Python自动化办公的十大场景脚本分享

import pandas as pd
from datetime import datetime

# 读取多个数据源
df1 = pd.read_csv('system_a_export.csv')
df2 = pd.read_excel('system_b_export.xlsx')

# 合并数据
merged = pd.merge(df1, df2, on='order_id', how='left')

# 添加统计
summary = merged.groupby('category')['amount'].sum().reset_index()

# 导出报表
today = datetime.now().strftime('%Y%m%d')
summary.to_excel(f'daily_report_{today}.xlsx', index=False)
print(f'日报已生成：daily_report_{today}.xlsx')

from PIL import Image
import os

def batch_compress_images(folder_path, quality=80):
    """批量压缩图片"""
    for filename in os.listdir(folder_path):
        if filename.endswith(('.jpg', '.png')):
            img = Image.open(os.path.join(folder_path, filename))
            img.save(
                os.path.join(folder_path, f'compressed_{filename}'),
                quality=quality,
                optimize=True
            )
    print(f'压缩完成：{folder_path}')

# 使用
batch_compress_images('./product_images')

import requests
from bs4 import BeautifulSoup
import schedule
import time

def check_price(url):
    """监控商品价格"""
    response = requests.get(url)
    soup = BeautifulSoup(response.text, 'html.parser')
    price = soup.find('span', {'class': 'price'}).text
    return price

def monitor():
    products = [
        ('竞品 A', 'https://example.com/product1'),
        ('竞品 B', 'https://example.com/product2'),
    ]
    
    for name, url in products:
        price = check_price(url)
        print(f'{name}: {price}')

# 每小时检查一次
schedule.every().hour.do(monitor)

while True:
    schedule.run_pending()
    time.sleep(60)

import smtplib
from email.mime.text import MIMEText

def send_email(subject, body, to_list):
    """发送邮件"""
    msg = MIMEText(body)
    msg['Subject'] = subject
    msg['From'] = 'your_email@example.com'
    msg['To'] = ', '.join(to_list)
    
    with smtplib.SMTP('smtp.example.com', 587) as server:
        server.starttls()
        server.login('your_email', 'your_password')
        server.send_message(msg)

# 使用
send_email(
    subject='项目进度更新',
    body='本周完成：xxx\n下周计划：xxx',
    to_list=['team@example.com']
)

import pandas as pd

def clean_data(file_path):
    """数据清洗"""
    df = pd.read_csv(file_path)
    
    # 删除空行
    df = df.dropna()
    
    # 删除重复
    df = df.drop_duplicates()
    
    # 格式标准化
    df['phone'] = df['phone'].str.replace('-', '')
    df['date'] = pd.to_datetime(df['date'])
    
    # 导出
    df.to_csv('cleaned_data.csv', index=False)
    return df

# 使用
clean_data('messy_data.csv')

from selenium import webdriver
from datetime import datetime

def capture_screenshot(url, save_path):
    """自动截图"""
    driver = webdriver.Chrome()
    driver.get(url)
    timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
    driver.save_screenshot(f'{save_path}_{timestamp}.png')
    driver.quit()

# 使用
capture_screenshot('https://example.com/dashboard', './screenshots/daily')

from selenium import webdriver
from selenium.webdriver.common.by import By

def auto_fill_form(url, data):
    """自动填表"""
    driver = webdriver.Chrome()
    driver.get(url)
    
    driver.find_element(By.NAME, 'username').send_keys(data['username'])
    driver.find_element(By.NAME, 'email').send_keys(data['email'])
    driver.find_element(By.NAME, 'phone').send_keys(data['phone'])
    driver.find_element(By.XPATH, '//button[@type="submit"]').click()
    
    driver.quit()

# 使用
data = {
    'username': 'your_name',
    'email': 'your@email.com',
    'phone': '13800138000'
}
auto_fill_form('https://example.com/register', data)

import shutil
from datetime import datetime

def backup_folder(source, dest):
    """自动备份文件夹"""
    timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
    backup_name = f'backup_{timestamp}'
    shutil.copytree(source, f'{dest}/{backup_name}')
    print(f'备份完成：{backup_name}')

# 使用
backup_folder('./important_files', './backups')

import requests
import json

def fetch_competitor_info(urls):
    """抓取竞品信息"""
    results = []
    for url in urls:
        response = requests.get(url)
        # 解析页面内容
        # ... 添加具体解析逻辑
        results.append({
            'url': url,
            'title': '竞品标题',
            'price': '价格',
            'timestamp': datetime.now().isoformat()
        })
    
    # 保存到文件
    with open('competitor_data.json', 'w') as f:
        json.dump(results, f, ensure_ascii=False, indent=2)
    
    return results

# 使用
urls = [
    'https://competitor1.com/product',
    'https://competitor2.com/product'
]
fetch_competitor_info(urls)

import schedule
import time

def job1():
    print('执行任务 1：发送日报')
    # 发送日报代码
    
def job2():
    print('执行任务 2：备份数据')
    # 备份代码

# 设置定时
schedule.every().day.at("09:00").do(job1)
schedule.every().friday.at("18:00").do(job2)

# 持续运行
while True:
    schedule.run_pending()
    time.sleep(60)