Create app.py

app.py

@@ -0,0 +1,82 @@
+import fitz  # PyMuPDF
+import pandas as pd
+import gradio as gr
+import tempfile
+import re
+
+def extract_po_to_excel(pdf_file):
+    # Regular expressions to match Toshiba PO fields
+    toshiba_item_pattern = re.compile(r'Pos\.\s*Item Code\s*Unit\s*Delivery Date\s*Quantity\s*Basic Price\s*Discount\s*Cur\.\s*Amount', re.IGNORECASE)
+    toshiba_data_pattern = re.compile(r'(\d+)\s+(\d+)\s+(\w+)\s+(\d{4}-\d{2}-\d{2})\s+([\d.]+)\s+([\d.]+)\s+([\d.]+)\s+(\w+)\s+([\d.]+)')
+    
+    # Regular expressions to match BHEL PO fields (different format)
+    bhel_data_pattern = re.compile(r'Sl No\s+Material Description\s+Unit\s+Quantity\s+Dely Qty\s+Dely Date\s+Unit Rate\s+Value', re.IGNORECASE)
+    bhel_data_line_pattern = re.compile(r'(\d+)\s+([A-Za-z0-9 ]+)\s+(\w+)\s+(\d+)\s+(\d+)\s+(\d{2}-\d{2}-\d{4})\s+([\d.]+)\s+([\d.]+)')
+    
+    # Initialize list to store extracted data
+    extracted_data = []
+
+    # Load PDF
+    with fitz.open(pdf_file.name) as pdf:
+        for page_num in range(pdf.page_count):
+            page = pdf[page_num]
+            text = page.get_text("text")
+            
+            # Check for Toshiba PO format and extract data
+            if toshiba_item_pattern.search(text):
+                matches = toshiba_data_pattern.findall(text)
+                for match in matches:
+                    pos, item_code, unit, delivery_date, quantity, basic_price, discount, currency, amount = match
+                    extracted_data.append({
+                        "Position": pos,
+                        "Item Code": item_code,
+                        "Unit": unit,
+                        "Delivery Date": delivery_date,
+                        "Quantity": quantity,
+                        "Basic Price": basic_price,
+                        "Discount": discount,
+                        "Currency": currency,
+                        "Amount": amount
+                    })
+            
+            # Check for BHEL PO format and extract data
+            elif bhel_data_pattern.search(text):
+                matches = bhel_data_line_pattern.findall(text)
+                for match in matches:
+                    sl_no, material_desc, unit, qty, dely_qty, dely_date, unit_rate, value = match
+                    extracted_data.append({
+                        "Sl No": sl_no,
+                        "Material Description": material_desc,
+                        "Unit": unit,
+                        "Quantity": qty,
+                        "Dely Qty": dely_qty,
+                        "Dely Date": dely_date,
+                        "Unit Rate": unit_rate,
+                        "Value": value
+                    })
+
+    # Create DataFrame
+    df = pd.DataFrame(extracted_data)
+    
+    # Save DataFrame to a temporary Excel file
+    temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".xlsx")
+    df.to_excel(temp_file.name, index=False)
+    temp_file.close()
+    
+    return temp_file.name
+
+def main(pdf_file):
+    excel_file_path = extract_po_to_excel(pdf_file)
+    return excel_file_path
+
+# Gradio interface
+interface = gr.Interface(
+    fn=main,
+    inputs=gr.File(label="Upload PO PDF"),
+    outputs=gr.File(label="Download Excel File"),
+    title="PO PDF to Excel Converter",
+    description="Upload a PO PDF file to extract and download it as an Excel sheet."
+)
+
+if __name__ == "__main__":
+    interface.launch()