Files & data
Read and write files safely; parse JSON, CSV, and common text formats.
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 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 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 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 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 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 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 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…
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.