Update app.py

app.py

@@ -3,32 +3,42 @@ import pdfplumber
 import pandas as pd
 
 def extract_data(pdf_file_path, start_pos, end_pos):
-    # Load PDF and extract specific rows
-    with pdfplumber.open(pdf_file_path) as pdf:
-        data = []
-        for page in pdf.pages:
-            text = page.extract_text()
-            # Parsing and extracting rows within the specified range goes here.
+    try:
+        # Attempt to load and process the PDF
+        with pdfplumber.open(pdf_file_path) as pdf:
+            data = []
+            for page in pdf.pages:
+                text = page.extract_text()
+                if text is None:
+                    return "Error: Could not extract text from the PDF. Please check the file format."
+                
+                # Print text for debugging
+                print(text)  # Debugging line
 
-        # Example extracted data (replace with actual extraction logic)
-        extracted_data = {
-            "Pos": [10, 20, 30],  # Replace with actual data
-            "Item Code": ["155569003011", "155569003012", "155569003013"],
-            "Quantity": [10, 10, 10],
-            "Basic Price": [57.66, 57.66, 57.66],
-            "Sub Total": [576.60, 576.60, 576.60]
-        }
-        
-        # Convert extracted data to a DataFrame
-        df = pd.DataFrame(extracted_data)
-        
-        # Save DataFrame to Excel
-        output_path = "/tmp/extracted_data.xlsx"
-        df.to_excel(output_path, index=False)
+                # Sample data collection logic; replace with actual parsing logic
+                # Here you would filter by 'Pos' values within start_pos to end_pos
+
+            # Example data to simulate output
+            extracted_data = {
+                "Pos": [10, 20, 30],  # Replace with actual data
+                "Item Code": ["155569003011", "155569003012", "155569003013"],
+                "Quantity": [10, 10, 10],
+                "Basic Price": [57.66, 57.66, 57.66],
+                "Sub Total": [576.60, 576.60, 576.60]
+            }
+            
+            # Convert to DataFrame and save to Excel
+            df = pd.DataFrame(extracted_data)
+            output_path = "/tmp/extracted_data.xlsx"
+            df.to_excel(output_path, index=False)
+            
+            return output_path
         
-        return output_path
+    except Exception as e:
+        # Return the error message if an exception occurs
+        return f"Error: {e}"
 
-# Updated Gradio interface using current components
+# Gradio interface setup
 interface = gr.Interface(
     fn=extract_data,
     inputs=[
@@ -40,4 +50,3 @@ interface = gr.Interface(
 )
 
 interface.launch()
-