Upload app.py

app.py

@@ -8,22 +8,24 @@ from PIL import Image
 
 
 def extract_text(file_path):
+    text = ''
     with open(file_path, "rb") as pdf_file:
         pdf_reader = PyPDF2.PdfReader(pdf_file)
         num_pages = len(pdf_reader.pages)
 
         for page_number in range(num_pages):
-            st.write(f"Page {page_number + 1}")
+            # st.write(f"Page {page_number + 1}")
             page = pdf_reader.pages[page_number]
             text = page.extract_text()
 
     images = convert_from_path(file_path)  # Convert PDF pages to images
     for i, image in enumerate(images):
-        st.write(f"Page {i + 1}")
+        # st.write(f"Page {i + 1}")
         image_text = pytesseract.image_to_string(image)
-        
-        text += image_text
-        st.write(text)  # Display the extracted text from the image
+
+        text = text + image_text
+    
+    st.write(text)  # Display the extracted text from the image
 
 def main():
     st.title("PDF Text Extractor")