Files & data
Read and write files safely; parse JSON, CSV, and common text formats.
How to Compute File SHA256 Hash with hashlib in Python
Compute the SHA256 hash of a file by reading it in chunks with hashlib and Path.open.
import hashlib
from pathlib import Path
def sha256_file(file_path: Path) -> str:
sha256_hash = hashlib.sha256()
with file_path.open("rb") as f:
for chunk in iter(lambda: f.read(4096), b""):
sha256_hash.update(chunk)
return sha256_hash.hexdigest()
if __name__ == "__main__":
demo_fi…How to Convert CSV Column Types While Reading in Python
Read a CSV file and automatically convert column values to int, float, str, or bool based on type suffixes in the header names.
import csv
from pathlib import Path
from typing import Any
def read_csv_with_types(filepath: str) -> list[dict[str, Any]]:
"""Read CSV and convert column types based on header suffixes."""
converters = {
"int": int,
"float": float,
"str": str,
"bool": lambda v: v.strip().lower(…How to Convert Images Between Formats in Python
Use the Pillow library to open an image from one file format and save it to another, with error handling for missing files or conversion issues.
from PIL import Image
import sys
def convert_image_format(input_path, output_path):
try:
img = Image.open(input_path)
img.save(output_path)
print(f"Converted {input_path} to {output_path}")
except FileNotFoundError:
print(f"Error: File {input_path} not found")
sys.exit(…How to Copy a File with shutil.copy2 in Python
Copy a file while preserving metadata like timestamps and permissions using Python's shutil.copy2 and pathlib.
import shutil
from pathlib import Path
source = Path("sample.txt")
destination = Path("sample_copy.txt")
source.write_text("Hello, PythonSkillset!")
if __name__ == "__main__":
shutil.copy2(source, destination)
copied = destination.read_text()
print(f"Copied content: {copied}")
print(f"Source exists:…How to Create Nested Directories with pathlib mkdir parents in Python
Create nested directories with pathlib's Path.mkdir using parents=True and exist_ok=True to avoid errors when paths already exist.
from pathlib import Path
def create_nested_directories(base_path: str, dirs: list[str]) -> None:
for directory in dirs:
path = Path(base_path) / directory
path.mkdir(parents=True, exist_ok=True)
print(f"Created: {path}")
if __name__ == "__main__":
root = "output"
nested_dirs = ["2…How to Decompress a gzip File in Python
This code provides a function to decompress a .gz file, writing the decompressed content to a new file and returning the text, using the gzip standard library module.
import gzip
from pathlib import Path
def decompress_gzip(filepath: str, output_path: str | None = None) -> str:
"""Decompress a .gz file and return the decompressed content."""
input_path = Path(filepath)
if output_path is None:
output_path = str(input_path.with_suffix(""))
with gzip.open…How to Delete a File if it Exists in Python
Delete a file safely in Python using pathlib's Path.unlink, checking existence first to avoid errors.
from pathlib import Path
def delete_file_if_exists(file_path: str) -> bool:
"""Delete a file if it exists. Returns True if deleted, False if not found."""
path = Path(file_path)
if path.exists():
path.unlink()
print(f"Deleted: {path}")
return True
else:
print(f"File not…How to Detect File Encoding: UTF-8 vs Latin-1 in Python
Detect whether a file is UTF-8 or Latin-1 encoded by attempting a UTF-8 decode and falling back to Latin-1.
import sys
def detect_encoding(file_path):
with open(file_path, 'rb') as f:
raw = f.read()
try:
raw.decode('utf-8')
return 'UTF-8'
except UnicodeDecodeError:
return 'latin1'
if __name__ == "__main__":
file_path = sys.argv[1] if len(sys.argv) > 1 else 'sample.txt'
…How to Extract IP Address Counts from Access Logs in Python
Read a web server access log, count occurrences of each IP address using regex and Counter, and print the ranked results.
import re
from collections import Counter
from pathlib import Path
def extract_ip_counts(log_file_path):
ip_pattern = r'^(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})'
ip_counter = Counter()
with open(log_file_path, 'r') as file:
for line in file:
match = re.match(ip_pattern, line)
…How to Extract Text from PDF Files in Python
Extract all readable text from a PDF file using PyPDF2, iterating over each page and concatenating the content.
import PyPDF2
def extract_text_from_pdf(pdf_path):
text = ""
with open(pdf_path, "rb") as file:
reader = PyPDF2.PdfReader(file)
for page in reader.pages:
text += page.extract_text() + "\n"
return text.strip()
if __name__ == "__main__":
pdf_path = "sample.pdf"
extracted…How to Fetch Weather Data from a Public API in Python
Fetches and parses weather data from a free public API using only the Python standard library.
import urllib.request
import json
def get_weather(city):
base_url = f"https://wttr.in/{city}?format=j1"
with urllib.request.urlopen(base_url) as response:
data = json.loads(response.read().decode())
current = data["current_condition"][0]
temp = current["temp_C"]
desc = current["weatherDesc…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"…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.