diff --git a/dags/hivemind_etl_helpers/src/db/discord/utils/transform_discord_raw_messges.py b/dags/hivemind_etl_helpers/src/db/discord/utils/transform_discord_raw_messges.py
index f6194145..7a10f7a7 100644
--- a/dags/hivemind_etl_helpers/src/db/discord/utils/transform_discord_raw_messges.py
+++ b/dags/hivemind_etl_helpers/src/db/discord/utils/transform_discord_raw_messges.py
@@ -1,3 +1,4 @@
+import re
 import logging
 from typing import Any
 
@@ -158,7 +159,7 @@ def prepare_document(
     content_url_updated, url_reference = prepare_raw_message_urls(content)
 
     # always has length 1
-    assert len(author_name) == 1
+    assert len(author_name) == 1, "Either None or multiple authors!"
 
     msg_meta_data = {
         "channel": message["channelName"],
@@ -209,6 +210,9 @@ def prepare_document(
     if check_no_content_only_links(content_url_updated):
         raise ValueError("Message just did have urls")
 
+    # removing null characters
+    content_url_updated = re.sub(r'[\x00-\x1F\x7F]', '', content_url_updated)
+
     doc: Document
     if not exclude_metadata:
         doc = Document(text=content_url_updated, metadata=msg_meta_data)