Update app.py

app.py

@@ -2,6 +2,8 @@ import pdfplumber
 import re
 import PyPDF2
 import pandas as pd
+import re
+import gradio as gr
 
 # Function to extract tables from PDF using pdfplumber
 def extract_table_from_pdf(pdf_path):
@@ -55,17 +57,21 @@ def process_po(pdf_path):
     
     return df
 
-# Main function to run the app
-def main(pdf_path):
-    df = process_po(pdf_path)
-    
-    # Save the results to an Excel file
-    output_file = 'extracted_data.xlsx'
-    df.to_excel(output_file, index=False)
-    
-    print(f"Data extracted successfully. Results saved to {output_file}")
+# Gradio Interface
+def gradio_interface(pdf_file):
+    """
+    Interface function for Gradio to process the PDF and return the Excel file.
+    """
+    return extract_data(pdf_file.name)
+
+# Define Gradio interface
+interface = gr.Interface(
+    fn=gradio_interface,
+    inputs=gr.File(label="Upload PDF"),
+    outputs=gr.File(label="Download Accurate Excel"),
+    title="Accurate BHEL PO Data Extractor",
+    description="Upload a PDF to extract accurate Material Numbers and related data into an Excel file."
+)
 
 if __name__ == "__main__":
-    # Example PDF Path
-    pdf_path = 'sample_po.pdf'  # Replace with your PDF file path
-    main(pdf_path)
+    interface.launch()