Update app.py

app.py

@@ -6,41 +6,54 @@ import re
 # Define function to extract data
 def extract_data(pdf_file):
     data = []
-    columns = ["Purchase Order No", "Date", "SI No", "Material Number", "Material Description", "HSN Code", "IGST", "Unit", "Quantity", "Dely Qty", "Dely Date", "Unit Rate", "Value"]
+    columns = ["Purchase Order No", "Date", "SI No", "Material Description", "Unit", "Quantity", "Dely Qty", "Dely Date", "Unit Rate", "Value"]
 
-    # Example Purchase Order Details (Adjust accordingly)
-    purchase_order_no = "7200018552"
-    purchase_order_date = "28.09.2024"
+    purchase_order_no = None
+    purchase_order_date = None
 
     with pdfplumber.open(pdf_file) as pdf:
         for page in pdf.pages:
             text = page.extract_text().splitlines()
-            for i, line in enumerate(text):
-                parts = line.split()
+            
+            # Extract Purchase Order No and Date dynamically from the first page
+            if not purchase_order_no or not purchase_order_date:
+                for line in text:
+                    # Search for Purchase Order No
+                    po_match = re.search(r'Purchase Order No[:\s]+(\d+)', line)
+                    if po_match:
+                        purchase_order_no = po_match.group(1)
+                    
+                    # Search for Date
+                    date_match = re.search(r'Date[:\s]+(\d{2}\.\d{2}\.\d{4})', line)
+                    if date_match:
+                        purchase_order_date = date_match.group(1)
+                    
+                    # Stop searching if both fields are found
+                    if purchase_order_no and purchase_order_date:
+                        break
+
+            # Process each line to extract relevant data rows
+            for line in text:
+                # Using regex or keywords to identify each row
                 try:
-                    si_no = int(parts[0])  # Extract SI No
-                    if si_no % 10 == 0:  # Assuming SI numbers are in multiples of 10
-                        # Extracting fields based on pattern and order as per the provided format
-                        material_desc = "BPS 017507"  # Based on your example; adjust if dynamic
-                        material_number = parts[3] if "Material" in parts else "220736540000"  # Default if not found
-                        hsn_code = "8310"  # Fixed HSN Code
-                        igst = "18%"       # Fixed IGST
-                        unit = parts[4]
-                        quantity = int(parts[5])
-                        dely_qty = int(parts[6])
-                        dely_date = parts[7]
-                        unit_rate = float(parts[8])
-                        value = float(parts[9])
+                    # Example row pattern match for SI No (Assuming starts with numbers in multiples of 10)
+                    if re.match(r'^\d+\s', line):  
+                        parts = line.split()
+                        si_no = parts[0]  # Extract SI No
+                        material_desc = "BPS 017507\nMaterial Number: {}\nHSN Code: 8310\nIGST: 18%".format(parts[2])  # Example Material Description
+                        unit = "NO"
+                        quantity = parts[3]
+                        dely_qty = parts[4]
+                        dely_date = parts[5]
+                        unit_rate = parts[6]
+                        value = parts[7]
 
-                        # Append extracted data in specified order
+                        # Append data as a row in the correct order
                         data.append([
                             purchase_order_no,
                             purchase_order_date,
                             si_no,
-                            material_number,
                             material_desc,
-                            hsn_code,
-                            igst,
                             unit,
                             quantity,
                             dely_qty,
@@ -49,9 +62,9 @@ def extract_data(pdf_file):
                             value
                         ])
                 except (ValueError, IndexError):
-                    continue  # Skip lines that don't match the format
+                    continue  # Skip lines that do not match the expected pattern
 
-    # Convert to DataFrame with specified columns
+    # Convert data to a DataFrame and save it as Excel
     df = pd.DataFrame(data, columns=columns)
     excel_path = "/tmp/Extracted_Purchase_Order_Data.xlsx"
     df.to_excel(excel_path, index=False)