Update app.py

app.py

@@ -23,11 +23,18 @@ def clean_text(text):
     
 # Function to extract text from PDF files
 def extract_text(pdf_file):
-    pdf_reader = PyPDF2.PdfReader(pdf_file)
-    text = ''
-    for page_num in range(len(pdf_reader.pages)):
-        text += pdf_reader.pages[page_num].extract_text()
-    return text
+    try:
+        pdf_reader = PdfReader(pdf_file)
+        if pdf_reader.is_encrypted:
+            print(f"Skipping encrypted file: {pdf_file}")
+            return None
+        text = ''
+        for page in pdf_reader.pages:
+            text += page.extract_text() or ''
+        return text
+    except Exception as e:
+        print(f"Error extracting text from {pdf_file}: {e}")
+        return None
 
 # Function to split text into chunks of a specified size
 def split_text(text, chunk_size=1024):