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 Network Ping Monitor in Python
A Python script that continuously pings a remote host using subprocess and reports connectivity status with timestamps and latency.
import subprocess
import time
def ping_host(host, count=4):
"""Ping a host and return the results."""
try:
# Platform-independent ping command
cmd = ["ping", "-c", str(count), host]
result = subprocess.run(cmd, capture_output=True, text=True, timeout=10)
return result.stdout, r…Check Service Ping Status and Exit Code in Python
Ping a list of hosts, print OK/FAIL per host, and exit with a non-zero code when any host is unreachable.
import subprocess
import sys
SERVICES = [
"8.8.8.8",
"1.1.1.1",
"invalid-host",
]
def main():
failed = []
for host in SERVICES:
result = subprocess.run(
["ping", "-c", "1", "-W", "2", host],
stdout=subprocess.DEVNULL,
stderr=subprocess.DEVNULL,
…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}")
…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 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()
…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 Download a List of URLs to a Directory in Python
This script downloads a list of URLs into a specified directory, creating the folder if needed and keeping original filenames.
import urllib.request
from pathlib import Path
def download_urls(url_list, directory):
"""Download each URL in url_list into directory, keeping original filenames."""
save_dir = Path(directory)
save_dir.mkdir(parents=True, exist_ok=True)
for url in url_list:
filename = url.rstrip('/').spl…How to Hash Duplicate Photos and Delete Copies in Python
This script hashes image files in a directory using SHA-256 and deletes duplicate copies while keeping the first occurrence, ideal for cleaning up photo libraries.
from pathlib import Path
import hashlib
def file_hash(path, chunk_size=8192):
hasher = hashlib.sha256()
with open(path, "rb") as f:
for chunk in iter(lambda: f.read(chunk_size), b""):
hasher.update(chunk)
return hasher.hexdigest()
def delete_duplicate_photos(directory):
directory …How to Map Network Drive Paths to Local Paths in Python
Convert mock SMB network drive paths (like 'S:\reports\q1.xlsx') to local placeholder paths and back using a simple mapping dictionary in Python.
"""Map mock SMB network drive paths to local placeholder paths."""
from dataclasses import dataclass
@dataclass(frozen=True)
class NetworkDrive:
letter: str
remote_path: str
DRIVES = {
"S:": NetworkDrive("S", r"\\server01\shares\sales"),
"M:": NetworkDrive("M", r"\\server02\media\movies"),
"X:": …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 Ping Multiple Hosts in Parallel with Python ThreadPoolExecutor
A parallel host-pinging script using ThreadPoolExecutor and subprocess to check connectivity across multiple addresses concurrently.
import subprocess
from concurrent.futures import ThreadPoolExecutor
from pathlib import Path
HOSTS = [
"google.com",
"github.com",
"stackoverflow.com",
"nonexistent.invalid",
"localhost",
]
def ping_host(host: str) -> str:
"""Ping a single host and return a status string."""
result = subp…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…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…Track Internet Connectivity and Downtime Automatically in Python
Monitors internet connectivity by pinging a remote host and logs any downtime events with timestamps and duration.
import time
import subprocess
from datetime import datetime
def check_internet(host="8.8.8.8", timeout=3):
"""Returns True if internet is reachable via ping."""
try:
subprocess.run(
["ping", "-c", "1", "-W", str(timeout), host],
capture_output=True,
timeout=timeout …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.