convert_full_pdf.py

import fitz  # PyMuPDF
import os
from PIL import Image

def convert_full_pdf_to_images(pdf_path, output_dir):
    if not os.path.exists(output_dir):
        os.makedirs(output_dir)
    
    doc = fitz.open(pdf_path)
    base_name = os.path.basename(pdf_path).split('.')[0]
    image_paths = []
    
    print(f"Converting all {len(doc)} pages of {pdf_path}...")
    for i in range(len(doc)):
        page = doc.load_page(i)
        pix = page.get_pixmap(matrix=fitz.Matrix(2, 2)) # Zoom for better OCR
        output_file = os.path.join(output_dir, f"{base_name}_page_{i+1}.png")
        # Convert to PIL Image
        img = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
        img.save(output_file)
        image_paths.append(output_file)
        print(f"Converted page {i+1}/{len(doc)}")
    
    return image_paths

if __name__ == "__main__":
    pdf_file = "doc_for_testing/pdf12_un.pdf"
    output_dir = "doc_images_full"
    if os.path.exists(pdf_file):
        convert_full_pdf_to_images(pdf_file, output_dir)
    else:
        print(f"File {pdf_file} not found.")