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 File Index by Relative Path Hash Map in Python
Recursively walk a directory and map normalized relative paths to absolute file paths using a defaultdict hash map.
import os
from collections import defaultdict
def build_file_index(root_dir):
index = defaultdict(list)
for dirpath, dirnames, filenames in os.walk(root_dir):
for filename in filenames:
full_path = os.path.join(dirpath, filename)
relative_path = os.path.relpath(full_path, roo…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:
…Convert File Data to a Dictionary in Python
This function scans a directory and converts each file's metadata (name, size, extension) into a structured dictionary for easy access.
from pathlib import Path
def convert_files_data(directory: str) -> dict:
data = {}
base = Path(directory)
if not base.exists():
return data
for file in base.iterdir():
if file.is_file():
data[file.name] = {
"size": file.stat().st_size,
"exten…Count Files by Extension in Python
Count files in a directory grouped by file extension using Python's standard library.
from pathlib import Path
def count_files_by_extension(directory: str) -> dict[str, int]:
"""Count files in a directory grouped by file extension."""
data = {}
for path in Path(directory).iterdir():
if path.is_file():
ext = path.suffix.lower() or "(no extension)"
data[ext] =…Create a Local File Versioning System Using Pure Python
Track file changes locally by copying versions with SHA-256 hashes and JSON metadata using only the Python standard library.
import os
import shutil
import hashlib
import json
import time
from pathlib import Path
class LocalFileVersioning:
def __init__(self, target_dir="versioned_files", versions_dir="versions"):
self.target_dir = Path(target_dir)
self.versions_dir = Path(versions_dir)
self.metadata_file = self.…Create a ZIP Archive of a Folder in Python
Recursively zip all files in a folder into a single archive using the standard library zipfile and pathlib modules.
import zipfile
from pathlib import Path
def zip_folder(source_dir: str, archive_path: str) -> None:
"""Zip all files in source_dir recursively into archive_path."""
source = Path(source_dir)
with zipfile.ZipFile(archive_path, "w", zipfile.ZIP_DEFLATED) as archive:
for file_path in source.rglob("*"…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…Download Files from Internet with Progress Bar in Python
Download a file from the internet while displaying a text progress bar in the terminal.
import urllib.request
import sys
def download_with_progress(url, filename):
"""Download a file with a simple text progress bar."""
def report_hook(block_count, block_size, total_size):
downloaded = block_count * block_size
if total_size > 0:
percent = min(100, int(downloaded * 100 …Encrypt and Decrypt Files Using Python
Encrypt and decrypt files using the cryptography library's Fernet symmetric encryption.
import os
from pathlib import Path
from cryptography.fernet import Fernet
def generate_key(key_file: Path) -> bytes:
key = Fernet.generate_key()
key_file.write_bytes(key)
return key
def load_key(key_file: Path) -> bytes:
return key_file.read_bytes()
def encrypt_file(input_path: Path, key: bytes, out…Export SQLite Query Results to CSV in Python
Connects to a SQLite database, runs a query, and writes the result rows and column headers to a CSV file using the standard library.
import sqlite3
import csv
def export_query_to_csv(db_path, query, csv_path):
conn = sqlite3.connect(db_path)
cursor = conn.cursor()
cursor.execute(query)
rows = cursor.fetchall()
column_names = [description[0] for description in cursor.description]
with open(csv_path, 'w', newline='', encodi…Extract a Single Member from a ZIP Archive in Python
Extract one specific file from a ZIP archive to an output directory using the standard zipfile and pathlib modules.
import zipfile
from pathlib import Path
def extract_single_member(zip_path: str, member_name: str, output_dir: str = ".") -> Path:
"""Extract a single member from a zip archive to the output directory."""
with zipfile.ZipFile(zip_path, "r") as archive:
archive.extract(member_name, output_dir)
retu…File Data Helper Functions in Python
Read and write text and JSON files, and list files in a directory, using pathlib-based helper functions.
from pathlib import Path
def load_text_file(filepath):
"""Read a text file and return its contents as a string."""
path = Path(filepath)
if not path.exists():
raise FileNotFoundError(f"File not found: {filepath}")
return path.read_text(encoding="utf-8")
def save_text_file(filepath, content):
…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…Generate a Beautiful Folder Tree Visualization in Python
A Python utility that creates a visual tree of a directory structure, excluding common files, with configurable depth.
import os
from pathlib import Path
class FolderTree:
def __init__(self, root_path=".", ignore_list=None, max_depth=3):
self.root = Path(root_path)
self.ignore = set(ignore_list or [".git", "__pycache__", ".DS_Store"])
self.max_depth = max_depth
def generate(self):
tree…Generate a Monthly Calendar PDF in Python
Create a Python utility that generates a monthly calendar PDF using ReportLab, with weekday headers and day numbers laid out in a grid.
from calendar import TextCalendar
from datetime import datetime
from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas
import os
def generate_monthly_calendar_pdf(year, month, filename="calendar.pdf"):
cal = TextCalendar()
days = cal.monthdays2calendar(year, month)
month_name …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 Atomically Write Files in Python with Temp File and Rename
Write a file atomically using a temporary file and os.replace so readers never see partial writes even if the process crashes mid-write.
import os
import tempfile
from pathlib import Path
def atomic_write(path: str | Path, content: str) -> None:
"""Write content to path atomically using a temp file and rename."""
path = Path(path)
path.parent.mkdir(parents=True, exist_ok=True)
fd, temp_path = tempfile.mkstemp(
dir=str(path.par…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.