Automation & scripting
CLI tools, scheduled jobs, filesystem tasks, and glue scripts that save time.
Automatically Clean Temporary Files from Applications Using Python
A Python script that safely deletes temporary files from common application temp directories across Windows, Linux, and macOS, tracking cleaned count and disk space.
import os
import shutil
import tempfile
import platform
def clean_application_temp_files():
"""Delete common temporary file locations safely."""
system = platform.system()
temp_dirs = []
if system == "Windows":
temp_dirs.extend([
os.path.join(os.getenv("LOCALAPPDATA"), "Temp"),
…Automatically Download the Latest Software Release from GitHub with Python
Use the GitHub API to fetch the latest release metadata and download the first asset (binary or archive) to a local directory.
import requests
import sys
from pathlib import Path
def download_latest_release(owner: str, repo: str, output_dir: str = ".") -> None:
"""Download the latest release asset from a GitHub repository."""
url = f"https://api.github.com/repos/{owner}/{repo}/releases/latest"
response = requests.get(url)
res…Automatically Generate Charts from CSV Files with One Command
Read a CSV file with headers, extract the first two numeric columns, and save a matplotlib line chart as a PNG image.
import csv
import sys
from pathlib import Path
import matplotlib.pyplot as plt
def generate_chart(csv_path: str) -> None:
"""Read a CSV file with headers and plot the first two numeric columns."""
data = []
with open(csv_path, 'r', newline='') as f:
reader = csv.reader(f)
headers = next(re…Build a Complete Web Scraper with Requests and BeautifulSoup in Python
Scrape multiple paginated pages from a website using Requests and BeautifulSoup, with retry logic, error handling, and CSV export.
import requests
from bs4 import BeautifulSoup
import csv
import time
from typing import List, Dict, Optional
class WebScraper:
def __init__(self, base_url: str, output_file: str = "scraped_data.csv"):
self.base_url = base_url
self.output_file = output_file
self.session = requests.Session()…Build an RSS feed from markdown blog posts in Python
Scans a folder of markdown files, extracts titles, dates, and excerpts, and generates a valid RSS 2.0 XML feed.
import re
from pathlib import Path
from xml.etree.ElementTree import Element, SubElement, tostring
from datetime import datetime, timezone
from xml.dom import minidom
def build_rss(blog_dir, site_url="https://example.com"):
feed = Element("rss", version="2.0")
channel = SubElement(feed, "channel")
SubElem…Convert DOCX to Text by Unzipping XML in Python
Extract plain text from a .docx file by unzipping the container and parsing word/document.xml with regex, using only Python's standard library.
import zipfile
import re
from pathlib import Path
def docx_to_text_unzip_xml(docx_path: str) -> str:
"""Extract plain text from a .docx file by unzipping and parsing document.xml."""
docx_path = Path(docx_path)
if not docx_path.exists():
raise FileNotFoundError(f"File not found: {docx_path}")
…Discover RSS Feeds From Any Website in Python
Scrape a website's HTML to automatically find all linked RSS or Atom feed URLs using requests, BeautifulSoup, and regex.
import requests
import re
from urllib.parse import urljoin, urlparse
from bs4 import BeautifulSoup
def discover_rss_feeds(url):
"""Discover all RSS/Atom feeds linked from a given website."""
try:
headers = {'User-Agent': 'Mozilla/5.0 (compatible; RSSDiscovery/1.0)'}
response = requests.get(url…Download Images from a Web Page Automatically in Python
Scrape all images from a webpage, filter by extension, and save them to a local folder using requests and BeautifulSoup.
import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin
import os
def download_images(url, output_folder="downloaded_images"):
"""Download all images from a given URL."""
os.makedirs(output_folder, exist_ok=True)
response = requests.get(url)
response.raise_for_status()
…Extract All Links from Any Website in Python
Scrape a webpage and extract all absolute HTTP/HTTPS links using requests and regex.
import requests
import re
from urllib.parse import urljoin
def extract_links(url):
try:
response = requests.get(url)
response.raise_for_status()
html = response.text
# Find all href attributes in anchor tags
pattern = r'href=["\'](.*?)["\']'
raw_links = re.findall(p…Extract Attachments from mbox Mailbox Files in Python
Extract file attachments from an mbox mailbox format using Python's standard library email and mailbox modules.
import email
import mailbox
from email.policy import default
from pathlib import Path
def extract_attachments(mbox_path, output_dir):
output_dir = Path(output_dir)
output_dir.mkdir(exist_ok=True)
mbox = mailbox.mbox(mbox_path)
for msg in mbox:
if msg.is_multipart():
for part i…Extract Every Open Graph and Social Media Meta Tag from Web Pages in Python
A Python script that fetches a webpage and extracts all Open Graph, Twitter Card, Facebook, and Article meta tags using the standard library HTML parser.
from html.parser import HTMLParser
import re
from urllib.request import urlopen
from urllib.parse import urlparse
class MetaExtractor(HTMLParser):
def __init__(self):
super().__init__()
self.meta_tags = []
def handle_starttag(self, tag, attrs):
if tag == 'meta':
attrs_…Find All Redirects on a Website in Python
Crawl a website from a starting URL, follow links within the same domain, and detect every HTTP redirect (301, 302, 303, 307, 308) using requests with redirects disabled.
import requests
from urllib.parse import urljoin, urlparse
from collections import deque
def find_redirects(start_url, max_pages=50):
visited = set()
redirects = {}
queue = deque([start_url])
while queue and len(visited) < max_pages:
url = queue.popleft()
if url in visited:
…Generate Beautiful Project Documentation from Python Source Code Automatically
Automatically generate a markdown summary of function docstrings from any Python source file using the AST module.
import ast
import inspect
from pathlib import Path
def extract_docstrings_from_file(filepath):
"""Parse a Python file and collect function docstrings."""
source = Path(filepath).read_text()
tree = ast.parse(source)
docs = []
for node in ast.walk(tree):
if isinstance(node, (ast.FunctionDef…How to Build a Cryptocurrency Price Tracker in Python
A continuous Python script that fetches real-time cryptocurrency prices from the CoinGecko API and displays them on a loop.
import requests
import time
def get_crypto_prices(coin_ids=["bitcoin", "ethereum", "solana"]):
url = "https://api.coingecko.com/api/v3/simple/price"
params = {
"ids": ",".join(coin_ids),
"vs_currencies": "usd"
}
try:
response = requests.get(url, params=params, timeout=10)
…How to Compare Two GitHub Repositories and Highlight Differences in Python
Fetch metadata from two GitHub repositories using the GitHub API and compare key attributes like stars, forks, license, and language, printing any differences.
import requests
import json
from pathlib import Path
def fetch_repo_data(owner, repo_name):
"""Fetch repository metadata from GitHub API."""
url = f"https://api.github.com/repos/{owner}/{repo_name}"
response = requests.get(url)
response.raise_for_status()
return response.json()
def compare_repos(…How to Download All Assets from GitHub Releases in Python
Downloads every asset attached to the latest GitHub release of a repository, saving them locally using the GitHub API and Python's requests and pathlib libraries.
import requests
import os
import zipfile
from pathlib import Path
def download_github_release_assets(owner: str, repo: str, output_dir: str = "release_assets") -> None:
"""Downloads all assets from the latest release of a GitHub repository."""
releases_url = f"https://api.github.com/repos/{owner}/{repo}/relea…How to Run Tesseract OCR from Python with subprocess
This script uses Python's subprocess module to invoke the Tesseract OCR engine from the command line and return the extracted text.
import subprocess
def ocr_image(image_path):
command = ["tesseract", image_path, "stdout"]
result = subprocess.run(command, capture_output=True, text=True)
return result.stdout.strip()
if __name__ == "__main__":
# Stub: call the actual tesseract (must be installed)
text = ocr_image("sample.png")
…How to apply Kubernetes YAML files from a folder in Python
Uses the Kubernetes Python client to apply all YAML manifests in a directory, with sorted processing and per-file error handling.
import os
import yaml
from kubernetes import client, config
from kubernetes.utils import create_from_yaml
def apply_yaml_folder(folder_path):
"""Apply all YAML files in a folder using the Kubernetes mock client."""
# Load mock configuration
config.load_kube_config()
k8s_client = client.ApiClient()
…Scrape HTML Tables in Python with html.parser
Extract data from HTML tables using Python's built-in html.parser module, without third-party dependencies, by overriding callback methods to track table, row, and cell states.
import html.parser
from urllib.request import urlopen
class TableParser(html.parser.HTMLParser):
def __init__(self):
super().__init__()
self.in_table = False
self.in_row = False
self.in_cell = False
self.current_cell = []
self.rows = []
self.row = []
d…Browse by section
Each section groups closely related Python snippets.
Automation & scripting — Python code examples
What you will find here
This page collects automation & scripting snippets — short, copy-ready Python you can paste into our free online IDE and run without installing anything. Each sample includes a plain-English explanation and the full source code.
Samples vs tutorials and challenges
Samples are quick reference — one concept per page. For step-by-step teaching, use our Python tutorials. To test yourself, try quizzes or coding challenges. Clean up style with the Python formatter.