Automation & scripting
CLI tools, scheduled jobs, filesystem tasks, and glue scripts that save time.
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…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 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_/-]+',…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
…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…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 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()
…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 Build a Python Tool That Finds Trending Open Source Projects Daily
A Python script that queries the GitHub Search API to fetch the top 5 trending repositories created in the last day, sorted by stars, with optional language filtering.
import requests
import json
import datetime
def fetch_trending_projects(language: str = "", since: str = "daily"):
url = "https://api.github.com/search/repositories"
date_limit = (datetime.date.today() - datetime.timedelta(days=1)).isoformat()
query = f"created:>{date_limit} language:{language}" if langua…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 Create a Link Graph Visualization for Any Website in Python
A Python script that crawls a website's internal links, builds a directed graph of parent-child URL relationships, and prints the graph to the console.
import requests
from bs4 import BeautifulSoup
from collections import defaultdict
from urllib.parse import urljoin, urlparse
import sys
def get_links(url, max_links=20):
try:
response = requests.get(url, timeout=5)
soup = BeautifulSoup(response.text, 'html.parser')
base_url = f"{urlparse(u…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 Download a GitHub Repository as a ZIP File in Python
Download any public GitHub repository as a ZIP file using the GitHub API and Python's requests and zipfile modules.
import requests
import zipfile
import io
import os
def download_github_repo_as_zip(repo_url, output_path='.'):
"""
Download a GitHub repository as a ZIP file.
Args:
repo_url (str): Full GitHub repository URL (e.g., 'https://github.com/username/repo')
output_path (str): Directory to sa…How to Monitor Website Content Changes in Python
This script fetches a webpage's content, computes its SHA-256 hash, and compares it with the last stored hash to detect and alert on changes.
import time
import hashlib
import requests
from pathlib import Path
def fetch_content_hash(url: str) -> str:
response = requests.get(url, timeout=10)
response.raise_for_status()
return hashlib.sha256(response.text.encode()).hexdigest()
def monitor_website(url: str, check_interval: int = 60):
hash_fil…How to Track GitHub Stars, Forks, and Watchers in Python
Automatically fetch and track stars, forks, and watchers for multiple GitHub repositories, saving snapshots locally as JSON files for historical analysis.
import os
import time
import json
import requests
from pathlib import Path
from datetime import datetime
REPOS = [
"psf/requests",
"python/cpython",
"pallets/flask",
]
DATA_DIR = Path("github_metrics")
def fetch_repo_stats(repo):
url = f"https://api.github.com/repos/{repo}"
resp = requests.get(ur…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.