20 个实用 Python 自动化脚本技巧

20 个实用 Python 自动化脚本技巧 | 极客日志

# Python 脚本按扩展名在目录中对文件进行排序
import os
from shutil import move

def sort_files(directory_path):
    for filename in os.listdir(directory_path):
        if os.path.isfile(os.path.join(directory_path, filename)):
            file_extension = filename.split('.')[-1]
            destination_directory = os.path.join(directory_path, file_extension)
            if not os.path.exists(destination_directory):
                os.makedirs(destination_directory)
            move(os.path.join(directory_path, filename), os.path.join(destination_directory, filename))

# Python 脚本在目录中删除空文件夹
import os

def remove_empty_folders(directory_path):
    for root, dirs, files in os.walk(directory_path, topdown=False):
        for folder in dirs:
            folder_path = os.path.join(root, folder)
            if not os.listdir(folder_path):
                os.rmdir(folder_path)

# Python 脚本在目录中重命名多个文件
import os

def rename_files(directory_path, old_name, new_name):
    for filename in os.listdir(directory_path):
        if old_name in filename:
            new_filename = filename.replace(old_name, new_name)
            os.rename(os.path.join(directory_path, filename), os.path.join(directory_path, new_filename))

# Python 脚本用于网络抓取，从网站提取数据
import requests
from bs4 import BeautifulSoup

def scrape_data(url):
    response = requests.get(url)
    soup = BeautifulSoup(response.text, 'html.parser')
    # 从网站提取相关数据的代码在此处

# Python 脚本从网站批量下载图片
import requests

def download_images(url, save_directory):
    response = requests.get(url)
    if response.status_code == 200:
        images = response.json() # 假设 API 返回一个图片 URL 的 JSON 数组
        for index, image_url in enumerate(images):
            image_response = requests.get(image_url)
            if image_response.status_code == 200:
                with open(f"{save_directory}/image_{index}.jpg", "wb") as f:
                    f.write(image_response.content)

# Python 脚本自动化网站上的表单提交
import requests

def submit_form(url, form_data):
    response = requests.post(url, data=form_data)
    if response.status_code == 200:
        # 在此处处理表单提交后的响应

# Python 脚本计算文本文件中的单词数
def count_words(file_path):
    with open(file_path, 'r') as f:
        text = f.read()
        word_count = len(text.split())
    return word_count

# Python 脚本在文件中查找和替换文本
def find_replace(file_path, search_text, replace_text):
    with open(file_path, 'r') as f:
        text = f.read()
        modified_text = text.replace(search_text, replace_text)
    with open(file_path, 'w') as f:
        f.write(modified_text)

# Python 脚本生成随机文本
import random
import string

def generate_random_text(length):
    letters = string.ascii_letters + string.digits + string.punctuation
    random_text = ''.join(random.choice(letters) for i in range(length))
    return random_text

# Python 脚本发送个性化邮件给收件人列表
import smtplib
from email.mime.text import MIMEText
from email.mime.multipart import MIMEMultipart

def send_personalized_email(sender_email, sender_password, recipients, subject, body):
    server = smtplib.SMTP('smtp.gmail.com', 587)
    server.starttls()
    server.login(sender_email, sender_password)
    for recipient_email in recipients:
        message = MIMEMultipart()
        message['From'] = sender_email
        message['To'] = recipient_email
        message['Subject'] = subject
        message.attach(MIMEText(body, 'plain'))
        server.sendmail(sender_email, recipient_email, message.as_string())
    server.quit()

# Python 脚本发送带有文件附件的邮件
import smtplib
from email.mime.multipart import MIMEMultipart
from email.mime.base import MIMEBase
from email import encoders

def send_email_with_attachment(sender_email, sender_password, recipient_email, subject, body, file_path):
    server = smtplib.SMTP('smtp.gmail.com', 587)
    server.starttls()
    server.login(sender_email, sender_password)
    message = MIMEMultipart()
    message['From'] = sender_email
    message['To'] = recipient_email
    message['Subject'] = subject
    message.attach(MIMEText(body, 'plain'))
    with open(file_path, "rb") as attachment:
        part = MIMEBase('application', 'octet-stream')
        part.set_payload(attachment.read())
        encoders.encode_base64(part)
        part.add_header('Content-Disposition', f"attachment; filename= {file_path}")
        message.attach(part)
    server.sendmail(sender_email, recipient_email, message.as_string())
    server.quit()

# Python 脚本发送自动邮件提醒
import smtplib
from email.mime.text import MIMEText
from datetime import datetime, timedelta

def send_reminder_email(sender_email, sender_password, recipient_email, subject, body, reminder_date):
    server = smtplib.SMTP('smtp.gmail.com', 587)
    server.starttls()
    server.login(sender_email, sender_password)
    now = datetime.now()
    reminder_date = datetime.strptime(reminder_date, '%Y-%m-%d')
    if now.date() == reminder_date.date():
        message = MIMEText(body, 'plain')
        message['From'] = sender_email
        message['To'] = recipient_email
        message['Subject'] = subject
        server.sendmail(sender_email, recipient_email, message.as_string())
    server.quit()

# Python 脚本读取和写入 Excel 电子表格中的数据
import pandas as pd

def read_excel(file_path):
    df = pd.read_excel(file_path)
    return df

def write_to_excel(data, file_path):
    df = pd.DataFrame(data)
    df.to_excel(file_path, index=False)

# 使用 pandas 和 matplotlib 进行数据分析和可视化的 Python 脚本
import pandas as pd
import matplotlib.pyplot as plt

def analyze_and_visualize_data(data):
    # 在此处进行数据分析和可视化的代码
    pass

# Python 脚本合并多个 Excel 电子表格
import pandas as pd

def merge_spreadsheets(file_paths, output_file_path):
    all_data = []
    for file_path in file_paths:
        df = pd.read_excel(file_path)
        all_data.append(df)
    merged_data = pd.concat(all_data, ignore_index=True)
    merged_data.to_excel(output_file_path, index=False)

# Python 脚本连接到数据库并执行查询
import sqlite3

def connect_to_database(database_path):
    connection = sqlite3.connect(database_path)
    cursor = connection.cursor()
    return cursor

def execute_query(cursor, query):
    cursor.execute(query)
    results = cursor.fetchall()
    return results

# Python 脚本备份数据库
import shutil

def backup_database(database_path, backup_path):
    shutil.copy(database_path, backup_path)

# Python 脚本迁移数据库数据
import sqlite3

def migrate_data(source_database, target_database):
    source_connection = sqlite3.connect(source_database)
    target_connection = sqlite3.connect(target_database)
    source_cursor = source_connection.cursor()
    target_cursor = target_connection.cursor()
    # 在此处添加迁移数据的代码
    source_connection.close()
    target_connection.close()

# Python 脚本自动发布推文到 Twitter
import tweepy

def post_to_twitter(consumer_key, consumer_secret, access_token, access_token_secret, tweet_text):
    auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
    auth.set_access_token(access_token, access_token_secret)
    api = tweepy.API(auth)
    api.update_status(status=tweet_text)

# Python 脚本自动发布图片到 Instagram
from instabot import Bot

def post_to_instagram(username, password, image_path, caption):
    bot = Bot()
    bot.login(username=username, password=password)
    bot.upload_photo(image_path, caption=caption)

# Python 脚本自动发布状态到 Facebook
import facebook

def post_to_facebook(access_token, message):
    graph = facebook.GraphAPI(access_token)
    graph.put_object(parent_object='me', connection_name='feed', message=message)

# Python 脚本自动关机计算机
import os

def shutdown_computer():
    os.system("shutdown /s /t 1")

# Python 脚本自动备份文件到指定目录
import shutil

def backup_files(source_directory, backup_directory):
    shutil.copytree(source_directory, backup_directory)

# Python 脚本自动更新软件
import os

def update_software():
    os.system("sudo apt-get update && sudo apt-get upgrade")

# Python 脚本批量重命名目录中的图片
import os

def rename_images(directory_path, prefix):
    for index, filename in enumerate(os.listdir(directory_path)):
        if filename.endswith(('.jpg', '.jpeg', '.png')):
            new_filename = f"{prefix}_{index}.jpg"
            os.rename(os.path.join(directory_path, filename), os.path.join(directory_path, new_filename))

# Python 脚本批量调整目录中的图片大小
from PIL import Image
import os

def resize_images(directory_path, width, height):
    for filename in os.listdir(directory_path):
        if filename.endswith(('.jpg', '.jpeg', '.png')):
            image_path = os.path.join(directory_path, filename)
            img = Image.open(image_path)
            img = img.resize((width, height))
            img.save(image_path)

# Python 脚本批量转换目录中的图片格式
from PIL import Image
import os

def convert_images(directory_path, output_format):
    for filename in os.listdir(directory_path):
        if filename.endswith(('.jpg', '.jpeg', '.png')):
            image_path = os.path.join(directory_path, filename)
            img = Image.open(image_path)
            new_filename = os.path.splitext(filename)[0] + f".{output_format}"
            img.save(os.path.join(directory_path, new_filename))

# Python 脚本自动连接到 VPN
import os

def connect_to_vpn(vpn_name):
    os.system(f"rasdial {vpn_name}")

# Python 脚本自动检测网络连接
import os

def check_network_connection():
    response = os.system("ping -c 1 google.com")
    if response == 0:
        return True
    else:
        return False

# Python 脚本自动从 URL 下载文件
import requests

def download_file(url, save_path):
    response = requests.get(url)
    with open(save_path, 'wb') as f:
        f.write(response.content)

# Python 脚本清理 CSV 文件中的数据
import pandas as pd

def clean_csv(file_path):
    df = pd.read_csv(file_path)
    # 在此处添加清理数据的代码
    df.to_csv(file_path, index=False)

# Python 脚本转换 CSV 文件到 JSON 格式
import pandas as pd

def csv_to_json(csv_file_path, json_file_path):
    df = pd.read_csv(csv_file_path)
    df.to_json(json_file_path, orient='records')

# Python 脚本转换 JSON 文件到 CSV 格式
import pandas as pd

def json_to_csv(json_file_path, csv_file_path):
    df = pd.read_json(json_file_path)
    df.to_csv(csv_file_path, index=False)

# Python 脚本合并多个 PDF 文件到一个文件
from PyPDF2 import PdfFileReader, PdfFileWriter

def merge_pdfs(pdf_file_paths, output_file_path):
    pdf_writer = PdfFileWriter()
    for pdf_file_path in pdf_file_paths:
        pdf_reader = PdfFileReader(pdf_file_path)
        for page_num in range(pdf_reader.numPages):
            page = pdf_reader.getPage(page_num)
            pdf_writer.addPage(page)
    with open(output_file_path, 'wb') as f:
        pdf_writer.write(f)

# Python 脚本从 PDF 文件提取文本
from PyPDF2 import PdfFileReader

def extract_text_from_pdf(pdf_file_path):
    pdf_reader = PdfFileReader(pdf_file_path)
    text = ""
    for page_num in range(pdf_reader.numPages):
        page = pdf_reader.getPage(page_num)
        text += page.extractText()
    return text

# Python 脚本加密 PDF 文件
from PyPDF2 import PdfFileReader, PdfFileWriter

def encrypt_pdf(pdf_file_path, output_file_path, password):
    pdf_reader = PdfFileReader(pdf_file_path)
    pdf_writer = PdfFileWriter()
    for page_num in range(pdf_reader.numPages):
        page = pdf_reader.getPage(page_num)
        pdf_writer.addPage(page)
    pdf_writer.encrypt(password)
    with open(output_file_path, 'wb') as f:
        pdf_writer.write(f)

# Python 脚本自动点击屏幕上的坐标
import pyautogui

def click_screen(x, y):
    pyautogui.click(x, y)

# Python 脚本自动填写屏幕上的表单
import pyautogui

def fill_form(fields):
    for field in fields:
        pyautogui.click(field['x'], field['y'])
        pyautogui.write(field['text'])

# Python 脚本自动截取屏幕上的区域
import pyautogui

def screenshot_region(x, y, width, height, save_path):
    screenshot = pyautogui.screenshot(region=(x, y, width, height))
    screenshot.save(save_path)

# Python 脚本自动化网站测试
from selenium import webdriver

def test_website(url):
    driver = webdriver.Chrome()
    driver.get(url)
    # 在此处添加自动化测试的代码
    driver.quit()

# Python 脚本自动化 API 测试
import requests

def test_api(api_url, method, headers, data):
    if method == 'GET':
        response = requests.get(api_url, headers=headers)
    elif method == 'POST':
        response = requests.post(api_url, headers=headers, data=data)
    # 在此处添加 API 测试的代码
    return response

# Python 脚本自动化 UI 测试
from selenium import webdriver

def test_ui(ui_elements):
    driver = webdriver.Chrome()
    for element in ui_elements:
        driver.find_element_by_id(element['id']).click()
        # 在此处添加 UI 测试的代码
    driver.quit()

# Python 脚本自动上传文件到 Google Drive
from pydrive.auth import GoogleAuth
from pydrive.drive import GoogleDrive

def upload_to_google_drive(file_path):
    gauth = GoogleAuth()
    gauth.LocalWebserverAuth()
    drive = GoogleDrive(gauth)
    file = drive.CreateFile()
    file.SetContentFile(file_path)
    file.Upload()

# Python 脚本自动从 Amazon S3 下载文件
import boto3

def download_from_s3(bucket_name, file_key, save_path):
    s3 = boto3.client('s3')
    s3.download_file(bucket_name, file_key, save_path)

# Python 脚本自动备份数据库到 Azure Blob Storage
from azure.storage.blob import BlobServiceClient

def backup_to_azure_blob(connection_string, container_name, database_path, blob_name):
    blob_service_client = BlobServiceClient.from_connection_string(connection_string)
    blob_client = blob_service_client.get_blob_client(container=container_name, blob=blob_name)
    with open(database_path, "rb") as f:
        blob_client.upload_blob(f)

# Python 脚本自动化获取股票数据
import yfinance as yf

def get_stock_data(ticker_symbol, start_date, end_date):
    stock = yf.Ticker(ticker_symbol)
    data = stock.history(start=start_date, end=end_date)
    return data

# Python 脚本自动化生成发票
from fpdf import FPDF

def generate_invoice(client_name, items, total_amount, save_path):
    pdf = FPDF()
    pdf.add_page()
    pdf.set_font("Arial", size=12)
    pdf.cell(200, 10, txt=f"Invoice for {client_name}", ln=True, align='C')
    for item in items:
        pdf.cell(200, 10, txt=item, ln=True)
    pdf.cell(200, 10, txt=f"Total Amount: ${total_amount}", ln=True, align='R')
    pdf.output(save_path)

# Python 脚本自动化跟踪预算
import pandas as pd

def track_budget(expenses, budget):
    total_expenses = sum(expenses)
    remaining_budget = budget - total_expenses
    return remaining_budget

# Python 脚本自动化数据预处理
import pandas as pd
from sklearn.preprocessing import StandardScaler

def preprocess_data(data):
    scaler = StandardScaler()
    scaled_data = scaler.fit_transform(data)
    return scaled_data

# Python 脚本自动化模型训练
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split

def train_model(data, target):
    X_train, X_test, y_train, y_test = train_test_split(data, target, test_size=0.2)
    model = LinearRegression()
    model.fit(X_train, y_train)
    return model

# Python 脚本自动化模型评估
from sklearn.metrics import mean_squared_error

def evaluate_model(model, X_test, y_test):
    predictions = model.predict(X_test)
    mse = mean_squared_error(y_test, predictions)
    return mse

# Python 脚本自动化转换音频格式
from pydub import AudioSegment

def convert_audio(input_file, output_format):
    audio = AudioSegment.from_file(input_file)
    output_file = input_file.split('.')[0] + f".{output_format}"
    audio.export(output_file, format=output_format)

# Python 脚本自动化剪辑视频
from moviepy.editor import VideoFileClip

def clip_video(input_file, start_time, end_time, output_file):
    video = VideoFileClip(input_file)
    clipped_video = video.subclip(start_time, end_time)
    clipped_video.write_videofile(output_file)

# Python 脚本自动化转换视频格式
from moviepy.editor import VideoFileClip

def convert_video(input_file, output_format):
    video = VideoFileClip(input_file)
    output_file = input_file.split('.')[0] + f".{output_format}"
    video.write_videofile(output_file)

# Python 脚本自动化模拟游戏玩家输入
import pyautogui

def simulate_game_input(keys):
    for key in keys:
        pyautogui.press(key)

# Python 脚本自动化测试游戏性能
import time

def test_game_performance(game_function):
    start_time = time.time()
    game_function()
    end_time = time.time()
    performance_time = end_time - start_time
    return performance_time

# Python 脚本自动化下载和安装游戏更新
import os

def update_game(update_url, save_path):
    response = requests.get(update_url)
    with open(save_path, 'wb') as f:
        f.write(response.content)
    os.system(f"install {save_path}")

# Python 脚本自动化生成随机密码
import random
import string

def generate_password(length):
    characters = string.ascii_letters + string.digits + string.punctuation
    password = ''.join(random.choice(characters) for i in range(length))
    return password

# Python 脚本自动化加密文件
from cryptography.fernet import Fernet

def encrypt_file(file_path, key):
    cipher = Fernet(key)
    with open(file_path, 'rb') as f:
        file_data = f.read()
    encrypted_data = cipher.encrypt(file_data)
    with open(file_path, 'wb') as f:
        f.write(encrypted_data)

# Python 脚本自动化解密文件
from cryptography.fernet import Fernet

def decrypt_file(file_path, key):
    cipher = Fernet(key)
    with open(file_path, 'rb') as f:
        encrypted_data = f.read()
    decrypted_data = cipher.decrypt(encrypted_data)
    with open(file_path, 'wb') as f:
        f.write(decrypted_data)

20 个实用 Python 自动化脚本技巧

前言

简介

1. 文件管理自动化

1.1 在目录中按扩展名排序文件

1.2 删除空文件夹

1.3 重命名多个文件

2. 使用 Python 进行网络抓取

2.1 从网站提取数据

2.2 批量下载图片

2.3 自动化表单提交

3. 文本处理和操作

3.1 计算文本文件中的单词数

3.2 查找和替换文本

3.3 生成随机文本

4. 邮件自动化

4.1 发送个性化邮件

4.2 邮件附件

4.3 自动邮件提醒

5. Excel 电子表格自动化

5.1 读取和写入 Excel

5.2 数据分析和可视化

5.3 合并多个表格

6. 与数据库交互

6.1 连接到数据库

6.2 数据库备份

6.3 数据库迁移

7. 社交媒体自动化

7.1 自动发布到 Twitter(同理其它）

7.2 自动发布到 Instagram

7.3 自动发布到 Facebook

8. 系统任务自动化

8.1 自动关机计算机

8.2 自动备份文件

8.3 自动更新软件

9. 图像编辑自动化

9.1 批量重命名图片

9.2 批量调整图片大小

9.3 批量转换图片格式

10. 网络自动化

10.1 自动连接到 VPN

10.2 自动检测网络连接

10.3 自动下载文件

11. 数据清理和转换

11.1 清理 CSV 文件

11.2 转换 CSV 到 JSON

11.3 转换 JSON 到 CSV

12. PDF 操作自动化

12.1 合并多个 PDF 文件

12.2 提取 PDF 文本

12.3 加密 PDF 文件

13. GUI 自动化

13.1 自动点击屏幕

13.2 自动填写表单

13.3 自动截屏

14. 测试自动化

14.1 自动化网站测试

14.2 自动化 API 测试

14.3 自动化 UI 测试

15. 云服务自动化

15.1 自动上传文件到 Google Drive

15.2 自动下载文件从 Amazon S3

15.3 自动备份数据库到 Azure Blob Storage

16. 财务自动化

16.1 自动化股票数据获取

16.2 自动化发票生成

16.3 自动化预算跟踪

17. 机器学习自动化

17.1 自动化数据预处理

17.2 自动化模型训练

17.3 自动化模型评估

18. 音频和视频自动化

18.1 自动化音频转换

18.2 自动化视频剪辑

18.3 自动化视频转换

19. 游戏自动化

19.1 自动化游戏玩家输入

19.2 自动化游戏测试

19.3 自动化游戏更新

20. 安全性自动化