Update app.py

app.py

@@ -5,24 +5,26 @@ import gradio as gr
 # Define function to extract data
 def extract_data(pdf_file):
     data = []
-    columns = ["SI No", "Material Description", "Material Number", "HSN Code", "IGST", "Unit", "Quantity", "Dely Qty", "Dely Date", "Unit Rate", "Value", "Purchase Order No", "Date"]
+    columns = ["Purchase Order No", "Date", "SI No", "Material Number", "Material Description", "HSN Code", "IGST", "Unit", "Quantity", "Dely Qty", "Dely Date", "Unit Rate", "Value"]
 
-    # Example Purchase Order Details (Adjust accordingly if needed)
+    # Example Purchase Order Details (Adjust accordingly or add dynamic extraction if possible)
     purchase_order_no = "PO12345"
     purchase_order_date = "04.11.2024"
 
     with pdfplumber.open(pdf_file) as pdf:
         for page in pdf.pages:
             text = page.extract_text().splitlines()
-            for line in text:
+            for i, line in enumerate(text):
                 parts = line.split()
                 try:
-                    si_no = int(parts[0])
-                    if si_no % 10 == 0:  # Assuming SI numbers are in multiples of 10 as per the sample
-                        material_desc = " ".join(parts[1:2])
-                        material_number = parts[3] if "Material" in parts else "220736540000"  # Use a default number if missing
-                        hsn_code = "8310"  # Fixed as per sample; adjust if required
-                        igst = "18%"  # Fixed IGST as per sample; adjust if required
+                    si_no = int(parts[0])  # Extract SI No
+                    # Check if the line follows the expected format for a row
+                    if si_no % 10 == 0:  # Assuming SI numbers are in multiples of 10 as per sample
+                        # Extract each field based on position and format
+                        material_desc = " ".join(parts[1:3])  # Adjust indexing if necessary
+                        material_number = parts[3] if "Material" in parts else "220736540000"  # Default if not found
+                        hsn_code = "8310"  # Fixed as per example; can be extracted if available
+                        igst = "18%"       # Fixed as per example; can be extracted if available
                         unit = parts[4]
                         quantity = int(parts[5])
                         dely_qty = int(parts[6])
@@ -30,11 +32,13 @@ def extract_data(pdf_file):
                         unit_rate = float(parts[8])
                         value = float(parts[9])
 
-                        # Append extracted data to maintain the order as per the sample screenshot
+                        # Append extracted data in specified order
                         data.append([
+                            purchase_order_no,
+                            purchase_order_date,
                             si_no,
-                            material_desc,
                             material_number,
+                            material_desc,
                             hsn_code,
                             igst,
                             unit,
@@ -42,13 +46,12 @@ def extract_data(pdf_file):
                             dely_qty,
                             dely_date,
                             unit_rate,
-                            value,
-                            purchase_order_no,
-                            purchase_order_date
+                            value
                         ])
                 except (ValueError, IndexError):
-                    continue
+                    continue  # Skip lines that don't match the format
 
+    # Convert to DataFrame with specified columns
     df = pd.DataFrame(data, columns=columns)
     excel_path = "/tmp/Extracted_Purchase_Order_Data.xlsx"
     df.to_excel(excel_path, index=False)