From c6ec1eac5da5c5d51634638cede00cfd2dd0cf53 Mon Sep 17 00:00:00 2001
From: Jun-te Kim <junte@domna.homes>
Date: Thu, 24 Jul 2025 09:51:15 +0000
Subject: [PATCH] push to this branch

---
 etl/hubSpotClient/hubspot.py                  |  5 +-
 ...pull_data_from_hubspot_and_ideally_push.py | 53 +++++++++++++++++++
 etl/surveyedData/surveryedData.py             |  2 +
 3 files changed, 59 insertions(+), 1 deletion(-)
 create mode 100644 etl/quick_script_to_pull_data_from_hubspot_and_ideally_push.py

diff --git a/etl/hubSpotClient/hubspot.py b/etl/hubSpotClient/hubspot.py
index 3b4913e..269862c 100644
--- a/etl/hubSpotClient/hubspot.py
+++ b/etl/hubSpotClient/hubspot.py
@@ -206,7 +206,7 @@ class HubSpotClient():
             after = response.paging.next.after
 
         all_deals = []
-        for deal in found_deals:
+        for i,deal in enumerate(found_deals):
             domna_id, landlord_id, uprn = self.get_domna_and_landlord_id(deal.id)
             try:
                 deal_name = deal.properties['dealname']
@@ -226,6 +226,9 @@ class HubSpotClient():
                     domna_id = domna_id,
                     uprn = uprn,
                 ))
+                if i > 1:
+                    # Break after just for speed
+                    break
             except Exception as e:
                 def format_error_note(e):
                     note_text = "⚠️ <b>Automated Verification Failed:</b><br><br>"
diff --git a/etl/quick_script_to_pull_data_from_hubspot_and_ideally_push.py b/etl/quick_script_to_pull_data_from_hubspot_and_ideally_push.py
new file mode 100644
index 0000000..34924cc
--- /dev/null
+++ b/etl/quick_script_to_pull_data_from_hubspot_and_ideally_push.py
@@ -0,0 +1,53 @@
+import os
+from pprint import pprint
+
+os.environ["SHAREPOINT_CLIENT_ID"] = "895e3b77-b1d7-43ec-b18f-dcfe07cdfeaf"
+os.environ["SHAREPOINT_CLIENT_SECRET"] = "SOf8Q~-is4wdQiqvEEm9FlJQRAY9ELGaj5Qz-a6E"
+os.environ["SHAREPOINT_TENANT_ID"] = "c3f7519c-2719-4547-af04-6da6cbfd8f8f"
+os.environ["SOUTH_COAST_INSULATION_SERVICE_SHAREPOINT_ID"] = "b5a51507-9427-4ee0-b03e-90ec7681e2d3"
+os.environ["JJC_SERVICE_SHAREPOINT_ID"] = "7fdd0485-bbf3-4b29-b30f-98c81c2a6284"
+
+from etl.hubSpotClient.hubspot import DealStage, HubSpotClient
+from etl.surveyedData.surveryedData import surveyedDataProcessor
+from etl.scraper.scraper import SharePointScraper, SharePointInstaller
+from etl.utils.utils import get_sharepoint_path
+
+def string_to_installer(installer):
+    if installer.upper() == "J & J CRUMP":
+        return SharePointInstaller.JJC
+    elif installer.upper() == "SCIS":
+        return SharePointInstaller.SOUTH_COAST_INSULATION
+    elif installer.upper() == "SGEC":
+        return SharePointInstaller.JJC
+    else:
+        return None
+    
+# Local development
+os.environ["DATABASE_URL"] = "postgresql://postgres:makingwarmhomes@db:5432/postgres"
+
+hubspotClient = HubSpotClient()
+
+# Gets all deals and puts it into a SubmissionInfoFromDeal class
+# KHALIM - I ADDED A SCRIPT TO ONLY DOWNLOAD 1 deal for speed sake
+deals = hubspotClient.get_deals_from_deal_stage(DealStage.SURVEYED_COMPLETE_NEEDS_SIGN_OFF)
+
+
+for deal in deals:
+    sharepoint_url = deal.submission_folder_path
+    installer = string_to_installer(deal.installer)
+    sp = SharePointScraper(installer)
+    path = get_sharepoint_path(sharepoint_url)
+
+    files = sp.download_files_from_path(path)
+    sdp = surveyedDataProcessor("fake address", files)
+
+    # Class Object for EPR Summary Informaiton ( Transform )
+    sdp.epr_summary_information 
+
+    # File path to epr
+    sdp.epr_summary_information_file_path
+
+    break
+
+
+
diff --git a/etl/surveyedData/surveryedData.py b/etl/surveyedData/surveryedData.py
index f75b112..a88b8da 100644
--- a/etl/surveyedData/surveryedData.py
+++ b/etl/surveyedData/surveryedData.py
@@ -43,6 +43,7 @@ class surveyedDataProcessor():
         self.hubspot_deal_id = None
         self.epr_with_data = None
         self.epr_summary_information = None
+        self.epr_summary_information_file_path = None
         self.full_sap_xml = None
         self.lig_sap_xml = None
         self.rd_sap_xml = None
@@ -69,6 +70,7 @@ class surveyedDataProcessor():
                         self.epr_with_data = pdf.get_reader()
                     elif pdf.type == ReportType.ENERGY_PERFORMANCE_REPORT_SUMMARY_INFORMATION:
                         self.epr_summary_information = pdf.get_reader()
+                        self.epr_summary_information_file_path = file
 
             elif file.lower().endswith('.xml'):
                 xml = xmlReader(file)