added token and dotenv so costco scrapes successfully 36 mo

scrape_costco.py

@@ -1,6 +1,9 @@
+import os
 import csv
 import json
 import time
+import re
+from dotenv import load_dotenv
 from calendar import monthrange
 from datetime import datetime, timedelta
 from pathlib import Path
@@ -208,8 +211,16 @@ ITEM_FIELDS = [
 ]
 
 
-def build_headers():
+def load_config():
+    load_dotenv()
     return {
+        "authorization": os.getenv("COSTCO_X_AUTHORIZATION", "").strip(),
+        "client_id": os.getenv("COSTCO_X_WCS_CLIENTID", "").strip(),
+        "client_identifier": os.getenv("COSTCO_CLIENT_IDENTIFIER", "").strip(),
+    }
+
+def build_headers(config):
+    headers = {
         "accept": "*/*",
         "content-type": "application/json-patch+json",
         "costco.service": "restOrders",
@@ -221,12 +232,18 @@ def build_headers():
             "Gecko/20100101 Firefox/148.0"
         ),
     }
+    if config["authorization"]:
+        headers["costco-x-authorization"] = config["authorization"]
+    if config["client_id"]:
+        headers["costco-x-wcs-clientId"] = config["client_id"]
+    if config["client_identifier"]:
+        headers["client-identifier"] = config["client_identifier"]
+    return headers
 
-
+def build_session(config):
-def build_session():
     session = requests.Session()
-    session.cookies.update(browser_cookie3.firefox(domain_name="costco.com"))
+    session.cookies.update(browser_cookie3.firefox(domain_name=".costco.com"))
-    session.headers.update(build_headers())
+    session.headers.update(build_headers(config))
     return session
 
 
@@ -254,6 +271,8 @@ def graphql_post(session, query, variables):
 
     raise RuntimeError("failed to fetch Costco GraphQL payload")
 
+def safe_filename(value):
+    return re.sub(r'[<>:"/\\|?*]+', "-", str(value))
 
 def summary_receipts(payload):
     return payload.get("data", {}).get("receiptsWithCounts", {}).get("receipts", [])
@@ -423,7 +442,7 @@ def flatten_costco_data(summary_payload, detail_payloads, raw_dir):
                 for row in summary_row.get("couponArray", []) or []
                 if row.get("upcnumberCoupon")
             }
-            raw_order_path = raw_dir / f"{receipt_id or order_id}.json"
+            raw_order_path = raw_dir / f"{safe_filename(receipt_id or order_id)}.json"
 
             orders.append(
                 {
@@ -568,16 +587,23 @@ def write_csv(path, rows, fieldnames):
 )
 @click.option(
     "--months-back",
-    default=3,
+    default=36,
     show_default=True,
     type=int,
     help="How many months of receipts to enumerate back from today.",
 )
 def main(outdir, document_type, document_sub_type, window_days, months_back):
     outdir = Path(outdir)
-    raw_dir = outdir / "raw"
+    raw_dir = outdir / "raw"    
     try:
-        session = build_session()
+        config = load_config()
+        click.echo(
+            "auth headers present: "
+            f"authorization={bool(config['authorization'])}, "
+            f"client_id={bool(config['client_id'])}, "
+            f"client_identifier={bool(config['client_identifier'])}"
+        )
+        session = build_session(config)
     except Exception as exc:
         raise click.ClickException(
             f"failed to load Costco Firefox cookies: {exc}"
@@ -607,7 +633,7 @@ def main(outdir, document_type, document_sub_type, window_days, months_back):
             {"barcode": barcode, "documentType": "warehouse"},
         )
         detail_payloads.append(detail_payload)
-        write_json(raw_dir / f"{receipt_id}.json", detail_payload)
+        write_json(raw_dir / f"{safe_filename(receipt_id)}.json", detail_payload)
 
     orders, items = flatten_costco_data(summary_payload, detail_payloads, raw_dir)
     write_csv(outdir / "orders.csv", orders, ORDER_FIELDS)
@@ -617,3 +643,4 @@ def main(outdir, document_type, document_sub_type, window_days, months_back):
 
 if __name__ == "__main__":
     main()
+