Update extractor.py

extractor.py

@@ -1,10 +1,9 @@
 from pptx import Presentation
 from pypdf import PdfReader
 
-def extract_ppt_text(file):
 
+def extract_ppt_text(file):
     prs = Presentation(file)
-
     text = ""
 
     for slide in prs.slides:
@@ -16,12 +15,14 @@ def extract_ppt_text(file):
 
 
 def extract_pdf_text(file):
-
     reader = PdfReader(file)
 
     text = ""
 
     for page in reader.pages:
-        text += page.extract_text()
+        page_text = page.extract_text()
+
+        if page_text:
+            text += page_text + "\n"
 
     return text