Update app.py

app.py

@@ -205,20 +205,21 @@ def extract_mime_type(file):
 
 import textract
 import os
-def extract_file_extension(file_str):
-    # Using regex pattern matching to find the file extension
-    pattern = r"name='.*?\.(.*?)'"
-    match = re.search(pattern, file_str)
+def extract_file_extension(file):
+    # Assume file is an UploadedFile object and get the name directly
+    file_name = file.name
+    pattern = r".*?\.(.*?)$"
+    match = re.search(pattern, file_name)
     if match:
         return match.group(1)
     else:
-        raise ValueError(f"Unable to extract file extension from {file_str}")
+        raise ValueError(f"Unable to extract file extension from {file_name}")
 
 def pdf2txt(pdf_docs):
     text = ""
-    for file_str in pdf_docs:
-        file_extension = extract_file_extension(file_str)
-        # Print the file extension
+    for file in pdf_docs:
+        file_extension = extract_file_extension(file)
+        # print the file extension
         print(f"File type extension: {file_extension}")
 
         # Simulate file reading
@@ -234,6 +235,7 @@ def pdf2txt(pdf_docs):
             text += f"\nExtracted text from PDF file..."
 
     return text
+
         
 def pdf2txt_old(pdf_docs):
     st.write(pdf_docs)