Files & data
Read and write files safely; parse JSON, CSV, and common text formats.
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 Parse XML Attributes into a Flat Dictionary in Python
Parses XML elements and attributes using ElementTree, building a flat dictionary keyed by element attributes.
import xml.etree.ElementTree as ET
xml_data = """<root>
<book id="1" category="fiction" price="9.99">
<title>The Catcher</title>
</book>
<book id="2" category="nonfiction" price="12.50">
<title>Deep Learning</title>
</book>
</root>"""
def parse_xml_attributes(xml_string):
root = E…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 Binary File Bytes and Inspect the Header in Python
Read the first bytes of a binary file with pathlib and display them as a hex dump plus an ASCII view to inspect file headers.
import pathlib
def inspect_binary_header(filepath: str, num_bytes: int = 16) -> None:
"""Read the first bytes of a binary file and display them as hex and ASCII."""
path = pathlib.Path(filepath)
data = path.read_bytes()[:num_bytes]
hex_str = ' '.join(f"{byte:02x}" for byte in data)
ascii_str …How to Read a File with Retry on Temporary IOError in Python
Read a file with automatic retries on temporary IOError/OSError failures, using the pathlib module with configurable attempts and delay.
import time
from pathlib import Path
def read_file_with_retry(filepath: str | Path, max_attempts: int = 3, delay: float = 0.5) -> str:
"""Read a file with retries on temporary IO errors."""
path = Path(filepath)
last_error = None
for attempt in range(max_attempts):
try:
return pat…How to Read a JSON File into a Dictionary in Python
Load a JSON file into a Python dictionary using the json.load() function with proper file handling and UTF-8 encoding.
import json
from pathlib import Path
def read_json_file(filepath: str) -> dict:
"""Read a JSON file and return its contents as a dictionary."""
path = Path(filepath)
with path.open("r", encoding="utf-8") as f:
data = json.load(f)
return data
if __name__ == "__main__":
# Create a sample JS…How to Read a TSV File in Python with csv.DictReader
Read a tab-separated (TSV) file into dictionaries using the csv module's DictReader with a tab delimiter.
import csv
from pathlib import Path
data_file = Path("data.tsv")
# Sample TSV content (tab-separated)
sample = """name\tage\tcity
Alice\t30\tNew York
Bob\t25\tLos Angeles
Carol\t35\tChicago
"""
data_file.write_text(sample)
with data_file.open("r", newline="", encoding="utf-8") as f:
reader = csv.DictReader(f, d…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 Record Audio from Your Microphone in Python
Record audio from your default microphone using PyAudio and save it as a WAV file with a simple reusable function.
import pyaudio
import wave
def record_audio(filename: str, duration: int = 5, sample_rate: int = 44100, chunk: int = 1024):
"""Record audio from default microphone and save as WAV file."""
audio_format = pyaudio.paInt16 # 16-bit resolution
channels = 1 # Mono
p = pyaudio.PyAudio()
stre…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 Scrape Headlines from a News Website Using Beautiful Soup in Python
Scrape headline text from a news website using requests and Beautiful Soup with a CSS selector.
import requests
from bs4 import BeautifulSoup
def scrape_headlines(url: str, selector: str) -> list:
"""
Scrape headlines from a news website using Beautiful Soup.
Args:
url: The URL of the news website.
selector: CSS selector for headline elements.
Returns:
List of h…How to Serialize a Python Object to Pickle Bytes in Memory
Serialize a Python object to pickle bytes in memory with pickle.dumps, then deserialize it back with pickle.loads and verify the roundtrip.
import pickle
class Person:
def __init__(self, name, age, skills):
self.name = name
self.age = age
self.skills = skills
def main():
person = Person("Alice", 30, ["Python", "SQL", "Docker"])
# Serialize to bytes in memory
pickle_bytes = pickle.dumps(person)
print(…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 Stream Large CSV Files in Python
Process a large CSV file in memory-efficient chunks using Python's csv module, yielding batches of rows instead of loading everything at once.
import csv
from pathlib import Path
def process_csv_in_chunks(file_path, chunk_size=1000):
"""Yield rows from a large CSV file in chunks without loading all into memory."""
with open(file_path, 'r', newline='') as f:
reader = csv.DictReader(f)
chunk = []
for row in reader:
…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 Sum a CSV Column by Group in Python
This code reads a CSV string and sums a specified column for each unique value of a group key using the csv module and defaultdict.
import csv
from collections import defaultdict
from io import StringIO
def aggregate_csv(csv_data, group_key, sum_column):
totals = defaultdict(float)
reader = csv.DictReader(StringIO(csv_data))
for row in reader:
key = row[group_key]
totals[key] += float(row[sum_column])
return dict(t…How to Sync Two Folders in Python (Lightweight Backup)
A Python script that synchronizes a source folder to a destination folder, copying new or updated files and removing files that no longer exist in the source.
import os
import shutil
import sys
from pathlib import Path
def sync_folders(src: Path, dst: Path):
"""Sync src folder to dst folder, copying missing/updated files."""
dst.mkdir(parents=True, exist_ok=True)
for src_path in src.rglob("*"):
relative = src_path.relative_to(src)
dst_path = ds…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 Use fcntl for Exclusive File Locking in Python
This code demonstrates how to acquire an exclusive advisory lock on a file using fcntl.flock with a non-blocking flag, simulate work, then release the lock.
import fcntl
import os
import tempfile
import time
def acquire_exclusive_lock(filepath):
fd = os.open(filepath, os.O_RDWR | os.O_CREAT)
try:
fcntl.flock(fd, fcntl.LOCK_EX | fcntl.LOCK_NB)
print(f"Exclusive lock acquired on {filepath}")
time.sleep(1) # Simulate work while holding the l…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…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.