Python爬取国家统计局的省市区

可以使用Python中的requests和BeautifulSoup库来实现爬取国家统计局的省市区信息。以下是示例代码：

import requests
from bs4 import BeautifulSoup

url = 'http://www.stats.gov.cn/tjsj/tjbz/tjyqhdmhcxhfdm/2019/index.html'
response = requests.get(url)
response.encoding = 'gbk'
soup = BeautifulSoup(response.text, 'html.parser')

province_list = soup.select('.provincetr a')
for province in province_list:
    province_name = province.text.strip()
    province_code = province['href'][:2]
    print(province_code, province_name)

    city_url = f'http://www.stats.gov.cn/tjsj/tjbz/tjyqhdmhcxhfdm/2019/{province_code}.html'
    city_response = requests.get(city_url)
    city_response.encoding = 'gbk'
    city_soup = BeautifulSoup(city_response.text, 'html.parser')

    city_list = city_soup.select('.citytr a')
    for city in city_list:
        city_name = city.text.strip()
        city_code = city['href'][3:5]
        print('\t', city_code, city_name)

        county_url = f'http://www.stats.gov.cn/tjsj/tjbz/tjyqhdmhcxhfdm/2019/{province_code}/{city_code}.html'
        county_response = requests.get(county_url)
        county_response.encoding = 'gbk'
        county_soup = BeautifulSoup(county_response.text, 'html.parser')

        county_list = county_soup.select('.countytr a') if len(county_soup.select('.countytr a')) > 0 else county_soup.select('.towntr a')
        for county in county_list:
            county_name = county.text.strip()
            county_code = county['href'][5:9]
            print('\t\t', county_code, county_name)

以上代码可以输出各个省市区的名称和代码。注意需要指定网页编码为`gbk`。