Files & data
Read and write files safely; parse JSON, CSV, and common text formats.
How to Filter CSV Rows by Column Value in Python
Filter CSV rows based on a column value condition using the standard csv module and a lambda function.
import csv
def filter_csv(input_file, output_file, column, condition):
with open(input_file, newline='', encoding='utf-8') as infile, \
open(output_file, 'w', newline='', encoding='utf-8') as outfile:
reader = csv.DictReader(infile)
fieldnames = reader.fieldnames
writer = csv.Dict…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…How to Find HTML Elements by Tag, Class, ID, CSS Selector, and Attribute in BeautifulSoup
Parse an HTML string with BeautifulSoup and demonstrate five distinct ways to locate elements: by tag name, by class, by ID, by CSS selector, and by attribute.
from bs4 import BeautifulSoup
html_content = """
<html><body>
<h1 id="title" class="heading">Hello World</h1>
<p class="content">First paragraph</p>
<p class="content special">Second paragraph</p>
<a href="https://example.com" class="link">Click here</a>
<div id="footer">
<p>© 2024</p>
…How to Generate Beautiful QR Codes with Embedded Logos in Python
Generate a high-error-correction QR code and paste a logo image in the center to create a branded, scannable QR code.
import qrcode
from PIL import Image
def generate_qr_with_logo(data, logo_path, output_path):
qr = qrcode.QRCode(
version=1,
error_correction=qrcode.constants.ERROR_CORRECT_H,
box_size=10,
border=4,
)
qr.add_data(data)
qr.make(fit=True)
qr_img = qr.make_image(fill_c…How to Generate an Inventory Report of All Files in Python
Walk a directory tree, collect metadata for every file, and write a CSV inventory report using Python's os, pathlib, and csv modules.
import os
import csv
from pathlib import Path
from datetime import datetime
def generate_inventory_report(root_dir: str = "/", output_file: str = "inventory_report.csv"):
headers = ["File Path", "Size (bytes)", "Last Modified", "File Type"]
rows = []
start_time = datetime.now()
for dirpath, dirna…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 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 a YAML Subset in Python Without PyYAML
Parse a flat, key-value YAML file with the Python standard library (re and pathlib), handling comments, quotes, and inline comments while skipping nested structures.
import re
from pathlib import Path
def load_yaml_subset(path):
"""Load a flat YAML file (key: value) without external dependencies."""
data = {}
with open(path, 'r', encoding='utf-8') as f:
for line in f:
# Skip empty lines and comments
line = line.strip()
if no…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 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 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 Merge Sorted Chunk Files in Python
Merge multiple sorted text files into one sorted output file using a heap for efficient k-way merging.
import heapq
def merge_sorted_chunks(chunks, output_path):
"""Merge multiple sorted iterables into single sorted output file."""
with open(output_path, "w") as out_f:
# Open all chunk files
handles = [open(chunk, "r") for chunk in chunks]
try:
# Heap of (value, index) tupl…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__"…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.