junte/survey-extraction
1
0
Fork 0
mirror of https://github.com/Hestia-Homes/survey-extraction.git synced 2026-06-30 13:10:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Merge pull request #132 from Hestia-Homes/feature/live_tracker_documentation

Browse source 
new and improved script
This commit is contained in:
Jun-te Kim 2026-03-03 16:38:44 +00:00 • committed by GitHub
commit f706f281fa
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 6 additions and 25 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

31
etl/osmosis_monday_to_sharepoint_automation.py
View file

@ -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")