21 – Real-World Python Projects – File Organizer (Advanced)

🎯 Project Objective

To create an advanced File Organizer that automatically scans folders, classifies files by type, renames duplicates, logs actions, and can run on a schedule for continuous cleanup.

🧩 Skills You’ll Learn

File handling with os and shutil
Pattern matching using fnmatch and re
Logging and reporting
Exception handling and automation
Scheduling cleanups with schedule
Building modular, maintainable code

⚙️ Technology Stack

Library	Purpose
`os`, `shutil`	File and directory operations
`re`, `fnmatch`	Pattern matching for file extensions
`time`, `datetime`	Scheduling and timestamps
`logging`	Tracking all actions performed
`pandas` (optional)	Generating CSV reports
`schedule` (optional)	Automate periodic cleanups

🔧 Auto-Install Dependencies

import subprocess, sys

def install(package):
    try:
        __import__(package)
    except ImportError:
        subprocess.check_call([sys.executable, "-m", "pip", "install", package])

for pkg in ["pandas", "schedule"]:
    install(pkg)

📂 Step 1 — Directory Setup

Create categorized folders automatically (if not present):

import os

TARGET_DIR = "C:/Users/YourName/Downloads"
CATEGORIES = {
    "Images": [".jpg", ".jpeg", ".png", ".gif", ".bmp"],
    "Documents": [".pdf", ".docx", ".txt", ".xlsx", ".pptx"],
    "Videos": [".mp4", ".mov", ".avi", ".mkv"],
    "Music": [".mp3", ".wav", ".aac"],
    "Archives": [".zip", ".rar", ".tar"],
    "Programs": [".exe", ".msi"],
    "Scripts": [".py", ".js", ".html", ".css"]
}

for folder in CATEGORIES.keys():
    path = os.path.join(TARGET_DIR, folder)
    if not os.path.exists(path):
        os.makedirs(path)

✅ Creates subfolders like “Images”, “Documents”, etc.

⚙️ Step 2 — Smart File Sorting Function

import shutil, re
from datetime import datetime

def organize_files():
    log_entries = []
    for file_name in os.listdir(TARGET_DIR):
        file_path = os.path.join(TARGET_DIR, file_name)
        if os.path.isfile(file_path):
            ext = os.path.splitext(file_name)[1].lower()
            moved = False

            for category, extensions in CATEGORIES.items():
                if ext in extensions:
                    dest = os.path.join(TARGET_DIR, category)
                    new_name = rename_if_duplicate(dest, file_name)
                    shutil.move(file_path, os.path.join(dest, new_name))
                    moved = True
                    log_entries.append((file_name, category, datetime.now()))
                    break

            if not moved:
                log_entries.append((file_name, "Uncategorized", datetime.now()))
    
    return log_entries

🧩 Step 3 — Handle Duplicate File Names

def rename_if_duplicate(dest, file_name):
    base, ext = os.path.splitext(file_name)
    counter = 1
    new_name = file_name

    while os.path.exists(os.path.join(dest, new_name)):
        new_name = f"{base}_{counter}{ext}"
        counter += 1
    return new_name

✅ Automatically renames duplicates like photo_1.jpg, photo_2.jpg, etc.

🧾 Step 4 — Logging Actions

import logging

logging.basicConfig(
    filename="file_organizer.log",
    level=logging.INFO,
    format="%(asctime)s - %(levelname)s - %(message)s"
)

def log_activity(entries):
    for file, category, timestamp in entries:
        logging.info(f"Moved: {file} → {category}")

📊 Step 5 — Generate CSV Report

import pandas as pd

def export_report(entries):
    df = pd.DataFrame(entries, columns=["File", "Category", "Timestamp"])
    df.to_csv("organizer_report.csv", index=False)
    print("✅ Report saved as 'organizer_report.csv'")

🔁 Step 6 — Automate Organization Periodically

import schedule, time

def job():
    print("Running file organizer...")
    entries = organize_files()
    log_activity(entries)
    export_report(entries)

# Run every 10 minutes
schedule.every(10).minutes.do(job)

while True:
    schedule.run_pending()
    time.sleep(1)

✅ Your computer now auto-organizes files every 10 minutes.

🧱 Full Combined Code (Advanced Organizer)

import os, shutil, logging, pandas as pd, schedule, time
from datetime import datetime

TARGET_DIR = "C:/Users/YourName/Downloads"
CATEGORIES = {
    "Images": [".jpg", ".jpeg", ".png", ".gif", ".bmp"],
    "Documents": [".pdf", ".docx", ".txt", ".xlsx", ".pptx"],
    "Videos": [".mp4", ".mov", ".avi", ".mkv"],
    "Music": [".mp3", ".wav", ".aac"],
    "Archives": [".zip", ".rar", ".tar"],
    "Programs": [".exe", ".msi"],
    "Scripts": [".py", ".js", ".html", ".css"]
}

for folder in CATEGORIES.keys():
    os.makedirs(os.path.join(TARGET_DIR, folder), exist_ok=True)

logging.basicConfig(filename="file_organizer.log", level=logging.INFO, format="%(asctime)s - %(message)s")

def rename_if_duplicate(dest, file_name):
    base, ext = os.path.splitext(file_name)
    counter = 1
    new_name = file_name
    while os.path.exists(os.path.join(dest, new_name)):
        new_name = f"{base}_{counter}{ext}"
        counter += 1
    return new_name

def organize_files():
    log_entries = []
    for file_name in os.listdir(TARGET_DIR):
        file_path = os.path.join(TARGET_DIR, file_name)
        if os.path.isfile(file_path):
            ext = os.path.splitext(file_name)[1].lower()
            moved = False
            for category, extensions in CATEGORIES.items():
                if ext in extensions:
                    dest = os.path.join(TARGET_DIR, category)
                    new_name = rename_if_duplicate(dest, file_name)
                    shutil.move(file_path, os.path.join(dest, new_name))
                    log_entries.append((file_name, category, datetime.now()))
                    moved = True
                    break
            if not moved:
                log_entries.append((file_name, "Uncategorized", datetime.now()))
    return log_entries

def log_activity(entries):
    for file, category, timestamp in entries:
        logging.info(f"Moved {file} → {category}")

def export_report(entries):
    df = pd.DataFrame(entries, columns=["File", "Category", "Timestamp"])
    df.to_csv("organizer_report.csv", index=False)

def job():
    entries = organize_files()
    log_activity(entries)
    export_report(entries)
    print(f"✅ Organized at {datetime.now()}")

schedule.every(10).minutes.do(job)

while True:
    schedule.run_pending()
    time.sleep(1)

💡 Optional Enhancements

Feature	Description
🗑️ Trash Manager	Move deleted files to a “Recycle Bin”
🔍 Duplicate Detector	Use file hashes to detect duplicates
🧠 AI File Sorting	Use NLP to auto-categorize based on filenames
🧰 GUI Interface	Add a Tkinter dashboard for manual control
☁️ Cloud Sync	Auto-sync organized files to Google Drive / Dropbox

🧠 Learning Outcomes

✅ File handling and directory traversal
✅ Automated file management
✅ Logging and reporting
✅ Scheduling with Python
✅ Writing professional, modular code