Initial

app.py

@@ -33,19 +33,16 @@ def parse_xml_response(xml_string: str) -> pd.DataFrame:
     """
     try:
         # Extract only the XML content between the outermost tags
-        xml_content = re.search(r'<[^>]+>.*</[^>]+>', xml_string, re.DOTALL)
-        if xml_content:
-            xml_string = xml_content.group(0)
-        else:
+        xml_content = re.findall(r'<[^>]+>.*?</[^>]+>', xml_string, re.DOTALL)
+        if not xml_content:
             print("No valid XML content found.")
             return pd.DataFrame()
 
         # Wrap the content in a root element to ensure there's only one root
-        xml_string = f"<root>{xml_string}</root>"
+        xml_string = f"<root>{''.join(xml_content)}</root>"
 
         # Parse the XML
-        parser = ET.XMLParser(recover=True)  # This allows for more lenient parsing
-        root = ET.fromstring(xml_string, parser=parser)
+        root = ET.fromstring(xml_string)
 
         result = {}
 
@@ -167,14 +164,6 @@ def process(file_content):
         response = get_response(message_file.id, demo.id)  # This now includes retry logic
         df = parse_xml_response(response)
         
-        # ... (rest of the function remains the same)
-
-    except Exception as e:
-        error_message = f"An error occurred while processing the file: {str(e)}"
-        print(error_message)
-        print(f"Traceback: {traceback.format_exc()}")
-        return f"<p>{error_message}</p>"
-        
         if df.empty:
             return "<p>No valid information could be extracted from the provided file.</p>"