Update app.py

app.py

@@ -226,12 +226,12 @@ def pdf2txt(pdf_docs):
         # You need to replace the following lines with actual file reading
         # based on the file_extension
         if file_extension in ['txt', 'html', 'htm', 'py', 'xml', 'json']:
-            # text += textract.process(file_str).decode("utf-8") 
+            text += textract.process(str(file).decode("utf-8") 
             text += f"\nExtracted text from {file_extension} file..."
         elif file_extension == 'pdf':
-            # pdf_reader = PdfReader(file_str)
-            # for page in pdf_reader.pages:
-            #     text += page.extract_text()
+            pdf_reader = PdfReader(file)
+            for page in pdf_reader.pages:
+                text += page.extract_text()
             text += f"\nExtracted text from PDF file..."
 
     return text