test_pdf_preview.py

#!/usr/bin/env python3
"""
Test PDF preview functionality
"""
import os
import io
from pathlib import Path
from pdf2image import convert_from_path
from PIL import Image

def test_pdf_preview():
    """Test converting a PDF to an image preview"""
    # Get the first PDF file from the input directory
    input_dir = Path(__file__).parent / "input"
    pdf_files = list(input_dir.glob("*.pdf"))
    
    if not pdf_files:
        print("No PDF files found in the input directory")
        return
    
    pdf_path = pdf_files[0]
    print(f"Testing PDF preview with file: {pdf_path}")
    
    try:
        # Convert first page of PDF to image
        images = convert_from_path(pdf_path, first_page=1, last_page=1)
        
        if not images:
            print("No images extracted from PDF")
            return
        
        # Save the preview image
        first_page = images[0]
        output_dir = Path(__file__).parent / "output"
        output_dir.mkdir(exist_ok=True)
        output_path = output_dir / f"{pdf_path.stem}_preview.jpg"
        
        first_page.save(output_path, format='JPEG')
        print(f"PDF preview saved to: {output_path}")
        
        # Demonstrate converting to bytes for Streamlit
        img_bytes = io.BytesIO()
        first_page.save(img_bytes, format='JPEG')
        img_bytes.seek(0)
        print(f"Successfully converted PDF to image bytes (size: {len(img_bytes.getvalue())} bytes)")
        
    except Exception as e:
        print(f"Error converting PDF to image: {str(e)}")

if __name__ == "__main__":
    test_pdf_preview()