[fix] engines: base URL can be a list or a string, but its not None!

The code injection and monkey patching examine the names in the module of the
engine; if a variable there starts without an underscore and has the value None,
then this variable needs to be configured. This outdated concept does not fit
engines that may have multiple URLs. At least not as long as the value of the
base URL (list) is None.

The default is now an empty list instead of None

Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>

searx/engines/__init__.py

@@ -270,7 +270,14 @@ def load_engines(engine_list: list[dict[str, t.Any]]):
     categories.clear()
     categories['general'] = []
     for engine_data in engine_list:
+        if engine_data.get("inactive") is True:
+            continue
         engine = load_engine(engine_data)
         if engine:
             register_engine(engine)
+        else:
+            # if an engine can't be loaded (if for example the engine is missing
+            # tor or some other requirements) its set to inactive!
+            logger.error("loading engine %s failed: set engine to inactive!", engine_data.get("name", "???"))
+            engine_data["inactive"] = True
     return engines

searx/engines/invidious.py

@@ -31,7 +31,7 @@ paging = True
 time_range_support = True
 
 # base_url can be overwritten by a list of URLs in the settings.yml
-base_url: list | str = []
+base_url: list[str] | str = []
 
 
 def init(_):

searx/engines/piped.py

@@ -72,7 +72,7 @@ categories = []
 paging = True
 
 # search-url
-backend_url: list[str] | str | None = None
+backend_url: list[str] | str = []
 """Piped-Backend_: The core component behind Piped.  The value is an URL or a
 list of URLs.  In the latter case instance will be selected randomly.  For a
 complete list of official instances see Piped-Instances (`JSON

searx/engines/pixiv.py

@@ -20,7 +20,7 @@ categories = ['images']
 
 # Search URL
 base_url = "https://www.pixiv.net/ajax/search/illustrations"
-pixiv_image_proxies: list = []
+pixiv_image_proxies: list[str] = []
 
 
 def request(query, params):

searx/engines/yacy.py

@@ -96,7 +96,7 @@ search_type = 'text'
 ``video`` are not yet implemented (Pull-Requests are welcome).
 """
 
-base_url: list[str] | str | None = None
+base_url: list[str] | str = []
 """The value is an URL or a list of URLs.  In the latter case instance will be
 selected randomly.
 """

searx/search/__init__.py

@@ -22,7 +22,7 @@ from searx.network import initialize as initialize_network, check_network_config
 from searx.results import ResultContainer
 from searx.search.checker import initialize as initialize_checker
 from searx.search.processors import PROCESSORS
-
+from searx.search.processors.abstract import RequestParams
 
 if t.TYPE_CHECKING:
     from .models import SearchQuery
@@ -79,16 +79,20 @@ class Search:
         return bool(results)
 
     # do search-request
-    def _get_requests(self) -> tuple[list[tuple[str, str, dict[str, t.Any]]], int]:
+    def _get_requests(self) -> tuple[list[tuple[str, str, RequestParams]], float]:
         # init vars
-        requests: list[tuple[str, str, dict[str, t.Any]]] = []
+        requests: list[tuple[str, str, RequestParams]] = []
 
         # max of all selected engine timeout
         default_timeout = 0
 
         # start search-request for all selected engines
         for engineref in self.search_query.engineref_list:
-            processor = PROCESSORS[engineref.name]
+            processor = PROCESSORS.get(engineref.name)
+            if not processor:
+                # engine does not exists; not yet or the 'init' method of the
+                # engine has been failed and the engine has not been registered.
+                continue
 
             # stop the request now if the engine is suspend
             if processor.extend_container_if_suspended(self.result_container):
@@ -133,7 +137,7 @@ class Search:
 
         return requests, actual_timeout
 
-    def search_multiple_requests(self, requests: list[tuple[str, str, dict[str, t.Any]]]):
+    def search_multiple_requests(self, requests: list[tuple[str, str, RequestParams]]):
         # pylint: disable=protected-access
         search_id = str(uuid4())
 

searx/search/processors/__init__.py

@@ -51,7 +51,6 @@ class ProcessorMap(dict[str, EngineProcessor]):
             eng_name: str = eng_settings["name"]
 
             if eng_settings.get("inactive", False) is True:
-                logger.info("Engine of name '%s' is inactive.", eng_name)
                 continue
 
             eng_obj = engines.engines.get(eng_name)

tests/unit/test_engines_init.py

@@ -61,7 +61,7 @@ class TestEnginesInit(SearxTestCase):
         with self.assertLogs('searx.engines', level='ERROR') as cm:  # pylint: disable=invalid-name
             engines.load_engines(engine_list)
             self.assertEqual(len(engines.engines), 0)
-            self.assertEqual(cm.output, ['ERROR:searx.engines:An engine does not have a "name" field'])
+            self.assertEqual(cm.output[0], 'ERROR:searx.engines:An engine does not have a "name" field')
 
     def test_missing_engine_field(self):
         settings['outgoing']['using_tor_proxy'] = False
@@ -72,5 +72,5 @@ class TestEnginesInit(SearxTestCase):
             engines.load_engines(engine_list)
             self.assertEqual(len(engines.engines), 0)
             self.assertEqual(
-                cm.output, ['ERROR:searx.engines:The "engine" field is missing for the engine named "engine2"']
+                cm.output[0], 'ERROR:searx.engines:The "engine" field is missing for the engine named "engine2"'
             )