Files & data
Read and write files safely; parse JSON, CSV, and common text formats.
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 List of Dicts to CSV in Python
Write a list of dictionaries (dataframe-like) to a CSV file with headers using the standard library csv module and verify by reading it back.
import csv
def export_to_csv(data, filename):
"""Export a list of dicts to a CSV file."""
if not data:
print("No data to export")
return
# Get column names from the keys of the first dict
fieldnames = list(data[0].keys())
with open(filename, 'w', newline='', encoding='utf…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 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)…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 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:
…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…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 Build a Dated Backup Filename with Timestamp in Python
Generate unique backup filenames with a timestamp using Python's datetime module and f-strings.
from datetime import datetime
def build_backup_filename(base_name: str, extension: str = "bak") -> str:
"""Generate a dated backup filename with timestamp."""
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
return f"{base_name}_{timestamp}.{extension}"
if __name__ == "__main__":
backup_file = bu…How to Bulk Insert Rows into SQLite in Python
Insert many rows into an SQLite table in one call with cursor.executemany, then verify them with a SELECT query.
import sqlite3
# Create an in-memory database and a table
conn = sqlite3.connect(":memory:")
cursor = conn.cursor()
cursor.execute("CREATE TABLE products (name TEXT, price REAL, quantity INTEGER)")
# Data to insert in bulk
products = [
("Laptop", 999.99, 5),
("Mouse", 19.99, 50),
("Keyboard", 49.99, 30),…How to Check Disk Free Space in Python with shutil.disk_usage
This Python script uses the standard library shutil.disk_usage to report total, used, and free disk space in bytes, plus a percentage usage figure.
import shutil
def check_disk_free_space(path="/"):
"""Return a tuple of total, used, and free disk space in bytes."""
usage = shutil.disk_usage(path)
return usage.total, usage.used, usage.free
if __name__ == "__main__":
total, used, free = check_disk_free_space()
print(f"Total: {total:,} bytes"…How to Compare Directory Trees in Python
This code recursively scans two directory trees and reports files that exist in only one directory, as well as files present in both but with different content.
from pathlib import Path
def compare_directories(path1, path2):
dir1 = Path(path1)
dir2 = Path(path2)
if not dir1.is_dir() or not dir2.is_dir():
raise ValueError("Both paths must be directories.")
files1 = {p.relative_to(dir1) for p in dir1.rglob("*") if p.is_file()}
files2 = {p.relative…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 Compress a String to Gzip Bytes in Python
Compress a string into gzip-compressed bytes entirely in memory using the standard library gzip module.
import gzip
def compress_to_gzip_bytes(data: str, encoding: str = "utf-8") -> bytes:
"""Compress a string to gzip-compressed bytes in memory."""
return gzip.compress(data.encode(encoding))
if __name__ == "__main__":
original = "Hello, world! " * 10
compressed = compress_to_gzip_bytes(original)
pr…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.