Compare commits

..

2 Commits

Author SHA1 Message Date
ben
861955557a added instructions 2026-03-16 17:34:22 -04:00
ben
6e1cde2c83 fix json data pull from /raw 2026-03-16 17:34:01 -04:00
2 changed files with 14 additions and 1 deletions

View File

@@ -213,9 +213,11 @@ def parse_costco_item(order_id, order_date, raw_path, line_no, item):
def iter_costco_rows(raw_dir):
for path in discover_json_files(raw_dir):
if path.name == "summary.json":
if path.name in {"summary.json", "summary_requests.json"}:
continue
payload = json.loads(path.read_text(encoding="utf-8"))
if not isinstance(payload, dict):
continue
receipts = payload.get("data", {}).get("receiptsWithCounts", {}).get("receipts", [])
for receipt in receipts:
order_id = receipt["transactionBarcode"]

View File

@@ -212,3 +212,14 @@ request:
- pull all orders by default
- add online orders
- copy header data from browser using selenium
* how to run
python scrape_giant.py
python enrich_giant.py
python scrape_costco.py
python enrich_costco.py
python build_observed_products.py
python build_review_queue.py
python build_canonical_layer.py
python validate_cross_retailer_flow.py