Files & data
Read and write files safely; parse JSON, CSV, and common text formats.
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 Extract Every Archive in a Folder with Python
Walk through a folder and extract all ZIP, RAR, and 7Z archives into separate subdirectories using Python.
import zipfile
import rarfile
import py7zr
import pathlib
def extract_archives(folder: str):
"""Extract every ZIP, RAR, and 7Z archive in the given folder."""
folder_path = pathlib.Path(folder)
for archive_file in folder_path.iterdir():
suffix = archive_file.suffix.lower()
try:
…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 Beautiful QR Codes with Embedded Logos in Python
Generate a high-error-correction QR code and paste a logo image in the center to create a branded, scannable QR code.
import qrcode
from PIL import Image
def generate_qr_with_logo(data, logo_path, output_path):
qr = qrcode.QRCode(
version=1,
error_correction=qrcode.constants.ERROR_CORRECT_H,
box_size=10,
border=4,
)
qr.add_data(data)
qr.make(fit=True)
qr_img = qr.make_image(fill_c…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 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…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…Read Parquet-Like Columnar CSV Chunks in Python
A Python generator that reads a CSV file column-by-column, yielding dictionary chunks where each key points to a list of values—mirroring how Parquet stores data columnar.
```python
import csv
from pathlib import Path
from typing import Iterator, List
def read_parquet_like_columnar(csv_path: str, column_names: List[str], chunk_size: int = 2) -> Iterator[dict]:
"""Read CSV data in columnar chunks, similar to how parquet stores columns."""
csv_file = Path(csv_path)
with csv_f…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.