Technical article

import pandas as pd

import os

# 1. 读取多个Excel并合并

input_dir = r'C:\data\input'

files = [f for f in os.listdir(input_dir) if f.endswith('.xlsx')]

dfs = []

for f in files:

df = pd.read_excel(os.path.join(input_dir, f))

df['来源文件'] = f

dfs.append(df)

merged = pd.concat(dfs, ignore_index=True)

# 2. 数据清洗

merged = merged.drop_duplicates() # 去重

merged['金额'] = pd.to_numeric(merged['金额'], errors='coerce').fillna(0)

merged['日期'] = pd.to_datetime(merged['日期'], errors='coerce')

# 3. 按区域分组汇总

summary = merged.groupby('区域').agg({

'金额': ['sum', 'mean', 'count'],

'订单号': 'nunique'

}).reset_index()

summary.columns = ['区域', '总金额', '平均金额', '订单数', '客户数']

# 4. 输出

output_path = r'C:\data\output\汇总结果.xlsx'

with pd.ExcelWriter(output_path) as writer:

merged.to_excel(writer, sheet_name='明细', index=False)

summary.to_excel(writer, sheet_name='汇总', index=False)

print(f'处理完成，共{len(merged)}条明细，{len(summary)}个区域')

import requests

import time

import json

def call_api(url, method='GET', headers=None, data=None, max_retries=3):

"""带重试的API调用"""

for attempt in range(max_retries):

try:

if method.upper() == 'GET':

resp = requests.get(url, headers=headers, params=data, timeout=30)

else:

resp = requests.post(url, headers=headers, json=data, timeout=30)

resp.raise_for_status()

return resp.json()

except Exception as e:

print(f'第{attempt+1}次调用失败: {e}')

if attempt < max_retries - 1:

time.sleep(2 ** attempt) # 指数退避

return None

# 使用示例

result = call_api(

'https://api.example.com/data',

method='POST',

headers={'Authorization': 'Bearer YOUR_TOKEN', 'Content-Type': 'application/json'},

data={'keyword': 'test', 'page': 1}

)

if result:

print(json.dumps(result, ensure_ascii=False, indent=2))