import fitz  # PyMuPDF
from PIL import Image
import io
import os

def check_pdf_images(pdf_path):
    if not os.path.exists(pdf_path):
        print(f"❌ {pdf_path} not found")
        return
    
    print(f"🖼️ Checking {pdf_path} for images...")
    
    try:
        doc = fitz.open(pdf_path)
        print(f"  Pages: {len(doc)}")
        
        for page_num in range(len(doc)):
            page = doc[page_num]
            print(f"\n  Page {page_num+1}:")
            
            # Get image list
            image_list = page.get_images()
            print(f"    Images found: {len(image_list)}")
            
            if image_list:
                for img_index, img in enumerate(image_list):
                    xref = img[0]
                    pix = fitz.Pixmap(doc, xref)
                    
                    if pix.n - pix.alpha < 4:  # this is GRAY or RGB
                        img_data = pix.tobytes("png")
                        img_size = len(img_data)
                        print(f"    Image {img_index+1}: {pix.width}x{pix.height}, {img_size} bytes")
                        
                        # Save the image for inspection
                        img_filename = f"ocr_page{page_num+1}_img{img_index+1}.png"
                        with open(img_filename, "wb") as f:
                            f.write(img_data)
                        print(f"      Saved as: {img_filename}")
                        
                        # Try to open and display image info
                        try:
                            pil_img = Image.open(io.BytesIO(img_data))
                            print(f"      Format: {pil_img.format}, Mode: {pil_img.mode}")
                        except Exception as e:
                            print(f"      Error opening image: {e}")
                    else:
                        print(f"    Image {img_index+1}: CMYK (skipped)")
                    
                    pix = None  # free pixmap resources
            else:
                print("    No images found on this page")
                
        doc.close()
        
    except Exception as e:
        print(f"❌ Error analyzing PDF: {e}")

if __name__ == "__main__":
    check_pdf_images("ocr.pdf")