国家统计局省市区数据

#!/usr/bin/python
# -*- coding: UTF-8 -*-
#   功能：  获取省市县数据
#   版本：v1.1
import importlib
import sys
import pymysql

importlib.reload(sys)
import requests
import lxml.etree as etree
import os


class chinese_city():
    # 初始化函数
    def __init__(self):
        self.baseUrl = 'http://www.stats.gov.cn/tjsj/tjbz/tjyqhdmhcxhfdm/2019/index.html'
        self.base = 'http://www.stats.gov.cn/tjsj/tjbz/tjyqhdmhcxhfdm/2019/'
        self.conn = pymysql.connect(host="localhost", port=3306, user="root", passwd="123456", db="test", charset='utf8')
        self.cur = self.conn.cursor()
        self.trdic = {
   
            1: '//tr[@class="provincetr"]',
            2: '//tr[@class="citytr"]',
            3: '//tr[@class="countytr"]',
            4: '//tr[@class="towntr"]',
            5: '//tr[@class="villagetr"]'
        }

    def __del__(self):
        if self.cur:
            self.cur.close()
        if self.conn:
            self.conn.close()

    def crawl_page(self, url):
        ''' 爬行政区划代码公布页 '''
        # print(f"crawling...{url}")
        headers = {
   'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:71.0) Gecko/20100101 Firefox/71.0',
                   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8'}
        i = 0
        while i < 3:
            try:
                html = requests.get(url, headers=headers, timeout=20)
                html.encoding = 'gbk'  # 这里添加一行
                # print(html.status_code)
                text = html.text
                return text
            except requests.exceptions.RequestException<