Files & data
Read and write files safely; parse JSON, CSV, and common text formats.
Find Duplicate Web Pages by Content Similarity in Python
Compute SHA-256 hashes of file contents to detect and report duplicate HTML pages or any files in a directory.
import hashlib
import os
from collections import defaultdict
def get_file_hash(filepath):
"""Compute SHA-256 hash of file contents."""
sha256 = hashlib.sha256()
with open(filepath, 'rb') as f:
for chunk in iter(lambda: f.read(4096), b''):
sha256.update(chunk)
return sha256.hexdiges…Generate Timesheet Reports from Daily Logs in Python
Aggregate daily log entries by project and produce a formatted timesheet report using Python's standard library.
import json
from pathlib import Path
from collections import defaultdict
def generate_timesheet_report(daily_logs: list[dict]) -> str:
"""
Generate a timesheet report from daily log entries.
Args:
daily_logs: List of dicts with 'date', 'project', 'hours', 'task' keys
Returns:
…Generate a Beautiful Folder Tree Visualization in Python
A Python utility that creates a visual tree of a directory structure, excluding common files, with configurable depth.
import os
from pathlib import Path
class FolderTree:
def __init__(self, root_path=".", ignore_list=None, max_depth=3):
self.root = Path(root_path)
self.ignore = set(ignore_list or [".git", "__pycache__", ".DS_Store"])
self.max_depth = max_depth
def generate(self):
tree…Generate a Monthly Calendar PDF in Python
Create a Python utility that generates a monthly calendar PDF using ReportLab, with weekday headers and day numbers laid out in a grid.
from calendar import TextCalendar
from datetime import datetime
from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas
import os
def generate_monthly_calendar_pdf(year, month, filename="calendar.pdf"):
cal = TextCalendar()
days = cal.monthdays2calendar(year, month)
month_name …How to Archive Old Files by Age in Python
Move files older than a specified number of days from a source directory to an archive directory using Python's pathlib and shutil modules.
import os
import shutil
import time
from pathlib import Path
def archive_old_files(source_dir: str, archive_dir: str, days_old: int) -> None:
cutoff_time = time.time() - (days_old * 86400) # 86400 seconds in a day
archive_path = Path(archive_dir)
archive_path.mkdir(parents=True, exist_ok=True)
for i…How to Atomically Write Files in Python with Temp File and Rename
Write a file atomically using a temporary file and os.replace so readers never see partial writes even if the process crashes mid-write.
import os
import tempfile
from pathlib import Path
def atomic_write(path: str | Path, content: str) -> None:
"""Write content to path atomically using a temp file and rename."""
path = Path(path)
path.parent.mkdir(parents=True, exist_ok=True)
fd, temp_path = tempfile.mkstemp(
dir=str(path.par…How to Audit Environment Variable Files for Missing Values in Python
A Python tool that reads an environment variable file and reports any variables with empty or missing values.
import os
import re
from pathlib import Path
def audit_env_file(filepath: str) -> None:
"""
Audit an environment variable file for missing values.
Prints file status and lists variables that have empty values.
"""
path = Path(filepath)
if not path.exists():
print(f"Error: File '{filepa…How to Automatically Extract Every Archive in a Folder with Python
Walk through a folder and extract all ZIP, RAR, and 7Z archives into separate subdirectories using Python.
import zipfile
import rarfile
import py7zr
import pathlib
def extract_archives(folder: str):
"""Extract every ZIP, RAR, and 7Z archive in the given folder."""
folder_path = pathlib.Path(folder)
for archive_file in folder_path.iterdir():
suffix = archive_file.suffix.lower()
try:
…How to Automatically Merge Hundreds of Excel Files Without Losing Formatting in Python
Merge all .xlsx files in a folder into a single Excel workbook, preserving individual sheet structures with sheet name prefixes.
import pandas as pd
from pathlib import Path
def merge_excel_files(folder_path: str, output_path: str) -> None:
"""
Merge all .xlsx files in a folder into a single Excel file,
preserving individual sheet structures.
"""
folder = Path(folder_path)
excel_files = list(folder.glob("*.xlsx"))
…How to Build a CSV Comparison Tool That Highlights Every Changed Cell in Python
Read two CSV files with DictReader, compare cell by cell, and return a list of dictionaries describing each changed cell using only the standard library.
import csv
from pathlib import Path
def csv_cell_diff(file_a: str, file_b: str) -> list[dict]:
rows_a = list(csv.DictReader(Path(file_a).open('r', newline='')))
rows_b = list(csv.DictReader(Path(file_b).open('r', newline='')))
if not rows_a or not rows_b:
return []
columns = list(rows_a[0].key…How to Check Disk Free Space in Python with shutil.disk_usage
This Python script uses the standard library shutil.disk_usage to report total, used, and free disk space in bytes, plus a percentage usage figure.
import shutil
def check_disk_free_space(path="/"):
"""Return a tuple of total, used, and free disk space in bytes."""
usage = shutil.disk_usage(path)
return usage.total, usage.used, usage.free
if __name__ == "__main__":
total, used, free = check_disk_free_space()
print(f"Total: {total:,} bytes"…How to Compare Directory Trees in Python
This code recursively scans two directory trees and reports files that exist in only one directory, as well as files present in both but with different content.
from pathlib import Path
def compare_directories(path1, path2):
dir1 = Path(path1)
dir2 = Path(path2)
if not dir1.is_dir() or not dir2.is_dir():
raise ValueError("Both paths must be directories.")
files1 = {p.relative_to(dir1) for p in dir1.rglob("*") if p.is_file()}
files2 = {p.relative…How to Compare Two Files by Content Hash Equality in Python
Compares two files by hashing their contents with SHA-256, skipping the hash if file sizes differ, and returns whether they are identical.
import hashlib
from pathlib import Path
def file_hash(path: Path, chunk_size: int = 8192) -> str:
sha256 = hashlib.sha256()
with path.open("rb") as f:
for chunk in iter(lambda: f.read(chunk_size), b""):
sha256.update(chunk)
return sha256.hexdigest()
def files_are_identical(file_a: Pat…How to Compress a String to Gzip Bytes in Python
Compress a string into gzip-compressed bytes entirely in memory using the standard library gzip module.
import gzip
def compress_to_gzip_bytes(data: str, encoding: str = "utf-8") -> bytes:
"""Compress a string to gzip-compressed bytes in memory."""
return gzip.compress(data.encode(encoding))
if __name__ == "__main__":
original = "Hello, world! " * 10
compressed = compress_to_gzip_bytes(original)
pr…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 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 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 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…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.