Automate File Conversion With Python: PDF, Images, Documents

Manual file conversion doesn't scale. Here's how to automate every common conversion type in Python with the best library for each job.

PDF to Images (PyMuPDF)

import fitz  # pip install pymupdf
import os

def pdf_to_images(pdf_path, output_dir, dpi=150):
    os.makedirs(output_dir, exist_ok=True)
    doc = fitz.open(pdf_path)
    paths = []
    for i, page in enumerate(doc):
        pix = page.get_pixmap(dpi=dpi)
        path = os.path.join(output_dir, f'page_{i+1:03d}.png')
        pix.save(path)
        paths.append(path)
    return paths

Images to WebP (Pillow)

from PIL import Image
import glob

def batch_to_webp(input_glob, quality=85):
    for path in glob.glob(input_glob):
        with Image.open(path) as img:
            out = path.rsplit('.', 1)[0] + '.webp'
            img.save(out, 'WEBP', quality=quality)
            print(f'{path} → {out}')

Word to PDF (LibreOffice)

import subprocess, glob, os

def batch_docx_to_pdf(input_dir, output_dir):
    os.makedirs(output_dir, exist_ok=True)
    files = glob.glob(os.path.join(input_dir, '*.docx'))
    subprocess.run([
        'libreoffice', '--headless', '--convert-to', 'pdf',
        '--outdir', output_dir, *files
    ], check=True)
    print(f'Converted {len(files)} files')

JSON to CSV (pandas)

import pandas as pd, json, glob

def batch_json_to_csv(input_glob):
    for path in glob.glob(input_glob):
        with open(path) as f:
            data = json.load(f)
        out = path.replace('.json', '.csv')
        pd.json_normalize(data).to_csv(out, index=False)
        print(f'{path} → {out}')

CSV to Excel (openpyxl)

import pandas as pd

def csv_to_excel(csv_path, excel_path):
    pd.read_csv(csv_path).to_excel(excel_path, index=False, engine='openpyxl')

Watcher Pattern (Convert on File Drop)

from watchdog.observers import Observer
from watchdog.events import FileSystemEventHandler

class ConvertHandler(FileSystemEventHandler):
    def on_created(self, event):
        if event.src_path.endswith('.docx'):
            batch_docx_to_pdf(os.path.dirname(event.src_path), 'output/')

observer = Observer()
observer.schedule(ConvertHandler(), 'watch_folder/', recursive=False)
observer.start()

One-off conversions: free online file converter →