疫情数据爬取实战

 

原网址：https://news.qq.com/zt2020/page/feiyan.htm?from=timeline&isappinstalled=0

import time
import json
import csv
import requests
ExcelName = 'C:/Epidemic-data.csv'

#当前日期时间戳
number = format(time.time() * 100, '.0f')

url = 'https://view.inews.qq.com/g2/getOnsInfo?name=disease_h5&callback=&_=%s' % number
datas = json.loads(requests.get(url=url).json()['data'])

print('更新时间：' + datas['lastUpdateTime'])

#写入表头
with open(ExcelName, 'w', encoding='utf-8', newline='') as csvfile:
    writer = csv.writer(csvfile)
    writer.writerow(["省份","城市","确诊","死亡","治愈","时间"])
    
for contry in datas['areaTree']:
    if contry['name'] == '中国':
        for province in contry['children']:
            for city in province['children']:
                with open(ExcelName, 'a', encoding='utf-8', newline='') as csvfile:
                    writer = csv.writer(csvfile)
                    writer.writerow([province['name'],city['name'], str(city['total']['confirm']),str(city['total']['dead']), str(city['total']['
heal']),datas['lastUpdateTime']])

爬取结果：