# 统计局县级及以上行政区划
import requests
from lxml import html

etree = html.etree
import json

area_url = 'http://www.mca.gov.cn/article/sj/xzqh/2020/20201201.html'
response = requests.get(area_url)
result = etree.HTML(response.text)
areacode_list = result.xpath('//tr/td[2]/text()')
areaname_list = result.xpath('//tr/td[3]/text()')
arr = []
for index, areacode in enumerate(areacode_list):
    obj = {
        'areacode': areacode,
        'areaname': areaname_list[index]
        # 'areaname': areaname_list[index+2]
    }
    arr.append(obj)
# jsonfile = open('area.json', 'w', encoding='utf-8')
# json.dump(arr, jsonfile, indent=2, ensure_ascii=False)
print(arr)