Files & data
Read and write files safely; parse JSON, CSV, and common text formats.
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("*"…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…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 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…How to Audit Environment Variable Files for Missing Values in Python
A Python tool that reads an environment variable file and reports any variables with empty or missing values.
import os
import re
from pathlib import Path
def audit_env_file(filepath: str) -> None:
"""
Audit an environment variable file for missing values.
Prints file status and lists variables that have empty values.
"""
path = Path(filepath)
if not path.exists():
print(f"Error: File '{filepa…How to Automatically Merge Hundreds of Excel Files Without Losing Formatting in Python
Merge all .xlsx files in a folder into a single Excel workbook, preserving individual sheet structures with sheet name prefixes.
import pandas as pd
from pathlib import Path
def merge_excel_files(folder_path: str, output_path: str) -> None:
"""
Merge all .xlsx files in a folder into a single Excel file,
preserving individual sheet structures.
"""
folder = Path(folder_path)
excel_files = list(folder.glob("*.xlsx"))
…How to Build a CSV Comparison Tool That Highlights Every Changed Cell in Python
Read two CSV files with DictReader, compare cell by cell, and return a list of dictionaries describing each changed cell using only the standard library.
import csv
from pathlib import Path
def csv_cell_diff(file_a: str, file_b: str) -> list[dict]:
rows_a = list(csv.DictReader(Path(file_a).open('r', newline='')))
rows_b = list(csv.DictReader(Path(file_b).open('r', newline='')))
if not rows_a or not rows_b:
return []
columns = list(rows_a[0].key…How to Compare Two Files by Content Hash Equality in Python
Compares two files by hashing their contents with SHA-256, skipping the hash if file sizes differ, and returns whether they are identical.
import hashlib
from pathlib import Path
def file_hash(path: Path, chunk_size: int = 8192) -> str:
sha256 = hashlib.sha256()
with path.open("rb") as f:
for chunk in iter(lambda: f.read(chunk_size), b""):
sha256.update(chunk)
return sha256.hexdigest()
def files_are_identical(file_a: Pat…How to Find Duplicate Files by Size and Hash in Python
Recursively scan a directory, group files by size, then hash candidates to identify exact duplicate files.
import hashlib
from pathlib import Path
def hash_file(path, chunk_size=8192):
hasher = hashlib.md5()
with open(path, 'rb') as f:
while chunk := f.read(chunk_size):
hasher.update(chunk)
return hasher.hexdigest()
def find_duplicates(directory):
size_map = {}
for path in Path(dir…How to Generate an Inventory Report of All Files in Python
Walk a directory tree, collect metadata for every file, and write a CSV inventory report using Python's os, pathlib, and csv modules.
import os
import csv
from pathlib import Path
from datetime import datetime
def generate_inventory_report(root_dir: str = "/", output_file: str = "inventory_report.csv"):
headers = ["File Path", "Size (bytes)", "Last Modified", "File Type"]
rows = []
start_time = datetime.now()
for dirpath, dirna…How to Load Pickle Files Safely in Python
This code demonstrates how to load pickle files safely in Python by using a restricted unpickler that only allows specific, trusted classes, preventing arbitrary code execution from untrusted pickles.
import pickle
# Default pickle.load is unsafe: it executes arbitrary code when unpickling.
class Unsafe:
def __reduce__(self):
return (eval, ("open('/tmp/pickle_demo.txt', 'w').write('pwned')",))
# Create a malicious payload (simulating untrusted source)
malicious_data = pickle.dumps(Unsafe())
# Safe ap…How to Memory Map Large Files Read-Only in Python
This code demonstrates reading only the tail of a large file using a read-only memory map (mmap) to avoid loading the entire file into memory.
import mmap
import os
def read_tail_with_mmap(filepath, bytes_from_end=64):
"""Read the last bytes of a large file using a read-only mmap."""
file_size = os.path.getsize(filepath)
start = max(0, file_size - bytes_from_end)
with open(filepath, "rb") as f:
with mmap.mmap(f.fileno(), length=0, a…How to Merge Sorted Chunk Files in Python
Merge multiple sorted text files into one sorted output file using a heap for efficient k-way merging.
import heapq
def merge_sorted_chunks(chunks, output_path):
"""Merge multiple sorted iterables into single sorted output file."""
with open(output_path, "w") as out_f:
# Open all chunk files
handles = [open(chunk, "r") for chunk in chunks]
try:
# Heap of (value, index) tupl…How to Parse Apache Log Files in Python
Parse Apache common log format lines into structured dictionaries using Python's standard library.
import re
from pathlib import Path
def parse_apache_line(line):
pattern = r'^(\S+) (\S+) (\S+) \[([^\]]+)\] "(\S+) (\S+) (\S+)" (\d{3}) (\S+)'
match = re.match(pattern, line)
if not match:
return None
ip, ident, user, timestamp, method, path, protocol, status, size = match.groups()
return …How to Stream Large CSV Files in Python
Process a large CSV file in memory-efficient chunks using Python's csv module, yielding batches of rows instead of loading everything at once.
import csv
from pathlib import Path
def process_csv_in_chunks(file_path, chunk_size=1000):
"""Yield rows from a large CSV file in chunks without loading all into memory."""
with open(file_path, 'r', newline='') as f:
reader = csv.DictReader(f)
chunk = []
for row in reader:
…How to Sync Two Folders in Python (Lightweight Backup)
A Python script that synchronizes a source folder to a destination folder, copying new or updated files and removing files that no longer exist in the source.
import os
import shutil
import sys
from pathlib import Path
def sync_folders(src: Path, dst: Path):
"""Sync src folder to dst folder, copying missing/updated files."""
dst.mkdir(parents=True, exist_ok=True)
for src_path in src.rglob("*"):
relative = src_path.relative_to(src)
dst_path = ds…How to Use fcntl for Exclusive File Locking in Python
This code demonstrates how to acquire an exclusive advisory lock on a file using fcntl.flock with a non-blocking flag, simulate work, then release the lock.
import fcntl
import os
import tempfile
import time
def acquire_exclusive_lock(filepath):
fd = os.open(filepath, os.O_RDWR | os.O_CREAT)
try:
fcntl.flock(fd, fcntl.LOCK_EX | fcntl.LOCK_NB)
print(f"Exclusive lock acquired on {filepath}")
time.sleep(1) # Simulate work while holding the l…How to Write a List of Lines to a Text File Safely in Python
This code atomically writes a list of strings as lines to a text file using a temporary file and os.replace to prevent corruption.
from pathlib import Path
import tempfile
import os
def write_lines_safely(lines: list[str], filepath: str | Path) -> None:
"""Write lines to a text file atomically to avoid corruption."""
path = Path(filepath)
path.parent.mkdir(parents=True, exist_ok=True)
fd, temp_path = tempfile.mkstemp(dir=str…Join two CSV files on shared key column in Python
Merge rows from two CSV files by a common key column, outputting combined records to a new file.
import csv
def join_csv(file1, file2, key, output="joined.csv"):
# Read first CSV into dict keyed by the join column
with open(file1, newline="") as f1:
reader1 = csv.DictReader(f1)
data1 = {row[key]: row for row in reader1}
# Read second CSV and merge matching rows
with open(file2, n…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.