import os
import zipfile

SRC = '/home/maxi/Projekt/wtc.waiswuaschd.de/data/import_2026'
IMG_OUT = '/home/maxi/Projekt/wtc.waiswuaschd.de/app/static/uploads/recipes'
os.makedirs(IMG_OUT, exist_ok=True)

extracted_images = {}

for f in sorted(os.listdir(SRC)):
    path = os.path.join(SRC, f)
    base = os.path.splitext(f)[0]
    ext = os.path.splitext(f)[1].lower()
    
    if ext in ['.docx', '.pptx']:
        try:
            with zipfile.ZipFile(path, 'r') as z:
                # Find images in word/media or ppt/media
                media_files = [m for m in z.namelist() if m.startswith(('word/media/', 'ppt/media/')) and m.lower().endswith(('.jpg', '.jpeg', '.png'))]
                # Filter out tiny icons (e.g. < 5KB)
                large_media = []
                for m in media_files:
                    info = z.getinfo(m)
                    if info.file_size > 15000: # > 15KB
                        large_media.append((m, info.file_size))
                
                large_media.sort(key=lambda x: x[1], reverse=True)
                if large_media:
                    best_img = large_media[0][0]
                    img_ext = os.path.splitext(best_img)[1].lower()
                    safe_name = "".join(c for c in base if c.isalnum() or c in (' ', '_', '-')).strip().replace(' ', '_').lower()
                    target_file = f"{safe_name}{img_ext}"
                    target_path = os.path.join(IMG_OUT, target_file)
                    with open(target_path, 'wb') as out_f:
                        out_f.write(z.read(best_img))
                    extracted_images[f] = f"/static/uploads/recipes/{target_file}"
                    print(f"Extracted image for {f}: {target_file} ({large_media[0][1]} bytes)")
        except Exception as e:
            print(f"Error extracting image from {f}: {e}")

print(f"\nTotal images extracted: {len(extracted_images)}")