python获取某天气网站公开天气数据

最新推荐文章于 2024-10-02 10:53:34 发布

马龙强_

最新推荐文章于 2024-10-02 10:53:34 发布

阅读量421

点赞数 6

文章标签： python 数据库

本文链接：https://blog.csdn.net/m0_74972727/article/details/136257269

版权

注意：代码仅用于学习

查找url :

查找城市ID：

城市ID文件demo.js(JavaScript):

function get_city(){
    var provqx=new Array();
    provqx[10]=['58321-H 合肥-58321|71873-B 包河-58321|58326-C 巢湖-58321|70000-C 长丰-58321|60765-F 肥西-58321|70005-F 肥东-58321|71459-Y 渝中-57516|60295-Y 云阳-57516|60297-Y 永川-57516|60284-Z 忠县-57516']
    return provqx;
}

相关代码：

import requests
import parsel
import csv
import execjs

#https://tianqi.2345.com/wea_history/57687/htm

# GETALL = tr.xpath('./td//text()').getall()
f = open('demo.js',mode='r',encoding='utf-8').read()
ctx = execjs.compile(f)
# provqx = ctx.call("get_city")
city_list = ctx.call("get_city")
areaInfoList = []
for city_li in city_list:
    if city_li:
        for city_info in city_li:
            info_list = city_info.split('|')
            for info in info_list:
                city_code = info.split('-')[0]
                # city_code = citys.split('-')[1]
                # city_name = citys.split('-')[0]
                city_names = info.split('-')[1]
                city_name = city_names.split(' ')[1]
                areaInfoList.append([city_name,city_code])
# print(areaInfoList)

                #
                # print(citys,citynames)

with open('全国天气数据.csv',mode='a',encoding='utf-8',newline='') as f:
    csv.writer(f).writerow(['日期','最高温度','最低温度','天气','风力风向','空气质量','城市'])

for areaInfo in areaInfoList:
    city_name = areaInfo[0]
    city_code = areaInfo[1]
    for year in range(2023,2024):
        for month in range(10,11):
            # csv_writer = csv.writer(f)
            # csv_writer.writerow(['日期','最高温度','最低温度','天气','风向','城市'])
            url = f'https://tianqi.2345.com/Pc/GetHistory?areaInfo%5BareaId%5D={city_code}&areaInfo%5BareaType%5D=2&date%5Byear%5D={year}&date%5Bmonth%5D={month}'
            response = requests.get(url=url)
            json_data = response.json()
            # print(json_data.get('data'))
            html_data = json_data.get('data')
            #
            select = parsel.Selector(html_data)

            trs = select.xpath('//tr')
            for tr in trs[1:]:
                # print(tr.xpath('string(td)').getall())
                # date = tr.xpath('string(td)').get()
                # print(tr.xpath('./td//text()').getall())
                tds = tr.xpath('./td//text()').getall()
                tds.append(city_name)
                print(tds)
                with open('全国天气数据.csv', mode='a', encoding='utf-8', newline='') as f:
                    # csv_writer = csv.writer(f)
                    # csv_writer.writerow(tds)
                    csv.writer(f).writerow(tds)

            #
            # #t clearfix
            #
            # for tr in trs[1:]:
            #     # tds = tr.css('td::text').getall()
            #     # tds GETALL
            #     print(tds)
            #     # with open('河南12月天气数据.csv', mode='a', encoding='utf-8', newline='') as f:
            #     #     csv_writer = csv.writer(f)
            #     #     csv_writer.writerow(tds)