世界，您好！

欢迎使用WordPress。这是您的第一篇文章。编辑或删除它，然后开始写作吧！

网址

python代码

#!/usr/bin/env python
# -*- coding:utf-8 -*-
import requests
from fake_useragent import UserAgent
from lxml import etree
import time
import pandas as pd
import os

if not os.path.exists('./weather'):
    os.mkdir('./weather')

class weather(object):

    def spider(self, url):
        headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36'}

        response = requests.get(url=url, headers=headers).content.decode()
        tree = etree.HTML(response)

        return tree

    def homepage(self):
        home_page_url = 'https://lishi.tianqi.com/'
        tree = self.spider(home_page_url)

        city_list = tree.xpath("//tbody/tr/td/ul[@class='table_list']/li/a/text()")
        href_list = tree.xpath("//tbody/tr/td/ul[@class='table_list']/li/a/@href")
        print(city_list)
        print(href_list)

        #判断地点
        while True:
            city_name = input('请输入城市的名字\n')
            if city_name in city_list:
                city_index = city_list.index(city_name)
                city_url = href_list[city_index]
                break
            else:
                print('输入错误')

        return city_url, city_name


    def weather_cheak(self, city_url):
        city_url = 'https://lishi.tianqi.com/'+ city_url


        #判断日期，若不判断，超出后自动转跳至index.html
        while True:
            now_month = time.strftime('%Y%m', time.localtime())
            weather_time = input('请输入查询的时间（格式202104）\n')
            if weather_time <= now_month:
                city_url = city_url.replace('index', weather_time)
                print(city_url)
                break
            else:
                print('日期错误，请重新输入')

        tree = self.spider(city_url)

        date = tree.xpath("//div[@class='tian_three']/ul[@class='thrui']/li/div[1]/text()")
        high_temperature = tree.xpath("//div[@class='tian_three']/ul[@class='thrui']/li/div[2]/text()")
        low_temperature = tree.xpath("//div[@class='tian_three']/ul[@class='thrui']/li/div[3]/text()")

        detail_weather = tree.xpath("//div[@class='tian_three']/ul[@class='thrui']/li/div[4]/text()")
        wind_direction = tree.xpath("//div[@class='tian_three']/ul[@class='thrui']/li/div[5]/text()")

        print(date)
        print(high_temperature)
        print(low_temperature)

        print(detail_weather)
        print(wind_direction)

        return date, high_temperature, low_temperature, weather_time, detail_weather, wind_direction

    def Tocsv(self, date ,high_temperature ,low_temperature, city_name, weather_time, detail_weather, wind_direction):
        DF = pd.DataFrame(
            {
                '日期':date,
                '最高温度':high_temperature,
                '最低温度':low_temperature,
                '详细天气':detail_weather,
                '风向':wind_direction
            }
        )
        print(DF)
        path = f'./weather/weather_{city_name}_{weather_time}.csv'
        DF.to_csv(path, index=0)

    def run(self):
        city_url, city_name = self.homepage()
        date, high_temperature, low_temperature, weather_time, detail_weather, wind_direction= self.weather_cheak(city_url)
        self.Tocsv(date, high_temperature, low_temperature, city_name, weather_time, detail_weather, wind_direction)

if __name__ == "__main__":
    city = weather()
    city.run()
    print('over!')