Files & data
Read and write files safely; parse JSON, CSV, and common text formats.
How to check file data in Python
Check if a file exists and is a regular file, then return its name, size, line count, and first line.
def check_file_data(file_path):
from pathlib import Path
path = Path(file_path)
if not path.exists():
return f"File '{file_path}' does not exist."
if not path.is_file():
return f"'{file_path}' is not a regular file."
size = path.stat().st_size
lines = path.read_text(encodin…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…How to write an INI config section with configparser in Python
Create an INI configuration file with sections using Python's configparser module and write it to disk.
import configparser
config = configparser.ConfigParser()
config["General"] = {
"host": "localhost",
"port": "8080",
"debug": "true"
}
config["Database"] = {
"name": "appdb",
"user": "admin",
"password": "secret"
}
with open("example.ini", "w") as file:
config.write(file)
with open("examp…Join two CSV files on shared key column in Python
Merge rows from two CSV files by a common key column, outputting combined records to a new file.
import csv
def join_csv(file1, file2, key, output="joined.csv"):
# Read first CSV into dict keyed by the join column
with open(file1, newline="") as f1:
reader1 = csv.DictReader(f1)
data1 = {row[key]: row for row in reader1}
# Read second CSV and merge matching rows
with open(file2, n…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…Move a file to an archive folder with shutil.move in Python
Move a file to an archive folder with shutil.move, creating the folder if needed, and return the new path.
from pathlib import Path
import shutil
def move_file_to_archive(source_file: str, archive_folder: str) -> Path:
"""Move a file to the archive folder, creating it if needed."""
src = Path(source_file)
archive = Path(archive_folder)
archive.mkdir(parents=True, exist_ok=True)
destination = archive / …Normalize CSV Column Names to snake_case in Python
Convert CSV header names to snake_case using a regular expression and write the updated file in place.
import csv
import re
import sys
def to_snake_case(header):
header = re.sub(r"(?<=[a-z0-9])(?=[A-Z])", "_", header)
header = re.sub(r"[^a-zA-Z0-9]+", "_", header).strip("_").lower()
return header
def normalize_csv_headers(input_path, output_path=None):
with open(input_path, newline="", encoding="utf…Parse Fixed Width Data File by Column Slices in Python
Extract fields from fixed-width text by slicing each line at defined column offsets, with a dictionary describing the boundaries.
from pathlib import Path
def parse_fixed_width(data: str, slices: dict[str, tuple[int, int]]) -> list[dict[str, str]]:
lines = data.strip().splitlines()
records = []
for line in lines:
record = {}
for name, (start, end) in slices.items():
record[name] = line[start:end].strip()…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…Read Parquet-Like Columnar CSV Chunks in Python
A Python generator that reads a CSV file column-by-column, yielding dictionary chunks where each key points to a list of values—mirroring how Parquet stores data columnar.
```python
import csv
from pathlib import Path
from typing import Iterator, List
def read_parquet_like_columnar(csv_path: str, column_names: List[str], chunk_size: int = 2) -> Iterator[dict]:
"""Read CSV data in columnar chunks, similar to how parquet stores columns."""
csv_file = Path(csv_path)
with csv_f…Read a CSV File with csv.DictReader in Python
Read a CSV file as a list of dictionaries, using csv.DictReader to map each row to column names.
import csv
from pathlib import Path
def read_csv_with_dictreader(file_path):
data = []
with open(file_path, mode='r', newline='', encoding='utf-8') as csvfile:
reader = csv.DictReader(csvfile)
for row in reader:
data.append(row)
return data
if __name__ == "__main__":
# Cre…Read an XML File with xml.etree.ElementTree in Python
Parse an XML file and print its root and child elements using the standard library's xml.etree.ElementTree module.
import xml.etree.ElementTree as ET
def read_xml_file(file_path):
"""Read an XML file and print its structure."""
tree = ET.parse(file_path)
root = tree.getroot()
print(f"Root element: {root.tag}")
for child in root:
print(f"Child element: {child.tag}, text: {child.text}")
if __name__ ==…Reassemble File Parts into Original File Bytes in Python
Read sorted part files from a directory and concatenate their bytes into the original file.
import os
import sys
from pathlib import Path
def reassemble_parts(parts_dir: Path, output_path: Path) -> int:
"""
Reassemble file parts into the original file.
Args:
parts_dir: Directory containing the part files
output_path: Path where the reassembled file will be written
Returns:
…Rotate Log Files in Python by Size
This code rotates a log file when its size exceeds a threshold, keeping a specified number of backups.
import os
import glob
from pathlib import Path
def rotate_log(log_path, max_size_bytes=1024, max_backups=3):
log_file = Path(log_path)
if log_file.stat().st_size <= max_size_bytes:
print(f"Log size {log_file.stat().st_size} bytes <= threshold, no rotation")
return
for i in range(max_backu…Scrape HTML Tables and Convert Them to CSV Using Beautiful Soup in Python
Scrape a Wikipedia table with Beautiful Soup and write the data to a CSV file using the csv module.
import requests
from bs4 import BeautifulSoup
import csv
url = "https://en.wikipedia.org/wiki/List_of_countries_by_GDP_(nominal)"
response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')
tables = soup.find_all('table', {'class': 'wikitable'})
if tables:
target_table = tables[2]
rows =…Split CSV Files into Smaller Chunks in Python
Splits a large CSV file into multiple smaller chunk files, preserving the header row in each chunk.
import csv
import os
def split_csv(input_file, chunk_size=1000, output_prefix="chunk"):
"""Split a large CSV file into smaller chunks."""
with open(input_file, 'r', newline='') as infile:
reader = csv.reader(infile)
header = next(reader)
file_count = 1
row_count = 0
…Sync only changed files between two folders in Python
This code compares two folders and copies only the new or modified files from source to destination, skipping unchanged ones by comparing SHA-256 hashes.
import hashlib
from pathlib import Path
import shutil
def file_hash(path: Path, chunk_size: int = 8192) -> str:
hasher = hashlib.sha256()
with path.open("rb") as f:
for chunk in iter(lambda: f.read(chunk_size), b""):
hasher.update(chunk)
return hasher.hexdigest()
def sync_files(src: s…Tail last N lines of growing log file in Python
Prints the last n lines of a log file and follows new content appended to it, polling for size changes.
import time
from pathlib import Path
def tail_log(file_path, n=10, poll_interval=1.0, timeout=10):
"""
Print the last n lines and follow new lines appended to a growing log file.
"""
path = Path(file_path)
# Read the last n lines from the current file
with path.open("r", encoding="utf-8") as f…Write CSV file with csv DictWriter in Python
Write a list of dictionaries to a CSV file using Python's csv.DictWriter, including a header row.
import csv
from pathlib import Path
fieldnames = ["name", "city", "age"]
rows = [
{"name": "Alice", "city": "New York", "age": 30},
{"name": "Bob", "city": "Los Angeles", "age": 25},
{"name": "Charlie", "city": "Chicago", "age": 35},
]
path = Path("people.csv")
with path.open("w", newline="") as csvfile:…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.