From 1ac5cb253a9d15cf0d535e332faefdaa997fcbb9 Mon Sep 17 00:00:00 2001 From: Jun-te Kim Date: Tue, 31 Mar 2026 14:47:52 +0000 Subject: [PATCH 1/3] make the fix for module name --- infrastructure/terraform/lambda/hubspot_deal_etl/main.tf | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/infrastructure/terraform/lambda/hubspot_deal_etl/main.tf b/infrastructure/terraform/lambda/hubspot_deal_etl/main.tf index 051c7154..5a529e85 100644 --- a/infrastructure/terraform/lambda/hubspot_deal_etl/main.tf +++ b/infrastructure/terraform/lambda/hubspot_deal_etl/main.tf @@ -39,6 +39,6 @@ module "hubspot_deal_etl" { } resource "aws_iam_role_policy_attachment" "lambda_s3_policy" { - role = module.lambda.role_name + role = module.hubspot_deal_etl.role_name policy_arn = data.terraform_remote_state.shared.outputs.hubspot_etl_s3_read_and_write_arn } \ No newline at end of file From ea84cf9fd4ae21d938598cc9043b19df67c35298 Mon Sep 17 00:00:00 2001 From: Jun-te Kim Date: Tue, 31 Mar 2026 15:51:43 +0000 Subject: [PATCH 2/3] added bulk --- backend/app/db/models/organisation.py | 24 ++++ etl/hubspot/hubspotClient.py | 31 ++++- etl/hubspot/hubspotDataTodB.py | 154 +++++++++++++++++++++-- etl/hubspot/scripts/scraper/bulk_load.py | 33 +++++ etl/hubspot/scripts/scraper/main.py | 2 +- sfr/principal_pitch/2_export_data.py | 8 +- 6 files changed, 236 insertions(+), 16 deletions(-) create mode 100644 etl/hubspot/scripts/scraper/bulk_load.py diff --git a/backend/app/db/models/organisation.py b/backend/app/db/models/organisation.py index e8649cdd..a9718c42 100644 --- a/backend/app/db/models/organisation.py +++ b/backend/app/db/models/organisation.py @@ -40,6 +40,30 @@ class HubspotDealData(SQLModel, table=True): coordination_status: Optional[str] = Field(default=None) design_status: Optional[str] = Field(default=None) + listing_id: Optional[str] = Field(default=None) + pashub_link: Optional[str] = Field(default=None) + sharepoint_link: Optional[str] = Field(default=None) + dampmould_growth: Optional[str] = Field(default=None) + pre_sap: Optional[str] = Field(default=None) + coordinator: Optional[str] = Field(default=None) + mtp_completion_date: Optional[datetime] = Field(default=None) + mtp_re_model_completion_date: Optional[datetime] = Field(default=None) + ioe_v3_completion_date: Optional[datetime] = Field(default=None) + proposed_measures: Optional[str] = Field(default=None) + approved_package: Optional[str] = Field(default=None) + designer: Optional[str] = Field(default=None) + design_completion_date: Optional[datetime] = Field(default=None) + actual_measures_installed: Optional[str] = Field(default=None) + installer: Optional[str] = Field(default=None) + installer_handover: Optional[str] = Field(default=None) + lodgement_status: Optional[str] = Field(default=None) + measures_lodgement_date: Optional[datetime] = Field(default=None) + lodgement_date: Optional[datetime] = Field(default=None) + expected_commencement_date: Optional[datetime] = Field(default=None) + surveyor: Optional[str] = Field(default=None) + confirmed_survey_date: Optional[datetime] = Field(default=None) + confirmed_survey_time: Optional[str] = Field(default=None) + created_at: datetime = Field( sa_column=Column( DateTime(timezone=True), diff --git a/etl/hubspot/hubspotClient.py b/etl/hubspot/hubspotClient.py index 8bbe8a63..e5461c61 100644 --- a/etl/hubspot/hubspotClient.py +++ b/etl/hubspot/hubspotClient.py @@ -189,6 +189,7 @@ class HubspotClient: ) listing_info: dict[str, str] = cast(dict[str, str], listing.properties) # type: ignore[reportUnknownMemberType] + listing_info["listing_id"] = listing_id self.logger.info(f"Listing info for deal {deal_id}: {listing_info}") return listing_info @@ -201,13 +202,35 @@ class HubspotClient: "dealname", "dealstage", "pipeline", - "outcome", # outcome, - "outcome_notes", # outcome notes + "outcome", + "outcome_notes", "project_code", "major_condition_issue_description", "major_condition_issue_photos", - "coordination_status__stage_1_", # Coordiantion Status (Stage 1), - "retrofit_design_status", # Retrofit Design Status + "coordination_status__stage_1_", + "retrofit_design_status", + "pashub_link", + "sharepoint_link", + "dampmould_growth", + "pre_sap", + "coordinator", + "mtp_completion_date", + "mtp_re_model_completion_date", + "ioe_v3_completion_date", + "proposed_measures", + "approved_package", + "designer", + "design_completion_date", + "actual_measures_installed", + "installer", + "installer_handover", + "lodgement_status", + "measures_lodgement_date", + "lodgement_date", + "expected_commencement_date", + "surveyor", + "confirmed_survey_date", + "confirmed_survey_time", ], ) diff --git a/etl/hubspot/hubspotDataTodB.py b/etl/hubspot/hubspotDataTodB.py index f7f79e46..38ec3e35 100644 --- a/etl/hubspot/hubspotDataTodB.py +++ b/etl/hubspot/hubspotDataTodB.py @@ -2,7 +2,7 @@ from backend.app.db.connection import db_read_session from backend.app.db.models.organisation import Organisation, HubspotDealData from sqlmodel import select from datetime import datetime, timezone -from typing import TypedDict +from typing import TypedDict, Optional from etl.hubspot.s3_uploader import S3Uploader import hashlib import os @@ -82,6 +82,14 @@ class HubspotDataToDb: .one_or_none() ) + def _parse_hs_date(self, value: Optional[str]) -> Optional[datetime]: + if not value: + return None + try: + return datetime.fromisoformat(value.replace("Z", "+00:00")) + except ValueError: + return None + def _sha256(self, file_path: str) -> str: """Compute SHA-256 checksum of a file.""" sha256 = hashlib.sha256() @@ -114,6 +122,10 @@ class HubspotDataToDb: deal_in_db.deal_id == hs_deal.get("hs_object_id"), "deal_id mismatch" ), soft_assert(deal_in_db.company_id == hs_company_id, "company_id mismatch"), + soft_assert( + deal_in_db.listing_id == hs_listing.get("listing_id"), + "listing_id mismatch", + ), soft_assert( deal_in_db.landlord_property_id == hs_listing.get("owner_property_id"), "landlord_property_id mismatch", @@ -157,6 +169,94 @@ class HubspotDataToDb: deal_in_db.design_status == hs_deal.get("retrofit_design_status"), "retrofit design mismatch", ), + soft_assert( + deal_in_db.pashub_link == hs_deal.get("pashub_link"), + "pashub_link mismatch", + ), + soft_assert( + deal_in_db.sharepoint_link == hs_deal.get("sharepoint_link"), + "sharepoint_link mismatch", + ), + soft_assert( + deal_in_db.dampmould_growth == hs_deal.get("dampmould_growth"), + "dampmould_growth mismatch", + ), + soft_assert( + deal_in_db.pre_sap == hs_deal.get("pre_sap"), + "pre_sap mismatch", + ), + soft_assert( + deal_in_db.coordinator == hs_deal.get("coordinator"), + "coordinator mismatch", + ), + soft_assert( + deal_in_db.mtp_completion_date == self._parse_hs_date(hs_deal.get("mtp_completion_date")), + "mtp_completion_date mismatch", + ), + soft_assert( + deal_in_db.mtp_re_model_completion_date == self._parse_hs_date(hs_deal.get("mtp_re_model_completion_date")), + "mtp_re_model_completion_date mismatch", + ), + soft_assert( + deal_in_db.ioe_v3_completion_date == self._parse_hs_date(hs_deal.get("ioe_v3_completion_date")), + "ioe_v3_completion_date mismatch", + ), + soft_assert( + deal_in_db.proposed_measures == hs_deal.get("proposed_measures"), + "proposed_measures mismatch", + ), + soft_assert( + deal_in_db.approved_package == hs_deal.get("approved_package"), + "approved_package mismatch", + ), + soft_assert( + deal_in_db.designer == hs_deal.get("designer"), + "designer mismatch", + ), + soft_assert( + deal_in_db.design_completion_date == self._parse_hs_date(hs_deal.get("design_completion_date")), + "design_completion_date mismatch", + ), + soft_assert( + deal_in_db.actual_measures_installed == hs_deal.get("actual_measures_installed"), + "actual_measures_installed mismatch", + ), + soft_assert( + deal_in_db.installer == hs_deal.get("installer"), + "installer mismatch", + ), + soft_assert( + deal_in_db.installer_handover == hs_deal.get("installer_handover"), + "installer_handover mismatch", + ), + soft_assert( + deal_in_db.lodgement_status == hs_deal.get("lodgement_status"), + "lodgement_status mismatch", + ), + soft_assert( + deal_in_db.measures_lodgement_date == self._parse_hs_date(hs_deal.get("measures_lodgement_date")), + "measures_lodgement_date mismatch", + ), + soft_assert( + deal_in_db.lodgement_date == self._parse_hs_date(hs_deal.get("lodgement_date")), + "lodgement_date mismatch", + ), + soft_assert( + deal_in_db.expected_commencement_date == self._parse_hs_date(hs_deal.get("expected_commencement_date")), + "expected_commencement_date mismatch", + ), + soft_assert( + deal_in_db.surveyor == hs_deal.get("surveyor"), + "surveyor mismatch", + ), + soft_assert( + deal_in_db.confirmed_survey_date == self._parse_hs_date(hs_deal.get("confirmed_survey_date")), + "confirmed_survey_date mismatch", + ), + soft_assert( + deal_in_db.confirmed_survey_time == hs_deal.get("confirmed_survey_time"), + "confirmed_survey_time mismatch", + ), ] # If discrepancies found, update from HubSpot @@ -238,6 +338,7 @@ class HubspotDataToDb: for attr, value in { "dealname": deal_data.get("dealname"), "dealstage": deal_data.get("dealstage"), + "listing_id": listing.get("listing_id"), "landlord_property_id": listing.get("owner_property_id"), "uprn": listing.get("national_uprn"), "outcome": deal_data.get("outcome"), @@ -250,16 +351,32 @@ class HubspotDataToDb: "major_condition_issue_photos": deal_data.get( "major_condition_issue_photos" ), - "major_condition_issue_description": deal_data.get( - "major_condition_issue_description" - ), - "major_condition_issue_photos": deal_data.get( - "major_condition_issue_photos" - ), "coordination_status": deal_data.get( "coordination_status__stage_1_" ), "design_status": deal_data.get("retrofit_design_status"), + "pashub_link": deal_data.get("pashub_link"), + "sharepoint_link": deal_data.get("sharepoint_link"), + "dampmould_growth": deal_data.get("dampmould_growth"), + "pre_sap": deal_data.get("pre_sap"), + "coordinator": deal_data.get("coordinator"), + "mtp_completion_date": self._parse_hs_date(deal_data.get("mtp_completion_date")), + "mtp_re_model_completion_date": self._parse_hs_date(deal_data.get("mtp_re_model_completion_date")), + "ioe_v3_completion_date": self._parse_hs_date(deal_data.get("ioe_v3_completion_date")), + "proposed_measures": deal_data.get("proposed_measures"), + "approved_package": deal_data.get("approved_package"), + "designer": deal_data.get("designer"), + "design_completion_date": self._parse_hs_date(deal_data.get("design_completion_date")), + "actual_measures_installed": deal_data.get("actual_measures_installed"), + "installer": deal_data.get("installer"), + "installer_handover": deal_data.get("installer_handover"), + "lodgement_status": deal_data.get("lodgement_status"), + "measures_lodgement_date": self._parse_hs_date(deal_data.get("measures_lodgement_date")), + "lodgement_date": self._parse_hs_date(deal_data.get("lodgement_date")), + "expected_commencement_date": self._parse_hs_date(deal_data.get("expected_commencement_date")), + "surveyor": deal_data.get("surveyor"), + "confirmed_survey_date": self._parse_hs_date(deal_data.get("confirmed_survey_date")), + "confirmed_survey_time": deal_data.get("confirmed_survey_time"), }.items(): setattr(existing, attr, value or getattr(existing, attr)) @@ -302,6 +419,7 @@ class HubspotDataToDb: deal_id=deal_id, dealname=deal_data.get("dealname"), dealstage=deal_data.get("dealstage"), + listing_id=listing.get("listing_id"), landlord_property_id=listing.get("owner_property_id"), uprn=listing.get("national_uprn"), outcome=deal_data.get("outcome"), @@ -316,6 +434,28 @@ class HubspotDataToDb: ), coordination_status=deal_data.get("coordination_status__stage_1_"), design_status=deal_data.get("retrofit_design_status"), + pashub_link=deal_data.get("pashub_link"), + sharepoint_link=deal_data.get("sharepoint_link"), + dampmould_growth=deal_data.get("dampmould_growth"), + pre_sap=deal_data.get("pre_sap"), + coordinator=deal_data.get("coordinator"), + mtp_completion_date=self._parse_hs_date(deal_data.get("mtp_completion_date")), + mtp_re_model_completion_date=self._parse_hs_date(deal_data.get("mtp_re_model_completion_date")), + ioe_v3_completion_date=self._parse_hs_date(deal_data.get("ioe_v3_completion_date")), + proposed_measures=deal_data.get("proposed_measures"), + approved_package=deal_data.get("approved_package"), + designer=deal_data.get("designer"), + design_completion_date=self._parse_hs_date(deal_data.get("design_completion_date")), + actual_measures_installed=deal_data.get("actual_measures_installed"), + installer=deal_data.get("installer"), + installer_handover=deal_data.get("installer_handover"), + lodgement_status=deal_data.get("lodgement_status"), + measures_lodgement_date=self._parse_hs_date(deal_data.get("measures_lodgement_date")), + lodgement_date=self._parse_hs_date(deal_data.get("lodgement_date")), + expected_commencement_date=self._parse_hs_date(deal_data.get("expected_commencement_date")), + surveyor=deal_data.get("surveyor"), + confirmed_survey_date=self._parse_hs_date(deal_data.get("confirmed_survey_date")), + confirmed_survey_time=deal_data.get("confirmed_survey_time"), ) # Handle upload at insert time diff --git a/etl/hubspot/scripts/scraper/bulk_load.py b/etl/hubspot/scripts/scraper/bulk_load.py new file mode 100644 index 00000000..fabf8a3f --- /dev/null +++ b/etl/hubspot/scripts/scraper/bulk_load.py @@ -0,0 +1,33 @@ +from etl.hubspot.hubspotClient import HubspotClient, Companies, Pipeline +from etl.hubspot.scripts.scraper.main import handler +from tqdm import tqdm + + +PIPELINE_ID = Pipeline.OPERATIONS_SOCIAL_HOUSING.value + +companies = list([Companies.THE_GUINESS_PARTNERSHIP, Companies.SOUTHERN_HOUSING_GROUP]) + + +def bulk_load(companies: list[Companies] | None = None) -> None: + """ + Load all deals from the given companies (defaults to all Companies enum values) + into the database, filtered to the Operations/Social Housing pipeline. + """ + hubspot = HubspotClient() + targets = companies or list(Companies) + + for company in tqdm(targets, desc="Companies"): + company_id = company.value + deal_ids = hubspot.get_deal_ids_from_company(company_id) + + for deal_id in tqdm(deal_ids, desc=f"{company.name}", leave=False): + deal_data = hubspot.from_deal_id_get_info(deal_id) + if deal_data.get("pipeline") != PIPELINE_ID: + continue + + handler({"hubspot_deal_id": deal_id}, context=None) + print(f"Processed deal {deal_id} (company: {company.name})") + + +if __name__ == "__main__": + bulk_load(companies) diff --git a/etl/hubspot/scripts/scraper/main.py b/etl/hubspot/scripts/scraper/main.py index 48864b22..f5afef52 100644 --- a/etl/hubspot/scripts/scraper/main.py +++ b/etl/hubspot/scripts/scraper/main.py @@ -4,7 +4,7 @@ 3) [completed] Load the db and check if upsert it into the table 4) [completed]Getting working on a AWS lambda 5) [completed] subtask and tasks history -6) [TODO]The new sexy deal properties, move it over +6) [completed]The new sexy deal properties, move it over """ from etl.hubspot.hubspotClient import HubspotClient diff --git a/sfr/principal_pitch/2_export_data.py b/sfr/principal_pitch/2_export_data.py index c89560cb..fece17e0 100644 --- a/sfr/principal_pitch/2_export_data.py +++ b/sfr/principal_pitch/2_export_data.py @@ -26,13 +26,13 @@ from backend.app.db.functions.materials_functions import get_materials from collections import defaultdict from sqlalchemy import func -PORTFOLIO_ID = 639 -SCENARIOS = [1157] +PORTFOLIO_ID = 640 +SCENARIOS = [1154] scenario_names = { - 1157: "EPC C - no EWI solid floor", + 1154: "EPC - 10k Budget", } -project_name = "Instagroup Sample" +project_name = "First Charterhouse Investments" def get_data(portfolio_id, scenario_ids): From fcf25f7cac88dd5790c2fb128d3b7e95e1a98144 Mon Sep 17 00:00:00 2001 From: Jun-te Kim Date: Tue, 31 Mar 2026 18:46:37 +0000 Subject: [PATCH 3/3] get rid of photos from local drive when i run it locally so its less verbose --- etl/hubspot/hubspotDataTodB.py | 9 +++++++++ etl/hubspot/scripts/scraper/bulk_load.py | 21 ++++++++++++++------- 2 files changed, 23 insertions(+), 7 deletions(-) diff --git a/etl/hubspot/hubspotDataTodB.py b/etl/hubspot/hubspotDataTodB.py index 38ec3e35..0c38f483 100644 --- a/etl/hubspot/hubspotDataTodB.py +++ b/etl/hubspot/hubspotDataTodB.py @@ -311,6 +311,9 @@ class HubspotDataToDb: f"⚠️ Failed to download/upload photo for deal_id {deal_in_db.deal_id}: {e}" ) # Continue without the file — don't crash the entire update + finally: + if "local_file" in locals() and os.path.exists(local_file): + os.remove(local_file) else: print(f"⚠️ Photo URL missing for deal_id {deal_in_db.deal_id}") @@ -405,6 +408,9 @@ class HubspotDataToDb: f"⚠️ Failed to download photo for deal_id {existing.deal_id}: {e}" ) # Continue without the file — don't crash the update + finally: + if "local_file" in locals() and os.path.exists(local_file): + os.remove(local_file) else: print(f"⚠️ Photo URL missing for deal_id {existing.deal_id}") @@ -475,6 +481,9 @@ class HubspotDataToDb: f"⚠️ Failed to download photo for deal_id {new_record.deal_id}: {e}" ) # Continue without the file — don't crash the insert + finally: + if "local_file" in locals() and os.path.exists(local_file): + os.remove(local_file) session.add(new_record) session.commit() diff --git a/etl/hubspot/scripts/scraper/bulk_load.py b/etl/hubspot/scripts/scraper/bulk_load.py index fabf8a3f..6fac23ea 100644 --- a/etl/hubspot/scripts/scraper/bulk_load.py +++ b/etl/hubspot/scripts/scraper/bulk_load.py @@ -16,17 +16,24 @@ def bulk_load(companies: list[Companies] | None = None) -> None: hubspot = HubspotClient() targets = companies or list(Companies) - for company in tqdm(targets, desc="Companies"): + for company in tqdm(targets, desc="Companies", unit="co"): company_id = company.value deal_ids = hubspot.get_deal_ids_from_company(company_id) - for deal_id in tqdm(deal_ids, desc=f"{company.name}", leave=False): - deal_data = hubspot.from_deal_id_get_info(deal_id) - if deal_data.get("pipeline") != PIPELINE_ID: - continue + processed = 0 + with tqdm(deal_ids, desc=company.name, unit="deal", leave=False) as deal_bar: + for deal_id in deal_bar: + deal_data = hubspot.from_deal_id_get_info(deal_id) + if deal_data.get("pipeline") != PIPELINE_ID: + deal_bar.set_postfix({"status": "skip", "deal": deal_id}) + continue - handler({"hubspot_deal_id": deal_id}, context=None) - print(f"Processed deal {deal_id} (company: {company.name})") + deal_bar.set_postfix({"status": "uploading", "deal": deal_id}) + handler({"hubspot_deal_id": deal_id}, context=None) + processed += 1 + deal_bar.set_postfix({"status": "done", "deal": deal_id}) + + tqdm.write(f"[{company.name}] {processed}/{len(deal_ids)} deals in pipeline") if __name__ == "__main__":