Create extractor.py

extractor.py

@@ -0,0 +1,42 @@
+from pptx import Presentation
+from pypdf import PdfReader
+
+
+def extract_ppt_text(file):
+
+    prs = Presentation(file)
+
+    slides_text = []
+
+    for slide in prs.slides:
+
+        slide_text = ""
+
+        for shape in slide.shapes:
+
+            if hasattr(shape, "text"):
+
+                slide_text += shape.text + "\n"
+
+        # avoid empty slides
+        if slide_text.strip():
+            slides_text.append(slide_text)
+
+    return slides_text
+
+
+def extract_pdf_text(file):
+
+    reader = PdfReader(file)
+
+    pages_text = []
+
+    for page in reader.pages:
+
+        text = page.extract_text()
+
+        if text and text.strip():
+
+            pages_text.append(text)
+
+    return pages_text