again + ignore image/audio

analyze.py

@@ -1,3 +1,4 @@
+import re
 from itertools import count, islice
 from typing import Any, Iterable, Literal, Optional, TypedDict, TypeVar, Union, overload
 
@@ -53,6 +54,8 @@ def get_strings(row_content: Any) -> str:
     if isinstance(row_content, str):
         return row_content
     if isinstance(row_content, dict):
+        if "src" in row_content:
+            return ""  # could be image or audio
         row_content = list(row_content.values())
     if isinstance(row_content, list):
         str_items = (get_strings(row_content_item) for row_content_item in row_content)