pdf_to_image.py

"""
PDF to Image Conversion using PyMuPDF (fitz)
Converts all pages of a PDF to PIL Images.
"""

import fitz  # PyMuPDF
from PIL import Image
from pathlib import Path
from typing import List, Tuple
import io


def pdf_to_images(pdf_path: str, dpi: int = 150) -> List[Image.Image]:
    """
    Convert all pages of a PDF to PIL Images.
    
    Args:
        pdf_path: Path to the PDF file
        dpi: Resolution for rendering (default 150, balance of quality/speed)
        
    Returns:
        List of PIL Images, one per page
    """
    images = []
    
    try:
        doc = fitz.open(pdf_path)
        
        for page_num in range(len(doc)):
            page = doc[page_num]
            # Create pixmap at specified DPI
            zoom = dpi / 72  # 72 is default PDF DPI
            matrix = fitz.Matrix(zoom, zoom)
            pix = page.get_pixmap(matrix=matrix)
            
            # Convert to PIL Image
            img_data = pix.tobytes("png")
            img = Image.open(io.BytesIO(img_data))
            images.append(img.convert("RGB"))
            
        doc.close()
        
    except Exception as e:
        print(f"Error converting {pdf_path}: {e}")
        return []
    
    return images


def get_pdf_page_count(pdf_path: str) -> int:
    """Get the number of pages in a PDF."""
    try:
        doc = fitz.open(pdf_path)
        count = len(doc)
        doc.close()
        return count
    except:
        return 0


def collect_pdfs(folder_path: str, recursive: bool = True) -> List[Path]:
    """
    Collect all PDF files from a folder.
    
    Args:
        folder_path: Path to folder containing PDFs
        recursive: Whether to search subfolders
        
    Returns:
        List of Path objects for each PDF
    """
    folder = Path(folder_path)
    
    if recursive:
        return list(folder.rglob("*.pdf"))
    else:
        return list(folder.glob("*.pdf"))


if __name__ == "__main__":
    # Quick test
    import sys
    
    if len(sys.argv) > 1:
        pdf_path = sys.argv[1]
        print(f"Converting: {pdf_path}")
        images = pdf_to_images(pdf_path)
        print(f"Extracted {len(images)} pages")
        
        if images:
            print(f"First page size: {images[0].size}")
    else:
        print("Usage: python pdf_to_image.py <path_to_pdf>")