ocr_pdf_parallel.py

#!/usr/bin/env python3
import os
import subprocess
from pathlib import Path
from concurrent.futures import ProcessPoolExecutor, as_completed
import multiprocessing

# Input and output directories
INPUT_DIR = "data"         # change to your directory of PDFs
OUTPUT_DIR = "ocr_output"

# Make sure output directory exists
Path(OUTPUT_DIR).mkdir(parents=True, exist_ok=True)

def ocr_pdf(input_path, output_path):
    try:
        subprocess.run(
            [
                "ocrmypdf",
                "-l", "ara",          # Arabic OCR
                # "--optimize", "3",    # aggressive optimization
                "--output-type", "pdfa",  # archive-friendly PDF
                # "--skip-text",        # skip OCR if text layer already exists
                str(input_path),
                str(output_path),
            ],
            check=True,
            capture_output=True,
        )
        return f"✅ OCR complete: {output_path}"
    except subprocess.CalledProcessError as e:
        return f"❌ Error processing {input_path}: {e.stderr.decode(errors='ignore')}"

def main():
    pdf_files = [
        f for f in os.listdir(INPUT_DIR) if f.lower().endswith(".pdf")
    ]
    if not pdf_files:
        print("No PDF files found.")
        return

    # Use all CPUs (or set max_workers to something smaller if needed)
    # e.g. multiprocessing.cpu_count() - 2
    max_workers = multiprocessing.cpu_count()

    with ProcessPoolExecutor(max_workers=max_workers) as executor:
        futures = []
        for filename in pdf_files:
            input_path = Path(INPUT_DIR) / filename
            output_path = Path(OUTPUT_DIR) / filename
            futures.append(executor.submit(ocr_pdf, input_path, output_path))

        for future in as_completed(futures):
            print(future.result())

if __name__ == "__main__":
    main()

ocr_pdfs.py

#! /usr/bin/env python3

import os
import subprocess
from pathlib import Path

INPUT_DIR = "data"
OUTPUT_DIR = "ocr_output"

Path(OUTPUT_DIR).mkdir(parents=True, exist_ok=True)

def ocr_pdf(input_path, output_path):
    try:
        subprocess.run(
            [
                "ocrmypdf",
                "-l", "ara",          # Arabic OCR
                "--optimize", "3",    # aggressive optimization
                "--output-type", "pdfa",  # archive-friendly PDF
                # "--skip-text",        # skip OCR if text layer already exists
                str(input_path),
                str(output_path),
            ],
            check=True
        )
        print(f"✅ OCR complete: {output_path}")
    except subprocess.CalledProcessError as e:
        print(f"❌ Error processing {input_path}: {e}")

def main():
    for filename in os.listdir(INPUT_DIR):
        if filename.lower().endswith(".pdf"):
            input_path = Path(INPUT_DIR) / filename
            output_path = Path(OUTPUT_DIR) / filename
            ocr_pdf(input_path, output_path)

if __name__ == "__main__":
    main()