python_files/cppc_python脚本/服务器脚本/demo_窄门数据获取.py

# -*- codeing = utf-8 -*-
# @Time : 2024/1/17 17:43
# @Author : Clown
# @File : demo_窄门数据获取.py
# @Software : PyCharm
import requests
import json
import pandas as pd
import time
import random
from dateutil.parser import parse


def downLoadShopsInfoByBrandId(brand_id,sessionId,brand_name,date_time):
    page = 0
    page_cnt = 1
    df_out = []
    start_time = time.time()
    while page < page_cnt:
        page += 1
        url = f'https://fa.kaoputou.com/api/brand/{brand_id}/shops?slug={brand_id}&status=1&page={page}'
        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 MicroMessenger/7.0.20.1781(0x6700143B) NetType/WIFI MiniProgramEnv/Windows WindowsWechat/WMPF WindowsWechat(0x63090819) XWEB/8531',
                   'sessionId': sessionId}
        a = 1
        while a == 1:
            try:
                resp = requests.get(url,headers=headers).json()
                a = 0
            except:
                print(page,'失败')
                time.sleep(10)
        if page == 1:
            try:
                shopStatus = resp['shopStatus']['open']
                page_cnt = shopStatus / 15
                print(f'总页数{page_cnt}')
            except:
                shopStatus = 15
                page_cnt = shopStatus / 15
                print(f'总页数{page_cnt}')
        print(f'当前正在获取--第{page}页')
        df_out =  df_out + resp['shops']
        time.sleep(random.uniform(3,4))
        # if page%10 == 0 :
        #     time.sleep(20)
    df_out = pd.DataFrame(df_out)
    date_list = lambda df_in: [time.strftime('%Y%m%d',time.strptime(i, "%a, %d %b %Y %H:%M:%S %Z")) for i in df_in]
    df_out['openDate'] = date_list(df_out['openDate'])
    df_out.to_excel(f'C:/Users/ClownHe/Desktop/导入/输出/{brand_name}-{brand_id}全国门店分布{date_time}.xlsx')
    time_spend = round((time.time()-start_time)/60)
    print(f'总计用时{time_spend}min')

if __name__ == '__main__':
    brand_id = 21903627
    brand_name = '楼兰辛香'
    sessionId = 'wx_ab1e429c8ef4b99ecda823313d13b810'
    date_time = time.strftime('%Y%m%d%H%M%S')
    downLoadShopsInfoByBrandId(brand_id,sessionId,brand_name,date_time)
    # openDate = 'Wed, 01 Mar 2023 10:00:00 GMT'
    # openDate = time.strptime(openDate, "%a, %d %b %Y %H:%M:%S %Z")
    # openDate = time.strftime('%Y%m%d',openDate)
    # print(openDate)