Update toshiba.py

toshiba.py

@@ -8,39 +8,57 @@ def extract_toshiba_data(pdf_file):
     purchase_order, order_date = None, None
 
     with pdfplumber.open(pdf_file) as pdf:
-        for page in pdf.pages:
-            text = page.extract_text().splitlines()
+        for page_num, page in enumerate(pdf.pages):
+            # Extract and print the raw text of each page for debugging
+            text = page.extract_text()
+            if text:
+                print(f"Page {page_num + 1} Content:\n{text}\n{'-' * 40}\n")
+            else:
+                print(f"Page {page_num + 1} has no extractable text.\n{'-' * 40}\n")
+                continue
+
+            # Split text into lines to analyze line by line
+            lines = text.splitlines()
 
             # Extract Purchase Order and Order Date if not already found
             if not purchase_order or not order_date:
-                for line in text:
+                for line in lines:
                     po_match = re.search(r'Purchase Order\s*:\s*(P\d+)', line)
                     date_match = re.search(r'Order Date\s*:\s*([\d-]+)', line)
                     if po_match:
                         purchase_order = po_match.group(1)
+                        print(f"Found Purchase Order: {purchase_order}")  # Debug
                     if date_match:
                         order_date = date_match.group(1)
+                        print(f"Found Order Date: {order_date}")  # Debug
 
-            # Extract item details using patterns
-            for line in text:
-                # Match each line with expected pattern for item rows
+            # Attempt to match item details using a general regex pattern
+            for line in lines:
                 item_match = re.match(r'(\d+)\s+(\d+)\s+(.*?)\s+([\d-]+)\s+([\d.]+)\s+([\d.]+)\s+([\d.]+)\s+([\d.]+)', line)
                 if item_match:
                     pos = int(item_match.group(1))                   # Position number
                     item_code = item_match.group(2)                 # Item Code
-                    item_name = item_match.group(3).strip()         # Item Name/Description (if available)
+                    item_name = item_match.group(3).strip()         # Item Name/Description
                     delivery_date = item_match.group(4)             # Delivery Date
                     quantity = float(item_match.group(5))           # Quantity
                     basic_price = float(item_match.group(6))        # Basic Price
                     amount = float(item_match.group(7))             # Calculated Amount
                     sub_total = float(item_match.group(8))          # Subtotal or final price
 
+                    # Append the extracted row to data list
                     data.append([purchase_order, order_date, pos, item_code, item_name, delivery_date, quantity, basic_price, amount, sub_total])
+                    print(f"Matched Item Row: {[purchase_order, order_date, pos, item_code, item_name, delivery_date, quantity, basic_price, amount, sub_total]}")  # Debug
 
-    # Define DataFrame with the corrected structure
+    # Define DataFrame with the expected structure
     df = pd.DataFrame(data, columns=["Purchase Order", "Order Date", "Pos", "Item Code", "Item Name", "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)
+    print(f"Data extracted to: {temp_file.name}")
     return temp_file.name
+
+# Usage example with debug output
+file_path = '/mnt/data/Toshiba PO.pdf'  # Replace this with the actual file path
+output_file = extract_toshiba_data(file_path)
+print(f"Extracted data saved to: {output_file}")