爬取腾讯网的世界疫情实时数据

1. 数据格式

2. 主函数代码
   

3. 爬取数据结果
   

4. 完整代码

import csv, requests  # 导入请求模块
import pymysql


def save_html(a):
    db = pymysql.connect('localhost', 'root', 'root', 'spider', charset='utf8')
    cursor = db.cursor()
    ins = 'insert into coronavirus values(%s, %s,%s, %s, %s, %s, %s)'
    cursor.execute(ins, a)
    db.commit()
    cursor.close()


class A(object):
    def __init__(self):  # 定义获取数据并写入csv文件里的函数
        url = "https://api.inews.qq.com/newsqa/v1/automation/foreign/country/ranklist"  # 请求网址
        response = requests.get(url).json()  # 发出请求并json化处理
        data = response['data']  # 提取数据部分

        for i in range(16):
            print(data[i])
            print(data[i]['name'], data[i]['confirm'], data[i]['confirmAdd'])

        with open("CoronavirusData.csv", "w+", newline="") as json_file:
            writer = csv.writer(json_file)
            header = ["date", "state", "continent", "confirm", "confirmAdd", "suspect", "dead", "heal"]  # 定义表头
            writer.writerow(header)
            for i in range(len(data)):
                data_row1 = [data[i]["date"], data[i]["name"], data[i]["continent"], data[i]["confirm"],
                             data[i]["confirmAdd"],
                             data[i]["suspect"], data[i]["dead"], data[i]["heal"]]
                writer.writerow(data_row1)
                save_html(data_row1)


if __name__ == "__main__":
    spider = A()
    spider.__init__()
在这里插入代码片