Files & data
Read and write files safely; parse JSON, CSV, and common text formats.
How to Transcode a File from Latin-1 to UTF-8 in Python
Read a latin1-encoded text file and rewrite it as UTF-8 using Python's pathlib and encoding parameters.
from pathlib import Path
def transcode_to_utf8(input_path, output_path):
"""Read a latin1-encoded file and write it as UTF-8."""
source = Path(input_path)
target = Path(output_path)
with source.open(encoding='latin1') as infile:
content = infile.read()
with target.open('w', encod…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 Validate a JSON File in Python
A beginner-friendly Python helper that reads a JSON file, catches common errors, and returns a status dictionary.
import json
from pathlib import Path
def get_valid_json_data(file_path: str) -> dict:
file = Path(file_path)
if not file.exists():
return {"status": "error", "message": f"File not found: {file_path}"}
try:
data = json.loads(file.read_text())
except json.JSONDecodeError as e:
…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…How to Write Bytes to a File in Python with 'wb'
Write a bytearray buffer to a binary file using Python's open() in 'wb' mode, then read it back to confirm the data.
data = bytearray([0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x20, 0x57, 0x6f, 0x72, 0x6c, 0x64])
with open("output.bin", "wb") as f:
f.write(data)
with open("output.bin", "rb") as f:
content = f.read()
print(f"Written {len(data)} bytes: {content}")
print(f"As string: {content.decode('ascii')}")How to Write Simple XML Documents with ElementTree in Python
Create well-structured XML documents in memory using Python's built-in ElementTree module, complete with nested elements, attributes, and text content.
import xml.etree.ElementTree as ET
def create_xml_document():
# Create root element
root = ET.Element("catalog")
# Create a book element with attributes and children
book1 = ET.SubElement(root, "book", id="bk101")
ET.SubElement(book1, "author").text = "Gambardella, Matthew"
ET.SubElement(…How to Write a Dict to a Pretty JSON File with Indent in Python
Serializes a Python dictionary to a readable JSON file using json.dump with indentation and sorted keys, then prints the file contents to stdout.
import json
from pathlib import Path
data = {
"name": "Python",
"version": 3.12,
"features": ["simple", "readable", "powerful"],
"nested": {"creator": "Guido van Rossum", "year": 1991}
}
output_path = Path("output.json")
with output_path.open("w", encoding="utf-8") as f:
json.dump(data, f, inden…How to check file data in Python
Check if a file exists and is a regular file, then return its name, size, line count, and first line.
def check_file_data(file_path):
from pathlib import Path
path = Path(file_path)
if not path.exists():
return f"File '{file_path}' does not exist."
if not path.is_file():
return f"'{file_path}' is not a regular file."
size = path.stat().st_size
lines = path.read_text(encodin…How to resolve a symlink to its real path in Python with pathlib
Use Path.resolve() to turn a symlink path into its absolute target path, handling relative symlinks and eliminating symbolic links.
from pathlib import Path
def resolve_symlink(path):
p = Path(path)
return str(p.resolve())
if __name__ == "__main__":
# Create a symlink to demonstrate the resolution
target = Path("/tmp/real_target.txt")
target.write_text("hello")
link = Path("/tmp/my_link.txt")
try:
link.symlink…How to write an INI config section with configparser in Python
Create an INI configuration file with sections using Python's configparser module and write it to disk.
import configparser
config = configparser.ConfigParser()
config["General"] = {
"host": "localhost",
"port": "8080",
"debug": "true"
}
config["Database"] = {
"name": "appdb",
"user": "admin",
"password": "secret"
}
with open("example.ini", "w") as file:
config.write(file)
with open("examp…Merge Multiple PDF Files into One Document in Python
Combines multiple PDF files into a single PDF document using the PyPDF2 library's PdfMerger class.
import PyPDF2
def merge_pdfs(input_paths, output_path):
merger = PyPDF2.PdfMerger()
for path in input_paths:
merger.append(path)
merger.write(output_path)
merger.close()
print(f"Merged {len(input_paths)} PDFs into '{output_path}'.")
if __name__ == "__main__":
files = ["file1.pdf", "fi…Move a file to an archive folder with shutil.move in Python
Move a file to an archive folder with shutil.move, creating the folder if needed, and return the new path.
from pathlib import Path
import shutil
def move_file_to_archive(source_file: str, archive_folder: str) -> Path:
"""Move a file to the archive folder, creating it if needed."""
src = Path(source_file)
archive = Path(archive_folder)
archive.mkdir(parents=True, exist_ok=True)
destination = archive / …Normalize CSV Column Names to snake_case in Python
Convert CSV header names to snake_case using a regular expression and write the updated file in place.
import csv
import re
import sys
def to_snake_case(header):
header = re.sub(r"(?<=[a-z0-9])(?=[A-Z])", "_", header)
header = re.sub(r"[^a-zA-Z0-9]+", "_", header).strip("_").lower()
return header
def normalize_csv_headers(input_path, output_path=None):
with open(input_path, newline="", encoding="utf…Parameterize SQL queries in Python to prevent SQL injection
Safely fetch users from a SQLite database using parameterized queries to prevent SQL injection attacks.
import sqlite3
def get_users_by_name(name):
"""Fetch users safely using parameterized query."""
conn = sqlite3.connect(':memory:')
cursor = conn.cursor()
# Create sample table and data
cursor.execute('CREATE TABLE users (id INTEGER, name TEXT)')
cursor.executemany('INSERT INTO users (name…Parse CSV with Custom Delimiter and Quote Character in Python
Reads a CSV string with a custom delimiter and quote character using the csv module, returning a list of rows.
import csv
from io import StringIO
def parse_csv(data, delimiter='|', quotechar='"'):
reader = csv.reader(StringIO(data), delimiter=delimiter, quotechar=quotechar)
rows = [row for row in reader]
return rows
if __name__ == "__main__":
sample = 'Alice|"Smith, Jr."|25\nBob|"Johnson, Sr."|30'
result …Parse Fixed Width Data File by Column Slices in Python
Extract fields from fixed-width text by slicing each line at defined column offsets, with a dictionary describing the boundaries.
from pathlib import Path
def parse_fixed_width(data: str, slices: dict[str, tuple[int, int]]) -> list[dict[str, str]]:
lines = data.strip().splitlines()
records = []
for line in lines:
record = {}
for name, (start, end) in slices.items():
record[name] = line[start:end].strip()…Read Entire File into String with read Method in Python
Open a file, read its entire content into a string using the .read() method, and clean up with a context manager.
from pathlib import Path
def read_file_to_string(file_path: str) -> str:
"""Read the entire file content into a string using the read method."""
with open(file_path, 'r', encoding='utf-8') as file:
content = file.read()
return content
if __name__ == "__main__":
# Create a temporary file for d…Read SQLite database with sqlite3 module in Python
Connect to a SQLite database and query rows with the standard library sqlite3 module, returning results as dictionaries.
import sqlite3
from pathlib import Path
# Create an in-memory database and a sample table
connection = sqlite3.connect(":memory:")
cursor = connection.cursor()
cursor.execute("""
CREATE TABLE employees (
id INTEGER PRIMARY KEY,
name TEXT NOT NULL,
department TEXT NOT NULL,
salary REAL
)
""")
# Inser…Read a CSV File with csv.DictReader in Python
Read a CSV file as a list of dictionaries, using csv.DictReader to map each row to column names.
import csv
from pathlib import Path
def read_csv_with_dictreader(file_path):
data = []
with open(file_path, mode='r', newline='', encoding='utf-8') as csvfile:
reader = csv.DictReader(csvfile)
for row in reader:
data.append(row)
return data
if __name__ == "__main__":
# Cre…Read an XML File with xml.etree.ElementTree in Python
Parse an XML file and print its root and child elements using the standard library's xml.etree.ElementTree module.
import xml.etree.ElementTree as ET
def read_xml_file(file_path):
"""Read an XML file and print its structure."""
tree = ET.parse(file_path)
root = tree.getroot()
print(f"Root element: {root.tag}")
for child in root:
print(f"Child element: {child.tag}, text: {child.text}")
if __name__ ==…Reassemble File Parts into Original File Bytes in Python
Read sorted part files from a directory and concatenate their bytes into the original file.
import os
import sys
from pathlib import Path
def reassemble_parts(parts_dir: Path, output_path: Path) -> int:
"""
Reassemble file parts into the original file.
Args:
parts_dir: Directory containing the part files
output_path: Path where the reassembled file will be written
Returns:
…Rotate Log Files in Python by Size
This code rotates a log file when its size exceeds a threshold, keeping a specified number of backups.
import os
import glob
from pathlib import Path
def rotate_log(log_path, max_size_bytes=1024, max_backups=3):
log_file = Path(log_path)
if log_file.stat().st_size <= max_size_bytes:
print(f"Log size {log_file.stat().st_size} bytes <= threshold, no rotation")
return
for i in range(max_backu…Split CSV Files into Smaller Chunks in Python
Splits a large CSV file into multiple smaller chunk files, preserving the header row in each chunk.
import csv
import os
def split_csv(input_file, chunk_size=1000, output_prefix="chunk"):
"""Split a large CSV file into smaller chunks."""
with open(input_file, 'r', newline='') as infile:
reader = csv.reader(infile)
header = next(reader)
file_count = 1
row_count = 0
…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.