Update app.py

app.py

@@ -39,8 +39,9 @@ def pdf_to_text(file):
         image_list = page.get_images(full=True)
         for img in image_list:
             xref, name, ext, color_space, width, height, bpc, image_data, image_mask, smask_data = img
-            # Decode image_data from base64 before opening it
-            image_data = base64.b64decode(image_data)
+            # Check if image_data is base64 encoded string
+            if isinstance(image_data, str) and re.match(r'^[A-Za-z0-9+/]+[=]{0,2}$', image_data):
+                image_data = base64.b64decode(image_data)
             try:
                 image = Image.open(io.BytesIO(image_data))
                 latex_code = image_to_latex(image)
@@ -59,12 +60,11 @@ def pdf_to_text(file):
     with open(output_file_name, 'w') as f:
         f.write(full_text)
 
-    return output_file_name, page_number
-
+    return output_file_name
 
 iface = gr.Interface(fn=pdf_to_text,
                      inputs=gr.inputs.File(label="Your PDF"),
-                     outputs=[gr.outputs.File(label="Download TXT"), gr.outputs.Textbox(label="Last Page Processed")],
+                     outputs=gr.outputs.File(label="Download TXT"),
                      title="PDF to TXT",
                      description="Convert your PDF files to clean text")
 iface.launch()