Files
scrape-giant/tests/test_scraper.py

129 lines
4.5 KiB
Python

import csv
import tempfile
import unittest
from pathlib import Path
import scraper
class ScraperTests(unittest.TestCase):
def test_flatten_orders_extracts_order_and_item_rows(self):
history = {
"records": [
{
"orderId": "abc123",
"serviceType": "PICKUP",
}
]
}
details = [
{
"orderId": "abc123",
"orderDate": "2026-03-01",
"deliveryDate": "2026-03-02",
"orderTotal": "12.34",
"paymentMethod": "VISA",
"totalItemCount": 1,
"totalSavings": "1.00",
"yourSavingsTotal": "1.00",
"couponsDiscountsTotal": "0.50",
"refundOrder": False,
"ebtOrder": False,
"pup": {
"storeName": "Giant",
"aholdStoreNumber": "42",
"storeAddress1": "123 Main",
"storeCity": "Springfield",
"storeState": "VA",
"storeZipcode": "22150",
},
"items": [
{
"podId": "pod-1",
"itemName": "Bananas",
"primUpcCd": "111",
"categoryId": "produce",
"categoryDesc": "Produce",
"shipQy": "2",
"lbEachCd": "EA",
"unitPrice": "0.59",
"groceryAmount": "1.18",
"totalPickedWeight": "",
"mvpSavings": "0.10",
"rewardSavings": "0.00",
"couponSavings": "0.00",
"couponPrice": "",
}
],
}
]
orders, items = scraper.flatten_orders(
history,
details,
history_path=Path("data/giant-web/raw/history.json"),
raw_dir=Path("data/giant-web/raw"),
)
self.assertEqual(1, len(orders))
self.assertEqual("abc123", orders[0]["order_id"])
self.assertEqual("giant", orders[0]["retailer"])
self.assertEqual("PICKUP", orders[0]["service_type"])
self.assertEqual("data/giant-web/raw/history.json", orders[0]["raw_history_path"])
self.assertEqual("data/giant-web/raw/abc123.json", orders[0]["raw_order_path"])
self.assertEqual(1, len(items))
self.assertEqual("1", items[0]["line_no"])
self.assertEqual("Bananas", items[0]["item_name"])
self.assertEqual("giant", items[0]["retailer"])
self.assertEqual("data/giant-web/raw/abc123.json", items[0]["raw_order_path"])
self.assertEqual("false", items[0]["is_discount_line"])
def test_append_dedup_replaces_duplicate_rows_and_preserves_new_values(self):
with tempfile.TemporaryDirectory() as tmpdir:
path = Path(tmpdir) / "orders.csv"
scraper.append_dedup(
path,
[
{"order_id": "1", "order_total": "10.00"},
{"order_id": "2", "order_total": "20.00"},
],
subset=["order_id"],
fieldnames=["order_id", "order_total"],
)
merged = scraper.append_dedup(
path,
[
{"order_id": "2", "order_total": "21.50"},
{"order_id": "3", "order_total": "30.00"},
],
subset=["order_id"],
fieldnames=["order_id", "order_total"],
)
self.assertEqual(
[
{"order_id": "1", "order_total": "10.00"},
{"order_id": "2", "order_total": "21.50"},
{"order_id": "3", "order_total": "30.00"},
],
merged,
)
with path.open(newline="", encoding="utf-8") as handle:
rows = list(csv.DictReader(handle))
self.assertEqual(merged, rows)
def test_read_existing_order_ids_returns_known_ids(self):
with tempfile.TemporaryDirectory() as tmpdir:
path = Path(tmpdir) / "orders.csv"
path.write_text("order_id,order_total\n1,10.00\n2,20.00\n", encoding="utf-8")
self.assertEqual({"1", "2"}, scraper.read_existing_order_ids(path))
if __name__ == "__main__":
unittest.main()