Create a file size analyzer for large folders

Here is a Python script that acts as a file size analyzer for large folders. It recursively scans all files in a given directory, calculates their sizes, and provides a summarized output sorted by size.

python
CopyEdit
import os
from pathlib import Path
from collections import defaultdict

def human_readable_size(size_bytes):
    """Convert bytes to human-readable format"""
    for unit in ['B', 'KB', 'MB', 'GB', 'TB']:
        if size_bytes < 1024:
            return f"{size_bytes:.2f} {unit}"
        size_bytes /= 1024
    return f"{size_bytes:.2f} PB"

def analyze_folder_size(directory):
    """Analyzes folder and prints size summary"""
    folder = Path(directory)
    if not folder.is_dir():
        print(f"Error: {directory} is not a valid directory.")
        return

    print(f"nAnalyzing folder: {directory}n")

    total_size = 0
    file_sizes = []
    folder_sizes = defaultdict(int)

    for dirpath, _, filenames in os.walk(folder):
        for filename in filenames:
            file_path = Path(dirpath) / filename
            try:
                file_size = file_path.stat().st_size
                total_size += file_size
                file_sizes.append((str(file_path), file_size))

                parent_folder = str(Path(dirpath))
                folder_sizes[parent_folder] += file_size
            except (PermissionError, FileNotFoundError):
                print(f"Skipped: {file_path}")
                continue

    # Sort files by size descending
    file_sizes.sort(key=lambda x: x[1], reverse=True)
    folder_sizes_sorted = sorted(folder_sizes.items(), key=lambda x: x[1], reverse=True)

    print("Top 10 Largest Files:n")
    for path, size in file_sizes[:10]:
        print(f"{human_readable_size(size):>12}  {path}")

    print("nTop 10 Largest Folders:n")
    for folder, size in folder_sizes_sorted[:10]:
        print(f"{human_readable_size(size):>12}  {folder}")

    print(f"nTotal size of '{directory}': {human_readable_size(total_size)}")

if __name__ == "__main__":
    import argparse

    parser = argparse.ArgumentParser(description="Analyze file sizes in a folder.")
    parser.add_argument("path", help="Path to the folder to analyze.")
    args = parser.parse_args()

    analyze_folder_size(args.path)

Features:

• Recursively traverses all files and subfolders.

• Calculates size of each file and aggregates sizes per folder.

• Shows top 10 largest files and folders.

• Displays total size in a human-readable format.

• Handles permissions and missing files gracefully.

Usage:

Save the script as folder_size_analyzer.py and run from the command line:

bash
CopyEdit
python folder_size_analyzer.py /path/to/your/folder

Let me know if you want a GUI version or CSV export functionality.