Files & data
Read and write files safely; parse JSON, CSV, and common text formats.
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 Load Pickle Files Safely in Python
This code demonstrates how to load pickle files safely in Python by using a restricted unpickler that only allows specific, trusted classes, preventing arbitrary code execution from untrusted pickles.
import pickle
# Default pickle.load is unsafe: it executes arbitrary code when unpickling.
class Unsafe:
def __reduce__(self):
return (eval, ("open('/tmp/pickle_demo.txt', 'w').write('pwned')",))
# Create a malicious payload (simulating untrusted source)
malicious_data = pickle.dumps(Unsafe())
# Safe ap…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 Memory Map Large Files Read-Only in Python
This code demonstrates reading only the tail of a large file using a read-only memory map (mmap) to avoid loading the entire file into memory.
import mmap
import os
def read_tail_with_mmap(filepath, bytes_from_end=64):
"""Read the last bytes of a large file using a read-only mmap."""
file_size = os.path.getsize(filepath)
start = max(0, file_size - bytes_from_end)
with open(filepath, "rb") as f:
with mmap.mmap(f.fileno(), length=0, a…How to Merge Environment-Specific Config JSON in Python
Loads a base JSON config and overlays environment-specific overrides, merging the two dictionaries into one final config.
import json
import pathlib
def load_config(base_path: pathlib.Path, env: str) -> dict:
base_config = json.loads(base_path.read_text())
env_path = base_path.with_name(f"config.{env}.json")
if env_path.exists():
env_config = json.loads(env_path.read_text())
return {**base_config, **env_conf…How to Parse Apache Log Files in Python
Parse Apache common log format lines into structured dictionaries using Python's standard library.
import re
from pathlib import Path
def parse_apache_line(line):
pattern = r'^(\S+) (\S+) (\S+) \[([^\]]+)\] "(\S+) (\S+) (\S+)" (\d{3}) (\S+)'
match = re.match(pattern, line)
if not match:
return None
ip, ident, user, timestamp, method, path, protocol, status, size = match.groups()
return …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 NDJSON Lines into a List in Python
Reads a JSON-lines (NDJSON) file line by line and converts each non-empty line into a Python object, returning a list.
import json
from pathlib import Path
def parse_ndjson(file_path: str) -> list:
data = []
with Path(file_path).open("r", encoding="utf-8") as f:
for line in f:
line = line.strip()
if line:
data.append(json.loads(line))
return data
if __name__ == "__main__"…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 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 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…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.