Add: fuction to convert html to text

archivist/utils/strings.py

@@ -51,3 +51,19 @@ def is_string_html(string: str) -> bool:
     '''
     return bool(BeautifulSoup(string, "html.parser").find())
 
+
+def html_to_text(string):
+    """
+    Converts an HTML string to plain text by removing all HTML tags and returning the resulting text.
+    
+    Parameters:
+        string (str): The HTML string to be converted.
+        
+    Returns:
+        str: The plain text version of the input HTML string.
+    """
+    if is_string_html(string):
+        soup = BeautifulSoup(string, "html.parser")
+        return soup.get_text()
+    else:
+        return string