Python3爬取2023省市区

qq_34221812

已于 2024-03-26 18:35:03 修改

阅读量615

点赞数 1

文章标签： python

于 2024-03-26 18:29:43 首次发布

本文链接：https://blog.youkuaiyun.com/qq_34221812/article/details/137054055

版权

爬取地址https://www.stats.gov.cn/sj/tjbz/tjyqhdmhcxhfdm/2023/

import re
import requests
import pandas as pd
import warnings
warnings.filterwarnings("ignore")
import time
from lxml import etree
import pymysql
t ,urls ,names = [],[],[]
INDEX_URL = "https://www.stats.gov.cn/sj/tjbz/tjyqhdmhcxhfdm/2023/" #初始url
 # 创建连接
conn = pymysql.connect(host='127.0.0.1',
                       port=3306,
                       user='**',
                       passwd='**', 
                       db='**',
                       charset='utf8mb4')
# 获取游标对象
cursor = conn.cursor()
insert_data_sql = "insert into region(code, name,pcode) values(%s, %s,%s);"
#row = cursor.execute(insert_data_sql, ('shark', 18))

headers = {
   
    'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6'
    }
# 创建不验证证书的上下文
# context = ssl.create_default_context()
# context.check_hostname = False
# context.verify_mode = ssl.CERT_NONE
#获取省份页面
#province_response = urllib.request.urlopen(INDEX_URL + "index.html",context=context).read().decode("utf-8")

province_response = requests.get(INDEX_URL + "index.html")
province_response.encoding= 'utf-8'     # 指定编码