Let's be honest: most of the repetitive file operations we do every day don't require our attention. Renaming hundreds of files, cleaning messy CSVs, resizing images one by one — these tasks are necessary but mind-numbing.
I've been collecting and writing Python automation scripts for the past few years, and I want to share five that have saved me the most time. You can copy these directly, adapt them to your workflow, and start automating today.
Before We Start
You'll need Python 3.8+ installed. Each script below is a single file — no complex setup required. Just save it, install any dependencies, and run.
pip install pillow pandas # for image and CSV scripts
1. Smart File Organizer
This one is my most-used script. Your Downloads folder is probably a mess — mine definitely was. This script sorts files into folders by type or date.
#!/usr/bin/env python3
import os
import shutil
import argparse
from collections import defaultdict
FILE_CATEGORIES = {
'Images': ['.jpg', '.jpeg', '.png', '.gif', '.webp', '.svg'],
'Documents': ['.pdf', '.docx', '.txt', '.md', '.xlsx', '.pptx'],
'Audio': ['.mp3', '.wav', '.flac', '.aac', '.m4a'],
'Video': ['.mp4', '.mov', '.avi', '.mkv', '.webm'],
'Archives': ['.zip', '.tar', '.gz', '.rar', '.7z'],
'Code': ['.py', '.js', '.ts', '.html', '.css', '.json', '.yaml'],
}
def organize_by_type(source_dir, target_dir=None, dry_run=False):
if not target_dir:
target_dir = source_dir
for filename in os.listdir(source_dir):
filepath = os.path.join(source_dir, filename)
if os.path.isfile(filepath):
ext = os.path.splitext(filename)[1].lower()
category = 'Other'
for cat, exts in FILE_CATEGORIES.items():
if ext in exts:
category = cat
break
dest = os.path.join(target_dir, category)
if dry_run:
print(f'[DRY RUN] Would move: {filename} -> {category}/')
else:
os.makedirs(dest, exist_ok=True)
shutil.move(filepath, os.path.join(dest, filename))
print(f'Moved: {filename} -> {category}/')
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Organize files by type')
parser.add_argument('directory', help='Directory to organize')
parser.add_argument('--dry-run', action='store_true', help='Preview only')
args = parser.parse_args()
organize_by_type(args.directory, dry_run=args.dry_run)
Usage:
# Preview what would happen
python file-organizer.py ~/Downloads --dry-run
# Actually organize
python file-organizer.py ~/Downloads
2. CSV Cleaner
CSV files from different sources are never consistent. Different separators, extra whitespace, missing values, duplicate rows — this script handles the common pain points.
#!/usr/bin/env python3
import csv
import sys
import argparse
def clean_csv(input_file, output_file, **options):
with open(input_file, 'r', encoding='utf-8') as f:
reader = csv.DictReader(f)
rows = list(reader)
fieldnames = reader.fieldnames
cleaned = []
seen = set()
for row in rows:
# Strip whitespace from all values
if options.get('strip'):
row = {k: v.strip() if isinstance(v, str) else v
for k, v in row.items()}
# Remove empty rows
if options.get('drop_empty'):
if all(v == '' or v is None for v in row.values()):
continue
# Remove duplicates
if options.get('drop_duplicates'):
row_key = tuple(row.values())
if row_key in seen:
continue
seen.add(row_key)
# Fill missing values
if options.get('fill'):
row = {k: (v if v != '' else options['fill'])
for k, v in row.items()}
cleaned.append(row)
with open(output_file, 'w', encoding='utf-8', newline='') as f:
writer = csv.DictWriter(f, fieldnames=fieldnames)
writer.writeheader()
writer.writerows(cleaned)
print(f'Cleaned: {len(rows)} -> {len(cleaned)} rows')
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Clean CSV files')
parser.add_argument('input', help='Input CSV file')
parser.add_argument('--output', '-o', default='cleaned.csv')
parser.add_argument('--strip', action='store_true')
parser.add_argument('--drop-duplicates', action='store_true')
parser.add_argument('--drop-empty-rows', action='store_true')
parser.add_argument('--fill', help='Fill missing values with this')
args = parser.parse_args()
clean_csv(args.input, args.output,
strip=args.strip,
drop_empty=args.drop_empty_rows,
drop_duplicates=args.drop_duplicates,
fill=args.fill)
Usage:
python csv-cleaner.py messy_data.csv --strip --drop-duplicates --output clean.csv
3. Batch Image Resizer
Need to resize 50 images for a website or social media post? Doing it manually in Photoshop is not the move.
#!/usr/bin/env python3
import os
from PIL import Image
import argparse
def resize_images(directory, max_width, output_format='webp', quality=85):
for filename in os.listdir(directory):
if not filename.lower().endswith(('.png', '.jpg', '.jpeg')):
continue
filepath = os.path.join(directory, filename)
img = Image.open(filepath)
# Calculate new height maintaining aspect ratio
ratio = max_width / img.width
new_size = (max_width, int(img.height * ratio))
img_resized = img.resize(new_size, Image.LANCZOS)
# Save in the chosen format
new_name = os.path.splitext(filename)[0] + f'.{output_format}'
output_path = os.path.join(directory, new_name)
if output_format.lower() == 'webp':
img_resized.save(output_path, 'WEBP', quality=quality)
elif output_format.lower() == 'jpg':
img_resized.save(output_path, 'JPEG', quality=quality)
else:
img_resized.save(output_path)
print(f'Resized: {filename} -> {new_name} ({new_size[0]}x{new_size[1]})')
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Batch resize images')
parser.add_argument('directory', help='Directory with images')
parser.add_argument('--max-width', type=int, default=1200)
parser.add_argument('--format', default='webp', choices=['webp', 'jpg', 'png'])
parser.add_argument('--quality', type=int, default=85)
args = parser.parse_args()
resize_images(args.directory, args.max_width, args.format, args.quality)
Usage:
python image-resizer.py ./photos --max-width 800 --format webp --quality 90
4. PDF Text Extractor
Need to pull text from multiple PDFs for analysis? This script handles it.
#!/usr/bin/env python3
import os
import json
import argparse
try:
import PyPDF2
except ImportError:
import subprocess
subprocess.check_call(['pip', 'install', 'PyPDF2'])
import PyPDF2
def extract_pdfs(directory, output_format='txt'):
results = {}
for filename in os.listdir(directory):
if not filename.lower().endswith('.pdf'):
continue
filepath = os.path.join(directory, filename)
text = []
with open(filepath, 'rb') as f:
reader = PyPDF2.PdfReader(f)
for page_num in range(len(reader.pages)):
page = reader.pages[page_num]
extracted = page.extract_text()
if extracted.strip():
text.append(f'--- Page {page_num + 1} ---\n{extracted}')
results[filename] = '\n'.join(text)
if output_format == 'json':
output = json.dumps(results, indent=2, ensure_ascii=False)
print(output)
else:
for pdf_name, content in results.items():
print(f'\n{"="*60}')
print(f'FILE: {pdf_name}')
print(f'{"="*60}')
print(content)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Extract text from PDFs')
parser.add_argument('directory', help='Directory with PDF files')
parser.add_argument('--format', choices=['txt', 'json'], default='txt')
args = parser.parse_args()
extract_pdfs(args.directory, args.format)
5. Batch File Renamer
Renaming files one by one is maybe the single most tedious task in computing. This script gives you pattern-based renaming with a dry-run mode so you never accidentally destroy your file names.
#!/usr/bin/env python3
import os
import re
import argparse
def rename_files(directory, pattern, replacement, dry_run=False):
for filename in os.listdir(directory):
filepath = os.path.join(directory, filename)
if not os.path.isfile(filepath):
continue
new_name = re.sub(pattern, replacement, filename)
if new_name == filename:
continue
new_path = os.path.join(directory, new_name)
if dry_run:
print(f'[DRY RUN] {filename} -> {new_name}')
else:
os.rename(filepath, new_path)
print(f'Renamed: {filename} -> {new_name}')
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Batch rename files')
parser.add_argument('directory', help='Target directory')
parser.add_argument('--pattern', '-p', required=True, help='Regex pattern')
parser.add_argument('--replace', '-r', required=True, help='Replacement')
parser.add_argument('--dry-run', action='store_true', help='Preview')
args = parser.parse_args()
rename_files(args.directory, args.pattern, args.replace, args.dry_run)
Usage:
# Replace spaces with underscores
python batch-renamer.py ./docs --pattern '\s+' --replace '_' --dry-run
# Remove "(1)" suffixes from duplicates
python batch-renamer.py ./downloads --pattern '\((\d+)\)' --replace ''
Putting It All Together
These scripts are intentionally simple — each one does one thing and does it well. Here are a few real workflows where I use them together:
Weekly photo processing:
# 1. Organize incoming photos
python file-organizer.py ~/CameraUploads --method date
# 2. Resize for web
python image-resizer.py ~/CameraUploads/2026-05 --max-width 1200 --format webp
# 3. Rename with consistent pattern
python batch-renamer.py ~/CameraUploads/2026-05 --pattern 'IMG_\d+' --replace 'vacation_'
Data pipeline cleanup:
# 1. Extract data from PDF reports
python pdf-extractor.py ~/Reports --format json > raw_data.json
# 2. Clean and normalize
python csv-cleaner.py raw_data.csv --strip --drop-duplicates --fill "N/A"
What's Next
If you found these useful, I've put together a bundle of 10 automation scripts with full documentation, proper error handling, and CLI interfaces for every script. It includes a web scraper, email sender, YouTube transcript downloader, text summarizer, and more — all ready to run.
Check it out here: AI Automation Scripts Bundle
The bundle also comes with a requirements.txt for one-command install and consistent logging across all scripts. Every script has a dry-run mode, so you can preview changes before making them.
Got a favorite automation script? Drop it in the comments. I'm always looking for new ideas to add to the collection.
Top comments (0)