Automation & scripting
CLI tools, scheduled jobs, filesystem tasks, and glue scripts that save time.
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 Complete Website Sitemap Generator Without External Services
Crawl a website recursively using only Python's standard library to generate a structured sitemap of internal links.
import json
from urllib.parse import urlparse, urljoin
from collections import deque
import urllib.request
import urllib.error
import re
from html.parser import HTMLParser
class SitemapParser(HTMLParser):
def __init__(self, base_url):
super().__init__()
self.base_url = base_url
self.links …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_/-]+',…Build a Website Accessibility Scanner Using Python
Scans a webpage for common accessibility issues like missing alt text, headings, labels, and landmarks using only Python.
import requests
from urllib.parse import urljoin
from html.parser import HTMLParser
import re
class AccessibilityParser(HTMLParser):
def __init__(self):
super().__init__()
self.images_without_alt = []
self.missing_headings = True
self.has_main_tag = False
self.label_for_inp…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…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:
…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 Automatically Download Every Favicon from a List of Websites in Python
Download each website's favicon.ico file by constructing its URL, making a GET request, and saving the binary content locally.
import requests
from urllib.parse import urlparse
import os
websites = [
"https://www.google.com",
"https://www.github.com",
"https://www.stackoverflow.com"
]
def download_favicon(url):
parsed = urlparse(url)
favicon_url = f"{parsed.scheme}://{parsed.netloc}/favicon.ico"
response = requests.g…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 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 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 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 generate website performance reports from HTTP requests in Python
Measure and report website load time, status code, and content size using Python's standard library.
import urllib.request
import time
def measure_website_load_time(url):
"""Measures total loading time of a website."""
start_time = time.time()
try:
with urllib.request.urlopen(url, timeout=10) as response:
content = response.read()
status_code = response.status
…Monitor Website Uptime with Python
Periodically check if a website is reachable and its HTTP status is 200, logging the status with timestamps.
import requests
import time
def check_website(url):
try:
response = requests.get(url, timeout=5)
if response.status_code == 200:
return True
else:
return False
except requests.ConnectionError:
return False
except requests.Timeout:
return Fals…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.