Files & data
Read and write files safely; parse JSON, CSV, and common text formats.
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…How to Group Files by Extension in Python
Group file names by their file extension using a dictionary and pathlib, producing a simple clear mapping for beginners.
from pathlib import Path
def group_data_by_extension(files: list[Path]) -> dict[str, list[str]]:
"""Group file names by their extension."""
grouped: dict[str, list[str]] = {}
for file in files:
ext = file.suffix.lower()
grouped.setdefault(ext, []).append(file.name)
return grouped
if…How to Handle Missing Values in a CSV Numeric Column in Python
Clean missing entries in a CSV numeric column by filling them with the mean, median, a custom value, or dropping rows.
import csv
from pathlib import Path
import statistics
def clean_csv_numeric(input_path: str, output_path: str, column: str, strategy: str = "mean") -> None:
"""
Handles missing values in a numeric column of a CSV file.
Strategies: 'mean', 'median', 'drop', or 'fill' with a specified value.
"""
row…How to List File Information in a Directory with Python
A helper that walks a directory and returns each file's name, size, and extension as a list of dictionaries.
from pathlib import Path
def get_files_data(directory: str) -> list[dict]:
"""Return basic info about all files in a directory."""
files = []
for path in Path(directory).iterdir():
if path.is_file():
files.append({
"name": path.name,
"size": path.stat()…How to List File Metadata in Python
This code walks a directory and returns a list of JSON-ready dicts with each file's name, size, and modification time.
from pathlib import Path
import json
def format_files_data(directory_path):
"""Return a list of JSON-serializable dicts with file metadata."""
base = Path(directory_path)
if not base.is_dir():
raise ValueError(f"Not a directory: {directory_path}")
files_data = []
for file_path in base.ite…How to List Files Matching a Glob Pattern in Python
Uses pathlib.Path.glob to find and sort all files matching a glob pattern like *.py in a directory.
from pathlib import Path
def list_files_matching(pattern: str, directory: str = ".") -> list[str]:
"""Return sorted list of file paths matching the glob pattern in a directory."""
return sorted(Path(directory).glob(pattern))
if __name__ == "__main__":
# Example: list all .py files in current directory
…How to List Tar Archive Contents in Python
Open a tar archive with the stdlib tarfile module and print each entry's type, size, and name.
import tarfile
from pathlib import Path
def list_tar_contents(archive_path):
"""List all entries in a tar archive."""
entries = []
with tarfile.open(archive_path, "r") as tar:
for member in tar.getmembers():
entry_type = "dir" if member.isdir() else "file"
entries.append(f"…How to Load and Save JSON Files in Python
Load and save JSON files with pretty formatting using Python's standard library json module and pathlib.
import json
from pathlib import Path
def load_json(filepath: str) -> dict:
"""Load JSON data from a file."""
path = Path(filepath)
with path.open("r", encoding="utf-8") as f:
return json.load(f)
def save_json(filepath: str, data: dict) -> None:
"""Save data to a JSON file with pretty format…How to Merge Dicts from Two JSON Files Like a Pro
This helper reads two JSON files that contain dicts, merges them with the second file overriding duplicate keys, and saves the result to a new file.
import json
from pathlib import Path
def merge_json_files(file1: str, file2: str, output: str = "merged.json") -> dict:
"""Merge two JSON files containing dicts, with file2 overriding file1."""
data1 = json.loads(Path(file1).read_text())
data2 = json.loads(Path(file2).read_text())
merged = {**data1,…How to Parse INI Config Files in Python with configparser
Load and read settings from an INI file using Python's built-in configparser module, with type-safe value access.
import configparser
from pathlib import Path
# Create a sample INI file for demonstration
sample_content = """
[Database]
host = localhost
port = 5432
user = admin
password = secret123
[Logging]
level = INFO
file = app.log
max_size = 10MB
"""
config_file = Path("sample_config.ini")
config_file.write_text(sample_con…How to Parse JSON, TXT, and CSV Files in Python
This code provides simple functions to read and parse JSON, text, and CSV files using Python's standard library, returning native data structures.
import json
from pathlib import Path
def parse_json_file(filepath):
"""Read and parse a JSON file, returning its contents."""
path = Path(filepath)
with path.open('r', encoding='utf-8') as f:
return json.load(f)
def parse_txt_lines(filepath):
"""Read a text file and return non-empty stripped …How to Parse Path Components with pathlib Path in Python
Parse a file path into parent directory, filename, stem, suffix, and parts using the standard library pathlib module.
from pathlib import Path
if __name__ == "__main__":
p = Path("data/reports/2024/final.txt")
print(f"Path: {p}")
print(f"Parent: {p.parent}")
print(f"Name: {p.name}")
print(f"Stem: {p.stem}")
print(f"Suffix: {p.suffix}")
print(f"Parts: {p.parts}")
print(f"Anchor: {p.anchor}")
print(…How to Prune Empty Directories in Python with os.walk
Remove all empty subdirectories bottom-up using os.walk with topdown=False and os.rmdir, safely ignoring non-empty folders.
import os
def prune_empty_dirs(root):
"""Remove all empty subdirectories under root, bottom-up."""
for dirpath, dirnames, filenames in os.walk(root, topdown=False):
if dirpath == root:
continue
try:
os.rmdir(dirpath)
print(f"Removed: {dirpath}")
exce…How to Read a Text File Line by Line in Python
Reads a text file line by line with an enumerated for loop and prints each line number and content.
from pathlib import Path
def read_lines(file_path):
with open(file_path, 'r', encoding='utf-8') as file:
for line_number, line in enumerate(file, start=1):
print(f"Line {line_number}: {line.rstrip()}")
if __name__ == "__main__":
sample_file = Path("sample.txt")
sample_file.write_text(…How to Read and Write Files in Python (JSON + Text)
A beginner-friendly helper module to read and write JSON and text files using Python's pathlib and json standard library modules.
import json
from pathlib import Path
def load_json_file(filepath):
"""Load data from a JSON file and return as dict/list."""
path = Path(filepath)
with path.open("r", encoding="utf-8") as f:
return json.load(f)
def save_json_file(filepath, data):
"""Save data to a JSON file."""
path = P…How to Read and Write Text Files in Python
This code provides simple helper functions to save and load text files using Python's standard pathlib library.
from pathlib import Path
def save_text_data(filename: str, content: str) -> None:
file_path = Path(filename)
file_path.write_text(content, encoding="utf-8")
def load_text_data(filename: str) -> str:
file_path = Path(filename)
return file_path.read_text(encoding="utf-8")
if __name__ == "__main__":…How to Sanitize Filenames in Python
Strip illegal filename characters and clean up names for safe filesystem use.
import re
from pathlib import Path
def sanitize_filename(filename: str, replacement: str = "_") -> str:
"""
Remove illegal characters from a filename.
Illegal characters: / \\ : * ? " < > |
Also strips leading/trailing spaces and dots.
"""
# Remove illegal characters
sanitized = re.su…How to Sort Files by Name and Size in Python
Sort a list of file dictionaries by name then size using Python's sorted() with a lambda key.
from pathlib import Path
def sort_files_data(files):
"""Sort a list of file dictionaries by name, then by size."""
return sorted(files, key=lambda f: (f["name"], f["size"]))
if __name__ == "__main__":
files_data = [
{"name": "report.pdf", "size": 2048},
{"name": "data.csv", "size": 1024},…How to Split Files by Extension in Python
Group files in a folder by their file extension into a dictionary using pathlib.
from pathlib import Path
def split_files_by_extension(folder_path):
folder = Path(folder_path)
files_by_ext = {}
for file_path in folder.iterdir():
if file_path.is_file():
ext = file_path.suffix.lower() or "no_extension"
files_by_ext.setdefault(ext, []).append(file_path.na…How to Split a Large File into Fixed-Size Parts in Python
Splits any binary or text file into multiple part files of a fixed byte size using Python's standard library.
import os
import math
def split_file(filepath, chunk_size_bytes):
"""Split a file into parts of fixed size (bytes). Creates part files in same directory."""
filepath = os.path.abspath(filepath)
basename = os.path.basename(filepath)
file_size = os.path.getsize(filepath)
num_parts = math.ceil(file_s…How to Strip BOM When Reading UTF-8 Files in Python
Read a UTF-8 text file with Python's pathlib while automatically stripping the Byte Order Mark (BOM) so the first character isn't a hidden glyph.
from pathlib import Path
def read_text_without_bom(file_path):
"""Read a UTF-8 text file, stripping the BOM if present."""
return Path(file_path).read_text(encoding='utf-8-sig')
if __name__ == "__main__":
# Create a sample file with BOM for demonstration
sample_path = Path("sample_with_bom.txt")
…How to Validate JSON Schema Shape in Python
Validate JSON data against a schema using manual checks for required fields, types, and constraints.
import json
from typing import Any, Dict
def validate_person_schema(data: Dict[str, Any]) -> bool:
"""Validate a person object against expected schema shape."""
if not isinstance(data, dict):
return False
# Required fields check
required_fields = {"name", "age", "email"}
if not requir…How to Walk a Directory Tree with os.walk in Python
A generator function that recursively walks a directory tree and yields every file path found using the os.walk generator.
import os
def walk_directory_tree(root_path: str):
"""Walk a directory tree and yield file paths using os.walk generator."""
for dirpath, dirnames, filenames in os.walk(root_path):
for filename in filenames:
yield os.path.join(dirpath, filename)
if __name__ == "__main__":
# Create a…How to Watch a Directory for New Files in Python
Poll a directory at regular intervals and detect newly added files, printing each one as it appears.
import time
import os
from pathlib import Path
WATCH_DIR = Path("watched_files")
def watch_for_new_files(directory: Path, sleep_time: float = 1.0, max_iterations: int = 10):
"""Poll a directory for new files and print when one appears."""
directory.mkdir(exist_ok=True)
existing = set(os.listdir(directory…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.