Python爬取世界疫情的实时数据

一、Python爬取世界疫情的实时数据

1、表结构（MySQL）

 

 

2、代码部分(数据：丁香医生)

import requests
from bs4 import BeautifulSoup
import json
import time
from pymysql import *

def mes():
    url = 'https://ncov.dxy.cn/ncovh5/view/pneumonia?from=timeline&isappinstalled=0'  #请求地址
    headers = {'user-agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.87 Safari/537.36 SLBrowser/6.0.1.6181'}#创建头部信息
    resp =  requests.get(url,headers = headers)  #发送网络请求
    content=resp.content.decode('utf-8')
    soup = BeautifulSoup(content, 'html.parser')
    listA = soup.find_all(name='script',attrs={"id":"getListByCountryTypeService2true"})
    account =str(listA)
    mes = account.replace('[<script id="getListByCountryTypeService2true">try { window.getListByCountryTypeService2true = ', '')
    mes=mes.replace('}catch(e){}</script>]','')
    #mes=account[95:-21]
    messages_json = json.loads(mes)
    times=time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time()))
    worldList=[]
    for item in messages_json:
        continents=item['continents']
        provinceName=item['provinceName']
        confirmedCount=item['confirmedCount']
        currentConfirmedCount=item['currentConfirmedCount']
        curedCount = item['curedCount']
        deadCount=item['deadCount']
        worldList.append((times,continents,provinceName,confirmedCount,currentConfirmedCount,curedCount,deadCount))
    insert(worldList)


def insert(worldList):
    worldTuple=tuple(worldList)
    cursor = db.cursor()
    sql = "insert into world values (0,%s,%s,%s,%s,%s,%s,%s) "
    try:
        cursor.executemany(sql,worldTuple)
        print("插入成功")
        db.commit()
    except Exception as e:
        print(e)
        db.rollback()
    cursor.close()
# 连接数据库的方法
def connectDB():
    try:
        db = connect(host='localhost', port=3306, user='root', password='123456', db='yiqing',charset='utf8')
        print("数据库连接成功")
        return db
    except Exception as e:
        print(e)
    return NULL
if __name__ == '__main__':
    db=connectDB()
    mes()

3、结果