Update toshiba.py

toshiba.py

@@ -11,6 +11,7 @@ def extract_toshiba_data(pdf_file):
         for page in pdf.pages:
             text = page.extract_text().splitlines()
 
+            # Extract Purchase Order and Order Date if not already found
             if not purchase_order or not order_date:
                 for line in text:
                     po_match = re.search(r'Purchase Order\s*:\s*(P\d+)', line)
@@ -20,20 +21,27 @@ def extract_toshiba_data(pdf_file):
                     if date_match:
                         order_date = date_match.group(1)
 
+            # Extract item details
             for line in text:
                 parts = line.split()
                 try:
                     pos = int(parts[0])
                     if 10 <= pos <= 450:
                         item_code = parts[1]
-                        quantity = float(parts[4])
-                        basic_price = float(parts[5])
-                        sub_total = float(parts[-1])
-                        data.append([purchase_order, order_date, pos, item_code, quantity, basic_price, sub_total])
+                        unit = parts[3]  # Assuming unit appears in a fixed position
+                        delivery_date = parts[4]  # Assuming delivery date is next
+                        quantity = float(parts[5])
+                        basic_price = float(parts[6])
+                        amount = quantity * basic_price
+                        sub_total = float(parts[-1])  # Assuming subtotal is the last item on the line
+                        data.append([purchase_order, order_date, pos, item_code, unit, delivery_date, quantity, basic_price, amount, sub_total])
                 except (ValueError, IndexError):
                     continue
 
-    df = pd.DataFrame(data, columns=["Purchase Order", "Order Date", "Pos", "Item Code", "Quantity", "Basic Price", "Sub Total"])
+    # Define DataFrame with the new structure
+    df = pd.DataFrame(data, columns=["Purchase Order", "Order Date", "Pos", "Item Code", "Unit", "Delivery Date", "Quantity", "Basic Price", "Amount", "SUB TOTAL"])
+    
+    # Save to Excel file
     temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".xlsx")
     df.to_excel(temp_file.name, index=False)
-    return temp_file.name
+    return temp_file.name