Automation & scripting
CLI tools, scheduled jobs, filesystem tasks, and glue scripts that save time.
Convert HTML Tables to Excel Reports in Python
Convert HTML tables into formatted Excel reports using BeautifulSoup and Pandas with auto-adjusted column widths.
import pandas as pd
from bs4 import BeautifulSoup
from pathlib import Path
def html_table_to_excel(html_file: str, excel_file: str) -> None:
"""Convert HTML table to formatted Excel report."""
with open(html_file, 'r', encoding='utf-8') as f:
html_content = f.read()
soup = BeautifulSoup(html_…Convert Markdown to HTML in Python (Batch)
Convert every Markdown file in a directory to HTML with the Python markdown library, saving each result with an .html extension.
import markdown
from pathlib import Path
def convert_md_to_html(source_dir: str, dest_dir: str) -> list[str]:
src = Path(source_dir)
dst = Path(dest_dir)
dst.mkdir(parents=True, exist_ok=True)
converted_files = []
for md_file in src.glob("*.md"):
html_content = markdown.markdown(md_file.…Create ICS Calendar Invites in Python
This script generates a batch of calendar invites in the ICS format using the ics library.
import ics
from datetime import datetime, timedelta
def create_invites(batch):
calendar = ics.Calendar()
for event_data in batch:
event = ics.Event()
event.name = event_data["name"]
event.begin = event_data["start"]
event.end = event_data["end"]
event.description = even…Create Mock Watermarked Image Bytes in Python Without PIL
Builds a mock image-like byte stream with an embedded watermark using only stdlib modules, for testing pipelines without PIL.
from io import BytesIO
import zlib
import struct
def create_watermarked_bytes(width: int, height: int, watermark: bytes) -> bytes:
"""Create a mock image-like byte stream with a watermark (no PIL)."""
header = struct.pack("<2I", width, height)
payload = watermark * max(1, (width * height // max(1, len(wa…Create a Local Search Engine to Instantly Find Files on Your Computer in Python
Build a local file search engine in Python that indexes files by name, extension, and glob pattern for instant retrieval.
import os
import sys
import time
from pathlib import Path
import fnmatch
class LocalSearchEngine:
def __init__(self, root_directory="."):
self.root_directory = Path(root_directory)
self.file_index = {}
def build_index(self):
"""Build a complete index of files in the root direc…Create a Python Script That Detects Website Technology Stack Automatically
This script sends an HTTP request to a URL and inspects headers and HTML content to identify technologies like servers, frameworks, and JavaScript libraries.
import requests
from re import search
def detect_tech_stack(url):
tech_stack = []
try:
response = requests.get(url, timeout=5, headers={'User-Agent': 'Mozilla/5.0'})
headers = response.headers
html = response.text.lower() if response.text else ''
# Check server header
…Create a Simple HTTP File Server in Python
This code creates a simple HTTP file server that serves files from the current working directory on port 8000 using Python's built-in http.server module.
import http.server
import socketserver
import os
PORT = 8000
DIRECTORY = os.getcwd()
class CustomHandler(http.server.SimpleHTTPRequestHandler):
def __init__(self, *args, **kwargs):
super().__init__(*args, directory=DIRECTORY, **kwargs)
def log_message(self, format, *args):
print(f"[{self.log…Detect Circular Imports Across Python Projects Automatically
This script walks through all .py files in a directory, builds an import graph, and uses depth-first search to find cycles—printing each circular dependency chain.
import ast
import sys
from pathlib import Path
from collections import defaultdict, deque
def find_imports(filepath):
"""Return set of module names imported by a Python file."""
imports = set()
try:
with open(filepath) as f:
tree = ast.parse(f.read())
except (SyntaxError, UnicodeDe…Detect Memory Leaks in Python with Weak References
A custom LeakDetector uses weak references and garbage collection to find class instances that survive past expected cleanup in long-running Python applications.
import gc
import sys
import weakref
import time
from collections import defaultdict
class LeakDetector:
def __init__(self):
self._tracked = defaultdict(list)
def track_class(self, cls):
"""Track all instances of a class for leak detection."""
old_init = cls.__init__
def new_in…Detect and Remove Blurry Images in Python with OpenCV
Automatically scan a directory of images, detect blur using Laplacian variance, and remove blurry images with a dry-run option for safety.
from pathlib import Path
import cv2
import numpy as np
def is_blurry(image_path, threshold=100.0):
"""
Detect if an image is blurry using Laplacian variance.
Returns True if blurry, False otherwise.
"""
img = cv2.imread(str(image_path), cv2.IMREAD_GRAYSCALE)
if img is None:
return True…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_…Fetch weather API mock and write dashboard HTML in Python
This script fetches a mock weather API response as a Python dict, builds a simple HTML dashboard, writes it to a file, and prints both the file path and JSON payload.
from datetime import datetime
import json
import os
def fetch_weather_mock(city: str) -> dict:
"""Return a mock weather payload for a given city."""
return {
"city": city,
"temperature_c": 21.5,
"condition": "Partly Cloudy",
"humidity": 58,
"wind_kph": 12.3,
"u…Fill PDF Form Fields from a Mock Template in Python
Fills a PDF-style form template dictionary with user data, preserving template fields and formatting output as JSON.
import json
template = {
"first_name": "",
"last_name": "",
"email": "",
"phone": "",
"date_of_birth": "",
"address": "",
"city": "",
"state": "",
"zip_code": "",
"agree_to_terms": False
}
def fill_pdf_form(template: dict, data: dict) -> dict:
for key, value in data.items…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:
…Find Best Meeting Time Across Time Zones in Python
This code calculates overlapping available hours among participants in different time zones and returns the best meeting time in UTC and each participant's local time.
from datetime import datetime, timedelta, timezone
from zoneinfo import ZoneInfo
from dataclasses import dataclass
from typing import List, Tuple, Optional
@dataclass
class Participant:
name: str
timezone: str
# weekdays availability: 0=Mon, start_hour (0-23), end_hour (0-23)
available_slots: List[Tup…Find Broken Image References Across a Website in Python
Crawl internal pages of a website, collect all image source URLs, then check each with HEAD requests to report any that return HTTP 4xx or connection errors.
import requests
from urllib.parse import urljoin, urlparse
from bs4 import BeautifulSoup
from concurrent.futures import ThreadPoolExecutor, as_completed
def find_all_links(base_url, max_pages=50):
visited, to_visit = set(), {base_url}
while to_visit and len(visited) < max_pages:
url = to_visit.pop()
…Find Dead Code in a Python Project Using AST
Walk a project tree, parse every Python file with ast, and list defined functions that are never called anywhere.
import ast
import os
import sys
def find_dead_code(project_path):
defined_functions = {}
called_functions = set()
for root, dirs, files in os.walk(project_path):
for file in files:
if file.endswith('.py'):
filepath = os.path.join(root, file)
with open(f…Find Orphan Files Not Referenced Anywhere in Python
Scan a project directory for files whose names never appear in the content of other files, identifying potentially unused resources.
import os
from pathlib import Path
import re
def find_orphan_files(root_dir: str, extensions: set = None, ignore_patterns: list = None):
"""Find files not referenced by any other file in the project."""
if extensions is None:
extensions = {'.txt', '.md', '.py', '.html', '.css', '.js', '.json', '.yaml'…Find Sensitive Information in Log Files with Python
Scan log files for emails, IP addresses, API keys, and passwords using regular expressions in Python.
import re
import os
from pathlib import Path
def find_sensitive_info(log_path):
"""Scans log files for patterns like emails, IPs, API keys, and passwords."""
patterns = {
'Email': r'[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}',
'IP Address': r'\b(?:\d{1,3}\.){3}\d{1,3}\b',
'API Key'…Find Unused Python Packages Automatically
Scan a Python project's source files for imports and list installed packages not imported anywhere.
import pkg_resources
import ast
import os
import sys
from pathlib import Path
def find_imports_in_project(project_dir="."):
imports = set()
for py_file in Path(project_dir).rglob("*.py"):
try:
with open(py_file, "r") as f:
tree = ast.parse(f.read())
for node in …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.