📁 Python File Operations - Cheat Sheet

🎯 Quick Reference

Essential Python file operations for reading, writing, searching, and manipulating files. Perfect for debugging, data processing, and automation tasks.

📖 Reading Files

Basic File Reading

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

# Read line by line
with open('filename.txt', 'r') as f:
    for line in f:
        print(line.strip())

# Read all lines into a list
with open('filename.txt', 'r') as f:
    lines = f.readlines()

# Read with error handling
try:
    with open('filename.txt', 'r') as f:
        content = f.read()
except FileNotFoundError:
    print("File not found!")
except PermissionError:
    print("Permission denied!")

Reading Specific Parts

# Read first N lines
with open('filename.txt', 'r') as f:
    first_lines = [f.readline() for _ in range(5)]

# Read specific line number
def read_line(filename, line_number):
    with open(filename, 'r') as f:
        for i, line in enumerate(f, 1):
            if i == line_number:
                return line.strip()
    return None

# Read file backwards (last lines first)
with open('filename.txt', 'r') as f:
    lines = f.readlines()
    for line in reversed(lines):
        print(line.strip())

# Read with different encoding
with open('filename.txt', 'r', encoding='utf-8') as f:
    content = f.read()

✏️ Writing Files

Basic File Writing

# Write (overwrite) file
with open('filename.txt', 'w') as f:
    f.write("Hello World\n")

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

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

# Write with formatting
data = {"name": "John", "age": 30}
with open('data.txt', 'w') as f:
    f.write(f"Name: {data['name']}\n")
    f.write(f"Age: {data['age']}\n")

Safe Writing with Backups

import shutil
import os

def safe_write(filename, content):
    # Create backup
    if os.path.exists(filename):
        shutil.copy(filename, f"{filename}.backup")
    
    try:
        with open(filename, 'w') as f:
            f.write(content)
        print(f"✅ Successfully wrote {filename}")
    except Exception as e:
        # Restore backup if write failed
        if os.path.exists(f"{filename}.backup"):
            shutil.copy(f"{filename}.backup", filename)
        print(f"❌ Write failed: {e}")

# Create file with timestamp
from datetime import datetime
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
filename = f"data_{timestamp}.txt"

🔍 Searching and Finding

Search for Text in Files

# Find lines containing specific text
def find_in_file(filename, search_text):
    matches = []
    with open(filename, 'r') as f:
        for line_num, line in enumerate(f, 1):
            if search_text in line:
                matches.append((line_num, line.strip()))
    return matches

# Usage
matches = find_in_file('ship_worker.py', 'def ')
for line_num, line in matches:
    print(f"Line {line_num}: {line}")

# Case-insensitive search
def find_case_insensitive(filename, search_text):
    search_text = search_text.lower()
    matches = []
    with open(filename, 'r') as f:
        for line_num, line in enumerate(f, 1):
            if search_text in line.lower():
                matches.append((line_num, line.strip()))
    return matches

# Find using regex
import re

def find_regex(filename, pattern):
    matches = []
    with open(filename, 'r') as f:
        for line_num, line in enumerate(f, 1):
            if re.search(pattern, line):
                matches.append((line_num, line.strip()))
    return matches

# Find function definitions
matches = find_regex('ship_worker.py', r'^def\s+\w+\(')

🔄 Find and Replace

Simple Replace

# Replace text in file
def replace_in_file(filename, old_text, new_text):
    with open(filename, 'r') as f:
        content = f.read()
    
    # Replace text
    new_content = content.replace(old_text, new_text)
    
    with open(filename, 'w') as f:
        f.write(new_content)
    
    print(f"Replaced '{old_text}' with '{new_text}'")

# Replace with backup
def safe_replace(filename, old_text, new_text):
    # Create backup
    shutil.copy(filename, f"{filename}.backup")
    
    try:
        replace_in_file(filename, old_text, new_text)
    except Exception as e:
        # Restore backup on error
        shutil.copy(f"{filename}.backup", filename)
        print(f"Error: {e}. Restored from backup.")

Advanced Replace Operations

# Replace only on specific lines
def replace_on_lines(filename, old_text, new_text, line_numbers):
    with open(filename, 'r') as f:
        lines = f.readlines()
    
    for line_num in line_numbers:
        if 1 <= line_num <= len(lines):
            lines[line_num - 1] = lines[line_num - 1].replace(old_text, new_text)
    
    with open(filename, 'w') as f:
        f.writelines(lines)

# Replace using regex
import re

def regex_replace(filename, pattern, replacement):
    with open(filename, 'r') as f:
        content = f.read()
    
    new_content = re.sub(pattern, replacement, content)
    
    with open(filename, 'w') as f:
        f.write(new_content)

# Replace tabs with spaces (like we did!)
def tabs_to_spaces(filename, spaces=4):
    with open(filename, 'r') as f:
        content = f.read()
    
    new_content = content.replace('\t', ' ' * spaces)
    
    with open(filename, 'w') as f:
        f.write(new_content)

📏 Line Operations

Working with Specific Lines

# Get specific line ranges
def get_lines(filename, start_line, end_line):
    with open(filename, 'r') as f:
        lines = f.readlines()
    
    # Python uses 0-based indexing
    return lines[start_line-1:end_line]

# Insert line at specific position
def insert_line(filename, line_number, new_line):
    with open(filename, 'r') as f:
        lines = f.readlines()
    
    # Insert new line
    lines.insert(line_number - 1, new_line + '\n')
    
    with open(filename, 'w') as f:
        f.writelines(lines)

# Delete specific lines
def delete_lines(filename, line_numbers):
    with open(filename, 'r') as f:
        lines = f.readlines()
    
    # Sort in reverse to delete from end first
    for line_num in sorted(line_numbers, reverse=True):
        if 1 <= line_num <= len(lines):
            del lines[line_num - 1]
    
    with open(filename, 'w') as f:
        f.writelines(lines)

# Count lines
def count_lines(filename):
    with open(filename, 'r') as f:
        return sum(1 for line in f)

🧹 File Cleanup and Processing

Text Cleaning

# Remove empty lines
def remove_empty_lines(filename):
    with open(filename, 'r') as f:
        lines = f.readlines()
    
    # Keep only non-empty lines
    non_empty = [line for line in lines if line.strip()]
    
    with open(filename, 'w') as f:
        f.writelines(non_empty)

# Remove trailing whitespace
def remove_trailing_whitespace(filename):
    with open(filename, 'r') as f:
        lines = f.readlines()
    
    # Strip trailing whitespace but keep newlines
    cleaned = [line.rstrip() + '\n' for line in lines]
    
    with open(filename, 'w') as f:
        f.writelines(cleaned)

# Sort lines alphabetically
def sort_file_lines(filename):
    with open(filename, 'r') as f:
        lines = f.readlines()
    
    # Sort lines (strip newlines for sorting, add back)
    sorted_lines = sorted(line.strip() for line in lines)
    
    with open(filename, 'w') as f:
        f.write('\n'.join(sorted_lines) + '\n')

File Comparison

# Compare two files
def compare_files(file1, file2):
    with open(file1, 'r') as f1, open(file2, 'r') as f2:
        content1 = f1.read()
        content2 = f2.read()
    
    if content1 == content2:
        print("✅ Files are identical")
        return True
    else:
        print("❌ Files are different")
        return False

# Find differences line by line
def find_differences(file1, file2):
    with open(file1, 'r') as f1, open(file2, 'r') as f2:
        lines1 = f1.readlines()
        lines2 = f2.readlines()
    
    differences = []
    max_lines = max(len(lines1), len(lines2))
    
    for i in range(max_lines):
        line1 = lines1[i] if i < len(lines1) else ""
        line2 = lines2[i] if i < len(lines2) else ""
        
        if line1 != line2:
            differences.append((i+1, line1.strip(), line2.strip()))
    
    return differences

🔧 Syntax and Compilation

Python File Validation

# Check Python syntax
import py_compile
import sys

def check_syntax(filename):
    try:
        py_compile.compile(filename, doraise=True)
        print(f"✅ {filename} syntax is valid")
        return True
    except py_compile.PyCompileError as e:
        print(f"❌ Syntax error in {filename}:")
        print(e)
        return False

# Check multiple Python files
import os

def check_all_python_files(directory='.'):
    python_files = [f for f in os.listdir(directory) if f.endswith('.py')]
    
    for file in python_files:
        print(f"Checking {file}...")
        check_syntax(file)

# Find Python imports
def find_imports(filename):
    imports = []
    with open(filename, 'r') as f:
        for line_num, line in enumerate(f, 1):
            line = line.strip()
            if line.startswith('import ') or line.startswith('from '):
                imports.append((line_num, line))
    return imports

📊 File Statistics and Analysis

File Analysis Tools

# Get file statistics
import os
from collections import Counter

def file_stats(filename):
    with open(filename, 'r') as f:
        content = f.read()
        lines = content.split('\n')
    
    stats = {
        'file_size': os.path.getsize(filename),
        'total_lines': len(lines),
        'non_empty_lines': len([line for line in lines if line.strip()]),
        'total_characters': len(content),
        'total_words': len(content.split()),
    }
    
    return stats

# Count word frequency
def word_frequency(filename):
    with open(filename, 'r') as f:
        content = f.read().lower()
    
    # Remove punctuation and split
    import string
    translator = str.maketrans('', '', string.punctuation)
    words = content.translate(translator).split()
    
    return Counter(words)

# Find longest lines
def find_longest_lines(filename, top_n=5):
    with open(filename, 'r') as f:
        lines = [(len(line), line_num, line.strip()) 
                for line_num, line in enumerate(f, 1)]
    
    # Sort by length, descending
    longest = sorted(lines, reverse=True)[:top_n]
    
    for length, line_num, content in longest:
        print(f"Line {line_num} ({length} chars): {content[:50]}...")

🛠️ Practical Examples

Log File Processing

# Extract errors from log file
def extract_errors(log_file):
    errors = []
    with open(log_file, 'r') as f:
        for line_num, line in enumerate(f, 1):
            if 'ERROR' in line or 'CRITICAL' in line:
                errors.append((line_num, line.strip()))
    return errors

# Find recent log entries
from datetime import datetime, timedelta

def find_recent_logs(log_file, hours=24):
    recent_entries = []
    cutoff = datetime.now() - timedelta(hours=hours)
    
    with open(log_file, 'r') as f:
        for line in f:
            # Assuming log format: YYYY-MM-DD HH:MM:SS message
            try:
                timestamp_str = line[:19]
                timestamp = datetime.strptime(timestamp_str, '%Y-%m-%d %H:%M:%S')
                if timestamp > cutoff:
                    recent_entries.append(line.strip())
            except:
                continue
    
    return recent_entries

Configuration File Management

# Read .env file
def read_env_file(filename='.env'):
    config = {}
    try:
        with open(filename, 'r') as f:
            for line in f:
                line = line.strip()
                if line and not line.startswith('#'):
                    key, value = line.split('=', 1)
                    config[key] = value
    except FileNotFoundError:
        print(f"Config file {filename} not found")
    return config

# Update .env file
def update_env_file(filename, key, value):
    lines = []
    key_found = False
    
    try:
        with open(filename, 'r') as f:
            lines = f.readlines()
    except FileNotFoundError:
        pass
    
    # Update existing key or add new one
    with open(filename, 'w') as f:
        for line in lines:
            if line.startswith(f"{key}="):
                f.write(f"{key}={value}\n")
                key_found = True
            else:
                f.write(line)
        
        # Add new key if not found
        if not key_found:
            f.write(f"{key}={value}\n")

⚡ Quick Commands

One-Liners for Common Tasks

# Count lines in file
lines = sum(1 for line in open('filename.txt'))

# Get file size
import os; size = os.path.getsize('filename.txt')

# Read file into list
lines = [line.strip() for line in open('filename.txt')]

# Write list to file
open('output.txt', 'w').write('\n'.join(my_list))

# Check if file exists
import os; exists = os.path.exists('filename.txt')

# Get file extension
import os; ext = os.path.splitext('filename.txt')[1]

# Read JSON file
import json; data = json.load(open('data.json'))

# Write JSON file
import json; json.dump(data, open('data.json', 'w'), indent=2)

🚨 Best Practices

Important Tips

Always use with open() - automatically closes files
Handle exceptions - files might not exist or be readable
Create backups before modifying important files
Use appropriate encoding - specify encoding='utf-8' when needed
Test with small files first before processing large datasets
Check file permissions before writing
Use absolute paths for critical files
Validate input before processing

🎯 Common Use Cases Summary

Debugging: Search for errors, extract log entries, find function definitions
Configuration: Read/write .env files, update settings
Code Maintenance: Replace text, fix indentation, remove unused code
Data Processing: Clean files, extract data, format output
Validation: Check syntax, compare files, verify formats