一、优化了，输入城市代码，获取城市信息

# coding=utf-8
import requests
import re
import csv
import datetime

class WeatherForecast(object):
    def __init__(self,city_code,start_year,end_year,end_month):
        self.city_code=city_code
        self.start_year=start_year
        self.end_year=end_year
        self.end_month=end_month

        # self.url = 'https://tianqi.2345.com/Pc/GetHistory?areaInfo%5BareaId%5D=59493&areaInfo%5BareaType%5D=2&date%5Byear%5D={0}&date%5Bmonth%5D={1}'
        # #西安地址链接  57036--->BareaId%5D=59493
        # self.url = 'https://tianqi.2345.com/Pc/GetHistory?areaInfo%5BareaId%5D=57036&areaInfo%5BareaType%5D=2&date%5Byear%5D={0}&date%5Bmonth%5D={1}'

        # 咸阳地址链接57048--->%5BareaId%5D=59493
        # self.url = 'https://tianqi.2345.com/Pc/GetHistory?areaInfo%5BareaId%5D=57048&areaInfo%5BareaType%5D=2&date%5Byear%5D={0}&date%5Bmonth%5D={1}'
        self.headers = {
            'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36 Edg/107.0.1418.24',
            'accept-encoding': 'gzip, deflate, br'
        }
        self.data_list = []

    def get_content(self, url):
        res = requests.get(url=url, headers=self.headers)
        content = res.json()
        # print(content['data'])
        return content['data']

    def parse_data(self, content):
        result = re.compile(r'<td>(?P<date>.*?)</td>.*?<td style="color:#ff5040;">(?P<max>.*?)</td>'
                            r'.*?<td style="color:#3097fd;" >(?P<min>.*?)</td>.*?<td>(?P<weather>.*?)</td>'
                            r'.*?<td>(?P<cloud>.*?)</td>.*?<td><span class="history-aqi wea-aqi.*?>(?P<sky>.*?)</span></td>',
                            re.S)
        find_result = result.finditer(content)
        for it in find_result:
            data_dict = it.groupdict()
            # print(data_dict)
            self.data_list.append(data_dict)
        return self.data_list

    def write_csv(self, data_list):
        curent_date=datetime.datetime.now().strftime("%Y%m%d")
        save_name=str(self.city_code)+curent_date+'.csv'
        with open(save_name, 'w',newline='') as f:
            writer = csv.writer(f)
            writer.writerow(['日期', '最高温度', '最低温度', '天气', '风力风向', '空气质量'])
            for i in data_list:
                writer.writerow(i.values())
                print(i.values())

    #     爬取数据的事项，只能获取整年，如果到月份的话                if year==2024 & month>6:
    #                     continue  通过他跳过指定的月份，获取数据
    def run(self):
        for year in range(self.start_year, self.end_year+1, 1):
            for month in range(1, 13, 1):
                if year>self.end_year:
                    continue
                elif  year==self.end_year:
                    if month>self.end_month:
                        continue


                url = f'https://tianqi.2345.com/Pc/GetHistory?areaInfo%5BareaId%5D={self.city_code}&areaInfo%5BareaType%5D=2&date%5Byear%5D={year}&date%5Bmonth%5D={month}'

                print('正在获取第{0}年{1}月的天气!'.format(year, month))
                content = self.get_content(url)
                data = self.parse_data(content)
                self.write_csv(data)
            print('全部获取完毕,请在程序目录获取下载xxxx.csv!')


# 使用办法  就是换里面的url地址，以及修改下面的年月
# 具体内容查看 “数据分析.txt”里面的信息
# 天气预报查询接口
# https://tianqi.2345.com/wea_history/57036.htm
if __name__ == '__main__':
    print("输入起始年，结束年，结束月")

    city_code = int(input("起始城市代码:"))

    start_year=int(input("起始年:"))
    end_year=int(input("结束年:"))
    end_month=int(input("结束年月:"))



    weather = WeatherForecast(city_code,start_year,end_year,end_month)
    weather.run()


    # 调整获取指定年份的指定月份之前的数据

二、代码分析

本次对数据提取进行分析：---》数据解析的分析

    def parse_data(self, content):
        result = re.compile(r'<td>(?P<date>.*?)</td>.*?<td style="color:#ff5040;">(?P<max>.*?)</td>'
                            r'.*?<td style="color:#3097fd;" >(?P<min>.*?)</td>.*?<td>(?P<weather>.*?)</td>'
                            r'.*?<td>(?P<cloud>.*?)</td>.*?<td><span class="history-aqi wea-aqi.*?>(?P<sky>.*?)</span></td>',
                            re.S)
        find_result = result.finditer(content)
        for it in find_result:
            data_dict = it.groupdict()
            # print(data_dict)
            self.data_list.append(data_dict)
        return self.data_list

 

上面返回的内容是个json文件，json中data就是需要的数据

 那么这个数据内容是什么呢？我们打印出来看下

 

 

  result = re.compile(r'<td>(?P<date>.*?)</td>.*?<td style="color:#ff5040;">(?P<max>.*?)</td>'
                            r'.*?<td style="color:#3097fd;" >(?P<min>.*?)</td>.*?<td>(?P<weather>.*?)</td>'
                            r'.*?<td>(?P<cloud>.*?)</td>.*?<td><span class="history-aqi wea-aqi.*?>(?P<sky>.*?)</span></td>',
                            re.S)

通过上面的正则就是可以提取出来其中的内容了