File Operations Reference

Complete reference for Python file operations, modes, and methods. This covers all aspects of file handling including opening, reading, writing, and managing files and directories.

File Opening Modes

*Fails if file exists | **Reading starts at beginning, writing at end

Mode Examples

# Basic file reading
with open('data.txt', 'w') as f:
    f.write("Hello World\nSecond Line")

with open('data.txt', 'r') as f:
    content = f.read()
    print(content)

# Basic file modes
with open('data.txt', 'r') as f:         # Read text file
    content = f.read()

with open('data.txt', 'w') as f:         # Write text file (overwrites)
    f.write("Hello World")

with open('data.txt', 'a') as f:         # Append to text file
    f.write("New line")

# Binary modes
with open('image.jpg', 'rb') as f:       # Read binary file
    data = f.read()

with open('output.jpg', 'wb') as f:      # Write binary file
    f.write(data)

# Read and write modes
with open('data.txt', 'r+') as f:        # Read and write existing file
    content = f.read()
    f.write("Additional text")

# Exclusive creation
try:
    with open('new_file.txt', 'x') as f: # Create new file (fails if exists)
        f.write("New file content")
except FileExistsError:
    print("File already exists")

File Object Methods

Reading Methods

Writing Methods

Position Methods

File State Methods

File Reading Examples

# Read with position tracking
with open('data.txt', 'w') as f:
    f.write("Hello World!")

with open('data.txt', 'r') as f:
    print(f"Position: {f.tell()}")  # 0
    first_5 = f.read(5)
    print(f"Read: {first_5}")
    print(f"Position: {f.tell()}")  # 5

# Read entire file
with open('data.txt', 'r') as f:
    content = f.read()
    print(content)

# Read specific number of characters
with open('data.txt', 'r') as f:
    chunk = f.read(100)  # Read first 100 characters
    
# Read line by line
with open('data.txt', 'r') as f:
    for line in f:  # Most efficient way to iterate
        print(line.strip())

# Read all lines into list
with open('data.txt', 'r') as f:
    lines = f.readlines()
    for line in lines:
        print(line.rstrip('\n'))

# Read with position tracking
with open('data.txt', 'r') as f:
    print(f"Position: {f.tell()}")  # 0
    first_10 = f.read(10)
    print(f"Position: {f.tell()}")  # 10
    f.seek(0)  # Back to beginning
    print(f"Position: {f.tell()}")  # 0

File Writing Patterns

Basic Writing

# Write string to file
with open('output.txt', 'w') as f:
    f.write("Hello World\n")
    f.write("Second line\n")

# Write multiple lines
lines = ["Line 1\n", "Line 2\n", "Line 3\n"]
with open('output.txt', 'w') as f:
    f.writelines(lines)

# Write with formatting
data = {"name": "Alice", "age": 25}
with open('output.txt', 'w') as f:
    f.write(f"Name: {data['name']}\n")
    f.write(f"Age: {data['age']}\n")

Append Mode

# Append to existing file
with open('log.txt', 'a') as f:
    f.write(f"[{datetime.now()}] New log entry\n")

# Append with data preservation
def log_message(message, filename='app.log'):
    with open(filename, 'a', encoding='utf-8') as f:
        timestamp = datetime.now().isoformat()
        f.write(f"[{timestamp}] {message}\n")

log_message("Application started")
log_message("User login successful")

File System Operations (os module)

Path Operations

Directory Operations

File Operations

Modern Path Handling (pathlib)

Path Creation and Properties

Path Operations

Error Handling in File Operations

Common File Exceptions

File Processing Patterns

Large File Processing

# Process large files efficiently
def process_large_file(filename, chunk_size=8192):
    """Process large file in chunks to avoid memory issues"""
    try:
        with open(filename, 'r') as f:
            while True:
                chunk = f.read(chunk_size)
                if not chunk:
                    break
                
                # Process chunk
                process_chunk(chunk)
                
    except Exception as e:
        print(f"Error processing large file: {e}")

def process_chunk(chunk):
    # Your processing logic here
    pass

# Line-by-line processing for text files
def process_text_file_lines(filename):
    """Efficiently process text file line by line"""
    try:
        with open(filename, 'r') as f:
            for line_number, line in enumerate(f, 1):
                # Process each line
                processed_line = line.strip().upper()
                print(f"Line {line_number}: {processed_line}")
    except Exception as e:
        print(f"Error processing file lines: {e}")

File Backup and Versioning

import shutil
from datetime import datetime

def create_backup(filename):
    """Create timestamped backup of file"""
    if not os.path.exists(filename):
        return None
    
    timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
    name, ext = os.path.splitext(filename)
    backup_name = f"{name}_backup_{timestamp}{ext}"
    
    try:
        shutil.copy2(filename, backup_name)
        return backup_name
    except Exception as e:
        print(f"Backup failed: {e}")
        return None

def safe_file_write(filename, content):
    """Write file with backup"""
    backup = None
    if os.path.exists(filename):
        backup = create_backup(filename)
    
    try:
        with open(filename, 'w') as f:
            f.write(content)
        print(f"File written successfully: {filename}")
        return True
    except Exception as e:
        print(f"Write failed: {e}")
        if backup:
            print(f"Backup available: {backup}")
        return False

Best Practices

• Always use context managers: Use with statement for automatic file closing
• Handle exceptions appropriately: Anticipate and handle file-related errors
• Choose correct file modes: Understand the differences between text and binary modes
• Use pathlib for path operations: More modern and cross-platform than os.path
• Process large files efficiently: Read in chunks to avoid memory issues
• Validate file paths: Check existence and permissions before operations
• Use appropriate encodings: Specify encoding explicitly for text files
• Close files properly: Even with context managers, be aware of resource management
• Consider atomic operations: Use temporary files for critical data operations