adding to extract eprs

etl/customers/stonewater/Wave 3 Preparation.py

@@ -18,6 +18,7 @@ def extract_summary_report(pdf_path):
     """
     data = {
         "Address": None,
+        "Postcode": None,
         "Current SAP Rating": None,
         "Space Heating": None,
         "Water Heating": None,
@@ -200,7 +201,9 @@ def extract_epr(pdf_path):
     """
     data = {
         "Address": None,
+        "Postcode": None,
         "Current SAP Rating": None,
+        "Potential SAP Rating": None,
         "Space Heating": None,
         "Water Heating": None,
         "Fuel Bill": None,
@@ -211,6 +214,16 @@ def extract_epr(pdf_path):
         "Number of Windows": None,
         "Total Number of Doors": None,
         "Number of Insulated Doors": None,
+        "Existing Primary Heating System": None,
+        "Existing Primary Heating PCDF Reference": None,
+        "Existing Primary Heating Controls": None,
+        "Existing Primary Heating % of Heat": None,
+        "Existing Secondary Heating System": None,
+        "Existing Secondary Heating PCDF Reference": None,
+        "Existing Secondary Heating Controls": None,
+        "Existing Secondary Heating % of Heat": None,
+        "Secondary Heating Code": None,
+        "Water Heating Code": None,
     }
 
     with open(pdf_path, "rb") as file:
@@ -222,41 +235,73 @@ def extract_epr(pdf_path):
         # Extract Address
         address_match = re.search(r"ENERGY REPORT\nDwelling Address\s*(.*?)\s*\nReference", text, re.DOTALL)
         data["Address"] = address_match.group(1).strip()
+        data["Postcode"] = data["Address"].split(",")[-1].strip()
 
-        # Extract Total Floor Area
+        # Extract Current and Potential SAP ratings
-        # area_match = re.search(r"Total Floor Area\s*(\d+ m2)", text)
-        # data["Total Floor Area"] = area_match.group(1)
-
-        # Extract Current SAP rating
-        # Updated Regular Expression to find "GG (1-20)" followed by two numbers
         sap_match = re.search(r"GG \(1-20\)(\d{1,2})(\d{1,2})", text)
+        current_sap, _ = int(sap_match.group(1)), int(sap_match.group(2))
+        data["Current SAP Rating"] = current_sap
 
-        # Extract and validate the Current and Potential SAP ratings
+        # Extract Fuel Bill
-        current_sap, potential_sap = int(sap_match.group(1)), int(sap_match.group(2))
-        # Ensure potential is greater than or equal to current
-        if 1 <= current_sap <= 99 and 1 <= potential_sap <= 99 and potential_sap >= current_sap:
-            data["Current SAP Rating"] = current_sap
-            data["Potential SAP Rating"] = potential_sap
-        else:
-            raise ValueError("Failed to parse SAP ratings correctly due to unexpected format.")
-
-        # Extract Space Heating (kWh)
-        space_heating_match = re.search(r"Space Heating\s+(\d+)\s+kWh", text)
-        data["Space Heating"] = int(space_heating_match.group(1))
-
-        # Extract Water Heating (kWh)
-        water_heating_match = re.search(r"Water Heating\s+(\d+)\s+kWh", text)
-        data["Water Heating"] = int(water_heating_match.group(1))
-
-        # Extract Fuel Bill (total estimated costs)
         fuel_bill_match = re.search(r"TOTAL\s*£(\d+)", text)
         data["Fuel Bill"] = f"£{fuel_bill_match.group(1)}"
 
-        # Extract the windows data
+        # Extract Total Number of Doors
+        total_doors_match = re.search(r"Total Doors:\s*(\d+)", text)
+        data["Total Number of Doors"] = int(total_doors_match.group(1))
+
+        # Extract Number of Insulated Doors
+        insulated_doors_match = re.search(r"Insulated Doors:\s*(\d+)", text)
+        data["Number of Insulated Doors"] = int(insulated_doors_match.group(1))
+
+        # Extract Primary Heating Section (Main Heating 1)
+        primary_heating_section = re.search(r"Main\s*Heating\s*1\s*(.*?)\s*Main\s*Heating\s*2", text, re.DOTALL)
+        primary_text = primary_heating_section.group(1)
+
+        data["Existing Primary Heating System"] = re.search(r"Main Heating Code\s*(.*?)\n", primary_text).group(
+            1).strip()
+        data["Existing Primary Heating PCDF Reference"] = re.search(r"PCDF boiler Reference\s*(\d+)",
+                                                                    primary_text).group(1)
+        data["Existing Primary Heating Controls"] = re.search(r"Main Heating Controls\s*(.*?)\n", primary_text).group(
+            1).strip()
+        data["Existing Primary Heating % of Heat"] = int(
+            re.search(r"Percentage of Heat\s*(\d+)\s*%?", primary_text).group(1)
+        )
+
+        # Extract Secondary Heating Section (Main Heating 2)
+        secondary_heating_section = re.search(r"Main\s*Heating\s*2\s*(.*?)\s*Secondary Heating", text, re.DOTALL)
+        secondary_text = secondary_heating_section.group(1)
+
+        data["Existing Secondary Heating System"] = re.search(r"Main Heating Code\s*(.*?)\n", secondary_text).group(
+            1).strip()
+        data["Existing Secondary Heating PCDF Reference"] = re.search(r"PCDF boiler Reference\s*(\d+)",
+                                                                      secondary_text).group(1)
+
+        if data["Existing Secondary Heating System"] == "":
+            data["Existing Secondary Heating Controls"] = ""
+        else:
+            data["Existing Secondary Heating Controls"] = re.search(r"Main Heating Controls\s*(.*?)\n",
+                                                                    secondary_text).group(1).strip()
+        data["Existing Secondary Heating % of Heat"] = int(
+            re.search(r"Percentage of Heat\s*(\d+)\s*%?", secondary_text).group(1)
+        )
+
+        # Extract Secondary Heating and Water Heating Codes
+        secondary_heating_code_match = re.search(r"Secondary Heating Code\s*(.*?)\n", text)
+        water_heating_code_match = re.search(r"Water Heating Code\s*(.*?)\n", text)
+
+        if data["Existing Secondary Heating System"] == "":
+            data["Secondary Heating Code"] = ""
+        else:
+            data["Secondary Heating Code"] = secondary_heating_code_match.group(1).strip()
+        data["Water Heating Code"] = water_heating_code_match.group(1).strip()
+
+        # Extract Windows information
         windows_section = re.search(r"Windows\s*(.*?)\s*Draught Proofing", text, re.DOTALL)
-        windows_text = windows_section.group(1)
+        if windows_section:
-        window_data = extract_window_age_description(windows_text)
+            windows_text = windows_section.group(1)
-        data.update(window_data)
+            window_data = extract_window_age_description(windows_text)
+            data.update(window_data)
 
     return data