Python 自动化脚本实战：从入门到生产力

Python 是自动化领域的首选语言：语法简洁、库生态丰富、跨平台。无论是文件处理、网页抓取、API 调用还是系统管理，Python 都能搞定。

1. 文件批量处理

批量重命名文件

import os
import re

def batch_rename(folder, pattern, replacement):
    """批量重命名文件夹中的文件"""
    for filename in os.listdir(folder):
        new_name = re.sub(pattern, replacement, filename)
        if new_name != filename:
            old_path = os.path.join(folder, filename)
            new_path = os.path.join(folder, new_name)
            os.rename(old_path, new_path)
            print(f"Renamed: {filename} → {new_name}")

# 示例：给所有 .txt 文件加前缀
batch_rename("./docs", r"^", "2025-")

批量转换文件格式

import csv
import json

def csv_to_json(csv_file, json_file):
    """CSV 转 JSON"""
    with open(csv_file, 'r') as f:
        reader = csv.DictReader(f)
        data = list(reader)

    with open(json_file, 'w') as f:
        json.dump(data, f, indent=2, ensure_ascii=False)

    print(f"Converted {len(data)} rows: {csv_file} → {json_file}")

2. 网页抓取

用 requests + BeautifulSoup 抓取

import requests
from bs4 import BeautifulSoup

def scrape_titles(url):
    """抓取网页中的所有标题"""
    resp = requests.get(url, headers={'User-Agent': 'Mozilla/5.0'})
    soup = BeautifulSoup(resp.text, 'html.parser')

    titles = []
    for tag in ['h1', 'h2', 'h3']:
        for elem in soup.find_all(tag):
            titles.append(elem.get_text(strip=True))

    return titles

用 Selenium 处理动态页面

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

def scrape_dynamic(url):
    """抓取 JavaScript 渲染的页面"""
    options = webdriver.ChromeOptions()
    options.add_argument('--headless')
    driver = webdriver.Chrome(options=options)

    driver.get(url)
    elements = driver.find_elements(By.CSS_SELECTOR, '.result-item')
    data = [e.text for e in elements]

    driver.quit()
    return data

3. API 调用自动化

REST API 封装

import requests
from typing import Optional, Dict, Any

class APIClient:
    def __init__(self, base_url: str, api_key: str):
        self.base_url = base_url
        self.session = requests.Session()
        self.session.headers.update({
            'Authorization': f'Bearer {api_key}',
            'Content-Type': 'application/json'
        })

    def get(self, path: str, params: Optional[Dict] = None) -> Any:
        resp = self.session.get(f"{self.base_url}{path}", params=params)
        resp.raise_for_status()
        return resp.json()

    def post(self, path: str, data: Dict) -> Any:
        resp = self.session.post(f"{self.base_url}{path}", json=data)
        resp.raise_for_status()
        return resp.json()

    def put(self, path: str, data: Dict) -> Any:
        resp = self.session.put(f"{self.base_url}{path}", json=data)
        resp.raise_for_status()
        return resp.json()

4. 系统管理

磁盘空间监控

import shutil
import smtplib
from email.mime.text import MIMEText

def check_disk_usage(threshold=80):
    """检查磁盘使用率，超过阈值发邮件"""
    usage = shutil.disk_usage('/')
    percent = usage.used / usage.total * 100

    if percent > threshold:
        msg = MIMEText(f"Disk usage: {percent:.1f}%")
        msg['Subject'] = f"⚠️ Disk Alert: {percent:.1f}% used"
        msg['From'] = '[e-mail]'
        msg['To'] = '[e-mail]'

        with smtplib.SMTP('localhost') as smtp:
            smtp.send_message(msg)

    return percent

进程监控

import psutil
import time

def monitor_process(name, interval=60):
    """监控进程是否存在，不存在则重启"""
    while True:
        running = any(p.name() == name for p in psutil.process_iter(['name']))
        if not running:
            print(f"Process {name} not found, restarting...")
            # subprocess.Popen([name])
        time.sleep(interval)

5. 定时任务

用 schedule 库

import schedule
import time

def job():
    print("Running scheduled task...")

# 每天 9:00 执行
schedule.every().day.at("09:00").do(job)

# 每小时执行
schedule.every().hour.do(job)

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

总结

Python 自动化的核心优势：

1. 快速开发：几行代码就能搞定复杂任务
2. 丰富生态：requests, beautifulsoup, selenium, psutil...
3. 跨平台：Windows/macOS/Linux 都能跑
4. 易于维护：代码简洁，逻辑清晰

从今天开始，把重复性工作交给 Python 吧！