Create text_extractor.py

text_extractor.py

@@ -0,0 +1,18 @@
+# text_extractor.py
+import docx2txt
+import fitz  # PyMuPDF
+
+def extract_text_from_file(file_path):
+    if file_path.endswith(".pdf"):
+        return extract_text_from_pdf(file_path)
+    elif file_path.endswith(".docx"):
+        return docx2txt.process(file_path)
+    else:
+        return "Unsupported file type."
+
+def extract_text_from_pdf(file_path):
+    text = ""
+    with fitz.open(file_path) as doc:
+        for page in doc:
+            text += page.get_text()
+    return text