Files & data
Read and write files safely; parse JSON, CSV, and common text formats.
Audit File Permissions Across a Project in Python
Walks through every file and directory in a project tree and prints POSIX permissions plus owner UID.
import os
import stat
from pathlib import Path
def audit_file_permissions(project_root):
"""Walk through project_root and print path, owner, and permissions for every file."""
results = []
for root, dirs, files in os.walk(project_root):
for name in files + dirs:
full_path = os.path.joi…Automatically Detect Corrupted Files Using SHA-256 Checksums in Python
Compute SHA-256 checksums of files and compare them to detect corruption in Python.
import hashlib
import os
def compute_sha256(filepath: str) -> str:
"""Compute SHA-256 checksum of a file."""
sha256 = hashlib.sha256()
with open(filepath, 'rb') as f:
for chunk in iter(lambda: f.read(4096), b''):
sha256.update(chunk)
return sha256.hexdigest()
def validate_file_int…Compare Two Folder Structures and Find Differences in Python
Walks two directories using os.walk, builds sets of relative paths, and prints items that exist in only one folder.
import os
def compare_folders(path1, path2):
"""
Compare the file/folder structure of two directories and print differences.
"""
def get_structure(root):
structure = set()
for dirpath, dirnames, filenames in os.walk(root):
rel_path = os.path.relpath(dirpath, root)
…Convert File Data to a Dictionary in Python
This function scans a directory and converts each file's metadata (name, size, extension) into a structured dictionary for easy access.
from pathlib import Path
def convert_files_data(directory: str) -> dict:
data = {}
base = Path(directory)
if not base.exists():
return data
for file in base.iterdir():
if file.is_file():
data[file.name] = {
"size": file.stat().st_size,
"exten…How to Bulk Insert Rows into SQLite in Python
Insert many rows into an SQLite table in one call with cursor.executemany, then verify them with a SELECT query.
import sqlite3
# Create an in-memory database and a table
conn = sqlite3.connect(":memory:")
cursor = conn.cursor()
cursor.execute("CREATE TABLE products (name TEXT, price REAL, quantity INTEGER)")
# Data to insert in bulk
products = [
("Laptop", 999.99, 5),
("Mouse", 19.99, 50),
("Keyboard", 49.99, 30),…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 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 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 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 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 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 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 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 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 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…How to Watch a Directory for New Files in Python
Poll a directory at regular intervals and detect newly added files, printing each one as it appears.
import time
import os
from pathlib import Path
WATCH_DIR = Path("watched_files")
def watch_for_new_files(directory: Path, sleep_time: float = 1.0, max_iterations: int = 10):
"""Poll a directory for new files and print when one appears."""
directory.mkdir(exist_ok=True)
existing = set(os.listdir(directory…How to Write a Dict to a Pretty JSON File with Indent in Python
Serializes a Python dictionary to a readable JSON file using json.dump with indentation and sorted keys, then prints the file contents to stdout.
import json
from pathlib import Path
data = {
"name": "Python",
"version": 3.12,
"features": ["simple", "readable", "powerful"],
"nested": {"creator": "Guido van Rossum", "year": 1991}
}
output_path = Path("output.json")
with output_path.open("w", encoding="utf-8") as f:
json.dump(data, f, inden…How to resolve a symlink to its real path in Python with pathlib
Use Path.resolve() to turn a symlink path into its absolute target path, handling relative symlinks and eliminating symbolic links.
from pathlib import Path
def resolve_symlink(path):
p = Path(path)
return str(p.resolve())
if __name__ == "__main__":
# Create a symlink to demonstrate the resolution
target = Path("/tmp/real_target.txt")
target.write_text("hello")
link = Path("/tmp/my_link.txt")
try:
link.symlink…Merge Multiple PDF Files into One Document in Python
Combines multiple PDF files into a single PDF document using the PyPDF2 library's PdfMerger class.
import PyPDF2
def merge_pdfs(input_paths, output_path):
merger = PyPDF2.PdfMerger()
for path in input_paths:
merger.append(path)
merger.write(output_path)
merger.close()
print(f"Merged {len(input_paths)} PDFs into '{output_path}'.")
if __name__ == "__main__":
files = ["file1.pdf", "fi…Read Entire File into String with read Method in Python
Open a file, read its entire content into a string using the .read() method, and clean up with a context manager.
from pathlib import Path
def read_file_to_string(file_path: str) -> str:
"""Read the entire file content into a string using the read method."""
with open(file_path, 'r', encoding='utf-8') as file:
content = file.read()
return content
if __name__ == "__main__":
# Create a temporary file for d…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.