Files & data
Read and write files safely; parse JSON, CSV, and common text formats.
Append a Line to a Log File in Python
Append a line to a file using a context manager and Path.open().
from pathlib import Path
def append_to_log(filepath, message):
with Path(filepath).open("a") as log_file:
log_file.write(f"{message}\n")
if __name__ == "__main__":
log_path = "log.txt"
append_to_log(log_path, "First entry")
append_to_log(log_path, "Second entry")
# Verify contents
…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 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 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("*"…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 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…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 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 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 Copy a File with shutil.copy2 in Python
Copy a file while preserving metadata like timestamps and permissions using Python's shutil.copy2 and pathlib.
import shutil
from pathlib import Path
source = Path("sample.txt")
destination = Path("sample_copy.txt")
source.write_text("Hello, PythonSkillset!")
if __name__ == "__main__":
shutil.copy2(source, destination)
copied = destination.read_text()
print(f"Copied content: {copied}")
print(f"Source exists:…How to Create Nested Directories with pathlib mkdir parents in Python
Create nested directories with pathlib's Path.mkdir using parents=True and exist_ok=True to avoid errors when paths already exist.
from pathlib import Path
def create_nested_directories(base_path: str, dirs: list[str]) -> None:
for directory in dirs:
path = Path(base_path) / directory
path.mkdir(parents=True, exist_ok=True)
print(f"Created: {path}")
if __name__ == "__main__":
root = "output"
nested_dirs = ["2…How to Delete a File if it Exists in Python
Delete a file safely in Python using pathlib's Path.unlink, checking existence first to avoid errors.
from pathlib import Path
def delete_file_if_exists(file_path: str) -> bool:
"""Delete a file if it exists. Returns True if deleted, False if not found."""
path = Path(file_path)
if path.exists():
path.unlink()
print(f"Deleted: {path}")
return True
else:
print(f"File not…How to Filter Files by Extension and Size in Python
Use pathlib to list files in a directory, filter by extension or minimum size, and return matching names or (name, size) pairs.
from pathlib import Path
def filter_files_by_extension(directory: str, extension: str) -> list:
"""Return a list of file names in directory with the given extension."""
path = Path(directory)
return [f.name for f in path.iterdir() if f.is_file() and f.suffix == extension]
def filter_files_by_size(directo…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 Find Files by Extension in Python
This code walks a directory tree with pathlib, collects all file paths, and counts them by extension to summarize a project's contents.
from pathlib import Path
def get_project_files(base_path="."):
"""Return a sorted list of all file paths under base_path."""
base = Path(base_path)
files = [p for p in base.rglob("*") if p.is_file()]
return sorted(files)
def count_by_extension(files):
"""Return a dict mapping extension (lowercase…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.