How to Automate File Management with Python: Complete Guide 2026

💡 Real example: A marketing team in Vancouver received 200+ raw image files every week from designers across three time zones. A Python script now automatically sorts them by project, renames them with the correct naming convention, and archives the previous week's files — saving 3 hours of manual work every Monday.

# Built-in modules — nothing to install
import os
import shutil
from pathlib import Path
import datetime
import hashlib

# For folder watching — one install needed
pip install watchdog

"""
File Organizer — sorts files in a folder by type
Run: python organize_by_type.py
"""
import shutil
from pathlib import Path

# Map file extensions → destination folder names
FILE_TYPES = {
    'Images':      ['.jpg', '.jpeg', '.png', '.gif', '.webp', '.svg', '.bmp'],
    'Documents':   ['.pdf', '.doc', '.docx', '.txt', '.odt', '.rtf'],
    'Spreadsheets':['.xls', '.xlsx', '.csv', '.ods'],
    'Videos':      ['.mp4', '.mov', '.avi', '.mkv', '.webm'],
    'Audio':        ['.mp3', '.wav', '.flac', '.aac', '.ogg'],
    'Archives':    ['.zip', '.tar', '.gz', '.rar', '.7z'],
    'Code':         ['.py', '.js', '.html', '.css', '.json', '.sql'],
}

def get_category(extension: str) -> str:
    """Return the folder name for a given file extension."""
    ext = extension.lower()
    for category, extensions in FILE_TYPES.items():
        if ext in extensions:
            return category
    return 'Other'

def organize_folder(folder_path: str) -> None:
    source = Path(folder_path)
    moved = 0

    for file in source.iterdir():
        if file.is_dir():
            continue  # skip subfolders

        category = get_category(file.suffix)
        destination_folder = source / category
        destination_folder.mkdir(exist_ok=True)

        shutil.move(str(file), str(destination_folder / file.name))
        print(f"Moved: {file.name} → {category}/")
        moved += 1

    print(f"\n✅ Done. Moved {moved} files.")

# Change this path to your target folder
organize_folder("/Users/yourname/Downloads")

✅ Tip: Before running on real files, add print(f"Would move: {file.name} → {category}/") instead of shutil.move() to do a dry run and verify the logic first.

"""
Sort files into Year/Month folders based on last-modified date.
Example result: Photos/2025/03/photo_001.jpg
"""
import shutil
import datetime
from pathlib import Path

def sort_by_date(source_folder: str) -> None:
    source = Path(source_folder)
    moved = 0

    for file in source.iterdir():
        if file.is_dir():
            continue

        # Get last modified time
        mod_time = datetime.datetime.fromtimestamp(file.stat().st_mtime)
        year  = str(mod_time.year)
        month = mod_time.strftime("%m-%B")  # e.g. "03-March"

        dest_folder = source / year / month
        dest_folder.mkdir(parents=True, exist_ok=True)

        shutil.move(str(file), str(dest_folder / file.name))
        print(f"Moved: {file.name} → {year}/{month}/")
        moved += 1

    print(f"\n✅ Done. Sorted {moved} files by date.")

sort_by_date("/Users/yourname/Photos/Unsorted")

from pathlib import Path

folder = Path("/Users/yourname/Exports")
files  = sorted(folder.glob("*.jpg"))

for index, file in enumerate(files, start=1):
    new_name = f"photo_{index:04d}{file.suffix}"  # photo_0001.jpg
    file.rename(folder / new_name)
    print(f"Renamed: {file.name} → {new_name}")

import datetime
from pathlib import Path

folder = Path("/Users/yourname/Reports")
today  = datetime.date.today().strftime("%Y-%m-%d")

for file in folder.glob("*.pdf"):
    new_name = f"{today}_{file.name}"  # 2026-03-14_report.pdf
    file.rename(folder / new_name)

from pathlib import Path

folder  = Path("/Users/yourname/Invoices")
old_text = "draft"
new_text = "final"

for file in folder.iterdir():
    if old_text in file.stem:
        new_name = file.name.replace(old_text, new_text)
        file.rename(folder / new_name)
        print(f"Renamed: {file.name} → {new_name}")

import shutil
from pathlib import Path

source_folder = Path("/Users/yourname/Downloads")
backup_folder = Path("/Users/yourname/Backup")
backup_folder.mkdir(exist_ok=True)

# Copy a single file
shutil.copy(
    source_folder / "report.pdf",
    backup_folder / "report.pdf"
)

# Move a single file
shutil.move(
    str(source_folder / "old_data.csv"),
    str(backup_folder / "old_data.csv")
)

# Copy an entire folder tree
shutil.copytree(
    str(source_folder / "project_files"),
    str(backup_folder / "project_files_backup")
)

# Create a ZIP archive of a folder
shutil.make_archive(
    base_name=str(backup_folder / "project_archive"),
    format='zip',
    root_dir=str(source_folder / "project_files")
)
print("✅ Backup complete.")

"""
Find duplicate files in a folder by comparing MD5 hashes.
Prints all duplicate groups — does NOT delete anything automatically.
"""
import hashlib
from pathlib import Path
from collections import defaultdict

def get_md5(filepath: Path) -> str:
    hash_md5 = hashlib.md5()
    with open(filepath, "rb") as f:
        for chunk in iter(lambda: f.read(8192), b""):
            hash_md5.update(chunk)
    return hash_md5.hexdigest()

def find_duplicates(folder_path: str) -> None:
    folder = Path(folder_path)
    hashes = defaultdict(list)

    print("Scanning files...")
    for file in folder.rglob("*"):  # rglob scans subfolders too
        if file.is_file():
            file_hash = get_md5(file)
            hashes[file_hash].append(file)

    duplicates_found = 0
    for file_hash, files in hashes.items():
        if len(files) > 1:
            duplicates_found += 1
            print(f"\n🔁 Duplicate group {duplicates_found}:")
            for f in files:
                print(f"   {f}")
            # To delete duplicates, keep files[0] and remove the rest:
            # for f in files[1:]:
            #     f.unlink()

    if duplicates_found == 0:
        print("✅ No duplicates found.")
    else:
        print(f"\nFound {duplicates_found} duplicate group(s). Review above before deleting.")

find_duplicates("/Users/yourname/Downloads")

⚠️ Safety note: The deletion code is commented out intentionally. Always review the output first. Only uncomment the delete lines once you have confirmed the duplicates are correct.

# pip install watchdog
import time
import shutil
from pathlib import Path
from watchdog.observers import Observer
from watchdog.events import FileSystemEventHandler

WATCH_FOLDER  = Path("/Users/yourname/Downloads")
OUTPUT_FOLDER = Path("/Users/yourname/Sorted")

FILE_TYPES = {
    '.pdf':  'Documents',
    '.jpg':  'Images',
    '.png':  'Images',
    '.xlsx': 'Spreadsheets',
    '.csv':  'Spreadsheets',
}

class FileHandler(FileSystemEventHandler):
    def on_created(self, event):
        if event.is_directory:
            return
        file = Path(event.src_path)
        category = FILE_TYPES.get(file.suffix.lower(), 'Other')
        dest = OUTPUT_FOLDER / category
        dest.mkdir(parents=True, exist_ok=True)
        shutil.move(str(file), str(dest / file.name))
        print(f"📂 Auto-sorted: {file.name} → {category}/")

observer = Observer()
observer.schedule(FileHandler(), str(WATCH_FOLDER), recursive=False)
observer.start()
print(f"👁️  Watching: {WATCH_FOLDER}  (Ctrl+C to stop)")

try:
    while True:
        time.sleep(1)
except KeyboardInterrupt:
    observer.stop()
observer.join()

Tutorial

How to Automate Excel Tasks with Python

Read, write, format, and auto-generate Excel reports using openpyxl, pandas, and xlwings.

Tutorial

Selenium Python Tutorial 2026

Master web automation with Selenium and Python with real code examples.

Guide

Python Automation Guide 2026

Complete beginner's guide to Python automation — from basics to real projects.