其他
独家 | 17个可以用于工作自动化的最佳Python脚本(上集)
翻译:付雯欣校对:赵茹萱
本文约5000字,建议阅读10分钟
我们将通过上下两个篇章为您介绍17个能够自动执行各种任务并提高工作效率Python脚本及其代码。
引言
目录(上篇)
1.自动化文件管理
1.1 对目录中的文件进行排序
```
# Python script to sort files in a directory by their extension
import os
fromshutil 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))
```
1.2 删除空文件夹
```
# Python script to remove empty folders in a directory
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)
```
1.3 重命名多个文件
```
# Python script to rename multiple files in a directory
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))
```
2. 使用Python进行网页抓取
2.1从网站提取数据
```
# Python script for web scraping to extract data from a website
import requests
from bs4 import BeautifulSoup
def scrape_data(url):
response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')
# Your code here to extract relevant data from the website
```
2.2从网站提取数据
```
# Python script to download images in bulk from a website
import requests
def download_images(url, save_directory):
response = requests.get(url)
if response.status_code == 200:
images = response.json() # Assuming the API returns a JSON array of image URLs
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)
```
2.3自动提交表单
```
# Python script to automate form submissions on a website
import requests
def submit_form(url, form_data):
response = requests.post(url, data=form_data)
if response.status_code == 200:
# Your code here to handle the response after form submission
```
3. 文本处理和操作
3.1计算文本文件中的字数
```
# Python script to count words in a text file
def count_words(file_path):
with open(file_path, 'r') as f:
text = f.read()
word_count = len(text.split())
return word_count
```
3.2从网站提取数据
```
# Python script to find and replace text in a file
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)
```
3.3生成随机文本
```
# Python script to generate random text
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
```
4.电子邮件自动化
4.1发送个性化电子邮件
```
# Python script to send personalized emails to a list of recipients
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()
```
4.2通过电子邮件发送文件附件
```
# Python script to send emails with file attachments
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()
```
此 Python 脚本允许您发送带有文件附件的电子邮件。只需提供发件人的电子邮件、密码、收件人的电子邮件、主题、正文以及要附加的文件的路径。
4.3自动邮件提醒
```
# Python script to send automatic email reminders
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()
```
5.自动化Excel电子表格
5.1Excel读&写
```
# Python script to read and write data to an Excel spreadsheet
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)
```
5.2数据分析和可视化
```
# Python script for data analysis and visualization with pandas and matplotlib
import pandas as pd
import matplotlib.pyplot as plt
def analyze_and_visualize_data(data):
# Your code here for data analysis and visualization
pass
```
此Python脚本使用pandas和matplotlib库来进行数据分析和可视化。它使您能够探索数据集、得出结论并得到数据的可视化表示。
5.3合并多个工作表
```
# Python script to merge multiple Excel sheets into a single sheet
import pandas as pd
def merge_sheets(file_path, output_file_path):
xls = pd.ExcelFile(file_path)
df = pd.DataFrame()
for sheet_name in xls.sheet_names:
sheet_df = pd.read_excel(xls, sheet_name)
df = df.append(sheet_df)
df.to_excel(output_file_path, index=False)
```
6.与数据库交互
6.1连接到一个数据库
```
# Python script to connect to a database and execute queries
import sqlite3
def connect_to_database(database_path):
connection = sqlite3.connect(database_path)
return connection
def execute_query(connection, query):
cursor = connection.cursor()
cursor.execute(query)
result = cursor.fetchall()
return result
```
此Python脚本允许您连接到SQLite数据库并执行查询。您可以使用适当的Python数据库驱动程序将其调整为与其他数据库管理系统(例如MySQL或PostgreSQL)配合使用。
6.2执行SQL查询
```
# Python script to execute SQL queries on a database
import sqlite3
def execute_query(connection, query):
cursor = connection.cursor()
cursor.execute(query)
result = cursor.fetchall()
return result
```
6.3数据备份与恢复
```
import shutil
def backup_database(database_path, backup_directory):
shutil.copy(database_path, backup_directory)
def restore_database(backup_path, database_directory):
shutil.copy(backup_path, database_directory)
```
7.社交媒体自动化
7.1发送个性化电子邮件
```
# Python script to automate posting on Twitter and Facebook
from twython import Twython
import facebook
def post_to_twitter(api_key, api_secret, access_token, access_token_secret, message):
twitter = Twython(api_key, api_secret, access_token, access_token_secret)
twitter.update_status(status=message)
def post_to_facebook(api_key, api_secret, access_token, message):
graph = facebook.GraphAPI(access_token)
graph.put_object(parent_object='me', connection_name='feed', message=message)
```
此 Python 脚本利用Twython和facebook-sdk库自动在Twitter和Facebook上发布内容。您可以使用它将 Python 脚本中的更新、公告或内容直接共享到您的社交媒体配置文件。
7.2社交媒体自动共享
```
# Python script to automatically share content on social media platforms
import random
def get_random_content():
# Your code here to retrieve random content from a list or database
pass
def post_random_content_to_twitter(api_key, api_secret, access_token, access_token_secret):
content = get_random_content()
post_to_twitter(api_key, api_secret, access_token, access_token_secret, content)
def post_random_content_to_facebook(api_key, api_secret, access_token):
content = get_random_content()
post_to_facebook(api_key, api_secret, access_token, content)
```
7.3 抓取社交媒体数据
```
# Python script for scraping data from social media platforms
import requests
def scrape_social_media_data(url):
response = requests.get(url)
# Your code here to extract relevant data from the response
```
8.自动化系统任务
8.1管理系统进程
```
# Python script to manage system processes
import psutil
def get_running_processes():
return [p.info for p in psutil.process_iter(['pid', 'name', 'username'])]
def kill_process_by_name(process_name):
for p in psutil.process_iter(['pid', 'name', 'username']):
if p.info['name'] == process_name:
p.kill()
```
8.2使用 Cron 安排任务
```
# Python script to schedule tasks using cron syntax
from crontab import CronTab
def schedule_task(command, schedule):
cron = CronTab(user=True)
job = cron.new(command=command)
job.setall(schedule)
cron.write()
```
8.3自动邮件提醒
```
# Python script to monitor disk space and send an alert if it's low
import psutil
def check_disk_space(minimum_threshold_gb):
disk = psutil.disk_usage('/')
free_space_gb = disk.free / (230) # Convert bytes to GB
if free_space_gb < minimum_threshold_gb:
# Your code here to send an alert (email, notification, etc.)
pass
```
9.自动化图像编辑
9.1图像大小调整和裁剪
```
# Python script to resize and crop images
from PIL import Image
def resize_image(input_path, output_path, width, height):
image = Image.open(input_path)
resized_image = image.resize((width, height), Image.ANTIALIAS)
resized_image.save(output_path)
def crop_image(input_path, output_path, left, top, right, bottom):
image = Image.open(input_path)
cropped_image = image.crop((left, top, right, bottom))
cropped_image.save(output_path)
```
9.2为图像添加水印
```
# Python script to add watermarks to images
from PIL import Image
from PIL import ImageDraw
from PIL import ImageFont
def add_watermark(input_path, output_path, watermark_text):
image = Image.open(input_path)
draw = ImageDraw.Draw(image)
font = ImageFont.truetype('arial.ttf', 36)
draw.text((10, 10), watermark_text, fill=(255, 255, 255, 128), font=font)
image.save(output_path)
```
```
# Python script to create image thumbnails
from PIL import Image
def create_thumbnail(input_path, output_path, size=(128, 128)):
image = Image.open(input_path)
image.thumbnail(size)
image.save(output_path)
```
结论
译者简介
付雯欣,中国人民大学统计学专业硕士研究生在读,数据科学道路上的探索者一枚。小时候梦想做数学家,现在依旧着迷于数据背后的世界。热爱阅读,热爱遛弯儿,不停感受打开生命大门的瞬间。欢迎大家和我一起用概率的视角看世界~
翻译组招募信息
工作内容:需要一颗细致的心,将选取好的外文文章翻译成流畅的中文。如果你是数据科学/统计学/计算机类的留学生,或在海外从事相关工作,或对自己外语水平有信心的朋友欢迎加入翻译小组。
你能得到:定期的翻译培训提高志愿者的翻译水平,提高对于数据科学前沿的认知,海外的朋友可以和国内技术应用发展保持联系,THU数据派产学研的背景为志愿者带来好的发展机遇。
其他福利:来自于名企的数据科学工作者,北大清华以及海外等名校学生他们都将成为你在翻译小组的伙伴。
点击文末“阅读原文”加入数据派团队~
转载须知
如需转载,请在开篇显著位置注明作者和出处(转自:数据派ID:DatapiTHU),并在文章结尾放置数据派醒目二维码。有原创标识文章,请发送【文章名称-待授权公众号名称及ID】至联系邮箱,申请白名单授权并按要求编辑。
发布后请将链接反馈至联系邮箱(见下方)。未经许可的转载以及改编者,我们将依法追究其法律责任。
点击“阅读原文”拥抱组织