Merge 08384a312e into c4b874e9b0

Avoid HTTP 404 and redirects. Requests to the JSON/YAML API use the base url [1]

    https://www.loc.gov/{endpoint}/?fo=json

[1] https://www.loc.gov/apis/json-and-yaml/requests/

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

requirements.txt

@@ -12,7 +12,7 @@ Brotli==1.1.0
 uvloop==0.21.0
 httpx-socks[asyncio]==0.7.7
 setproctitle==1.3.4
-redis==5.0.8
+redis==5.2.0
 markdown-it-py==3.0.0
 fasttext-predict==0.9.2.2
 tomli==2.0.2; python_version < '3.11'

searx/engines/loc.py

@@ -27,7 +27,7 @@ categories = ['images']
 paging = True
 
 endpoint = 'photos'
-base_url = 'https://loc.gov'
+base_url = 'https://www.loc.gov'
 search_string = "/{endpoint}/?sp={page}&{query}&fo=json"
 
 

searx/network/network.py

@@ -233,8 +233,7 @@ class Network:
             del kwargs['raise_for_httperror']
         return do_raise_for_httperror
 
-    @staticmethod
-    def patch_response(response, do_raise_for_httperror):
+    def patch_response(self, response, do_raise_for_httperror):
         if isinstance(response, httpx.Response):
             # requests compatibility (response is not streamed)
             # see also https://www.python-httpx.org/compatibility/#checking-for-4xx5xx-responses
@@ -242,8 +241,11 @@ class Network:
 
             # raise an exception
             if do_raise_for_httperror:
-                raise_for_httperror(response)
-
+                try:
+                    raise_for_httperror(response)
+                except:
+                    self._logger.warning(f"HTTP Request failed: {response.request.method} {response.request.url}")
+                    raise
         return response
 
     def is_valid_response(self, response):
@@ -269,7 +271,7 @@ class Network:
                 else:
                     response = await client.request(method, url, **kwargs)
                 if self.is_valid_response(response) or retries <= 0:
-                    return Network.patch_response(response, do_raise_for_httperror)
+                    return self.patch_response(response, do_raise_for_httperror)
             except httpx.RemoteProtocolError as e:
                 if not was_disconnected:
                     # the server has closed the connection:

searx/search/processors/online.py

@@ -137,9 +137,6 @@ class OnlineProcessor(EngineProcessor):
         self.engine.request(query, params)
 
         # ignoring empty urls
-        if params['url'] is None:
-            return None
-
         if not params['url']:
             return None