notebookVB

2026-06-01 07:24:46 +02:00
parent e3522f4017
commit 5073c01692
8 changed files with 1056 additions and 261 deletions
@@ -0,0 +1,93 @@
+"""
+Test DB layer: load products_300102013.json (already scraped data)
+and upsert into MongoDB 'rohlik' database.
+
+No scraping needed — just validates the db.py functions work
+with real API response shapes.
+"""
+
+import json
+import sys
+import io
+from pathlib import Path
+from db import get_db, ensure_indexes, upsert_products, upsert_category
+
+sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding="utf-8", errors="replace")
+
+DATA_FILE = Path(__file__).parent / "products_300102013.json"
+
+
+def main():
+    db = get_db()
+    print(f"Connected to: {db.client.address} / {db.name}")
+
+    ensure_indexes(db)
+    print("Indexes created.\n")
+
+    # --- test category upsert ---
+    upsert_category(db, {
+        "_id": 300102013,
+        "name": "Okurky, cukety a lilky",
+        "slug": "okurky-cukety-a-lilky",
+        "path": [300102000, 300102008, 300102013],
+        "pathNames": ["Ovoce a zelenina", "Zelenina", "Okurky, cukety a lilky"],
+        "parentId": 300102008,
+        "isLeaf": True,
+    })
+    print("Category 300102013 upserted.")
+
+    # --- load scraped products ---
+    products = json.loads(DATA_FILE.read_text(encoding="utf-8"))
+    print(f"Loaded {len(products)} products from {DATA_FILE.name}\n")
+
+    # split merged records back into the 4 lists that upsert_products expects
+    bases = []
+    prices_list = []
+    stocks = []
+    categories_list = []
+
+    for p in products:
+        base = p.get("base", {})
+        prices = p.get("prices", {})
+        stock = p.get("stock", {})
+        cats = p.get("categories", {})
+
+        bases.append(base)
+        prices_list.append(prices)
+        stocks.append(stock)
+        categories_list.append(cats)
+
+    upsert_products(db, bases, prices_list, stocks, categories_list)
+    print(f"Upserted {len(bases)} products.\n")
+
+    # --- verify ---
+    n_products = db.products.count_documents({})
+    n_history = db.price_history.count_documents({})
+    n_cats = db.categories.count_documents({})
+
+    print(f"DB counts:")
+    print(f"  products:      {n_products}")
+    print(f"  price_history: {n_history}")
+    print(f"  categories:    {n_cats}")
+
+    # show one sample
+    sample = db.products.find_one({"_id": 1407650})
+    if sample:
+        print(f"\nSample product: {sample['name']}")
+        print(f"  price:    {sample['currentPrice']} {sample['currency']}")
+        print(f"  per unit: {sample['currentPricePerUnit']}/{sample.get('unit', '?')}")
+        print(f"  inStock:  {sample['inStock']}")
+        print(f"  sale:     {sample['sale']}")
+        print(f"  badges:   {[b['title'] for b in sample.get('badges', [])]}")
+
+    # show price_history entry
+    hist = db.price_history.find_one({"productId": 1407650})
+    if hist:
+        print(f"\n  price_history record: price={hist['price']}, "
+              f"inStock={hist['inStock']}, scrapedAt={hist['scrapedAt']}")
+
+    print("\nDone.")
+
+
+if __name__ == "__main__":
+    main()