get addresses and jobs from watford file

backend/pashub_fetcher/handler/Dockerfile

@@ -5,7 +5,7 @@ ADD https://github.com/aws/aws-lambda-runtime-interface-emulator/releases/latest
 RUN chmod +x /usr/local/bin/aws-lambda-rie
 
 # Install Lambda runtime client
-RUN pip install awslambdaric playwright==1.58.0 requests msal
+RUN pip install awslambdaric playwright==1.58.0 requests msal openpyxl
 
 # Set working directory (Lambda task root)
 WORKDIR /var/task

backend/pashub_fetcher/handler/handler.py

@@ -1,5 +1,9 @@
+import os
+import re
 import time
-from typing import Any, List, Mapping
+from typing import Any, Dict, List, Mapping
+
+from openpyxl import load_workbook
 
 from backend.pashub_fetcher.job import Job
 from backend.pashub_fetcher.pashub_client import PashubClient, UnauthorizedError
@@ -12,9 +16,62 @@ from utils.sharepoint.domna_sites import DomnaSites
 logger = setup_logger()
 
 
+def extract_jobs(filepath: str) -> List[Job]:
+    wb = load_workbook(filepath, data_only=True)
+    ws = wb["watford warm homes (wave 3) mai"]
+
+    HEADER_ROW = 3
+
+    headers: Dict[str, int] = {}
+    for col in range(1, ws.max_column + 1):
+        value = str(ws.cell(row=HEADER_ROW, column=col).value)
+        if value:
+            headers[value.strip()] = col
+
+    name_col = headers["Name"]
+    link_col = headers["Pashub Link"]
+
+    jobs: List[Job] = []
+
+    for row in range(HEADER_ROW + 1, ws.max_row + 1):
+        name = ws.cell(row=row, column=name_col).value
+        link = ws.cell(row=row, column=link_col).value
+
+        if not name or not link:
+            continue
+
+        link = str(link)
+
+        match = re.search(r"/jobs/([0-9a-fA-F\-]+)/", link)
+        if not match:
+            continue
+
+        job_id = match.group(1)
+
+        jobs.append({"id": job_id, "address": str(name)})
+        if not match:
+            continue
+
+        job_id = match.group(1)
+
+        jobs.append({"id": job_id, "address": str(name)})
+
+    return jobs
+
+
 def handler(event: Mapping[str, Any], context: Any) -> None:
-    pas_hub_email = "random@test.com"
+    BASE_DIR = os.path.dirname(os.path.dirname(__file__))
-    pas_hub_password = "my_fake_password"
+    filepath = os.path.join(BASE_DIR, "Watford_Warm_Homes_Wave_3_RA Downloads .xlsx")
+
+    jobs: List[Job] = extract_jobs(filepath)
+
+    logger.info("Successfully loaded jobs from spreadsheet")
+
+    # pas_hub_email = "random@test.com"
+    # pas_hub_password = "my_fake_password"
+
+    pas_hub_email = "sebastian@osmosis-acd.com"
+    pas_hub_password = "Osmosis2025!"
 
     try:
         token: str = get_token_from_local_storage(pas_hub_email, pas_hub_password)
@@ -28,17 +85,6 @@ def handler(event: Mapping[str, Any], context: Any) -> None:
         sharepoint_location=DomnaSites.SOCIAL_HOUSING_WAVE_3
     )
 
-    jobs: List[Job] = [
-        {
-            "id": "5abf6e27-e4c4-4ba8-b69d-9e34939e0002",
-            "address": "FLAT 11 Abbey View, Garsmouth Way, Watford, WD25 9DY",
-        },
-        {
-            "id": "047f4455-85e2-4293-97b1-6b460137d33e",
-            "address": "FLAT 14 Abbey View, Garsmouth Way, Watford, WD25 9DY",
-        },
-    ]  # TODO: get these from request body or spreadsheet
-
     sharepoint_client.makedir("Watford Test", "/JTK Test Folder")
 
     saved_file_paths: List[str] = []