From 5ccc2e3b888922c9066b11679e2c8c45ddc71cf0 Mon Sep 17 00:00:00 2001
From: Jun-te Kim <juntekim@googlemail.com>
Date: Tue, 3 Mar 2026 16:38:01 +0000
Subject: [PATCH] new and improved script

---
 ...osmosis_monday_to_sharepoint_automation.py | 31 ++++---------------
 1 file changed, 6 insertions(+), 25 deletions(-)

diff --git a/etl/osmosis_monday_to_sharepoint_automation.py b/etl/osmosis_monday_to_sharepoint_automation.py
index 7647672..28c0f0c 100644
--- a/etl/osmosis_monday_to_sharepoint_automation.py
+++ b/etl/osmosis_monday_to_sharepoint_automation.py
@@ -48,7 +48,7 @@ def retry(max_attempts: int = 3, base_delay: float = 1.0):
 # Folder Creation Logic (Wrapped with retry)
 # --------------------------------------------------
 
-@retry(max_attempts=3)
+@retry(max_attempts=5)
 def process_asset(address: pd.Series):
     folder_name = f"{address['Name']} {address['Postcode']}"
     print(f"\n📁 Processing {folder_name}")
@@ -97,7 +97,7 @@ def process_asset(address: pd.Series):
 results = []
 failed_rows = []
 
-MAX_WORKERS = 5
+MAX_WORKERS = 10
 
 with ThreadPoolExecutor(max_workers=MAX_WORKERS) as executor:
     futures = [
@@ -121,26 +121,7 @@ print(f"❌ Failed: {len(failed_rows)}")
 if failed_rows:
     pd.DataFrame(failed_rows).to_excel("failed_rows.xlsx", index=False)
     print("📄 Saved failed rows to failed_rows.xlsx")
-# # Run this is you just want to get url
-# def just_url(asset_list):
-#     new_asset_list = []
-#     for index, address in tqdm(asset_list.iterrows()):
-#         folder_name = address['Name'] + " " + address['Postcode']
-#         webUrl = osmosis.create_dir(folder_name, parent_folder)
-#         asset_data = {
-#             "Name": address['Name'],
-#             "Postcode": address['Postcode'],
-#             "Sharepoint": webUrl,
-#         }
-#         print(asset_data)
-
-#         new_asset_list.append(asset_data)
-#     return new_asset_list
-
-# # new_asset_list = just_url(asset_list=asset_list)
-
-# df = pd.DataFrame(new_asset_list)
-# df.to_csv("output.csv", index=False)
-
-
-
+if results:
+    results_df = pd.DataFrame(results)
+    results_df.to_csv("sharepoint_results.csv", index=False)
+    print("📄 Saved successful results to sharepoint_results.csv")