爬取最新疫情数据

题目：

编程爬取每日最新的疫情统计数据。

并将爬取结果导入到数据库中。

将可视化结果与统计数据结合，实时显示当前最新数据。

这次的作业与上次周的可视化可以整合成一个完整的代码，只需要在这次加上python爬取数据即可

本次爬取的是丁香医生网站的数据，网址为：https://ncov.dxy.cn/ncovh5/view/pneumonia

爬取的代码如下

from os import path
import requests
from bs4 import BeautifulSoup
import json
import pymysql
#import numpy as np
import time
from _ast import Try

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; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36'}#创建头部信息
response =  requests.get(url,headers = headers)  #发送网络请求
#print(response.content.decode('utf-8'))#以字节流形式打印网页源码
content = response.content.decode('utf-8')
#print(content)
soup = BeautifulSoup(content, 'html.parser')
listA = soup.find_all(name='script',attrs={"id":"getAreaStat"})
#世界确诊
listB = soup.find_all(name='script',attrs={"id":"getListByCountryTypeService2"})
#listA = soup.find_all(name='div',attrs={"class":"c-touchable-feedback c-touchable-feedback-no-default"})
account = str(listA)
world_messages = str(listB)[87:-21]
messages = account[52:-21]
messages_json = json.loads(messages)
world_messages_json = json.loads(world_messages)
valuesList = []
cityList = []
worldList = []
localtime = time.localtime(time.time())
L=time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
print(L)
for i in range(len(messages_json)):
    #value = messages_json[i]
    #value = (messages_json[i].get('provinceName'),messages_json[i].get('provinceShortName'),messages_json[i].get('currentConfirmedCount'),messages_json[i].get('confirmedCount'),messages_json[i].get('suspectedCount'),messages_json[i].get('curedCount'),messages_json[i].get('deadCount'),messages_json[i].get('comment'),messages_json[i].get('locationId'))
    value = (messages_json[i].get('provinceName'),messages_json[i].get('confirmedCount'),messages_json[i].get('curedCount'),messages_json[i].get('deadCount'),messages_json[i].get('locationId'))
    valuesList.append(value)
    cityValue = messages_json[i].get('cities')
    #print(cityValue) 一个省内没有划分开的值
    for j in range(len(cityValue)):
        #cityValueList = (cityValue[j].get('cityName'),cityValue[j].get('currentConfirmedCount'),cityValue[j].get('confirmedCount'),cityValue[j].get('suspectedCount'),cityValue[j].get('curedCount'),cityValue[j].get('deadCount'),cityValue[j].get('locationId'),messages_json[i].get('provinceShortName'))
        cityValueList = (messages_json[i].get('provinceName'),cityValue[j].get('cityName'),cityValue[j].get('confirmedCount'),cityValue[j].get('curedCount'),cityValue[j].get('deadCount'),cityValue[j].get('locationId'))
        #print(cityValueList)  省份内各个城市的值
        cityList.append(cityValueList)
    
#print(cityList)  #城市
#print(valuesList)  #省份
db=pymysql.connect("localhost","root","123456","payiqing", charset='utf8')
cursor = db.cursor()
     
sql_city="insert into info_copy (Province,City,Confirmed_num,Cured_num,Dead_num,Code,Date) values (%s,%s,%s,%s,%s,%s,'"+L+"')"
sql_province="insert into info_copy (Province,Confirmed_num,Cured_num,Dead_num,Code,Date) values (%s,%s,%s,%s,%s,'"+L+"')"
#print(sql)
 
value_tuple= tuple(valuesList)
city_tuple=tuple(cityList)
 
try:
    cursor.executemany(sql_province,valuesList)
    cursor.executemany(sql_city,city_tuple)
    db.commit()
except:
    print('执行失败，进入回调4')
    db.rollback()   
     
     
     
db.close()

加上上次的代码，效果如下图所示：

 

 psp表格

缺陷记录日志