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:
…Build a Simple ETL Pipeline in Python
A simple ETL pipeline that reads JSON Lines, transforms records with filtering and normalization, and writes the result to JSON.
import json
from pathlib import Path
def read_input(file_path: Path) -> list[dict]:
"""Read JSON lines file into list of dicts."""
with file_path.open("r", encoding="utf-8") as f:
return [json.loads(line) for line in f if line.strip()]
def transform(records: list[dict]) -> list[dict]:
"""Transf…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 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 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)
…Create an In-Memory SQLite Table and Query It in Python
This code creates an in-memory SQLite database, defines an employees table, inserts sample rows, and runs a filtered query with sorted results.
import sqlite3
conn = sqlite3.connect(":memory:")
cursor = conn.cursor()
cursor.execute("""
CREATE TABLE employees (
id INTEGER PRIMARY KEY,
name TEXT NOT NULL,
department TEXT NOT NULL,
salary REAL
)
""")
employees = [
(1, "Alice", "Engineering", 95000),
(2, "Bob", "…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…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 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):
…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 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 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…How to Compute File SHA256 Hash with hashlib in Python
Compute the SHA256 hash of a file by reading it in chunks with hashlib and Path.open.
import hashlib
from pathlib import Path
def sha256_file(file_path: Path) -> str:
sha256_hash = hashlib.sha256()
with file_path.open("rb") as f:
for chunk in iter(lambda: f.read(4096), b""):
sha256_hash.update(chunk)
return sha256_hash.hexdigest()
if __name__ == "__main__":
demo_fi…How to Convert CSV Column Types While Reading in Python
Read a CSV file and automatically convert column values to int, float, str, or bool based on type suffixes in the header names.
import csv
from pathlib import Path
from typing import Any
def read_csv_with_types(filepath: str) -> list[dict[str, Any]]:
"""Read CSV and convert column types based on header suffixes."""
converters = {
"int": int,
"float": float,
"str": str,
"bool": lambda v: v.strip().lower(…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.