Automation & scripting
CLI tools, scheduled jobs, filesystem tasks, and glue scripts that save time.
Aggregate Log Errors Count by Hour in Python
Counts ERROR log lines per hour using regex and Counter, returning a sorted dictionary of hourly totals.
import re
from collections import Counter
from datetime import datetime
def aggregate_errors_by_hour(log_lines):
pattern = re.compile(r'^(\d{4}-\d{2}-\d{2} \d{2}):\d{2}:\d{2}.*ERROR')
hourly_counts = Counter()
for line in log_lines:
match = pattern.match(line)
if match:
ho…Build a Python Tool to Find All API Endpoints on a Website
A Python script that crawls a website, searches for common API endpoint patterns in HTML and JavaScript, and returns all discovered public API URLs.
import re
import requests
from urllib.parse import urljoin, urlparse
from collections import deque
def find_api_endpoints(base_url, max_pages=10):
visited = set()
queue = deque([base_url])
api_endpoints = set()
api_patterns = [
r'/api/[a-zA-Z0-9_/-]+',
r'/v[0-9]+/[a-zA-Z0-9_/-]+',…Bulk Rename Files in Python with Regex Replacement
Renames every file in a directory by applying a regex substitution to its filename using Python's stdlib re and pathlib.
import re
from pathlib import Path
def bulk_rename_regex(directory, pattern, replacement):
path = Path(directory)
renamed = []
for file in path.iterdir():
if file.is_file():
new_name = re.sub(pattern, replacement, file.name)
if new_name != file.name:
new_pat…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…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…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'…How to Bump Version in pyproject.toml Using Regex in Python
Updates the version field in a pyproject.toml file using a regex substitution with the Python standard library.
import re
from pathlib import Path
def bump_version(pyproject_path: str, new_version: str) -> None:
"""Update version in pyproject.toml using regex."""
path = Path(pyproject_path)
content = path.read_text()
# Match version = "x.y.z" (simple or PEP 440 with pre-release)
pattern = r'^version\s*=\s*…How to Detect Unused Images in a Project with Python
A Python script that scans a website project folder, identifies all image files, and checks HTML/CSS/JS files to find which images are never referenced.
import os
import re
from pathlib import Path
def find_unused_images(project_path):
image_exts = {'.png', '.jpg', '.jpeg', '.gif', '.svg', '.webp'}
used_images = set()
all_images = set()
# Find all image files
for root, _, files in os.walk(project_path):
for file in files:
…How to Kill Zombie Processes Matching a Name in Python
Scans running processes with ps, finds zombies whose command name matches a pattern, and attempts to kill them with SIGKILL.
import subprocess
import re
import signal
def find_zombies(name_pattern):
"""Find PIDs of zombie processes matching the given pattern."""
result = subprocess.run(["ps", "-eo", "pid,stat,comm"], capture_output=True, text=True)
zombies = []
for line in result.stdout.splitlines()[1:]: # Skip header
…How to Scan Configuration Files for Security Issues in Python
Automatically scan configuration files for common security mistakes using regex rules in Python.
import re
import os
from pathlib import Path
SECURITY_RULES = [
(r'^#\s*INSECURE_', 'Insecure comment starts with # INSECURE_'),
(r'password\s*=\s*("|\\\')?[^"\\\'"\s]+("|\\\')?$', 'Hardcoded password'),
(r'debug\s*=\s*True', 'Debug mode enabled'),
(r'[Pp]ermit[Rr]ootLogin\s+yes', 'PermitRootLogin ena…Parse WHOIS Data with Python Regex
Extract domain registration fields from a mock WHOIS record using regex and compute days until expiration.
import re
from datetime import datetime
def parse_whois(whois_text: str) -> dict:
"""Extract key registration fields from a mock WHOIS record."""
patterns = {
"domain": r"Domain Name:\s*(.+)",
"registrar": r"Registrar:\s*(.+)",
"creation_date": r"Creation Date:\s*(.+)",
"expir…Parse nginx access log top IPs in Python
Reads an nginx access log line by line, extracts the client IP, and returns the most frequent IPs using a regex and Counter.
import re
from collections import Counter
def top_ips(log_file, n=10):
ip_pattern = re.compile(r'^(\S+)')
ip_counts = Counter()
with open(log_file, 'r') as f:
for line in f:
match = ip_pattern.match(line)
if match:
ip_counts[match.group(1)] += 1
return…Pin Python package versions in requirements.txt
Pin package versions in requirements.txt-style text by adding ==version when no specifier is present, while preserving existing version constraints and comments.
import re
from pathlib import Path
def pin_versions(requirements_text: str) -> str:
"""
Pin package versions in requirements.txt-style text.
Adds ==version if no version specifier is present.
Keeps existing specifiers (>=, <=, ~=, etc.) unchanged.
"""
lines = requirements_text.strip().splitli…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.