Create app.py

app.py

@@ -0,0 +1,34 @@
+import gradio as gr
+import pytesseract
+from pdf2image import convert_from_path
+import tempfile
+import os
+
+def ocr_pdf(file_path):
+    with tempfile.TemporaryDirectory() as temp_dir:
+        # Convert PDF to images
+        images = convert_from_path(file_path, output_folder=temp_dir)
+        
+        # Extract text from each page image
+        extracted_text = ""
+        for i, image in enumerate(images):
+            text = pytesseract.image_to_string(image)
+            extracted_text += f"--- Page {i+1} ---\n{text}\n\n"
+        
+        # Save the extracted text to a .txt file
+        output_txt_path = os.path.join(temp_dir, "extracted_text.txt")
+        with open(output_txt_path, "w") as f:
+            f.write(extracted_text)
+        
+        return output_txt_path
+
+# Gradio Interface
+iface = gr.Interface(
+    fn=lambda file: ocr_pdf(file.name),  # Pass file path instead of file object
+    inputs=gr.File(label="Upload PDF File"), 
+    outputs=gr.File(label="Download Extracted Text (.txt)"),  # Outputs a downloadable .txt file
+    title="PDF to Text OCR"
+)
+
+if __name__ == "__main__":
+    iface.launch()