single_page.py

import fitz  # PyMuPDF
import argparse
import os
import glob

def convert_pdf_to_images(pdf_path, output_dir, dpi=300, image_format="png"):
    """
    Convert the FIRST PAGE of a PDF to an image, perfectly maintaining native page proportions.
    """
    # Create a dedicated subfolder for each PDF's images to keep things organized
    pdf_name = os.path.splitext(os.path.basename(pdf_path))[0]
    pdf_output_dir = os.path.join(output_dir, pdf_name)
    
    if not os.path.exists(pdf_output_dir):
        os.makedirs(pdf_output_dir)

    try:
        doc = fitz.open(pdf_path)
        print(f"Processing '{pdf_name}' | Total pages: {len(doc)} (Extracting page 1 only)")
        
        # Prevent errors if an empty PDF is somehow loaded
        if len(doc) == 0:
            print(f"  -> Skipping '{pdf_name}': PDF has no pages.")
            return

        # PDFs have a standard base resolution of 72 DPI.
        # We calculate a zoom factor to scale the native page size up to your desired DPI.
        zoom = dpi / 72.0 
        mat = fitz.Matrix(zoom, zoom) # This matrix dynamically adapts to ANY page size

        # Load ONLY the first page (Index 0)
        page = doc.load_page(0)
        
        # Apply the matrix to render the high-quality, perfectly proportioned image
        pix = page.get_pixmap(matrix=mat, alpha=False)
        
        output_file = os.path.join(pdf_output_dir, f"cover_page.{image_format}")
        pix.save(output_file)
        print(f"  -> Saved first page (Dynamic Resolution: {pix.width}x{pix.height})")
            
    except Exception as e:
        print(f"Error processing {pdf_path}: {e}")

def process_all_pdfs(input_path, output_dir, dpi=300, image_format="png"):
    """Determines if the input is a single file or a directory of files."""
    if os.path.isfile(input_path):
        convert_pdf_to_images(input_path, output_dir, dpi, image_format)
    elif os.path.isdir(input_path):
        pdf_files = glob.glob(os.path.join(input_path, "*.pdf"))
        if not pdf_files:
            print(f"No PDF files found in directory: {input_path}")
            return
        
        print(f"Found {len(pdf_files)} PDF(s). Starting batch conversion of first pages...\n")
        for pdf in pdf_files:
            convert_pdf_to_images(pdf, output_dir, dpi, image_format)
            print("-" * 40)
        print("All batch conversions complete!")
    else:
        print("Invalid input path. Please provide a valid PDF file or folder.")

if __name__ == "__main__":
    parser = argparse.ArgumentParser(description="Convert the first page of PDFs to auto-adjusting high-quality images.")
    parser.add_argument("input_path", help="Path to a single PDF file OR a folder containing PDFs")
    parser.add_argument("--output", "-o", default="output", help="Output directory (default: 'output')")
    parser.add_argument("--dpi", type=int, default=300, help="Output image DPI (default: 300)")
    parser.add_argument("--format", "-f", default="png", help="Output image format (default: png)")
    
    args = parser.parse_args()
    
    # Ensure base output directory exists
    if not os.path.exists(args.output):
        os.makedirs(args.output)
        
    process_all_pdfs(args.input_path, args.output, args.dpi, args.format)