爬“丁香网”最新的肺炎数据，并保存csv文件
import requests
import re
import json
import pandas as pd
#import time
from datetime import datetime
#1、获取网页源码
def gethtml():
#伪装（程序——》浏览器）头部信息
headers ={'user-agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36'}
url = 'https://ncov.dxy.cn/ncovh5/view/pneumonia'
page = requests.get(url,headers-headers).content.decode('utf-8')
# print(page)
#2、解析全球数据
reg = '<script id="getListByCountryTypeService2">([^<]+)'
data = re.findall(reg,page)#匹配切片取值 可使用split分割
#print(data)
#3、数据分析处理
#字符转换
data = json.loads(data)
#print(type(data))
#时间戳--正常格式
for row in data:
for key in row:
if key in ['createTime','modifyTime']:
row = datetime.fromtimestamp(row/1000).strftime("%Y-%m-%d %H:%M:%S")
#print(row)
df = pd.DataFrame(data)
#print(df)
df.to_csv("最新的肺炎数据.csv",mode = "a",encoding = "UTF_8_SIG")
gethtml()
可以的
页:
[1]