Python Code
Samples
Medium snippets you can copy, study, and run in the browser editor.
Extract Hyperlinks from Word Documents in Python
Parses a .docx file using Python's standard library to extract every hyperlink's display text and target URL.
import zipfile
from pathlib import Path
import xml.etree.ElementTree as ET
def extract_hyperlinks_from_docx(filepath: str) -> list[dict]:
"""
Extract all hyperlinks from a .docx file.
Returns a list of dicts with 'text' and 'target' keys.
"""
hyperlinks = []
with zipfile.ZipFile(Path(filepath)…Find Duplicate Web Pages by Content Similarity in Python
Compute SHA-256 hashes of file contents to detect and report duplicate HTML pages or any files in a directory.
import hashlib
import os
from collections import defaultdict
def get_file_hash(filepath):
"""Compute SHA-256 hash of file contents."""
sha256 = hashlib.sha256()
with open(filepath, 'rb') as f:
for chunk in iter(lambda: f.read(4096), b''):
sha256.update(chunk)
return sha256.hexdiges…How to Scrape Headlines from a News Website Using Beautiful Soup in Python
Scrape headline text from a news website using requests and Beautiful Soup with a CSS selector.
import requests
from bs4 import BeautifulSoup
def scrape_headlines(url: str, selector: str) -> list:
"""
Scrape headlines from a news website using Beautiful Soup.
Args:
url: The URL of the news website.
selector: CSS selector for headline elements.
Returns:
List of h…Scrape HTML Tables and Convert Them to CSV Using Beautiful Soup in Python
Scrape a Wikipedia table with Beautiful Soup and write the data to a CSV file using the csv module.
import requests
from bs4 import BeautifulSoup
import csv
url = "https://en.wikipedia.org/wiki/List_of_countries_by_GDP_(nominal)"
response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')
tables = soup.find_all('table', {'class': 'wikitable'})
if tables:
target_table = tables[2]
rows =…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…Build an RSS feed from markdown blog posts in Python
Scans a folder of markdown files, extracts titles, dates, and excerpts, and generates a valid RSS 2.0 XML feed.
import re
from pathlib import Path
from xml.etree.ElementTree import Element, SubElement, tostring
from datetime import datetime, timezone
from xml.dom import minidom
def build_rss(blog_dir, site_url="https://example.com"):
feed = Element("rss", version="2.0")
channel = SubElement(feed, "channel")
SubElem…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}")
…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_…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…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_…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 apply Kubernetes YAML files from a folder in Python
Uses the Kubernetes Python client to apply all YAML manifests in a directory, with sorted processing and per-file error handling.
import os
import yaml
from kubernetes import client, config
from kubernetes.utils import create_from_yaml
def apply_yaml_folder(folder_path):
"""Apply all YAML files in a folder using the Kubernetes mock client."""
# Load mock configuration
config.load_kube_config()
k8s_client = client.ApiClient()
…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…How to Implement Content Negotiation with JSON and XML in Python
Build an HTTP server that returns JSON or XML responses based on the client's Accept header, with a 406 response for unsupported formats.
import json
import xml.etree.ElementTree as ET
from http.server import BaseHTTPRequestHandler, HTTPServer
class RequestHandler(BaseHTTPRequestHandler):
def do_GET(self):
data = {"message": "Hello, world!"}
accept_header = self.headers.get("Accept", "")
if "application/json" in accept_hea…Detect Concept Drift in Python with a Simple Statistical Test
Detect concept drift by comparing the mean of recent data against a reference distribution using a z-score-like threshold.
import random
import statistics
def detect_drift(recent, reference, threshold=1.5):
ref_mean = statistics.mean(reference)
ref_std = statistics.stdev(reference)
recent_mean = statistics.mean(recent)
drift_score = abs(recent_mean - ref_mean) / (ref_std if ref_std > 0 else 1)
drifted = drif…How to Build a Mock ML Pipeline with Prefect in Python
Create a lightweight Prefect flow with mock preprocessing, training, and evaluation tasks to prototype an ML pipeline end-to-end.
from prefect import task, flow
from datetime import datetime
@task
def preprocess_data(raw_value: float) -> float:
"""Mock preprocessing: normalize the input value."""
return raw_value / 100.0
@task
def train_model(features: float) -> dict:
"""Mock training: return a fake model artifact."""
return …How to Create a Mock ONNX Model in Python
Build and export a minimal mock ONNX model with a Reshape and Gemm layer using the onnx helper API.
import onnx
import numpy as np
from onnx import helper, TensorProto
def create_mock_model():
# Define input and output tensors
input_tensor = helper.make_tensor_value_info('input', TensorProto.FLOAT, [1, 3, 224, 224])
output_tensor = helper.make_tensor_value_info('output', TensorProto.FLOAT, [1, 10])
…How to Detect Data Drift with PSI in Python
Calculate the Population Stability Index (PSI) in Python to compare expected vs actual distributions and detect data drift in machine learning pipelines.
import numpy as np
def calculate_psi(expected, actual, buckets=10):
"""Calculate Population Stability Index (PSI) between two distributions."""
# Create bucket edges based on expected distribution percentiles
edges = np.percentile(expected, np.linspace(0, 100, buckets + 1))
edges[-1] = np.inf # Ensur…How to Mock Kedro Pipeline Nodes in Python
Create a modular Kedro pipeline with node functions, namespacing, and input/output mapping to mock pipeline execution locally.
from kedro.pipeline import Pipeline, node
from kedro.pipeline.modular_pipeline import pipeline as modular_pipeline
def preprocess(data: list) -> list:
"""Clean data by removing None values."""
return [item for item in data if item is not None]
def transform(data: list) -> list:
"""Add 1 to each numeric…How to Mock MLflow Model Registration in Python
Build a lightweight in-memory mock of MLflow's MlflowClient to test model registration, versioning, and stage transitions without a tracking server.
from mlflow.tracking import MlflowClient
from mlflow.entities import ModelVersion, Model
class MockMlflowClient:
"""Minimal mock of MlflowClient's model registration methods."""
def __init__(self):
self.registered_models = {}
self.model_versions = {}
def register_model(self, mod…How to Mock ROC AUC in Python
Compute ROC AUC from scratch in Python using pairwise comparisons between positive and negative score distributions, ideal for testing ML models without sklearn.
import random
from math import comb
def mock_roc_auc(scores, labels):
"""Compute mock ROC AUC by simulating a classifier's score distribution."""
random.seed(42)
n = len(labels)
pos_scores = [scores[i] for i in range(n) if labels[i] == 1]
neg_scores = [scores[i] for i in range(n) if labels[i] == …Browse by section
Each section groups closely related Python snippets.
Guide: free Python code samples library
Copy-ready Python snippets for learners and developers
PythonSkillset code samples are short, focused examples organised by topic and difficulty. Every snippet is server-rendered HTML — readable by search engines and easy to copy. Open any sample, read the notes, copy the code, then press Try in editor to run it in the browser with Pyodide.
How to use this library
- Pick a topic section — strings, lists, files, functions, and more
- Open a sample, read How it works, and copy the code block
- Run it in the IDE, tweak values, then take a related quiz or tutorial lesson
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.