radionica3d/backend/services/link_importer.py

import re
import requests
import os
import zipfile
import io
import uuid
from typing import List, Dict

# Standard headers to avoid bot detection
HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8",
}

class LinkImporter:
    @staticmethod
    def extract_id(url: str):
        # Thingiverse: thingiverse.com/thing:12345 or thingiverse.com/thing:12345/files
        thing_match = re.search(r"thingiverse\.com/thing:(\d+)", url)
        if thing_match:
            return "thingiverse", thing_match.group(1)
        
        # Printables: printables.com/model/12345-name or printables.com/en/model/12345
        printables_match = re.search(r"printables\.com/(?:[a-z]{2}/)?model/(\d+)", url)
        if printables_match:
            return "printables", printables_match.group(1)
            
        return None, None

    @staticmethod
    def download_and_extract(url: str, upload_dir: str, background_tasks=None) -> List[Dict]:
        service, item_id = LinkImporter.extract_id(url)
        if not service:
            raise ValueError("Unsupported URL format. Please use Thingiverse or Printables link.")

        download_url = ""
        if service == "thingiverse":
            download_url = f"https://www.thingiverse.com/thing:{item_id}/zip"
        elif service == "printables":
            download_url = f"https://www.printables.com/model/{item_id}/files/zip"

        print(f"DEBUG: Importing from {service} ID {item_id}. URL: {download_url}")
        
        try:
            response = requests.get(download_url, headers=HEADERS, stream=True, timeout=60)
            response.raise_for_status()
        except Exception as e:
            raise Exception(f"Failed to download from {service}: {e}")

        import db
        import hashlib
        from services import order_processing

        # Process the ZIP in memory
        imported_files = []
        with zipfile.ZipFile(io.BytesIO(response.content)) as z:
            for file_info in z.infolist():
                filename = os.path.basename(file_info.filename)
                if not filename or filename.startswith('.') or filename.startswith('__MACOSX'):
                    continue
                
                ext = os.path.splitext(filename)[1].lower()
                if ext in ['.stl', '.obj', '.step', '.stp', '.3mf']:
                    unique_name = f"{uuid.uuid4().hex}{ext}"
                    save_path = os.path.join(upload_dir, unique_name)
                    db_file_path = f"uploads/{unique_name}"
                    
                    # Read content to memory to hash it
                    content = z.read(file_info.filename)
                    with open(save_path, "wb") as target:
                        target.write(content)
                    
                    file_hash = hashlib.sha256(content).hexdigest()
                    file_size = len(content)
                    
                    # Check cache for filament/time
                    filament_g = None
                    print_time = None
                    cached = db.execute_query(
                        "SELECT filament_g, print_time FROM order_files WHERE file_hash = %s AND print_time IS NOT NULL LIMIT 1",
                        (file_hash,)
                    )
                    if cached:
                        filament_g = cached[0]['filament_g']
                        print_time = cached[0]['print_time']
                    
                    # Insert into DB
                    query = "INSERT INTO order_files (order_id, filename, file_path, file_size, quantity, file_hash, print_time, filament_g, preview_path) VALUES (NULL, %s, %s, %s, 1, %s, %s, %s, NULL)"
                    f_id = db.execute_commit(query, (filename, db_file_path, file_size, file_hash, print_time, filament_g))
                    
                    # Trigger background processing (previews, etc.)
                    if background_tasks:
                        background_tasks.add_task(order_processing.process_single_file_async, f_id)
                    
                    imported_files.append({
                        "id": f_id,
                        "filename": filename,
                        "size": file_size,
                        "print_time": print_time,
                        "filament_g": filament_g,
                        "status": "success"
                    })
        
        if not imported_files:
            raise Exception("No valid 3D models found in the downloaded archive.")
            
        return imported_files