python爬虫获取疫情信息并存入mysql数据库实践

上一次做了全国疫情统计可视化图表，这次尝试着能不能实现数据库里的更新操作，首先考虑的就是python爬虫，因为它易操作，并且python学习也是日后必须的。

通过从网上查阅学习，代码如下：

import requests
from bs4 import BeautifulSoup
import re
import pymysql
import json


def create():
    db = pymysql.connect("localhost", "root", "0000", "grabdata_test",charset='utf8')  # 连接数据库

    cursor = db.cursor()
    cursor.execute("DROP TABLE IF EXISTS info")

    sql = """CREATE TABLE info (
            Id INT PRIMARY KEY AUTO_INCREMENT,
            Date varCHAR(255),
            Province varchar(255),
            City varchar(255),
            Confirmed_num varchar(255),
            Yisi_num varchar(255),
            Cured_num varchar(255),
            Dead_num varchar(255),
            Code varchar(255))"""

    cursor.execute(sql)

    db.close()


def insert(value):
    db = pymysql.connect("localhost", "root", "0000", "grabdata_test",charset='utf8')

    cursor = db.cursor()
    sql = "INSERT INTO info(Date,Province,City,Confirmed_num,Yisi_num,Cured_num,Dead_num,Code) VALUES ( %s,%s,%s,%s,%s,%s,%s,%s)"
    try:
        cursor.execute(sql, value)
        db.commit()
        print('插入数据成功')
    except:
        db.rollback()
        print("插入数据失败")
    db.close()


create()  # 创建表

url = 'https://raw.githubusercontent.com/BlankerL/DXY-2019-nCoV-Data/master/json/DXYArea.json'
response = requests.get(url)
# 将响应信息进行json格式化
versionInfo = response.text
# print(versionInfo)#打印爬取到的数据
# print("------------------------")#重要数据分割线↓

#一个从文件加载，一个从内存加载#json.load(filename)#json.loads(string)
jsonData = json.loads(versionInfo)

#用于存储数据的集合
dataSource = []
provinceShortNameList = []
confirmedCountList = []
curedCount = []
deadCountList = []
#遍历对应的数据存入集合中
for k in range(len(jsonData['results'])):
    if(jsonData['results'][k]['countryName'] == '中国'):
        provinceShortName = jsonData['results'][k]['provinceName']
        if("待明确地区" == provinceShortName):
            continue;

        for i in range(len(jsonData['results'][k]['cities'])):
            confirmnum=jsonData['results'][k]['cities'][i]['confirmedCount']
            yisi_num=jsonData['results'][k]['cities'][i]['suspectedCount']
            cured_num=jsonData['results'][k]['cities'][i]['curedCount']
            dead_num=jsonData['results'][k]['cities'][i]['deadCount']
            code=jsonData['results'][k]['cities'][i]['locationId']
            cityname=jsonData['results'][k]['cities'][i]['cityName']
            date='2020-3-10'
            insert((date,provinceShortName,cityname,confirmnum,yisi_num,cured_num,dead_num,code))