Add shared browser session bootstrap

scrape_costco.py

@@ -1,17 +1,16 @@
-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
 
 import click
-import browser_cookie3
 from curl_cffi import requests
 
+from retailer_sessions import load_costco_session
+
 BASE_URL = "https://ecom-api.costco.com/ebusiness/order/v1/orders/graphql"
 RETAILER = "costco"
 
@@ -210,16 +209,7 @@ ITEM_FIELDS = [
     "is_coupon_line",
 ]
 
-
-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):
+def build_headers(auth_headers):
     headers = {
         "accept": "*/*",
         "content-type": "application/json-patch+json",
@@ -232,18 +222,14 @@ def build_headers(config):
             "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"]
+    headers.update(auth_headers)
     return headers
 
-def build_session(config):
+def build_session():
+    retailer_session = load_costco_session()
     session = requests.Session()
-    session.cookies.update(browser_cookie3.firefox(domain_name=".costco.com"))
-    session.headers.update(build_headers(config))
+    session.cookies.update(retailer_session.cookies)
+    session.headers.update(build_headers(retailer_session.headers))
     return session
 
 
@@ -596,17 +582,10 @@ def main(outdir, document_type, document_sub_type, window_days, months_back):
     outdir = Path(outdir)
     raw_dir = outdir / "raw"    
     try:
-        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)
+        session = build_session()
     except Exception as exc:
         raise click.ClickException(
-            f"failed to load Costco Firefox cookies: {exc}"
+            f"failed to load Costco browser session: {exc}"
         ) from exc
     start_date, end_date = resolve_date_range(months_back)