Update document_scrapped.py

document_scrapped.py

@@ -5,6 +5,7 @@ import json
 import io
 import fitz
 from pptx import Presentation
+from io import BytesIO
 import chardet
 from docx import Document
 import pandas as pd
@@ -96,7 +97,7 @@ def excel(link : str) -> str:
         response = requests.get(link)
         if response.status_code == 200:
             file_content = response.content
-            df = pd.read_excel(file_content)
+            df = pd.read_excel(BytesIO(file_content))
             if df.shape[0] > 50:
                       sample_size = 50
                       sample_df = df.sample(n=sample_size, random_state=42)