Update app.py

app.py

@@ -13,18 +13,22 @@ def extract_text_from_pdf(pdf_file):
                 pdf_file.seek(0)
         else:
             pdf_content = pdf_file
-            
+
         pdf_reader = PyPDF2.PdfReader(io.BytesIO(pdf_content))
         for page_num in range(len(pdf_reader.pages)):
             page_text = pdf_reader.pages[page_num].extract_text()
             if page_text:
                 text += page_text + "\n\n"
-            else:
-                text += f"[Page {page_num+1} - No extractable text found]\n\n"
-        
+
         if not text.strip():
-            return "No text could be extracted from the PDF. The document may be scanned or image-based."
+            # Fall back to OCR
+            text = extract_with_ocr(pdf_content)
+            if not text.strip():
+                return "No text could be extracted, even with OCR."
+            return f"[Extracted with OCR]\n\n{text}"
+
         return text
+
     except Exception as e:
         return f"Error extracting text from PDF: {str(e)}"