python爬取某气象网站数据

网站地址

http://www.tz121.com/index.php/Observation

视频教程

https://www.bilibili.com/video/BV1Y3411F726/

python代码

# -*- coding: utf-8 -*-
# @Author: Null119 微信公众号/网站：治廷君
# @Desc: { 台州气象数据获取 }
# @Date: { 2022/7/5 }

import csv,requests,re
from datetime import datetime

r=requests.Session()

varName=['温度','降水','平均风速','最大阵风','最大平均风速','相对温度','海平面气压','本站气压','能见度','近24小时能见度']
varId=['T','Pr','Wind10','WindExMax','WindMax','Rh','Slp','P','Vis','VisMin']

def write_csv(contents,name,typeid):
    csvname=f'{name}-{varName[typeid]}-data-{datetime.now().strftime("%Y%m%d%H%M%S")}.csv'
    with open(f'./{csvname}','w', encoding='UTF8', newline='') as f:
        writer = csv.writer(f)
        writer.writerow(['datatime',varId[typeid]])
        writer.writerows(contents)
    print(csvname,'写入完成.')

def get_time():
    GMT = '%a %b %d %Y %H:%M:%S GMT+0800'
    nowtime=datetime.now()
    return nowtime.strftime(GMT)+' (中国标准时间)',nowtime.strftime("%Y-%m-%d %H:%M:%S")

def get_token():
    response=r.get('http://www.tz121.com/index.php/Observation')
    try:
        token=re.search(r'name="_token" value="(.*?)"',response.text).group(1)
    except:
        token=''
    setCookieContent=response.headers['Set-Cookie']
    XTOKEN =re.search('(XSRF-TOKEN=.*?);',setCookieContent).group(1)
    taizhou_session =re.search('(taizhou_session=.*?);',setCookieContent).group(1)
    cookie=f'{XTOKEN};{taizhou_session};'
    return token,cookie

def get_data(name,day,typeid):
    token,cookie=get_token()
    dtStart,dtEnd=get_time()
    postdata={
        "varId":varId[typeid],
        "dtEnd":dtEnd,
        "dtStart":dtStart,
        "timeUnit":"H",
        "timeSpan":"0",
        "timeStep":"1",
        "timeFixEnd":"-1",
        "sqlFunc":"",
        "county":"台州"
    }
    headers={
        "Accept":"*/*",
        "Content-Type":"application/x-www-form-urlencoded; charset=UTF-8",
        "Cookie":cookie,
        "Referer":"http://www.tz121.com/index.php/Observation",
        "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.5060.53 Safari/537.36 Edg/103.0.1264.37",
        "X-CSRF-Token":token,
        "X-Requested-With":"XMLHttpRequest"
    }
    response=r.post('http://www.tz121.com/index.php/Observation/PostObsData',data=postdata,headers=headers)
    data=response.json()['data']
    id=''
    for i in range(len(data)):
        if name==data[i]['name']:
            id= data[i]['id']
            break
    if id!='':
        postdata={
            "stid":id,
            "varId":varId[typeid],
            "dtEnd":datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
            "sqlFunc":"",
            "hourSpan":"0",
            "daySpan":day,
            "timeFixEnd":"-1"
        }
        response=r.post('http://www.tz121.com/index.php/Observation/PostObsDataList',data=postdata,headers=headers)
        data=response.json()['data']
        rdata=[]
        for i in range(len(data)):
            rdata.append([data[i]['t'],data[i]['v1']])
            print(data[i]['t'],data[i]['v1'])
        write_csv(rdata,name,typeid)
    else:
        print('没有找到对应id,请检查后再试.')

if __name__ == '__main__':
    for i in range(len(varName)):
        print(i,varName[i])
    type=input('输入要获取的数据类型:')

    #点位名称,获取天数,获取类型
    get_data('天台','1',int(type))