Files & data
Read and write files safely; parse JSON, CSV, and common text formats.
Audit File Permissions Across a Project in Python
Walks through every file and directory in a project tree and prints POSIX permissions plus owner UID.
import os
import stat
from pathlib import Path
def audit_file_permissions(project_root):
"""Walk through project_root and print path, owner, and permissions for every file."""
results = []
for root, dirs, files in os.walk(project_root):
for name in files + dirs:
full_path = os.path.joi…Automatically Detect Corrupted Files Using SHA-256 Checksums in Python
Compute SHA-256 checksums of files and compare them to detect corruption in Python.
import hashlib
import os
def compute_sha256(filepath: str) -> str:
"""Compute SHA-256 checksum of a file."""
sha256 = hashlib.sha256()
with open(filepath, 'rb') as f:
for chunk in iter(lambda: f.read(4096), b''):
sha256.update(chunk)
return sha256.hexdigest()
def validate_file_int…Automatically Highlight Data Validation Errors Inside Excel Files in Python
Load an Excel file with openpyxl, iterate over cells, and highlight invalid data (empty, negative) with a red fill and error message.
import openpyxl
from openpyxl.styles import PatternFill
from pathlib import Path
def highlight_validation_errors(filepath: str, output_path: str = None):
wb = openpyxl.load_workbook(filepath)
red_fill = PatternFill(start_color="FF0000", end_color="FF0000", fill_type="solid")
for sheet in wb.worksheet…Build a Command-Line To-Do List Application with Data Persistence in Python
A persistent command-line to-do list that saves tasks as JSON, supporting add, show, toggle done, and quit commands.
import json
import os
TODO_FILE = "todos.json"
def load_todos():
if not os.path.exists(TODO_FILE):
return []
with open(TODO_FILE, "r") as f:
return json.load(f)
def save_todos(todos):
with open(TODO_FILE, "w") as f:
json.dump(todos, f, indent=2)
def show_todos(todos):
if not…Build a Python Script That Detects and Deletes Empty Files Across Folders
A Python script that recursively finds and removes all zero-byte files across nested directories, returning a list of deleted paths.
import os
from pathlib import Path
def find_and_delete_empty_files(root_dir: str) -> list:
"""Find and delete all empty files under root_dir. Returns list of deleted paths."""
deleted = []
for file_path in Path(root_dir).rglob('*'):
if file_path.is_file() and file_path.stat().st_size == 0:
…Compare Two Folder Structures and Find Differences in Python
Walks two directories using os.walk, builds sets of relative paths, and prints items that exist in only one folder.
import os
def compare_folders(path1, path2):
"""
Compare the file/folder structure of two directories and print differences.
"""
def get_structure(root):
structure = set()
for dirpath, dirnames, filenames in os.walk(root):
rel_path = os.path.relpath(dirpath, root)
…Compress and Extract ZIP Files Programmatically in Python
Create a ZIP archive with in-memory files and extract its contents to a directory using Python's stdlib zipfile and pathlib modules.
import zipfile
from pathlib import Path
import tempfile
import os
def create_sample_zip(zip_path: str, files: dict) -> None:
"""Create a ZIP file containing the given files (name -> content mapping)."""
with zipfile.ZipFile(zip_path, 'w', zipfile.ZIP_DEFLATED) as zf:
for filename, content in files.ite…Convert All Markdown Files in a Folder to HTML in Python
Batch convert every .md file in a folder to .html using the `markdown` library with the 'extra' extensions.
import os
import markdown
from pathlib import Path
def convert_md_folder_to_html(input_folder="markdown_files", output_folder="html_pages"):
input_path = Path(input_folder)
output_path = Path(output_folder)
output_path.mkdir(exist_ok=True)
for md_file in input_path.glob("*.md"):
with open…Convert CSV Files to JSON in Python
Convert a CSV file to a JSON file using Python's built-in csv and json modules.
import csv
import json
def csv_to_json(csv_filepath, json_filepath):
"""Convert a CSV file to a JSON file."""
with open(csv_filepath, mode='r', newline='') as csv_file:
reader = csv.DictReader(csv_file)
data = [row for row in reader]
with open(json_filepath, mode='w') as json_file:
…Create a Personal Knowledge Base That Searches Notes Instantly in Python
Build a lightweight personal knowledge base with JSON storage and instant case-insensitive full-text search across note titles and content.
import json
import re
import sys
class PersonalKnowledgeBase:
def __init__(self, file_path="kb_notes.json"):
self.file_path = file_path
self.notes = self._load_notes()
def _load_notes(self):
try:
with open(self.file_path, "r") as f:
return json.load(f)
…Detect Outliers in CSV Data Using Z-Score in Python
Read a CSV file and detect outliers in a numeric column by computing z-scores, flagging those exceeding a given threshold — no machine learning required.
import csv
import statistics
from math import sqrt
def detect_outliers(csv_path, column_name, threshold=2.0):
"""Detect outliers in a numeric column using z-score method."""
values = []
with open(csv_path, 'r', newline='') as f:
reader = csv.DictReader(f)
if column_name not in reader.field…Generate Timesheet Reports from Daily Logs in Python
Aggregate daily log entries by project and produce a formatted timesheet report using Python's standard library.
import json
from pathlib import Path
from collections import defaultdict
def generate_timesheet_report(daily_logs: list[dict]) -> str:
"""
Generate a timesheet report from daily log entries.
Args:
daily_logs: List of dicts with 'date', 'project', 'hours', 'task' keys
Returns:
…How to Archive Old Files by Age in Python
Move files older than a specified number of days from a source directory to an archive directory using Python's pathlib and shutil modules.
import os
import shutil
import time
from pathlib import Path
def archive_old_files(source_dir: str, archive_dir: str, days_old: int) -> None:
cutoff_time = time.time() - (days_old * 86400) # 86400 seconds in a day
archive_path = Path(archive_dir)
archive_path.mkdir(parents=True, exist_ok=True)
for i…How to Convert Images Between Formats in Python
Use the Pillow library to open an image from one file format and save it to another, with error handling for missing files or conversion issues.
from PIL import Image
import sys
def convert_image_format(input_path, output_path):
try:
img = Image.open(input_path)
img.save(output_path)
print(f"Converted {input_path} to {output_path}")
except FileNotFoundError:
print(f"Error: File {input_path} not found")
sys.exit(…How to Extract Text from PDF Files in Python
Extract all readable text from a PDF file using PyPDF2, iterating over each page and concatenating the content.
import PyPDF2
def extract_text_from_pdf(pdf_path):
text = ""
with open(pdf_path, "rb") as file:
reader = PyPDF2.PdfReader(file)
for page in reader.pages:
text += page.extract_text() + "\n"
return text.strip()
if __name__ == "__main__":
pdf_path = "sample.pdf"
extracted…How to Fetch Weather Data from a Public API in Python
Fetches and parses weather data from a free public API using only the Python standard library.
import urllib.request
import json
def get_weather(city):
base_url = f"https://wttr.in/{city}?format=j1"
with urllib.request.urlopen(base_url) as response:
data = json.loads(response.read().decode())
current = data["current_condition"][0]
temp = current["temp_C"]
desc = current["weatherDesc…How to Find HTML Elements by Tag, Class, ID, CSS Selector, and Attribute in BeautifulSoup
Parse an HTML string with BeautifulSoup and demonstrate five distinct ways to locate elements: by tag name, by class, by ID, by CSS selector, and by attribute.
from bs4 import BeautifulSoup
html_content = """
<html><body>
<h1 id="title" class="heading">Hello World</h1>
<p class="content">First paragraph</p>
<p class="content special">Second paragraph</p>
<a href="https://example.com" class="link">Click here</a>
<div id="footer">
<p>© 2024</p>
…How to Record Audio from Your Microphone in Python
Record audio from your default microphone using PyAudio and save it as a WAV file with a simple reusable function.
import pyaudio
import wave
def record_audio(filename: str, duration: int = 5, sample_rate: int = 44100, chunk: int = 1024):
"""Record audio from default microphone and save as WAV file."""
audio_format = pyaudio.paInt16 # 16-bit resolution
channels = 1 # Mono
p = pyaudio.PyAudio()
stre…Merge Multiple PDF Files into One Document in Python
Combines multiple PDF files into a single PDF document using the PyPDF2 library's PdfMerger class.
import PyPDF2
def merge_pdfs(input_paths, output_path):
merger = PyPDF2.PdfMerger()
for path in input_paths:
merger.append(path)
merger.write(output_path)
merger.close()
print(f"Merged {len(input_paths)} PDFs into '{output_path}'.")
if __name__ == "__main__":
files = ["file1.pdf", "fi…Split CSV Files into Smaller Chunks in Python
Splits a large CSV file into multiple smaller chunk files, preserving the header row in each chunk.
import csv
import os
def split_csv(input_file, chunk_size=1000, output_prefix="chunk"):
"""Split a large CSV file into smaller chunks."""
with open(input_file, 'r', newline='') as infile:
reader = csv.reader(infile)
header = next(reader)
file_count = 1
row_count = 0
…Browse by section
Each section groups closely related Python snippets.
Files & data — Python code examples
What you will find here
This page collects files & data 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.