Upload E-Commerce Product Intelligence Dashboard

backend/scraper.py

@@ -2,7 +2,7 @@ import os
 import logging
 import pandas as pd
 from pathlib import Path
-from kaggle.api.kaggle_api_extended import KaggleApi
+import subprocess
 import shutil
 
 logging.basicConfig(level=logging.INFO)
@@ -15,24 +15,21 @@ OUTPUT_PARQUET = Path("data/ecommerce_products.parquet")
 os.makedirs("data", exist_ok=True)
 
 
-def setup_kaggle_api():
-    """Auth Kaggle API."""
-    token = os.getenv("KAGGLE_API_TOKEN")
-    if not token:
-        raise ValueError("KAGGLE_API_TOKEN environment variable not set!")
-
-    api = KaggleApi()
-    api.api_token = token
-    return api
-
-
 def download_dataset():
-    """Download dataset từ Kaggle."""
-    api = setup_kaggle_api()
+    """Download dataset từ Kaggle bằng CLI."""
     TEMP_DIR.mkdir(parents=True, exist_ok=True)
 
     logger.info(f"Downloading dataset: {DATASET_SLUG}")
-    api.dataset_download_files(DATASET_SLUG, path=str(TEMP_DIR), unzip=True)
+
+    result = subprocess.run(
+        ["kaggle", "datasets", "download", "-d", DATASET_SLUG, "-p", str(TEMP_DIR), "-u"],
+        capture_output=True, text=True
+    )
+
+    if result.returncode != 0:
+        logger.error(f"Download failed: {result.stderr}")
+        raise RuntimeError(f"Kaggle download failed: {result.stderr}")
+
     logger.info("Download complete.")
     return TEMP_DIR