Python爬取全球COVID-19当日数据（网易版）

Python爬取全球COVID-19当日数据（网易版）

了解数据结构（右键检查–>Network–>XHR–>Ctrl+R）：

如箭头所示，我们需要的数据在这里：

headers在这里获得：

URL在这里获得：

代码：

import requests
import pandas as pd
import json
import time
def get_html (Url,Headers):
    try:
        ret = requests.get(url=Url, headers=Headers)
        print(ret)  # 打印请求状态
        return ret.text
    except:
        print('呜呜呜，爬取失败了!\n学生请不要用校园网嗷')
def get_data (dic_data, index):
    info = pd.DataFrame(dic_data)[index]
    print(info)
    tdy_data = pd.DataFrame([country["today"] for country in dic_data])
    tdy_data.columns = ["today_" + col for col in tdy_data.columns]
    ttl_data = pd.DataFrame([country["total"] for country in dic_data])
    ttl_data.columns = ["total_" + col for col in ttl_data.columns]
    return pd.concat([info, tdy_data, ttl_data], axis=1)    #axis = 1 按列合并链接的轴
def data_save(data, name):
    try:
        f_name = time.strftime("%Y%m%d", time.localtime(time.time())) + name + ".csv"
        data.to_csv(f_name, index=None, encoding="gbk")
        print(f_name + " 已成功保存")
    except:
        print('数据保存失败')
if __name__ == "__main__":
    start = time.time()
    url="https://c.m.163.com/ug/api/wuhan/app/data/list-total"
    headers = {
      "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
                          "AppleWebKit/537.36 (KHTML, like Gecko) "
                          "Chrome/83.0.4103.61 Safari/537.36 "}
    ret_txt = get_html(url,headers)
    world_data = json.loads(ret_txt)["data"]["areaTree"]
    index = ["id", "name", "lastUpdateTime"]
    world_rlt_data = get_data(world_data, index)
    data_save(world_rlt_data, "_World_COVID-19")
    end = time.time()
    print("本次爬虫历时：", end - start, "秒")

结果截图：

数据展示：

仅供学习使用。