2021年3月25日

时间:2个小时左右

代码:100行左右

博客:1

内容:使用了flask框架进行了疫情数据的爬取

import requests
import json

# https://view.inews.qq.com/g2/getOnsInfo?name=disease_h5
# https://view.inews.qq.com/g2/getOnsInfo?name=disease_foreign

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.114 Safari/537.36"

}
# 历史数据
url_history = "https://view.inews.qq.com/g2/getOnsInfo?name=disease_foreign"
resp = requests.get(url_history, headers)
# 获取页面的json字符串
json_data = resp.text
print(type(json_data))
print(json_data)
# 把json转换为dict
d_data = json.loads(json_data)
print(type(d_data))
print(d_data)

print(d_data['data'])
data_history = json.loads(d_data['data'])
for item in data_history.keys():
    print(item)
    print(data_history[item])

# details 详细数据
url = "https://view.inews.qq.com/g2/getOnsInfo?name=disease_h5"

resp = requests.get(url, headers)

json_data = resp.text
print(json_data)
# 转换为字典
dict_data = json.loads(json_data)
print(dict_data)

data = json.loads(dict_data['data'])
for item in data.keys():
    print(item)
    print(data[item])

print(data['chinaTotal'])
print(data['chinaAdd'])

print(data['areaTree'])

print("*******")

i = 1
for item in data['areaTree'][0]:
    print(item)

for item in data['areaTree'][0]['children']:
    print(item)