From e6308b8167e28a7452e9b87d913c1279f43b130a Mon Sep 17 00:00:00 2001
From: Markus Heiser <markus.heiser@darmarit.de>
Date: Tue, 1 Apr 2025 09:20:19 +0200
Subject: [fix] hardening against arguments of type None, where str or dict is
 expected

On a long-running server, the tracebacks below can be found (albeit rarely),
which indicate problems with NoneType where a string or another data type is
expected.

result.img_src::

    File "/usr/local/searxng/searxng-src/searx/templates/simple/result_templates/images.html", line 13, in top-level template code
      <img src="" data-src="{{ image_proxify(result.img_src) }}" alt="{{ result.title|striptags }}">{{- "" -}}
      ^
    File "/usr/local/searxng/searxng-src/searx/webapp.py", line 284, in image_proxify
      if url.startswith('//'):
         ^^^^^^^^^^^^^^
    AttributeError: 'NoneType' object has no attribute 'startswith'

result.content::

    File "/usr/local/searxng/searxng-src/searx/result_types/_base.py", line 105, in _normalize_text_fields
      result.content = WHITESPACE_REGEX.sub(" ", result.content).strip()
                       ~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^
    TypeError: expected string or bytes-like object, got 'NoneType'

html_to_text, when html_str is a NoneType::

    File "/usr/local/searxng/searxng-src/searx/engines/wikipedia.py", line 190, in response
      title = utils.html_to_text(api_result.get('titles', {}).get('display') or api_result.get('title'))
    File "/usr/local/searxng/searxng-src/searx/utils.py", line 158, in html_to_text
      html_str = html_str.replace('\n', ' ').replace('\r', ' ')
                 ^^^^^^^^^^^^^^^^
    AttributeError: 'NoneType' object has no attribute 'replace'

presearch engine, when json_resp is a NoneType::

    File "/usr/local/searxng/searxng-src/searx/engines/presearch.py", line 221, in response
      results = parse_search_query(json_resp.get('results'))
    File "/usr/local/searxng/searxng-src/searx/engines/presearch.py", line 161, in parse_search_query
      for item in json_results.get('specialSections', {}).get('topStoriesCompact', {}).get('data', []):
                  ^^^^^^^^^^^^^^^^
    AttributeError: 'NoneType' object has no attribute 'get'

Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
---
 searx/utils.py | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'searx/utils.py')

diff --git a/searx/utils.py b/searx/utils.py
index ee044704b..a28171a32 100644
--- a/searx/utils.py
+++ b/searx/utils.py
@@ -154,6 +154,8 @@ def html_to_text(html_str: str) -> str:
         >>> html_to_text(r'regexp: (?<![a-zA-Z]')
         'regexp: (?<![a-zA-Z]'
     """
+    if not html_str:
+        return ""
     html_str = html_str.replace('\n', ' ').replace('\r', ' ')
     html_str = ' '.join(html_str.split())
     s = _HTMLTextExtractor()
-- 
cgit v1.2.3