 属性
            qymctext = a_tag[0].text  # 直接获取 text 属性
            if urlsxq:  # 确保 href 存在
                url1 = urlindex + urlsxq;
                # 省级输出
                worksheet.write(i, 0, dataid)
                worksheet.write(i, 2, qymctext)
                worksheet.write(i, 3, 0)
                worksheet.write(i, 4, 1)
                oneid = dataid;
                dataid = dataid+1
                i = i+1
                print(f"一级url：{urlsxq}")
                print(f"一级名称：{qymctext}")
                resp1 = requests.get(url1, headers=dic)
                resp1.encoding = 'zh-CN'
                httpCode1 = resp1.status_code
                if (httpCode1 != 200):
                    while httpCode1 != 200:
                        time.sleep(2)
                        resp1 = requests.get(url, headers=dic)
                        resp1.encoding = 'zh-CN'
                        httpCode1 = resp1.status_code
                page1 = BeautifulSoup(resp1.text, "html.parser")
                table1 = page1.find_all("table", attrs={"class": "citytable"})
                city0ne = len(table1);
                for taTr in table1:
                    tr1 = taTr.find_all("tr", attrs={"class":"citytr"})
                    for tdTr in tr1:
                        td1 = tdTr.find_all("a")
                        url2 = td1[0].get("href")
                        qhbm = td1[0].text
                        qhmc = td1[1].text
                        if url2 !='' and qhmc != '':
                            worksheet.write(i, 0, dataid)
                            worksheet.write(i, 1, qhbm)
                            worksheet.write(i, 2, qhmc)
                            worksheet.write(i, 3, oneid)
                            worksheet.write(i, 4, 2)
                            twoid = dataid
                            dataid = dataid + 1
                            i=i+1
                            print(f"二级url：{url2}")
                            print(f"二级编码：{qhbm}")
                            print(f"二级名称：{qhmc}")
                onebm = qhbm[0:2]+"000000000"
                worksheet.write(oneid-1, 1, onebm)
    workbook.close()

if __name__ == '__main__':
    mainClass()