Update app.py

app.py

@@ -15,6 +15,7 @@ def extract_data_from_pdf(pdf_file):
             # Extract text from each page
             text = page.extract_text()
             if text:
+                print(f"Extracted text from page {page.page_number}:\n{text}\n")  # Debugging: Print extracted text
                 text_data.append(text)
 
     # Initialize list for parsed data
@@ -38,13 +39,7 @@ def extract_data_from_pdf(pdf_file):
                 row["discount"] = float(row["discount"])
                 row["amount"] = float(row["amount"])
 
-                # Calculate Sub Total with assumed tax rate
-                central_gst = row["amount"] * 0.09  # Central GST 9%
-                state_gst = row["amount"] * 0.09    # State GST 9%
-                row["Central GST"] = round(central_gst, 2)
-                row["State GST"] = round(state_gst, 2)
-                row["Sub Total"] = round(row["amount"] + central_gst + state_gst - row["discount"], 2)
-
+                # Append extracted row to data
                 data.append(row)
 
     # Create DataFrame if data was extracted
@@ -52,7 +47,7 @@ def extract_data_from_pdf(pdf_file):
         df = pd.DataFrame(data)
         df.columns = [
             "Pos", "Item Code", "Description", "Unit", "Delivery Date", "Quantity", "Basic Price",
-            "Discount", "Currency", "Amount", "Central GST", "State GST", "Sub Total"
+            "Discount", "Currency", "Amount"
         ]
         
         # Save the DataFrame to a temporary Excel file
@@ -78,7 +73,7 @@ iface = gr.Interface(
     description=(
         "Upload a PDF file to extract structured purchase order data and download it as an Excel file. "
         "The app will parse rows with fields like Position, Item Code, Description, Quantity, Price, etc. "
-        "Calculated fields (like Central GST, State GST, and Sub Total) are automatically included."
+        "No additional calculations are performed; it simply extracts the data as it appears."
     ),
 )